ICT Analysis and Applications

This article focuses on Customer Relationship Management (CRM) or management customer relationship. We discussed this concept by focusing on its dimension analytical orientation justified by the choice of our subject, namely OLAP analysis tools and data mining. As we will see later, analytical CRM relies heavily on computing. Whether at the level of data production, storage or finally the analysis, useful also to optimize processes and decision of decision, IT is omnipresent. We have chosen to sometimes leave aside some aspects, particularly technical. That said, this work hopes to offer a vision most widely possible key issues related to analytical CRM in particular, as well as the management of customer relationships in general.

The large number of requests flow exceeds the capacity of the target server drives to denial in the service to the legitimate users. Due to the server’s oversized prospective, the flooding requests increase the server capacity generated by the malicious attackers from distributed environment defining the distributed denial of service attack. From the contemporary literature it is evident that applying the knowledge gained from the findings of previous request distributions is a suitable strategy to block the DDoS attacks. This strategy’s key limitation is frisking to detect the new patterns of request flooding excavated by the attacker at the server from the previous knowledge on earlier attack distributions patterns. Therefore, this paper explains a novel trained ensemble classifier with new features which reflects in the traffic flow properties, so that, the traffic flow shows distribution diversity from each other which is considered and attached to individual classifiers. Ensemble classifier and AdaBoost are used to detect the flow by discovering the distribution resemblance involved in the multiple classifiers in the ensemble classification model. The experiment worked out on the voluminous traffic flow with visible distribution variety.

The low profile nature of a microstrip patch array is advantageous in stealth applications. However, the feed network of a typical corporate-fed patch array contributes considerably toward antenna scattering. A proximity coupled feeding technique can be adopted to overcome this problem. Since the feed network comes beneath the substrate, the radar cross-section (RCS) of the whole array can be reduced to an extent, with an added advantage of providing wider bandwidth. However, the multiple resonances that will be generated from proximity coupled arrays may contribute to higher RCS at corresponding frequencies. Incorporating slots in the ground plane helps in changing the path of surface current, thereby reducing the RCS peaks due to resonant modes. Further, results show that cutting slots in the ground plane of a proximity coupled patch array has aided in gain and bandwidth enhancement. A proximity coupled patch array with high impedance surface (HIS) layer and reduced slotted ground plane is proposed towards wideband structural RCS reduction from 11 to 30 GHz.

The effort, cost, and time play a vital role in the success or failure of the software. The ratio of software project failure nowadays is growing like a storm in the world. One of the reasons behind this failure proportion is an imprecise and inappropriate estimate of required effort, cost, and budget for particular software project development. The motivation behind our research is to estimate the effort for software development accurately. Accurately estimate effort for software development is one of the most challenging tasks because from a very early stage it requires in-depth study as well as detailed statistics. Participation of members of the team is important during the development of the project along with various activities like domain area, sector, nature, software process methodology, and other resources. All these proofs do not appear in the initial phase of development, but on the other side, they discovered as software growth progresses. Many models proposed for estimating effort related to software development, but only a few are adaptable for effort estimation task in the academic software project. From the study of nearly 600 academic software projects and inputs from more than 30 Software Engineering experts, this research paper proposes an innovative model based on 8 parameters and 24 sub-parameters. Each of the sub-parameters is weighted twice, and the final effort estimation obtained by summation of the individual product of the weight of the parameter and weight of sub-parameter. We have coined the term “ASPEE units” (Academic Software Project Effort Estimation) for the estimated effort.

One of the biggest challenges for higher educational institutes is to increase the placement ratio. Another challenge is to increase the holistic development of the students. Looking at the global requirement, the companies require people not only excellent in the domain knowledge but required excellent in the soft skill too. Finding and predicting the performance factor of the student may help in improving the system and also give an indication to improve pedagogy being offered to students. Many tutoring systems and continuous evaluation patterns adopted by many institutes help in improving the performance of a student. As the trend changes toward holistic development of the students, focus is also upon the soft skills measurement factor. This encouraged us to have a model that helps predicting the holistic performance of a student based on the continuous evaluation as well as performance indicator of a student in other activities too. A gray-based decision-making theory helps assessing the required parameters that find the continuous performance measurement of a learner for each aspect. The multi-attribute situation decision-making theory helps in improving the criticality of the information system by recognizing the sensitivity of the criteria.

