Skip to main content

2023 | Book

Proceedings of Seventh International Congress on Information and Communication Technology

ICICT 2022, London, Volume 2

Editors: Dr. Xin-She Yang, Dr. Simon Sherratt, Dr. Nilanjan Dey, Dr. Amit Joshi

Publisher: Springer Nature Singapore

Book Series: Lecture Notes in Networks and Systems


About this book

This book gathers selected high-quality research papers presented at the Seventh International Congress on Information and Communication Technology, held at Brunel University, London, on February 21–24, 2022. It discusses emerging topics pertaining to information and communication technology (ICT) for managerial applications, e-governance, e-agriculture, e-education and computing technologies, the Internet of Things (IoT) and e-mining. Written by respected experts and researchers working on ICT, the book offers a valuable asset for young researchers involved in advanced studies. The work is presented in four volumes.

Table of Contents

Visualizing Student Engagement and Performance in Online Course: A Step to Smart Learning Environment

Students’ Engagement and Performance (EP) of online courses are analyzed and visualized in order to assist instructors in improving student’s performance at an early stage before the end of the academic semester. A fully online course for undergraduate students in the Department of Information Studies, College of Education, Sultan Qaboos University (SQU), was conducted. The total number of students in the course was 38. Students studied each course module and the instructor evaluated them based on a set of assessments. This paper explores the existence of possible relationships between student’s engagement and performance. In this paper, the authors only considered the results of the Mid Term Exam part. They extracted the necessary data for analysis purposes for the above-mentioned factors from the log file of the course. The results revealed promising relationships between the student’s engagement and performance. This indicates the importance of conducting this kind of case study as a step forward to achieve a smart learning environment.

Iman Al-Kindi, Zuhoor Al-Khanjari
IoT Automated Pill Dispenser for Elderly Care

This project is fabricated to ease medication consumption, especially for the elderly that always forget the proper time to consume their prescribed medicine. Thousands of cases have been recorded throughout the decade of wrong consumption of medicine. This may lead to serious issue as improper medicine dose is ineffective for the sickness that they suffer. This paper aims to develop an automated pill dispenser that triggers the alarm to the elderly, records the medication drop data using ThingSpeak, and notifies the caretaker through the Blynk application. This paper uses Arduino ATmega 2560 as the microcontroller for the device. It will be connected to a Wi-Fi module to transmit the data for the ThingSpeak platform and notifies the caretaker through the Blynk application. The paper will surely help eliminate the underdose and overdose issue, especially among the elderly and ease guardian’s worries about their absentness at the moment of medicine consumption. It is hoped that this paper can be used to replace hand-held pillbox device that is a hassle toward the elderly.

Saidatunnajwa Abdul Aziz, Aznida Abu Bakar Sajak, Ruwaida Ramly, Mohd Hanif Zulfakar
Android Malware Classification Addressing Repackaged Entities by the Evaluation of Static Features and Multiple Machine Learning Algorithms

Expanded usage and prevalence of android apps allows developers of malware to create new ways in various applications to unleash malware in various packaged types. This malware causes various leakage of information and a loss of revenue. In addition, the discovered software is repeatedly launched by unethical developers after classifying the program as malware. Unluckily, the program still remains undetected even after being repackaged. In this research, the topic of repackaging was discussed, emphasizing the implementation based on source code using the bag-of-words algorithm and testing the findings through machine learning. The findings of the assessment demonstrate comparatively improved result in this aspect than the existing implantation based on source code by adapting the bag-of-words strategy and implementing some supplementary dataset preprocessing. A vocabulary for identifying the malicious code has been developed in this study. Bag-of-words was used to classify malware trends using custom implementation. The findings were instantiated using various algorithms of machine learning. The concept was eventually implemented in a practical application too. The suggested method sets out a fairly new methodology for examining source code for android malware to tackle repackaging of malware.

Md Rashedul Hasan
Enterprise Architecture Quality Assessment

The enterprise architecture (EA) assessment can be provided in different ways. In general, the EA assessment supports information communication technology (ICT) implementation. Beyond that, business organization stakeholders have an opportunity to monitor effectiveness and efficiency of business processes. They can modify the business structure, increase the business innovativeness, and ensure business strategy realization. Nowadays, EA stakeholders establish their own methodologies for EA quality assessment. This paper includes analyzes of the architecture frameworks, assessment models, and standards. This article aims to answer the question, if the design science research (DSR) paradigm is useful for EA quality assessment. Hence, this paper includes a proposal of new approach to EA quality assessment, based on emphasizing the relevance and rigor as key concepts.

Małgorzata Pańkowska
Planning Rendezvous for Interplanetary Trajectories

Great interests are always brought by the scientific community for the exploration of the solar system. Thus, important efforts are to be furnished to this goal. This paper aims to develop an approach of making rendezvous for the planets in the solar system as well as for a big asteroid. All the necessary equations are established by distinguishing the inside and the outside planets orbits relative to the earth. After that a simulation for the departure, the waiting time and the return trip are elaborated. This is followed obviously by an evaluation and comparison of the trip duration for each planet in the solar system. These simulation results would be without doubt very useful in the elaboration of the rendezvous planning strategies.

Aziz Anouar, Mohammed Bennani
Peak Shaving in Microgrids Using Hybrid Storage

In this contribution, we focus on technical and economic aspects of using hybrid storage in microgrids for peak shaving. We perform feasibility analysis of hybrid storage consisting of conventional supercapacitors and chemical batteries. We use multiple real-life consumption profiles from various industry-oriented microgrids. The primary purpose is to construct digital twin model for reserved capacity simulation and prediction. The main objective is to find the equilibrium between technical innovations, acquisition costs, and energy cost savings.

Juraj Londák, Radoslav Vargic, Pavol Podhradský
A Machine Learning Approach to Predict SEER Cancer

The SEER database is among the persuading stores regarding malignancy pointers inside us. The SEER list helps impact investigation for the gigantic measure of patients’ bolstered viewpoints for the most part ordered as an insightful segment and impact. Assistant careful proof nearly the carcinoma dataset is ordinarily started on the site of the National Cancer Institute. The main point of this work is that depending on the individual’s manifestations, and we will foresee whether individuals are in danger of malignant growth or not. Perseverance and desire for the benefit of malignant growth patients have the option to upsurge prophetic exactitude and limit in the end cause better-educated decisions. To the current end, various amendments smear AI to disease data of the surveillance, epidemiology, and end results database. It may be used to better forecast cancer in the medical sector, and these studies can give a good chance to enhance existing models and build new models for uncommon cancers of minority groups in particular. In this paper, the authors contribute to getting more predicted accuracy for SEER cancer and use it to better forecast cancer in the medical sector.

Dm. Mehedi Hasan Abid, Tariqul Islam, Zahura Zaman, Fahim Yusuf, Md. Assaduzzaman, Syed Akhter Hossain, Md. Ismail Jabiullah
Digitization and Society: Forms of Interaction and Expression

This article aims to reveal the digitalization as an integral part of the society. Every process, phenomenon, community and relationship is related to digitalization and information technology. This analysis presents different forms of symbiosis between society and digitalization. The objectives of the paper are to show specific dimensions of the advent of digitization and the various technologies in the Bulgarian society. The main research questions are related to the performance of high-tech level of Bulgarian online environment and focus on the main features of online learning, which are identified as new educational activities. Methodology of this article is based on results obtained from an online survey conducted in March 2021 with people of different ages, occupations and education. The survey questionnaire included topics that directly relate to the digitalization of society, the use of various digital devices and the Internet, participation in online education and attitudes toward it. The results obtained are indicators that digitalization of society is a real fact as well as that online learning has a place in the Bulgarian educational system. This article focuses on peoples' reactions, their assessments and views on ongoing online learning and its formatting. The whole article and the survey carried out are under the national project “Digital Media Literacy in the context of “Knowledge Society”: state and challenges”, № КП–06–H25/4, funded by National Science Fund—Bulgaria.

Valentina Milenkova, Boris Manov, Dobrinka Peicheva
E-Managing the Pre-election Messages During the 2021 Parliamentary Campaigns in Bulgaria

The pre-election campaign for the early parliamentary vote in Bulgaria on July 11, 2021 was held in the conditions of an uncertain COVID-19 situation, political confrontation and the games of the European Football Championship. Following the trend of the previous regular elections of April 4 after which no government was appointed, Internet platforms and especially social networks have become increasingly popular channels for politicians to communicate with voters. The aim of the study focuses on the dynamics of pre-election online communication. The object is the specifics of the Internet connection between the audiences and the candidates for members of Parliament during the election campaign in July compared to the previous one in April. The subject refers to the digital election messages of the leaders of the political forces, presented in their Facebook profiles. The methodology is an empirical study and comparative analysis. The scope includes those political forces that have passed the 4% electoral threshold. The results are indicative for those interested in digital political communication during social isolation of pandemic.

Neli Velinova, Mariyan Tomov, Lilia Raycheva, Lora Metanova
Highly Stochastic Time Series Modeling using HTM in Comparison with Commonly Used Methods

This study compares the HTM models applicability in highly stochastic time series forecasting problems, to a range of commonly used approaches. The models were tested on a real-world data, representing raw material usage in a food processing company. The comparison was done on a set of 21 data series with a high disparity of underlying process characteristics. HTM models were evaluated against 6 other approaches. As a result, HTM models were able to outperform other models in 8 out of 21 cases, with an average improvement of around 20% of RMSE value, scoring in the first place as a most accurate approach.