In the developing countries, tuberculosis (TB) is the primary and foremost cause of death in the infectious disease category. At present, the research for tuberculosis diagnostics tool development focuses on extemporizing microscopy procedure with a simpler technology for detecting smear-positive TB. In tandem, recent diagnostics are aiming at increasing the sensitivity or simplicity of diagnosing active TB disease. Smear microscopy of sputum is often the first TB test to be used in countries with a high rate of TB infection. Sputum smear microscopy examination is economical and modest, although the sensitivity is only about 50–60%. Automated detection of TB bacilli could accelerate diagnosis, enhance quantitative classification and reduce the manual errors pertaining to diagnosis. The bright-field microscopy screening can be assisted by latest computer vision technique for detection of TB using the minimalistic computer-assisted infrastructure setting at the rural health centers. In this paper we discuss the implementation of one of the computer vision techniques for grading of the Mycobacterium Bacilli for conventional ZN-stained images. The objective of the implementation is to detect the edges of the bacilli by considering the area and perimeter filtering of the given input images.

Carbon dioxide is a major contributor to climate change. It absorbs the outgoing longwave radiation, thereby increasing the temperature in the atmosphere. This study examines the variables which contribute to the flux of CO2 over the 50-acre sprawling green campus of DA-IICT at Gandhinagar, Gujarat. The previous approach to this problem was to employ differential equations to model the CO2 emissions. We believe that a compartment-based model that incorporates fossil fuels, electricity, human emissions, and a Light Use Efficiency (LUE) model would provide a better approximation. The LUE based model computes the total carbon that is sequestered by plants. It uses the Primary Productivity Capacity ($$ \varepsilon $$) of plants and APAR (Absorbed Photosynthetically Active Radiation) to calculate the Gross Primary Productivity (GPP). Further, the Net Primary Productivity (NPP) is derived from the GPP. Three dedicated separate models using monthly MODIS NDVI, MODIS FPAR, and MODIS NPP time-series datasets were used to model this. To integrate the above, a Decision Tree-based algorithm was applied to compute the best fit curve and approximate it to the Keeling curve which is a graph of the accumulation of CO2 in the Earth’s atmosphere recorded at the Mauna Loa Observatory, Hawaii for all the three cases. The resultant curves indicated an MSE (Mean Square Error) close to zero and an upward trend was noticed for the future validation dataset.

Scalar neural network algorithms are limited in their ability to understand scale, rotational, or affine transformations within images and resort to average or max-pooling techniques which result in translational invariance. In an attempt to overcome these limitations, Hinton et al. introduced vectorized capsule network frameworks which support equivariance while capturing spatial relationships between data points, thus enhancing predictive capabilities of networks. However, experimenting with activation functions, hyperparameters, and optimizers have proven faster convergence and orthogonalizing weights within the layers of capsules enhance performance by slashing associated average error rates.

A supermarket is a place where customers come to purchase items for their everyday needs. The long queues at the billing counter and manual billing makes way for a lot of errors and wastage of time. These problems can be overcome with the help of the smart shopping cart which is discussed in this paper. The smart cart will also recommend products based on the customers’ purchase history which helps the shopping mart with increasing its sales and customers to remember the products they might forget. Finger print sensor has been used for registering/identifying customers, RFID technology for detection of products being added to the cart, and NodeMCU ESP8266 for Wi-Fi communication between the cart and the centralized system. Content-based filtering is used for implementation of Recommender systems [5].

The paper provides a comparative overview of machine learning techniques in medical diagnosis. We present a performance evaluation analysis of some of the state-of-the-art machine learning approaches applied for medical diagnosis. The research considered six machine learning classification algorithms: Naïve Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), and two decision trees classifying algorithms: C5.0 and Random Forest. UCI three medical data sets: Cleveland Heart Disease dataset, Wisconsin Diagnostic Breast Cancer dataset, and Pima Indians Diabetes Datasets. Our experimental results show the SVM classification algorithm has achieved the most promising result over all the three medical datasets.