Filip Begiełło, Tomasz Bławucki
Preliminary Results on Constraint Programming and Branch & Bound Algorithms for the Cyclic Bandwidth Sum Problem

The cyclic bandwidth sum problem (CBSP) consists in embedding a host graph into a cycle graph while minimizing the sum of cyclic distances between guest adjacent vertices embedded in the host. While the problem has been addressed by heuristic and metaheuristic methods, to the best of our knowledge, this is the first effort to apply exact methods. This work presents preliminary results on the use of constraint programming (CP) and a branch & bound (B &B) algorithm to solve the cyclic bandwidth sum problem in small graphs from commonly employed topologies. We created a CP model of the CBSP and devised two further refined versions by adding new constraints based in problem-specific knowledge. For our proposed B &B algorithm, we designed a custom criterion for search priority employing estimations of potential cost. The results provided an assessment of the pros and cons of both methodologies, with the CP approach offering a more reliable alternative in terms of solved instances, execution time, and implementation effort.

Valentina Narvaez-Teran, Eduardo Rodriguez-Tello, Frédéric Lardeux, Gabriel Ramírez-Torres
Analysis of Vulnerability Trends and Attacks in OT Systems

For operational technology (OT) systems, security has been given an high priority in recent years after specific cyber-incidents targeting them. Earlier, these systems were focused mainly on reliability, and at present, security is also considered as an important factor to avoid production damage and financial losses. To improve the security in industrial systems, it is necessary to understand the flaws and provide countermeasures. In this paper, we focus on the cyber-incidents reported in Common Vulnerability Exposure (CVE) database on OT sub-systems like smart grids, Supervisory Control and Data Acquisition (SCADA) systems, embedded devices, and Programmable Logic Controllers (PLCs). We summarize the possible attacks on each of these sub-systems to gain broader insight of vulnerabilities present in them and use CVE database to enumerate trends.

Sandeep Gogineni Ravindrababu, Jim Alves-Foss
Simulation Model of Respiratory Sound and Technology for Separating Characteristics of Pulmonary Disease

In the process of human breathing, respiratory sounds are produced, and these sounds contain a lot of information related to the structure of the human airway. This paper uses computer and signal processing technology to collect and analyze the breath sounds to study the frequency spectrum difference between normal and abnormal respiratory sounds. Furthermore, it provides doctors/patients with a simple, quantitative, objective, intuitive, non-invasive auxiliary diagnosis tool for certain respiratory dysfunction diseases and respiratory physiology research methods.

Yiyang Luo, V. I. Lutsenko, S. M. Shulgar, Nguyen Xuan Anh
Emergent Insight of the Cyber Security Management for Saudi Arabian Universities: A Content Analysis

While cyber security has become a prominent concept of emerging information governance, the Kingdom of Saudi Arabia has been dealing with severe threats to individual and organizational IT systems for a long time. These risks have recently permeated into educational institutions, thereby undermining the confidentiality of information as well as the delivery of education. Recent research has identified various causes and possible solutions to the problem. However, most scholars have considered a reductionist approach, in which the ability of computer configurations to prevent unwanted intrusions is evaluated by breaking them down to their constituent parts. This method is inadequate at studying complex adaptive systems. Therefore, the proposed project is designed to utilize a holistic stance to assess the cybersecurity management and policies in Saudi Arabian universities. Qualitative research, entailing a thorough critical review of ten public universities, will be utilized to investigate the subject matter. The subsequent recommendations can be adopted to enhance the security of IT systems, not only in institutional settings but also in any other environment in which such structures are used.

Hamzah Hadi Masmali, Shah J. Miah
Central Bank Digital Currencies (CBDCs) as a New Tool of E-Government: Socio-economic Impacts

A central bank digital currency (CBDC) in comparison with other forms of digital money presents a direct claim on the issuing central bank. There are three architecture types of CBDC, namely indirect CBDCs, hybrid CBDCs, and direct (retail) CBDCs, all based on blockchain technology. This paper briefly discusses these three types and outlines the major socio-economic effects this new e-government tool could have on the economy.

Galia Kondova, Patrik Rüegg
An Adaptive Self-modeling Network Model for Multilevel Organizational Learning

Multilevel organizational learning concerns an interplay of different types of learning at individual, team, and organizational levels. These processes use complex dynamic and adaptive mechanisms. A second-order adaptive network model for this is introduced here and illustrated.

Gülay Canbaloğlu, Jan Treur, Peter Roelofsma
A Novel Video Prediction Algorithm Based on Robust Spatiotemporal Convolutional Long Short-Term Memory (Robust-ST-ConvLSTM)

Recently, video prediction algorithms based on neural networks have become a promising research direction. Therefore, a new recurrent video prediction algorithm called “Robust Spatiotemporal Convolutional Long Short-Term Memory” (Robust-ST-ConvLSTM) is proposed in this paper. Robust-ST-ConvLSTM proposes a new internal mechanism that is able to regulate efficiently the flow of spatiotemporal information from video signals based on higher-order Convolutional-LSTM. The spatiotemporal information is carried through the entire network to optimize and control the prediction potential of the ConvLSTM cell. In addition, in traditional ConvLSTM units, cell states, that carry relevant information throughout the processing of the input sequence, are updated using only one previous hidden state, which holds information on previous data unit already seen by the network. However, our Robust-ST-ConvLSTM unit will rely on N previous hidden states, that provide temporal context for the motion in video scenes, in the cell state updating process. Experimental results further suggest that the proposed architecture can improve the state-of-the-art video prediction methods significantly on two challenging datasets, including the standard Moving MNIST dataset, and the commonly used video prediction KTH dataset, as human motion dataset.

Wael Saideni, David Helbert, Fabien Courreges, Jean Pierre Cances
System Using Profinet Communication for Improving a Laser Engraver

This article presents a system created by the authors using Profinet communication for improving a laser engraver machine used in industrial processes for creating parts. Especially in the automotive industry, but also in many other manufacturing processes, a laser engraver is used to ensure the recognition and traceability of the parts within the production process. The system incorporates an operator panel for management, an easier way to define and apply engraving models, and a user permission system for better operability. The productivity is increased by changing the landmark involves two simple operations, changing the nest and the recipe. By introducing the Electronic Key system is eliminated unauthorized changes. Due to the RFID system and working with recipes is making impossible the incorrectly loading of the inscription program. The system allows modification of the laser program for each piece, and in the case of complex parts, data from the 2D code of the components received from another supplier to be found in the 2D code on the assembled part. Due to the multitude of messages and signals, an easy diagnosis of the machine is displayed on the operator panel, showing the status of the sensors on the machine, the status of the monitoring signals, and the error messages. A correct treatment of non-compliant parts by evaluating the signals and implementing the scrap box is making available.

Milian Badea, Sorin-Aurel Moraru, Vlad Ștefan Petre
Verification and Validation for a Project Information Model Based on a Blockchain

Agile project management based on minimum viable products has some benefits against the traditional waterfall method. Agile supports an early return of investment that supports circular reinvesting and makes the product more adaptable to variable social-economical environments. However, agile also presents some intrinsic issues due to its iterative approach. Project information requires an efficient record of the requirements, aims, governance not only for the investors, owners or users but also to keep evidence in future health and safety and other statutory compliance-related issues. In order to address the agile project management issues and address new safety regulations, this paper proposes a project information model (PIM) based on a distributed ledger technology (DLT) with a ranked procedure for the verification and validation (V&V) of data. Each V&V phase inserts a process of authenticity, data abstraction and analytics that adds value to the information founded on artificial intelligence (AI) and natural language processing (NLP). The underlying DLT consists of smart contracts embedded on a private Ethereum blockchain. This approach supports a decentralised approach in which every project stakeholder owns, manages and stores the data. The presented model is validated in a real scenario: University College London—Real Estate—Pearl Project.

Will Serrano, Jeremy Barnett
Automatic Synthesis of Cognitive Model for Revealing Economic Sectors’ Needs in Digital Technologies

The paper addresses the automation of cognitive modelling for decision-making support in revealing economic sectors needs in digital technologies. It requires to take into consideration many factors, some of which have non-formalizable character. Some aspects do not have retrospective statistic history and are latent. Cognitive modelling is one of the artificial intelligence (AI) methods for describing such situations. It considers factors of enriching AI models by cognitive semantics, which experts help to create. The actual practice has shown that the process of model building can be costly and long term. An analysis of relevant big data (BD) can help to automate the process of cognitive modelling. There are two directions of automation: a) verification of cognitive models and b) synthesizing ones. The author’s convergent approach based on the inverse problem-solving method and the genetic algorithm for decision-making on the cognitive model was applied. It helps to make the process of cognitive modelling more purposeful and stable. An experimental test and actual practice application of the approach have shown a high level of the models’ verifications accuracy (about 93%) but a low level of accuracy of models synthesizing (about 34%). One of the reasons for such a low result lies in the fact that representatives of economic sectors and the digital industry often use different terminologies.

Alexander Raikov, Alexei Ermakov, Alexander Merkulov, Sergey Panfilov
Prototype Based on a LoRaWAN Network for Storing Multivariable Data, Oriented to Agriculture with Limited Resources

Due to the advancement in information digitization in the agricultural area that has resulted in processes which are more intelligent and independent of precision agriculture, having as objective the verification, quantification, calculation, processing, and storage of variables immersed in the agricultural area, the present work shows a LoRa sensors network system, with visualization in a cloud environment through The Things Network and data analysis in an IoT platform called ThingSpeak. The objective of the use of sensors in precision agriculture (PA) is to measure the different environmental parameters (e.g., temperature, humidity, soil pH value), which are sent through a LoRaWAN gateway that receives the variables sensed by the final nodes and in turn incorporates a specialized node based on artificial vision to obtain the vegetation index. In addition, a comparison with a commercial datalogger is carried out, achieving an average error of 3.67% in the measured variables and a cost 17 times smaller in the design of the proposed system.

Steven Castro, Jhonattan Iñacasha, Gustavo Mesias, William Oñate
Real-Time and Zero-Footprint Bag of Synthetic Syllables Algorithm for E-mail Spam Detection Using Subject Line and Short Text Fields

Contemporary e-mail services have high availability expectations from the customers and are resource-strained because of the high-volume throughput and spam attacks. Deep machine learning architectures, which are resource hungry and require offline processing due to the long processing times, are not accepted at the front-line filters. On the other hand, the bulk of the incoming spam is not sophisticated enough to bypass even the simplest algorithms. While the small fraction of the intelligent, highly mutable spam can be detected only by the deep architectures, the stress on them can be unloaded by the simple near real-time and near zero-footprint algorithms such as the bag of synthetic syllables algorithm applied to the short texts of the e-mail subject lines and other short text fields. The proposed algorithm creates a circa 200 sparse dimensional hash or vector for each e-mail subject line that can be compared for the cosine or Euclidean proximity distance to find similarities to the known spammy subjects. The algorithm does not require any persistent storage, dictionaries, additional hardware upgrades or software packages. The performance of the algorithm is presented on the one day of the real SMTP traffic.

Stanislav Selitskiy
An Approach for Learning Polish Braille Mathematical Notation by Sighted Teachers Based on Liblouis Converters

Teaching mathematics to blind students is not an easy task. To read and write formulas, the blind students use the Braille alphabet and special Braille mathematical notations that are different forms in different countries. Such notation encodes mathematical symbols and whole structure of the formula in the form of Braille point signs. Teachers in mainstream schools usually encounter various problems while teaching the blind to math. One of these difficulties is their lack of knowledge of the Braille alphabet and, in particular, of Braille mathematical notation. To facilitate their cooperation with blind students, we propose a solution by which these teachers can learn the basics of Polish Braille mathematical notation (in short, BNM). It was implemented as a web application and tested by four sighted users. The application received positive feedback, although a solution must be improved and more deeply tested.

Dariusz Mikulowski
Low Energy Response of Spike Train Encoded Data

A low energy response of data encoded from a single time representation into a temporal spike train results in a sparse non-binary digital code useful for instantaneous or near-instantaneous communication of select messages. When an integrated circuit senses, an analog signal is typically converted to binary digital information. Instead, we create Markov chain data generator circuits to produce temporal spike trains which are non-binary digital signals with varying degrees of ergodicity or non-ergodic. We build a software emulator of a hardware non-binary digital circuit to demonstrate efficient data transfer of information as a non-binary digital signal. We demonstrate data reduction on streaming digital video and emulate the hardware design of an analog to non-binary digital circuit implementation. The ergodic non-binary digital signals achieve 100 $$\times $$ × data reduction over conventional binary data.

Carrie Hartley Segal
Investigations into Secure IaC Practices

Security is one of the major concerns for companies, as security attacks are rapidly increasing. There are many laws and regulations which provide guidelines to companies for securing their applications. A few of those laws impose heavy fines when appropriate measures for security are not taken. Provisioning infrastructure using manual configuration can also be a difficult task as it involves multiple steps. In this paper, we investigate securely provisioning infrastructure automatically. Security and automatic infrastructure provisioning can be achieved using source code analysis tool, container security tool, and IaC tools. We show that source code and containers can be scanned for vulnerabilities, and when critical vulnerabilities are not found, the infrastructure can be automatically provisioned using Terraform script. The authors observed that implemented systems can be scanned for vulnerabilities in source code and containers provisioned automatically using secure IaC script.

Keerthi Neharika, Ruth G. Lennon
ANETtE—Automated Network Evaluation and Test Environment

Continuous tests and measurements, as well as the evaluation of their results, are important tasks to ensure the smooth operation of modern computer networks. As this paper demonstrates, this is especially true for 5G research networks that encompass use cases with varying requirements. A fully automated approach to define, execute, and evaluate measurements in such a network is described. The resulting system consists of four distinct modules that are fully containerized and interact with each other based on well-defined interfaces. Furthermore, the automatic generation of comprehensible reports for different user groups is covered within this system. Thereby, the workload of the involved test engineers and the potential for errors are greatly reduced.

Christoph Uran, Valentin Egger, Kurt Horvath, Helmut Wöllik
A Security and Privacy-Preserving Accessing Data Protocol in Vehicular Crowdsensing Using Blockchain

This paper exploits the advantage of blockchain to fulfill secure data storage and access in vehicular crowdsensing. In vehicular crowdsensing, organizations can have a right to access vehicles’ profiles with unlimited privilege, which results in security and privacy disclosure. Thus, based on the proposed blockchain, we design a secure and privacy-preserving vehicle’s profile record accessing (BSPPA) protocol. The proposed BSPPA is able to store the vehicle’s sensing data and indexes as encrypted data for a secure indexes search. This will result in controlling the privilege of data access and prevent vehicle’s data from being revealing private data. Analysis of the security is demonstrated to show the efficiency of the BSPPA scheme. Furthermore, the performance evaluation shows the efficiency of the BSPPA protocol.

Abdulrahman Alamer, Sultan Basudan
Unconditionally Fast Secure Multi-party Computation with Multi-depths Gates Using Pre-computed Information

In secure multi-party computation (MPC), n participants execute secure communication in a circuit to compute any given function using their private inputs such that the system does not reveal any information about their inputs. Computing a share of n-inputs ( $$n>2$$ n > 2 ) multiplication gates with various multiplicative depths has been an important subject in this research field as it increases the round complexity using, for example, Beaver’s triples method. That is because just the shares of the multiplication gates with the same depth can be computed each time of implementing the existing MPC protocols, and thus, the communication rounds of a circuit with different multiplicative levels increase. In this paper, we present a secure protocol which enables computing a share of simultaneous n-inputs multiplication gates as well as the addition gate in just one round of online computation phase. Therefore, our protocol enables computing a share of any given function in just one round of computation which would result in fast computation and gives an improvement on the current MPC systems. To achieve it, we employ the technique of (Theory of cryptography conference. Springer, pp 213-230, [2]), based on hyper-invertible matrices, for generating pre-computed shares of random values. Our protocol has the unconditionally security against a coalition of t parties controlled by a passive adversary with the communication complexity $$O(n^2)$$ O ( n 2 ) for computing a share of n-inputs multiplication with different depths.

Amirreza Hamidi, Hossein Ghodosi
Real-Time Pain Detection Using Deep Convolutional Neural Network for Facial Expression and Motion

At present, in every corner of the world, including developing and developed, countries got affected by infectious diseases such as the COVID-19 virus. Our objective was to create a real-time pain detection for everyone that can use it by themselves before going to the hospital. In this research, we used a dataset from the University of Northern British Columbia (UNBC) and the Japanese Female Facial Expression (JAFFE) as a training set. Furthermore, we used unseen data from webcam or video as a testing set. In our system, pain is divided into three categories: mild, moderate-to-severe-to-painful, and severe. The system’s efficiency was assessed by contrasting its results with those of a highly qualified physician. Classification accuracy rates were 96.71, 92.16, and 98.40% for the not hurting, getting uncomfortable, and painful categories. To summarize, our research has created a simple, cost-effective, and readily understood alternate method for the general public and healthcare professionals to screen for pain before admission.

Kornprom Pikulkaew, Waraporn Boonchieng, Ekkarat Boonchieng
Machine Learning Analysis in the Prediction of Diabetes Mellitus: A Systematic Review of the Literature

In recent years, diabetes mellitus has increased its prevalence in the global landscape, and currently, due to COVID-19, people with diabetes mellitus are the most likely to develop a critical picture of this disease. In this study, we performed a systematic review of 55 researches focused on the prediction of diabetes mellitus and its different types, collected from databases such as IEEE Xplore, Scopus, ScienceDirect, IOPscience, EBSCOhost and Wiley. The results obtained show that one of the models based on support vector machine algorithms achieved 100% accuracy in disease prediction. The vast majority of the investigations used the Weka platform as a modeling tool, but it is worth noting that the best-performing models were developed in MATLAB (100%) and RStudio (99%).

Marieta Marres-Salhuana, Victor Garcia-Rios, Michael Cabanillas-Carbonell
Industrial Pumps Anomaly Detection and Semi-supervised Anomalies Labeling Through a Cascaded Clustering Approach

Automation technology has brought significant changes to agriculture, industry, commerce and other fields, among which the machine learning algorithms are the important applications of predictive maintenance of industrial equipment. In general, anomalous trends should be detected timely before failure occurs so that unscheduled downtime can be avoided. In addition, predictive maintenance can avoid unnecessary maintenance and make good use of component remaining life by setting appropriate maintenance periods for worn parts. In this paper, based on the real case in which data collected by the various sensors on coal mine pumping system, we propose a cascaded unsupervised clustering method that consists of DBSCAN and spectral clustering to identify uncommon abnormal data and classify the common abnormal data. As equipment continuously operating, the proposed cascaded clustering method can gradually utilize the obtained uncommon abnormal data to enlarge the common abnormal data. This process implemented through periodic manually labeling is regarded as a semi-supervised manner. The results show that DBSCAN has good discriminative power for uncommon abnormal data, and the spectral clustering can properly classify working condition of water pumps with 93% accuracy on test data.