Machine simulation of human reading is an active research area since the introduction of digital computers. Optical character recognition aims at the recognition of printed or handwritten text from document images and converting the same into a machine-readable form. The focus of this work is handwritten character recognition of MODI Script. A proper recognition system for handwritten documents enables it to be conveniently viewed, edited, and shared via electronic means. The development of a character recognition system for some of the ancient script is still a challenging task due to the complex nature of the script. MODI script is one such script which is the shorthand form of the Devanagari script in which Marathi was written. Though at present MODI script is not an official script, there exists a huge collection of MODI documents in various libraries. In addition, it is observed that scholars and historians are taking serious effort to revive the script. The purposed study based on the implementation of two algorithms for the classification of handwritten MODI script. The algorithms use distance classifier method. The first experiment is done using Euclidean distance classifiers and the second one is with Manhattan distance classifier and the accuracy achieved is 99.28% & 94% respectively.

Advancements in information technology have played a central role in the economic, political and cultural globalization of the world. While commercial ventures have thrived by leveraging information technology, governments and multilateral institutions might often view technology as a means for doing things as opposed to the way of doing things. Owing to the multitude of development initiatives being carried out at any given point in time development institutions face challenges in scaling the collective impacts of such interventions. In order to address these gaps, the technology division for social inclusion at Mindtree has developed a cloud-based ‘Public Goods Platform’. The objective is to enable governments to provide digital platforms as a public service to its citizens, integrating multiple social development models, theories of market economics and scaling the impact to a larger section of the society especially the vulnerable sections. The core tenant of the Public Goods Platform is inspired by the concept of public goods—‘it is non-excludable’ and ‘non-rivalrous’.

Recommender Systems is a special type of information filtering system which has become important in the information overloaded and strategic decision making environment. Recommender System is used to produce meaningful suggestions about new items for particular consumers. These recommendations may be based on the user profile or item ratings, facilitate the users to make decisions in multiple contexts, such as what items to buy, what online news to read or what music to listen. Recommender Systems helps their founders to increase profits by recommending items and attracting new consumers. Collaborative filtering technique recommends items basis of conclusion of opinions about various products by users of similar profile to the active user. This technique requires user-items-ratings matrix. Although this is the most mature and commonly implemented technique, it faces major problem of Data Sparsity problem. Sparsity Problem occurs as a result of lack of enough information when only a few of the total number of items are rated by the users. This produces a sparse user item matrix leads to weak recommendations. This paper presents a recommender system using collaborative filtering implemented with RapidMiner tool. The proposed recommendation system is designed with users’ similarity calculated by Sequence and Set Similarity Measure (S3M) with utilizing similarity upper approximation and a Singular Value Decomposition (SVD) model based technique used for recommending ratings for removing sparsity.

Orthorectification plays vital role in satellite image processing. This process imposes challenges due to the dynamism in capturing environment, capturing unit, satellite rotation, sensors parameters and overlying regions on earth. The required geometric modelling needs an accurate estimation of Ground Control Points (GCPs) and their processing. Most of the proposed models are computational intensive and use manual approach for locating GCPs. Further, GCPs co-ordinates are floating point numbers the computational capability of the system imposes the constraint on the accuracy and robustness of the respective models. In this paper we have studied orthorectification process and proposed instinctive processing framework for orthorectification of optical pushbroom sensor based satellite imagery. The frame work accompany metadata extraction, automatic ground control point (GCP) extraction using parallel processing, geometric modeling, orthorectification and image stitching processes. Experimental results with proposed framework confirmed the robustness of the technique and provided sub pixel accuracy on independent check points with positional accuracy around one pixel for orthoimage. Parallel SIFT features are extracted using SIMD architecture while performing image stitching.

Flower Pollination Algorithm (FPA) is a significant addition made to Nature Inspired Metaheuristic Optimization Algorithms (NIMOA). It is inspired by the pollination process of flowering plants. In this research, FPA is used for Test Case Prioritization (TCP) in Regression Testing (RT). The algorithm uses code coverage of test cases as the input. The algorithm has no prior information of faults covered by the test cases. This study deals with prioritizing (ordering) the test cases in such a way that only those test cases are executed that covers maximum faults in minimum time of execution. For validation of the results Average Percentage of Fault Detected (APFD) metrics is used. APFD values for different ordering of test cases is calculated for three applications written in Java. The empirical results of APFD metrics for FPA order (TS1) and FPA order (TSp) are better as compared to Random Order of Original Test Suite (TSo) and Reverse Random Order of (TSo). Therefore, this paper states that FPA for TCP gives efficient results in RT.

Purpose: The research study aims at exploring the effectiveness of online marketing strategies of packaged health food brands w.r.t. income of the customers. The study aims to investigate the relationship between buyer satisfaction and buyer recommendation w.r.t. the income of the customers. For the research, both primary data and secondary data were used. The researchers have conducted the pilot study on 105 respondents to investigate the effectiveness of online marketing strategies on packaged health food brands with respect to the income of the customers. The researchers have used a non-probabilistic convenience sampling method for the study. SPSS 21 version was used for the data analysis. Following hypotheses were proposed for the study: H 1 There is some association between the awareness of packaged health food brands and the income of the customers. H 2 There is some association between frequency of being online and income of the customers. H 3 There is some association between frequency of online buying and income of the customers. Findings: Results indicates that the higher the income level of the customers, the higher would be the awareness of health food brands among the customers.Research Implications and Limitations: Practical implications—The marketers can apply the findings of this study in creating more effective online marketing strategies for the packaged health food brands with respect to the Income of the customers.

People in rural India encounter greater paucity of facilities and services compared to their urban counterparts in scaling the opportunities created by technological advancement. Information and Communication Technologies (ICT) have the potential to provide much-needed succor by bridging the challenges of remoteness with satellite, web and mobile based applications. Education, being a critical requirement for social and economic well-being, and primarily a media-based service, lends itself well for technological interventions which aid in addressing the urban-rural divide. The case study that we have done shows that there are challenges in the eco-system that impact the smooth implementation of digital technologies in rural areas. Inadequacy in infrastructure both in terms of quality and quantity, inefficiencies and other systemic issues impact the ICT solution roll-outs causing delays and unmanageable cost escalations, thereby making solutions infeasible. The way forward is urgent, serious and needs concurrent efforts on many dimensions, which require strong collaboration of public as well as private partners.

With advent of social media, need for scheduling very large meetings while proving a degree of privacy to the participants has become an important problem. Existing solutions based on a global calendar expose individuals data to the calendar provider and thus are unsuitable for open meetings with quorum constraints. We propose an online distributed dynamic meeting scheduler (ODDMS). It is able to efficiently schedule meetings involving a large number of participants, without having complete knowledge of individual participants and their preferences, thus preserving privacy. The algorithm uses a modified negotiation-based distributed schedule that resolves the problem of deadlock and contention using hidden naive Bayes learning method. We compare our work with a baseline centralized algorithm and two existing algorithms based on voting mechanism and naive Bayesian methods. Simulation studies show that ODDMS performs similar to baseline centralized algorithm under light load condition and significantly outperforms the existing distributed algorithms under heavy load condition.

Digital Readiness Index (DRI) also referred to as Networked Readiness Index or Technology Index indicates the status and growth of information and communications technologies (ICT) and how it is effectively used to achieve maximum benefits to the country and its citizens. DRI explains the status of digital sovereignty of a nation and is used to monitor and compare developments in ICT domain. The Index is designed to understand the ICT Development Index (IDI) of a country, by which it can be ascertained the level of ‘digital readiness’ of the nation. The importance of ICT for digital India and E-Governance has been well brought out in the National Digital Communication Policy (NDCP) 2018 by Government of India. Development of Digital Readiness Index has been envisaged in the NDCP document. In this paper, important aspects of NDCP for making India digitally sovereign have been explained. The government policy on E-governance in ICT sector for making the country as ‘digital India’ has been explained in this article. The parameters of DRI and their significance for empowering the Nation has been brought out in this article. Methods by which these parameters could be measured and the difficulties involved therein are elaborated. Further, the importance of developing DRI and socio-economic impacts of measuring the index are explained in this article. The benefits to the people, to the States and the nation as a whole, by bringing out DRI of the States are brought out in this paper.

This paper presents the development of lane detection techniques using video processing which works in real time on highway and various similar roads. The Canny edge detection algorithm is used for detection of edges of lanes on the road which provides robust output. Hysteresis thresholding is used to identify the pixel that belongs to real edge pixels in the captured image. To get clear identification of lane markings Hough transform is used on respective edges.

Network is called as a good network if the packet/data delivery is on time or delay rate is as much as it can be tolerated but if the delay rate is high then the network resources are being affected. The demand for a good network nowadays has increased which is making the need for proper communication mechanism a great pressure. The challenge is to choose a network that will not only satisfy the customer need but also channel reliability and data security. Depending upon some features like bandwidth and services, the wired and wireless communication does the same work but if we talk about the wired communication it will show us some other factors and talking about wireless communication leads us to think about the security. This paper focused on some key elements which can be useful to choose a proper network for communication in the aspect of security, communication medium, real-time application, etc.