Qiang Duan, Zhihang Jiang, Wei Li, Kai Jiang, Weiduo Jin, Ling Yu, Mengmeng Jiang, Jing Zhao, Rui Li, Hui Zhang
Is It Citizen-Centric? A Tool for Evaluating E-government Websites’ Citizen-Centricity

A citizen-centric e-government website is an important component for today’s governments because it is a significant instrument for increasing access to and from citizens. Evaluation of citizen-centric e-government websites content deserves attention, and a tool that focuses on evaluating e-government websites that provide a checklist of important citizen-centric characteristics is needed for e-government practitioners. This paper aims to develop an evaluation tool to measure citizen-centricity in e-government websites and demonstrate the application of this tool in Malaysia e-government websites. Using qualitative methods of literature analysis and website observation, four components and thirty-nine characteristics in seven themes were identified and incorporated into a tool named Citizen-centric Checklist for E-Government Website (CCEW). This assessment tool provides a checklist of citizen-centric characteristics that should be present in the content of e-government websites. It is designed to be a guideline for evaluators of e-government websites from government or external agencies mandated to perform e-government websites evaluation. To demonstrate the tool, CCEW is employed into Malaysia’s 5-stars e-government websites to identify its citizen-centricity level.

Kamalia Azma Kamaruddin, Nur Jannah Johari
An Application Framework for Blockchain on Smart Factory Locations Using a Datacenter Approach

We offer an in-pocket platform which allows data providers, virtual servers and AI designers to collaborate for machine knowledge representations in a permission less AI marketplace. The information is a valuable numerical tool that is important for group's perspectives. Our initiative assists data owners in protecting data access and security while supporting AI developers’ use of their data for training. Comparably, AI developers can use the calculation tools from the cloud provider against relinquishing power or privacy. Our framework protocols are designed to allow all three entities data owners, cloud vendors and AI developers to legitimately increase their behavior in the public system to test and approve of misconduct or conflict arbitration with the blockchain system. The Hyperledger Fabric is an analogy to centralized AI networks that do not have protection for information prior to modeling. We present investigational outcomes which show dormancy in various access networks where blockchain colleagues are accessible via dissimilar data centers. Our findings specify that the planned approach is well tailored to numerous data. Also, model owners can educate up to 70 models to a 12-peer un-optimized blockchain system and some 30 prototypes to a 24-peer framework.

Awatef Salem Balobaid, Saahira Ahamed, Shermin Shamsudheen, Padmanayaki Selvarajan, Praveetha Gobinathan, Betty Elezebeth Samuel
Comparison of the Improved Control of Three-Phase Two-Level and Multi-level Inverters with Sinusoidal (SPWM) and Space Vector (SVPWM) Control for Grid-Connected Photovoltaic Systems (PV)

This article is a proposal toward improved control of the three-phase two-level and multi-level photovoltaic inverter with two new control methods, by the sinusoidal (SPWM) and space vector (SVPWM) control for a nonlinear load. The contribution of this study concerns the strategies of control of the active and reactive power injected by this inverter in the grid in order to improve the losses of harmonics current in the grid. The main objective of this method is to respond to the problems encountered with the photovoltaic inverter to effectively filter the harmonics of the current. After comparing the results of the two systems, our findings suggest that the current THDi of the interlaced (multi-level) inverter is lower than that obtained with the two-level inverter, provide higher-quality waveforms, reducing current and losses caused by high-frequency harmonics. The simulation results demonstrate the effectiveness of these propose techniques in this work.

Abdelhak Lamreoua, Anas Benslimane, Jamal Bouchnaif, Mostafa El Ouariachi
Senior Citizens’ Training Experience in Secure Electronic Payment Methods

Virtual training is a mechanism that enables contemporary society to be literate, allowing up-to-date information on the technological environment, improving cognitive abilities as well as soft skills required in the workplace where individuals can develop their maximum performance. The following article presents results obtained in the literacy of older adults of Santiago de Chile, belonging to the Los Andes Compensation Fund in the area of Information Security in Electronic Payment Means, through the application of the alternative action research method under an apprehensive level methodology of the comparative analytical type of quantitative data, oriented in the development of a virtual object that allows to reduce the knowledge gap and lose the fear of the use of technology through the integration of media literacy and informational (MIL) focused on the transmission of updated knowledge and training in technological resources.

Clara Lucía Burbano González, Miguel Ángel castillo Leiva, Alex Torres, Sandra Rodriguez Álvarez
Automatic Jammer Signal Classification Using Deep Learning in the Spectrum of AI-Enabled CR-IoT

The emerging Internet of things (IoT) technology facilitates ubiquitous and seamless connectivity of various objects to provide different services. It is envisioned to incorporate self-awareness (SA) capabilities into the IoT devices to make the entire network autonomous and intelligent, giving the concept of cognitive radio (CR) CR-IoT network. Like other wireless networks, CR-IoT suffers from various kinds of abnormal attacks. However, due to the developments of deep learning models, it has become possible to efficiently recognize and classify malicious signals present in the signal transmission. In this work, we implemented deep learning models (AlexNet and GoogLeNet) to classify jammer signals present in a CR-IoT network using fast Fourier transform (FFT) and continuous wavelet transform (CWT) features extracted from the received orthogonal frequency division multiplexing (OFDM) signal spectrum. The CR-IoT network is considered in which users and a jammer are present. Both models are capable of classifying signals into the normal signal spectrum, jammer with high power, and jammer with low power. The performance of the proposed method is evaluated using receiver operating characteristic (ROC) curves.

Muhammad Farrukh, Tariq Jamil Saifullah Khanzada, Asma Khan
Arm-Z as a Modular Tracking Device

Arm-Z is a hyper-redundant manipulator based on a sequence of linearly joined identical modules. Each module has only one degree of freedom—a twist relative to the previous module. Arm-Z can be potentially economical, as the modules can be mass-produced. Arm-Z is also robust, as the malfunctioning module can be replaced. Moreover, if some modules malfunction, the device can still execute tasks with certain accuracy. However, the disadvantage of Arm-Z is a non-intuitive and difficult control. This paper presents a concept of a modular tracking device comprised of four identical modules. As an example, the Sun-tracking setup is used with possible application for solar energy harvesting.

Ela Zawidzka, Jacek Szklarski, Machi Zawidzki
Epidemiological Profile of Cutaneous and Visceral Leishmaniasis in the City of Meknes, During the Period from 2014 to 2019

Introduction Leishmaniasis is a common parasitosis of humans and animals. They are caused by flagellated protozoa belonging to the genus Leishmania and transmitted to humans by the bites of insect vectors, called female sandflies. They are the second most common cause of parasitic death worldwide after malaria and are endemic in Asian and African countries. In Morocco, they pose a real public health problem. The objective of our work is to analyse the spatial and temporal distribution of cutaneous and visceral leishmaniasis in order to evaluate the epidemiological situation of these parasitoses in the region of Meknes and to appreciate their evolution according to the nature of the environment. Material and method In this context, we conducted a retrospective study during the period from 2014 to 2019, collecting all cases of leishmaniasis reported in this city. Epidemiological data were collected from the registers of new cases of leishmaniasis at the service of infrastructure and ambulatory actions of the provincial and prefectural delegation of the Ministry of Health of Meknes. Results A total of fifty-four new cases were declared infected, these data shows that there is coexistence of both forms of leishmaniasis: cutaneous (79.63%) and visceral (20.37%) with a predominance of rural areas (61.11%), as well as, the sex ratio was 0.86 and the average annual incidence was 9 cases per year. Conclusion The major challenge for Morocco between now and 2030 is the definitive elimination of leishmaniasis, which requires the adoption of a global approach by acting on the sources of contamination through surveillance and appropriate management, effective control of vectors and reservoirs, and innovative strategies to raise awareness in local society.

Abdelfatah Benchahid, Driss Belghyti, Zakaria Zgourdah, Omar Lahlou, Said Lotfi, Khadija El Kharrim
A Novel Context-Aware Recommendation Approach Based on Tensor Decomposition

In the information age, the ability to analyze data has a fundamental role. In this field, recommender systems, that are able to provide suggests to users analyzing the information provided to system, play a central role. Moreover, the use of contextual information make recommender systems more reliable. This paper aims to describe a novel approach for context-aware recommender systems that exploits the tensor decomposition CANDECOMP properties in order to provide ratings forecasts. The proposed approach is tested on DePaulMovie dataset in order to evaluate its accuracy, and the numerical results are promising.

Francesco Colace, Dajana Conte, Brij Gupta, Domenico Santaniello, Alfredo Troiano, Carmine Valentino
Application of E-commerce Technologies in Accelerating the Success of SME Operation

Application of electronic commerce (e-commerce) technologies has increased notably over the past two decades in different business sectors. In particular, the technologies of B2C operations have significantly improved the productivity of online small businesses such as SMEs. Systematic literature reviews in this domain categorized different, benefits but a limited number of studies on SME success from the view of information systems (IS) research exist, which needs to be taken for further attention. Through a comprehensive analysis, this study introduces a conceptual framework for the application of e-commerce technologies in accelerating SME operation. Content analysis methodology was adopted for generating the outcome associated with the success of the technologies in SMEs.

Ziad Almtiri, Shah J. Miah, Nasimul Noman
Cibercidadão: Evolution of Citizen Participation in Public Administration

The Cibercidadão initiative began with the advent of digital transformation and the digital government law, which identified the need for efforts to improve digital public services. However, it was also observed that the improvement of digital public services would not be achieved individually with a view only from the public service, but together with the view of the citizen who uses this service. Thus, we identified that the citizen himself would be the most interesting part of this transformation process, as digital public services must be developed to meet the needs and expectations of citizens. In this scenario, we identified the existence of the Cibercidadão in society, that active and participative citizen of the public administration, which contributes to the improvement of public services. Thus, the Cibercidadão methodology places the citizen at the center of the digital transformation, sending ideas about technology and government, developing software solutions, testing and evaluating the solutions made available to society. Finally, the Cibercidadão is applied in a Government Program aimed at the development of innovative and citizen-centered software solutions, whose results are already promising.