Image captioning, which aims at generating automated descriptions for an image, is the large focus in current research while most of the previous works have dealt with the association between the single image and single sentences. This paper proposes to take one step further to investigate the summarized version of the narrative description for the image stream and in more generalized form for a normal user. The major challenge in the proposed work is to consider the visual variance in an ordered image collection and in preserving coherence relation among multiple sentences. Our proposed work is aimed to retrieve a coherent flow of multiple sentences that use multimodal neural architecture and ranking-based summarization to generate the summarized description of possibly larger image streams. With qualitative evaluation, the proposed work has attained significant performance improvement over traditional state-of-the-art method for text sequence generation and has captured the relevant context with syntactic meaning with respect to summarized version of the detailed descriptions.

The Internet of Things (IoT) is exploding disruptively. The IoT is making life easier for ordinary consumers and workers, but it is also generating zettabytes of dark data. The real time analytics involving close interaction between humans and instruments on the Internet is the main commercial motivation behind the IoT revolution. This means the data that are consumed instantly and their interpretation that is filed in an indexed and structured form are the main productive outcomes, while dark data and haphazardly stored interpretations add to the tare, bringing down efficiency and increasing costs. Since out of all data stored in the world today, almost all are generated in the recent three years, and the phenomenal growth will soon lead to a crisis, we need to put in place a global framework that never lets dark data clog the information highways but actually harnesses the real time analytics for a better planned future. We propose here a plan to build a “Data Waste Management” or “Data Sewerage” and local “Data Reservoir” system.

Network transmission has evolved over a period, beginning from 1G in 1980s, 4G networks have been established and work is done in deploying the standards of 5G technologies so far, 4G is yet to be established across the globe. Despite that, working on the establishment of new technologies has been started as 4G is proving to be insufficient to get along with the extended necessity regarding the highly dense network. So, to surpass these issues implementation of 5G technologies are going on as it provides, high-speed data rate, minimize latency, conserve energy, videos can be transferred without affecting its quality. The main challenges faced by developing countries in implementing 5G technologies are lack of infrastructure which includes poor fiber construction, no proper mechanism for the rapid increase in a number of users, low rate of data speed and the high cost and many more. This paper will represent the challenges in the implementation of 5G in India, discuss its future scope, its applications, comparisons from ongoing networks and the challenges in the implementation of 5th generation in the developing country.

Information security dictates today’s digital era of electronic commerce and business applications. DNA cryptography is surfacing as one of the fastest emerging technologies and opens a plethora of optimism in unbreakable algorithms. For transmission and storage of data DNA can be used and its scads of lengthy polymers of linked nucleotides are segregated into Adenine(A), Cytosine(C), Gaunine(G), and Thymine(T) that inherently include nitrogen base. Secret messages are concealed in these DNA sequences and are transformed into RNA sequences. To provide another security layer, quantum cryptography techniques were evolved to process the encoded text. Then the text is processed to an encryption function. To encrypt at this level, a 64 bit secret key is generated using genetic algorithm Roulette wheel selection to encrypt secret messages.

The research paper evaluates the use and contribution of Information and Communication Technologies (ICTs) in the design and development of financial engineered life insurance policies and financially engineered life insurance business processes in the growth of the life Insurance Business in India. The research study explores the use of ICTs in various product development stages of financially engineered life insurance policies and the use of ICTs in insurance processes. Specifically, this paper reports a theoretical examination that simultaneously considers the effects of these relationships among ICTs, Financial Engineering, Insurance Business and growth of the insurance business in India, and the role and contribution of ICTs in the financial engineering applications in financially engineered life policies and processes. It encapsulates the role of ICTs in FE applications in the design and development of Financially Engineered policies, business processes of insurers including companies’ performance management.

The widespread use of image-based memes on socioeconomic or political issues has witnessed a booming effect unparallel to any form of media in the recent years. The ability to go viral on social media in seconds and the popularity of memes on online platforms give a wide scope and pathway for research as it will help in understanding the usage patterns of the public and in turn be used for analyzing their sentiment toward a specific topic/event. In this paper, initially gap analysis on the features used for sentiment extraction on memes is presented. Exploring the correlation of image based and textual features, this paper gives a novel approach (correlating the facial features along with the text in the meme itself) for the extraction of sentiment from image-based memes. This paper also addresses the challenges faced in this relatively new area of sentiment extraction on memes. Finally, this paper concludes with insightful results.