Camila Z. Aguiar, Tasso M. Lugon, Delvani A. Mateus, Ádler O. S. Neves, Uliane B. Bernadino
A Low-Cost and Energy Autonomous IoT Framework for Environmental Monitoring

The emergence of IoT devices that support sensor technology has gain much attention for their integration into smart city applications to improve citizens’ quality of life. In industrial territories, people that suffer from chronic respiratory diseases, e.g., chronic obstructive pulmonary disease, asthma, occupational lung diseases and pulmonary hypertension require special care, targeted information and efficient treatment, when the environment deteriorates their condition. This article presents the design of an IoT framework that wirelessly connects devices of low-cost, low-power consumption and integrates multi-sensor measurement capabilities (CO2 concentration, humidity, temperature, particulate matters concentrations) with an open-source IoT platform aiming to alert the aforementioned population, when the combination of aerial pollution and weather conditions severe impact their daily activities. The energy autonomy of the IoT devices that are connected via wireless sensor network is explored and utilized. Finally, we evaluate the functionality and the accuracy of the low-cost sensors and demonstrate how proper filtering can improve their performance and mitigate problems stemming from outage times. For the latter, we have evaluate the effectiveness of forecasting algorithms like ARIMAX, LSTM and PROPHET on the measurement data.

Vasileios Galafagas, Fotios Gioulekas, Panagiotis Maroulidis, Nikolaos Petrellis, Panagiotis Katsaros
Cloud-Based E-learning: Concepts, and its Beneficial Role During the COVID-19 Dilemma

In the epoch of education and emerging technologies, information technology plays a considerable role in the field of education. Cloud computing is one of the most leading emerging paradigms in computing’s leverage on education due to its dynamic scalability, high availability, and other valuable characteristics. Traditional E-learning systems have a high infrastructure required to provide concurrent service to various learners. The use of a cloud computing platform offers an effective solution to enhance the quality of education by providing novel methods of learning and teaching which affect both learners and instructors. This paper will introduce why cloud-based E-learning enhances the quality of education by first investigating its concepts, including its architecture and characteristics. A shift from E-learning to cloud-based E-learning is also discussed. Accordingly, the benefits of using cloud-based E-learning are highlighted for the institutions, learners, and instructors. The recent challenges of cloud-based E-learning are also explained, and future work will provide ways to overcome them. The sudden (COVID-19) pandemic has affected general safety, the economy, and education worldwide. As a result, many preventive measures such as lockdowns and social distancing are enforced. Such changes put unprecedented pressure on the education process. To keep up sustained and productive education, educational institutions of all nations switched to online teaching and learning. Hence, the demand for cloud-based E-learning applications has increased to engage learners in the online mode settings. This paper also discusses the impact and benefits of the cloud-based E-learning systems during COVID 19 dilemma.

Rasha Al Bashaireh
Packet Replays Prevention Protocol for Secure B5G Networks

The beyond 5G networks (B5G) are characterized by high throughputs at extremely low latencies and better energy consumptions. This has seen them being deployed as the backbone of numerous Internet of Things (IoT) application domains such as smart homes, smart cities and in intelligent transport systems. Massive and private data flows in these ultra-dense networks and hence the need to protect them. As such, the Third-Generation Partnership Project (3GPP) has defined Authentication and Key Agreement (AKA) protocols for secure signaling and packet exchanges in these networks. However, these AKA protocols are susceptible to numerous attacks, such as impersonation and packet replays. This has seen the development of numerous schemes based on techniques such as public key cryptography, biometrics, group signatures and blockchain. Unfortunately, these schemes fail to offer the required levels of security and privacy protection at low execution time, energy and bandwidths. In this paper, a protocol is developed that leverages on the message authentication codes, symmetric cryptography and elliptic curve cryptography. It is shown that the proposed protocol is secure under the Dolev–Yao model. In terms of performance, it exhibited the lowest execution time and has the lowest bandwidth requirements.

Vincent Omollo Nyangaresi, Junchao Ma, Mustafa A. Al Sibahee, Zaid Ameen Abduljabbar
Measuring the Uptaking of Digital Health Platforms on AAL/AHA Domain

This paper presents a method to determine the metrics to assess the uptake of Ambient Assisted Living (AAL) platforms. The different platforms are offering various resources to construct digital health products oriented to Active and Healthy Aging (AHA) and social health care. This research work is addressed to identify and define which metrics could be Key Performance Indicators (KPIs) to be tracked for successful uptake, interoperability, synergies, and cost–benefit analysis of open platforms.

Carlos Juiz, Belen Bermejo, Alexander Nikolov, Silvia Rus, Andrea Carboni, Dario Russo, Davide Moroni, Efstathios Karanastasis, Vassiliki Andronikou, Christina Samuelsson, Frederic Lievens, Ad van Berlo, Willeke van Staalduinen, Maria Fernanda Cabrera-Umpierrez
Improving Arabic Hate Speech Identification Using Online Machine Learning and Deep Learning Models

Due to the rising use of social media platforms on a global scale to interact and express thoughts freely, the spread of hate speech has become very noticeable on these platforms. Governments, organizations, and academic institutions have all spent substantially on discovering effective solutions to handle this issue. Numerous researches have been performed in several languages to find automated methods for identifying hate speech, but there has been minimal work done in Arabic. The findings of a performance evaluation of two machine learning models, namely the passive-aggressive classifier (PAC) and the Bidirectional Gated Recurrent Unit (Bi-GRU) augmented with an attention layer, are investigated in this work. Proposed models are developed and evaluated using a multi-platform Arabic hate speech dataset. We employ term frequency-inverse document frequency (TF-IDF) and Arabic word embeddings for feature extraction techniques after running a variety of pre-processing steps. The experimental results reveal that the two proposed models (PAC, Bi-GRU with attention layer) provide an accuracy of 98.4% and 99.1%, respectively, outperforming existing methods reported in the literature.

Hossam Elzayady, Mohamed S. Mohamed, Khaled Badran, Gouda Salama
Application of Fuzzy Logic in Sales Inventory System: A Literature Review

The largest revenue comes from most sales. If the company offers far fewer types of goods than the types demanded, the company loses the opportunity to generate maximum revenue and vice versa. Therefore, planning the number of product purchases for inventory becomes very important. The purpose of this study is to review what factors cause inventory to increase. The literature review is primarily based on questions, methodologies, similarities, and additional research suggestions. This study uses seven papers including using the fuzzy method for inventory in sales. Based on the results of those papers, the fulfillment of inventory prices built by fuzzy logic will help to understand the purchase of various products in inventory in the next month. The analysis found that the inventory that is close to optimal is obtained through calculations using the fuzzy method.

Gede Indrawan, I. Putu Andika Subagya Putra, Luh Joni Erawati Dewi, I. Gede Aris Gunadi
Statement Emotion Decision Model for Human-Friendly Chatbot

A chatbot is a software that gives proper answers and information for users, and provides useful information to users. Users basically express their feelings to others, and seek to exchange their feelings. However, the chatbot does not respond to the user’s emotional state, but focuses on providing information. Since the chatbot understands the intention of the question without considering the user’s emotional state, the accuracy of intention analysis is poor, and cannot provide accurate answers. In this paper, we develop a module that can know the user’s mood, including newly coined terms and emojis, and apply it to the chatbot. The chatbot consists of an intent decision module that analyzes the user’s intention, a mood decision module that infers the user’s internal mood, and an answer decision module that generates answers to the user’s sentences. The mood decision module consists of an emotion classification model that classifies the user’s emotions through the sentences of users, and a mood determination model that infers the user’s mood through the classified emotions. It infers the user’s current mood state in real-time using the emotion classification model and the mood determination model. The chatbot analyzes morphemes and syntax for user sentences. By building a sentiment dictionary based on the Korean dictionary, the emotions of morpheme-analyzed words are classified. To classify the emotions of new words and emojis, the newly coined terms and emojis emotion dictionary is used to classify the emotions of newly coined terms and emojis. Emotions are classified using naive Bayes classification, and for words that are not classified by naive Bayes classification, an artificial neural network model is used to increase the accuracy of emotion classification. The chatbot infers the mood state using the mood determination model. The mood state consists of the emotional state representing the eight emotions to be classified and each emotional value, and infers the user’s mood with the mood state extracted through the mood determination process.

Kyoungil Yoon, HeeSeok Choi, Kwang Sik Chung
Secured Supercomputer Technologies in Russia: Functional Computing Units Based on Multithread-Stream Cores with Specialized Accelerators

A new direction in the design and implementation of Russian secure supercomputers is massively parallel reconfigurable computers. This article describes further development of secured strategic supercomputer “Angara.” The service nodes are built on conventional superscalar microprocessors. Computing nodes are built on special multicore multithread-stream microprocessors (microprocessors of the J-series) are combined into modules in the form of multi-socket boards and can work on a logically single addressable memory (globally addressable memory). Author demonstrates basic features of new functional computing units with specialized accelerators.

Andrey S. Molyakov
Systematics Review on Detecting Cyberattack Threat by Social Network Analysis and Machine Learning

This literature review gives an up-to-date overview of studies aimed at analyzing the information contained in social media messages, which reflect malicious activity that threatens cyberspace. This work presented studies aimed at detecting and predicting cyberattacks with the intent of altering, controlling, manipulating, damaging, or affecting victims’ digital services, computing equipment, and communications equipment of the victims. The method used in this systematic literature review is based on the model proposed by Petersen et al. The conclusion from the studies showed that the use of machine learning algorithms, deep learning, and natural language processing tools contributes to better detection of threats in social media. For future research, it is necessary to continue the implementation of the most recent tools of machine learning and deep learning and natural language processing, to improve the effectiveness of the results. The findings of this systematic review will enable the researcher to develop methodologies and mechanisms that could help detect and prevent future cyberattacks.

Rizal Tjut Adek, Bustami Bustami, Munirul Ula
Adaptive Multi-attention for Image Sentence Generator Using C-LSTM

Capturing image feature and multi-object region of an image and transferring it into a Natural Language Sentence is a research issue needs to be addressed with natural language processing. Technically, the attention mechanism will force every word representation to an corresponding image region, however at times it do neglect certain words like ‘the’ in the description text, as it misleads the text interpretation. The captioning of an image involves not only detecting the features from various images, but also decoding the collaborations between the items into significant image text. The focus of the suggested work, predicts the image sentence in a more detailed way for every region/frame of an image. To overcome, an image feature extraction is carried out using CNN and LSTM for the image text generation with the help of adaptive attention mechanism, which will be add in the layer of LSTM to predict better image sentence is constructed. The above mentioned deep network methods have been analyzed using two output combination. Experiments have been implemented using Flickr8k dataset. The implementation analysis illustrates that adaptive attention performs significantly better than without adaptive attention of image sentence model and generates more meaningful captions compared to any of the individual models used. From the results on test images, the suggested network gives the accuracy, bleu score with and without using adaptive attention in the LSTM of 81.53, 61.94 and 73.53, 57.94%.

K. A. Vidhya, S. Krishnakumar, B. Cynddia
A Low-Cost Smart Monitoring Device for Demand-Side Response Campaigns

The energy transition requires an increasing penetration of renewable resources, particularly at MV/LV levels. The emerging production scheme is characterized by distributed power plants, imposes a capillary control of production and consumption among the distribution network (DN). The implementation of demand-side response (DSR) campaigns is widely seen as a solution that can increase grid stability, but they require a complex and expensive monitoring infrastructure to select the optimal operating point of the production/consumption systems. This paper suggests a cheap and reliable smart monitoring device based on Raspberry Pi technology. The communication infrastructure adopted in the smart building of ASM S.p.A., the distribution system operator (DSO) of Terni city, shows the feasibility of implementing this prototype on a large scale.

A. Geri, F. M. Gatta, M. Maccioni, J. Dell’Olmo, F. Carere, M. A. Bucarelli, P. Poursoltan, N. Hadifar, M. Paulucci
Investigating the Sinkhole Attack in Cognitive Wireless Sensor Network

Wireless sensor network (WSN) is a network that senses its environment, collects data, and routes data to sink node through wireless links. However, security is a challenge. Sinkhole attack is one of the main security issues that threatens the operation of WSN. Sinkhole nodes advertise themselves as best link route to the base station for malicious reasons. Thereafter, the attacker drops packets and modifies data, enabling other attacks such as selective forwarding and worm-hole attacks to be launched. This study focusses on investigating the effectiveness of sinkhole attack mitigation schemes in cognitive WSN and designed a framework for future research. MATLAB simulation tool was utilized to simulate and evaluate the sinkhole attack mitigation schemes, and comparative results were generated. The metrics which were considered in the simulation are the packet delivery ratio, probability of detection, and the probability of false alarm. The results show that the mitigation of sinkhole attacks requires further attention.

Zenzele Malale, Mthulisi Velempini, Sekgoari Semaka Mapunya
A Novel Software Architecture to Calculate Effort Estimation for Industrial Big Data

Software development effort estimation is one of the main sub-disciplines of software cost estimation, which comes under software project management. To estimate effort accurately, we noted different estimation models. With the combination of expert judgment, data mining, and machine learning, the motive of this study is to propose a new software architecture for effort estimation. The proposed architecture uses techniques such as expert judgment along with K-means clustering and machine learning techniques such as ANN, SVR, LR, RF, and KNN. At last, we used RMSE, MAE, MMRE, and Pred (.25). After the experimentation, we noted the increase in estimation accuracy was seen with the use of the proposed estimation model. Moreover, support vector regression outperformed all other algorithms with K = 3 and 5 and expert input. Therefore, we concluded the effort estimation of industrial big data is an important step and needs to be given attention in software organizations.

Sadia Khan, Ammad Adil
Scientific Music Therapy Technologies for Psychological Care and Rehabilitation in the COVID-19 Pandemic

This article analyzes the complex challenges of the pandemic and prospects of the scientific music therapy technologies used in psychological care and rehabilitation patients with COVID-19. First, the researchers found that COVID-19 can occur in asymptomatic or mild clinical forms and severe clinical forms with the development of pneumonia and respiratory failure. More recently, another severe problem of the pandemic has appeared, and it is different mental disorders. The achievements of scientific music therapy are so significant that they improve mood and optimize the function of vital systems, even online, which is very actual for patients with COVID-19. That was the reason to present the basics and technologies of SMT, including the concept model of the multifunctional autonomous robot “Helper” for medical services, rehabilitation, and music therapy. The article's conclusive idea is that integration of science, advanced technologies, and art will play an increasingly significant role in modern rehabilitation treatment and hospital services in pandemics.

Sergey V. Shushardzhan, Natalya Eremina, Ruben Shushardzhan, Tatiana Allik, Kumyszhan Mukasheva
Analysis of the Development of Electrification of Urban Public Transport in China Based on Life Cycle Cost Theory

Since 2009, under the vigorous promotion and drive of the country’s active industrial development policy, China’s public transport has evolved from a single traditional fuel public transport to natural gas, hybrid, electric, and hydrogen in just ten years. This paper takes these five types of public transport as the research object and uses the life cycle cost theory to analyzing their economy, the relevant actual operation data are collected by investigation and establishes the life cycle cost measurement model of the above five types of urban public transportation. The difference analysis is carried out on the initial purchase cost, use cost, maintenance cost, scrap income, and life cycle cost. On this basis, this paper analyzes the reasons from an economic perspective why China has chosen pure electric power as the development path of urban public transport in a variety of energy types after years of exploration.

Qingdong Luo, Jingjing Lou, Xiyuan Wan, Yunhan Li, Pengfei Zheng
A Systematized Literature Review: Internet of Things (IoT) in the Remote Monitoring of Diabetes

The Internet of Things (IoT) is an important emerging technology that enables (usually) pervasive ubiquitous devices to connect to the Internet. Medical and Healthcare Internet of Things (MHIoT) represents one of the application areas for IoT that has revolutionized the healthcare sector. In this study, a systematized literature review on the adoption of MHIoT for diabetes management is done to investigate the application of IoT in the monitoring of diabetes, key challenges, what has been done, in which context, and the research gap using Denyer and Transfield’s systematic literature review methodology. The key findings reveal that developing nations are lagging despite the greater benefits of MHIoT in such resource-constrained contexts. The findings suggest that infrastructure costs, security, and privacy issues are most important in the adoption of MHIoT for diabetes management. The opportunities presented by MHIoT surpass the challenges as healthcare costs are reduced in a resource-constrained context. Further research in infrastructural needs and privacy concerns is needed to take full advantage of these benefits and address the challenges.

Belinda Mutunhu, Baldreck Chipangura, Hossana Twinomurinzi
Application of Sound of Kobyz in Online Therapy and Health Improvement

Due to the tense modern rhythm of life, environmental, economic and social problems, there is an alarming trend toward an overall increase in mental illness and psychological disorders (Gusakova in Musical-therapeutic potential of elementary music-making and individual improvisation activity. I International Scientific and Practical Conference “Music and Health”. Collection of reports and abstracts M.: National Association of Music Therapists, p. 31, 2009). Therefore, the search for new non-drug methods of psychological correction and health improvement of the population is the most urgent modern task. Recently, methods of music therapy have become more and more widespread. The author of the method has released a therapeutic disk “Gylkobyzdyn shipasy”, which includes seven compositions reproduced by the author. The novelty of this research lies in the study of psychological, physiological and ethnocultural aspects of the use of the ancient Kazakh musical instrument Kobyz for health purposes. “Kobyztherapy” is a universal, progressive method of online recovery in areas such as psychology, sociology, health care and the social sphere, especially in the current COVID-19 pandemic.

Kumyszhan Mukasheva, Engelika Zhumataeva
Building a NoSQL ERP

Enterprise resource planning (ERP) systems are needed in many business activities. Small and medium enterprises (SMEs) are not well-served by current ERPs, as such systems are hard to tailor. This prompts us to experiment with building an ERP on top of a NoSQL database, which intends to be more flexible, as it is based on JSON and not on a relational data model. We present a novel ERP solution specifically designed to grow and evolve as the world changes. The ERP is for a service company which bills for time spent on customer projects. The work involves various challenges: data modelling, query specification, write and read performance analysis, versioning, user interface generation and query optimisation. Here, we report on the performance of a NoSQL ERP using MongoDB and show that writes are fast and queries and reports are fast enough.

Ela Pustulka, Stefan von Arx, Lucia de Espona
Models for Estimation of Concrete Compressive Strength Based on Experimental Research with Destructive and Non-destructive Methods

This article presents experimental studies for assessing the concrete compressive strength in existing reinforced concrete members with destructive and non-destructive methods. For the destructive tests, 12 cube test specimens and 12 reinforced concrete beams (from which, 11 cores were drilled) were prepared in one day with the same recipe composition of the concrete. For two years, the reinforced concrete members were indoors, and in the following years, they were left outdoors exposed to external atmospheric influences. The research is aimed at the combined use (SonReb method) of two non-destructive methods: the method of elastic rebound (Schmidt rebound hammer) and ultrasonic pulse velocity method (UPVM) in order to achieve greater accuracy in assessing the compressive strength of concrete. Models have been developed describing the correlation between the determined compressive strength in the destructive test of cubes and cores with the measured rebound number and ultrasonic pulse velocity for the age of the concrete 1126th and 1926th day. The analysis was performed in Microsoft Excel environment.

Ivan Ivanchev
IU-AutoSVD++: An Item–User Features-Based Recommender System Using Contractive Autoencoder and Matrix Factorization

Matrix factorization is a successful approach in recommender systems that is used largely to provide adequate recommendations to users. In the last years, many approaches based on deep learning, such as autoencoders, were used or combined with other methods to extract nonlinear relationships between items. But most of these models do not include user’s information side in the rating process. In the present article, we have proposed a new model IU-AutoSVD++ combining the matrix factorization and the contractive autoencoder in order to include item features and user side information. Experiments results prove that our model performs better than many baselines models.

Abdelghani Azri, Adil Haddi, Hakim Allali
Model Learning and Tactical Maneuver Planning for Automatic Driving

Tactical maneuver planning is one of the key enablers for automated driving. The challenges include complex situations in urban areas and the uncertain behavior of other road users. In this paper, we present an approach to model the decision problem of tactical maneuver planning as a Markov decision process (MDP) for a two-lane road. It is shown how this model can be used to make tactical maneuver decisions on a three-lane road without increasing the complexity of the MDP. Furthermore, it is shown how the model can be learned and improved in a three-lane simulation environment using real-world experience. The results show that the learned model represents the environment better than the manually modeled MDP and that a significantly better driving strategy is calculated based on this.

Micha Helbig, Jens Hoedt, Ulrich Konigorski
Fake Review Detection with Concept Drift in the Data: A Survey

Online reviews have a great impact on the e-commerce industry. Online users are free to post their perspective on products, which might not always be unbiased or accurate. Such unbiased reviews from the customers can affect both buyers and sellers in the industry. The details of this paper focus on a fake review detection system. This paper examines different techniques used in fake review detection which involves data pre-processing to pre-process and extract features from raw data, classification to classify review as fake or real. Also, our study deals with drift in data, its detection methods, as well as drift adaptation strategies.

Ketan Sanjay Desale, Swati Shinde, Nikita Magar, Snehal Kullolli, Anjali Kurhade
A Survey on Research Directions in Blockchain Applications Usability

This research systematically reviews blockchain usability studies published between 2017 and 2021. It analyzes direction trends aimed at improving the overall blockchain application’s real-world adoption. After determining the inclusion and exclusion criteria, 22 articles were included in the review. This work presents the major existing challenges found in Blockchain applications, such as privacy issues and non-regulation, and the proposed solutions, including increased transparency and simple usable applications. Major findings include the fact that user surveys are the most popular method among these studies compared to expert surveys or observational studies. Most of the current blockchain usability studies are performed for applications related to the financial domain, followed by health care, supply chain applications, energy, and e-voting. The majority of these studies include less than 20 participants for the expert-based and less than 40 for user-based ones. This study further investigates the domain-specific target systems. The healthcare-related surveys concentrated on the usability of users’ data on electronic medical record (EMR). In the financial field, the focus was mostly on the use of crypto wallets or crypto applications. The main concern among participants in healthcare-related applications was the privacy of their medical data while in finance, the concern was the lack of a local regulatory body. This research has important implications that can help researchers address challenges and implement appropriate solutions, which can improve their adoption rate.

Vivek Sharma, Tzipora Halevi
Detection of Respiratory Disease Patterns Using Mask R-CNN

The analysis and identification of pathological signs associated with different respiratory diseases are is not an easy task. One of the imaging modalities for these signs identification is examining chest CT scans. However, it requires expert knowledge to avoid human error. The purpose of this work is to implement, test, and analyze the performance of a neural network based on a mask R-CNN model able to identify some pathological signs of respiratory disease. The CT images used were manually labeled and pre-classified as positive and negative cases by specialists to prepare them for the training process. Preliminary results reached detection of ground-glass opacity with a sensitivity of 81.89% using the validation set and 92.66% using the test set. Nevertheless, low percentages were obtained for pulmonary nodules detection with a sensitivity of 51.08 and 40.34% using validation and test sets, respectively.

Eisler Aguilar, Alexandra La Cruz, Raul Albertti, Martin Carnier, Liliana Gavidia, Erika Severeyn
Efficient Support Vector Machine Toward Medical Data Processing

This work explores the efficient and practical scheme of medical data analysis through machine learning algorithms. The support vector machine (SVM) mechanism is specifically employed for building an artificial intelligence (AI) assistant diagnosis systems. Considering the practical demands on clinical diagnosis, the plain SVM algorithm is hardly used since the poor number of classes (typically, two classes) and explosion of samples. Therefore, a sample domain description technology is developed to realize a one-class SVM for flexibly expending the number of classes. Furthermore, a constantly online learning strategy is proposed to implement high-performance classification/diagnosis with greatly reduced database. For proof-of-concept, several medical databases are employed for diagnosis test. From the test results, the diagnosis correct rate is improved with compact database; and the scale of database is reduced while the similar correct rate is achieved by plain SVM algorithm. Maintaining the best accuracy, the proposed online learning SVM reduces the numbers of active samples (support vectors) to $$23.4 \%$$ 23.4 % , $$54.6 \%$$ 54.6 % , $$70.9 \%$$ 70.9 % of the plain for diagnosing the breast cancer, diabetes, and liver disorders, respectively, where the best accuracy is superior or similar to state-of-the-arts.

Guang Shi, Zheng Chen, Renyuan Zhang
Geometric and Physical Building Representation and Occupant’s Movement Models for Fire Building Evacuation Simulation

Building evacuation simulation allows for a better assessment of fire safety conditions in existing buildings, which is why it is of interest to develop an easy-to-use Web platform that helps fire safety technicians in this assessment. To achieve this goal, the geometric and physical representation of the building and installed fire safety devices are necessary, as well as the modelling of occupant movement. Although these are widely studied areas, in this paper, we present two new model approaches, either for the physical and geometric representation of a building or for the occupant’s movement simulation, during a building evacuation process. To test both models, we develop a multi-agent Web simulator platform. The tests carried out show the suitability of the model approaches herein presented.

Joaquim Neto, A. J. Morais, Ramiro Gonçalves, António Leça Coelho
Safety State Assessment of Network Control System Based on Belief Rule Base

The current network control system (NCS) cannot assess the system safety state in a timely, comprehensive, and accurate manner, which leads to serious security problems in NCS. Directing at the defects of existing security state assessment models for the NCS, a method of safety state assessment of the NCS based on the belief rule base (BRB) expert system is proposed in this paper. Firstly, the expert system of the BRB is used to combine qualitative knowledge with quantitative monitoring data. Then, the evidential reasoning (ER) algorithm is used for knowledge reasoning, and the initial parameters of BRB model are optimized. Finally, taking the data of a gas NCS as an example, the experimental results illustrate that the assessment accuracy is higher than that of back propagation (BP) and support vector machines (SVM) evaluation models.

Ying Han, Limin Xiao, Jie Luo, Jie Zeng, Xin Su
Bringing Explainability to Model Deployment Pipeline in Deep Learning Workbench

Widespread use of highly accurate and trustworthy deep learning architectures is becoming a noticeable trend in the industry. Model accuracy and inferencing performance traditionally remain the two important factors to be considered before model deployment to any business application. Additionally to these two requirements, the problem of model explainability is becoming increasingly acute. In this paper, we propose a methodology for ensuring that pretrained deep learning models provide optimal performance, have an acceptable accuracy level, and make trustworthy decisions. The methodology is tested on a classification computer vision model, taking into account specified business requirements.

Alexander Demidovskij, Tatiana Savina, Alexander Suvorov, Mikhail Fedorov, Yury Gorbachev
A Review of a Research in 2021 on Coronavirus Disease (COVID-19) in Pediatric Patients

Background Although there were other reviews in 2019 and 2020, this is the first review of research that summarizes clinical features of the children with COVID-19 mentioned in literature in 2021. This paper analyses the findings on COVID-19 infection in children in three countries. Objective The purpose of this paper is to review publications using chest CT scans and chest X-ray findings for children with COVID-19 in 2021. Materials and methods Studies on COVID-19 for articles presenting scan findings in children with COVID-19 have been included in this review. This review focused on articles including 0 < age and age < 18 years using descriptive statistics to identify patterns including duration and several symptoms of the disease, and their relationship with outcomes. Results 12 research articles (n = 6212 children) based on chest CT scans and chest X-ray have been examined. The main results of this review article are as follows: (i) Approximately 1728 (27.81%) of pediatric patients with COVID-19 had normal chest CT scans and chest X-ray images. (ii) The most frequently detected parenchymal lesion was ground glass opacity (GGO) and also bilateral lesions were the common signs of lung lesions. (iii) The lung CT scan findings in children with COVID‐19 were less severe than in adult patients.

Burcu Kir Savaş
Transferability of Quantum Adversarial Machine Learning

Quantum adversarial machine learning lies at the intersection of quantum computing and adversarial machine learning. As the attainment of quantum supremacy demonstrates, quantum computers have already outpaced classical computers in certain domains (Arute et al. in Nature 574:505–510, 2019 [3]). The study of quantum computation is becoming increasingly relevant in today’s world. A field in which quantum computing may be applied is adversarial machine learning. A step toward better understanding quantum computing applied to adversarial machine learning has been taken recently by Lu et al. (Phys Rev Res 2:1–18, 2020 [13]), who have shown that gradient-based adversarial attacks can be transferred from classical to quantum neural networks. Inspired by Lu et al. (Phys Rev Res 2:1–18, 2020 [13]), we investigate the existence of the transferability of adversarial examples between different neural networks and the implications of that transferability. We find that, when the fast gradient sign attacks, as described by Goodfellow et al. (Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 [9]), is applied to a quantum neural network, the adversarially perturbed images produced with that method have transferability between quantum neural networks and from quantum to classical neural networks. In other words, adversarial images produced to deceive a quantum neural network can also deceive other quantum and classical neural networks. The results demonstrate that there exists transferability of adversarial examples in quantum machine learning. This transferability suggests a similarity in the decision boundaries of the different models, which may be an important subject of future study in quantum machine learning theory.

Vincent Li, Tyler Wooldridge, Xiaodi Wang
Conceptual Analysis and Design of Semantic Interoperability of Smart City Services

Smart city projects now mainly focus on developing data management platforms. They help to store, process, visualize and provide data access for better services. The smart city knowledge management platform (KMP) is a more complex solution. Developing the city IT infrastructure based on KMP helps to achieve semantic interoperability between city actors and create a digital eco-system of smart services capable to negotiate, compete and cooperate. In this work, a detailed approach and step-by-step design and development instruction for KMP and semantic interoperability are presented.

Sergei Kozhevnikov
Construction and Analysis of Kepler’s Cosmographic Mystery, for Learning the Platonic Solids Using Mathematica

This research work revolves around the need to learn regular polyhedral constructions and find the relationships that exist with the spheres that inscribe them in the structure of Kepler’s Cosmographic Mystery. We often do not realize that polyhedra are present in almost everything around us, and that throughout history, man has been fascinated by Platonic solids. At present, students live in reverse in the massive use of electronic equipment in their learning, as well as software and applications. Given the high demand for the acquisition of digital skills worldwide, students can be motivated to strengthen their learning of mathematics and acquire programming skills by observing, analyzing and arguing a programming strategy to design the Cosmographic Mystery of Kepler, also the existing relationships in the structure under study. Therefore, through this work, it is intended to provide the teacher with resources and programming skills for the teaching of regular polyhedra. Mathematica software has been considered for its high programming and display quality. In addition, the Wolfram programming language is accessible through the Raspberry computer. The objective of the research work is to provide a working methodology for the study of regular polyhedra and acquire programming skills. Also, strengthen their observation and analysis skills from their models for the design of Platonic polyhedra through the programming language, allowing students to explore 3D spaces.

Felícita M. Velásquez-Fernández, Judith K. Jiménez-Vilcherrez, Carlos E. Arellano-Ramírez, Robert Ipanaqué-Chero, Ricardo Velezmoro-León
Meaningful Learning of Regular Basic Education Students in the Construction of Polyhedra from the Cube in a Graphical 3D Geometry Environment

This research paper revolves around the need to learn polyhedral constructions. Students often do not realize that polyhedra are present in almost everything around them: microorganisms, minerals, architectural constructions and virtual reality objects. Currently, there is an accelerated process in the acquisition of digital skills worldwide, which can motivate and strengthen the meaningful learning of mathematics. For this reason, it is important that the teacher manages technological resources for the teaching of mathematics and thus awaken the student’s interest in learning. We consider GeoGebra free software as an excellent tool to develop digital and spatial skills in the student for the understanding and construction of polyhedra from previous geometric concepts. The objective of the research work is to propose a work methodology for the construction of new polyhedra from the regular hexahedron using GeoGebra, allowing students to explore 3D spaces.

Felícita M. Velásquez-Fernández, Judith K. Jiménez-Vilcherrez, Daniel A. Flores-Córdova, Robert Ipanaqué-Chero, Ricardo Velezmoro-León
Harmonize: A Comprehensive Patient and Provider Connectivity Solution for the Management of Mental Disorders

Mental illness and associated disorders are deep social problems that are largely ignored. Individuals with mental illnesses face many obstacles such as stigma, prejudice, and unemployment, which dissuades them from seeking help. The emergence of COVID-19 brought light to the importance of mental health. Current online patient–provider networking services act as the proverbial phone book, and finding the right provider can be a shot in the dark. There is a lack of opportunity to converse, connect or interact with providers without paying for a formal appointment. As a result, patients have a hard time finding a compatible provider. In this paper, we present details of a comprehensive journal-like patient and provider connectivity solution for the management of mental disorders. In addition to providing a platform for individuals with mental disorders to confidentially connect with medical service and insurance providers, it allows for group forums among peers. Communication and trust can be enriched with a networking application that allows patients (under an anonymous alias) and providers to freely monitor, like mention and interact with one another before initial contact. Building a privacy-focused networking platform on top of well-known communication mediums like forums and blogs can enhance communication, visibility, and understanding. Better communication, trust, and understanding lead to high-quality therapy.

Dion Wayne Pieterse, Sampson Akwafuo
A Post-quantum Zero-Knowledge Proof System Using Quantum Information Theory

In recent decades, the importance of protecting computer systems and networks from information disclosure (relevant to information technology and cybersecurity fields) has risen to the utmost importance. With wide applications in subjects such as voting registration, insurance, credit card information, personal identity security, and as of recently crypto-based blockchains, the field is becoming increasingly significant. Due to the perpetual and expanding reliance on computer systems, the way that we handle and send our data is vital. Improper methods of establishing privacy for secure data transmission can compromise substantial amounts of user data, making the development of high-level privacy-preserving mechanisms impervious to tampering of immense importance. For example, the existence of most cryptographic systems is threatened by the development of quantum computing, and therefore, the development of making post-quantum/quantum-resistant cryptographic systems is in great demand. In this research, unlike most current existing systems, we propose a classical to quantum mapping channel for zero-knowledge that will not be negatively affected by the existence of quantum technologies.

Sonok Mahapatra, Tyler Wooldridge, Xiaodi Wang
Balance Model of Ukraine’s Gross Domestic Product Optimization on the National Economy Branches on the Basis of Information and Communication Technologies

Increasing productivity of the economy branches determines the formation of the basis for achieving sustainable development for both states and individual territories. The aim of this investigation is a production processes optimizing of different economy sectors on the basis of a balance model, to develop international cooperation in the field of introduction of information–communication technologies between Ukraine and European Union. The authors examine the processes of Ukraine’s industrial production activities and, in particular, on the level of some brunches of national economy. A set of measures for stimulating the provision of gross domestic product has been offered. Determined income per unit of gross output gives each of the industries in Ukraine. The next step is to set the required volume of gross output to obtain a unit of income.

Alina Yakymchuk, Mykola Shershun, Andriy Valyukh, Taras Mykytyn
Identify and Classify CORN Leaf Diseases Using a Deep Neural Network Architecture

Disease attacks on vegetable plants must be anticipated and treated promptly to avoid yield loss. The majority of diseases that affect vegetable plants manifest themselves in their leaves or stems. Disease classification using leaf images is now possible due to advancements in deep learning algorithms. The primary objective is to design a system based on deep learning for the prediction and categorization of vegetable leaf disease. Corn vegetable crops are considered in this work. A publicly available dataset was used for training and testing. Convolutional neural network Inception V3 utilized to develop and test the system. As a result, the performance of the system is projected to be at its most significant level.

Naresh Kumar Trivedi, Shikha Maheshwari, Abhineet Anand, Ajay Kumar, Vijay Singh Rathor
Consideration for NoSQL Databases Technical Consolidation

In the era of business analytics, enterprises are processing and persisting data from a variety of sources. Data sources include structured, unstructured, and semi-structured. Some data sources are schema driven and many are schema-agnostic. NoSQL databases serve the need of persisting, processing, and managing unstructured as well as structured data in different ways. It is important to select the right set of NoSQL for analytics-driven organizations. In the paper, the intention is to determine guidelines and consideration that can help enterprises to select the right set of NoSQL and consolidate NoSQL technologies for optimization. The right combination of NoSQL databases can help homogeneous technology footprint along with cost benefits & effort benefits for an analytics-driven enterprise. Design principals to help select between graph databases, document databases, and in-memory databases and in memory.

Abhijeet Singh Bais, Navneet Sharma
A Review on Proteomic Function Prediction in Pathogenic Bacterial Organism Using Machine Learning

In the realm of health research and the medical business, machine learning plays a vital role. In today’s world, protein research is critical in the development of medicinal drugs. Proteins are responsible for the structure, function, and regulation of our biological tissues, organ functionality as well as the majority of cell work. A pathogen is an organism that can infect its host and causes disease, and virulence refers to the severity of the symptoms. Some infections are only able to live in specific hosts. Other diseases can infect a broad array of species. It is easy to identify the characteristics and behavior of known bacterial proteins but the prediction of unknown proteins is a cumbersome task. The paper discusses the objectivity of machine learning in predicting the unknown proteins along with their functions, specifically in harmful bacterial species.

Anushri Vijay, Neha Tiwari, Amita Sharma
Proceedings of Seventh International Congress on Information and Communication Technology
Dr. Xin-She Yang
Dr. Simon Sherratt
Dr. Nilanjan Dey
Dr. Amit Joshi
Copyright Year
Springer Nature Singapore
Electronic ISBN
Print ISBN