Suspended sediment model and predicting its concentration in a natural stream are important fundamentals in managing water recourses policy worldwide. Present investigation considers adaptive neuro-fuzzy inference system (ANFIS) and backpropagation neural network (BPNN) to model suspended sediment load (SSL). Rainfall, temperature and SSL data are used to train and validate the model from Mahanadi river in Odisha, India. The estimation results obtained by using the neuro-fuzzy technique are tested and contrasted to those of artificial neural networks (ANNs). Root mean squared errors (RMSE) and coefficient of determination (R2) are utilized as assessing criterion to evaluate the model performances. Based on research finding ANFIS provides superlative value of R2 is 0.9625 and 0.9814, but for BPNN it delivers 0.9376 and 0.9592, respectively. Assessment outcomes show that ANFIS is better suited to apply for estimating suspended sediment daily.

Cognitive content, that a lot of IoT application on home automation have implemented, the methodical to build an IoT device is still an obscure. So building an architecture based on microservices for the home automation makes things a little better. The primary objective of this paper is to design microservices architecture for home automation. The service for each sensor is done through microservices based on microservices architecture. The designed system follows rather than a Monolithic Architecture. Microservices architecture is purely a concept when we have so many sensors, where service is created for each sensor which is not dependent on other sensor services. The prototype has been designed to prove that architecture is workable.

SMART Robotic Palm is developed to mimic the motion of a human thumb, fingers, and palm. This paper proposes embedded technology-driven electromechanical setup capable of imitating human palm gestures and movements with the use of electronics. This setup is capable of generating voltage corresponding to motion of fingers and then feeding it to the controller in the transmitting glove, which translates the voltage values to angles (in degrees). The angle values (or the value change) are transmitted to the Cloud-based Internet of Things platform using transmitter controller’s Wi-Fi capability via the Internet in form of data packets. The receiver end or the artificial robotic palm’s controller receives these angle values in real time to duplicate and replicate this motion or imitation. The SMART Robotic Palm’s dexterity and its finesse in imitation of motion is achieved using linear potentiometers, NodeMCU DEVKIT 1.0 as the Internet of Things platform which consists of ESP8266EX as its microcontroller and the servo motors in the robotic palm’s fingers actuating motion. More precise control and motion shall be useful in numerous applications especially in the health sector for performing surgeries remotely in critical and/or emergency situations.

A business in the fruit market is totally dependent on the quality of the fruit, its physical appearance, color, shape and size. The fruit market needs fast and effective methods in identifying the worth of the fruits. The present research work employs outer texture of the fruits captured through a digital and a thermal camera. In this present work, eleven different varieties of fruits have been used as main elements for creating a texture-based image database using digital and thermal image capturing devices. The fruit is kept on the revolving tray which can be rotated from 0° to 360° and the entire system is controlled through an interface of stepper motor and the Arduino system and the images are captured from both the image capturing devices. The videos thus captured have been converted to frames for the final creation of the images database having normal RGB and thermal images for further application of image preprocessing techniques. The two image databases upon conversion to gray scale are subjected to texture-based feature extraction technique for studying the outer texture of the fruits. The eleven texture features extracted are subjected to further classification and analysis process for final demarcation of fruits being classified into infected and noninfected grades.

The volume of digital documents is increasing day by day and thus the task of automatic categorization of document is very important for information and knowledge discovery. Classification is the most common method for finding the mine rule from the large databases. Ambiguity is the major problem in Requirement Engineering (RE) documents. Our proposed work uses WEKA text classification technique to identify and classify ambiguity in the RE document. The present study uses different algorithms on the ambiguity detection dataset and on the basis of different statistical measures like accuracy, time, and error rate we find suitable algorithms for this purpose. The main aim of this paper is to do a comparative study of various classification techniques and methodologies and a detailed analysis of different statistical parameters that are used in classification algorithms in order to analyze the quality of classification.

An efficient Cab Recommender System (CRS) assists the cab drivers with the shortest distance for the next passenger location. For this, it becomes imperative for a CRS to generate clusters for Geolocations. Clustering of Geolocations faces major challenges like noise, identification of meaningful clusters, semantic locations, etc. Therefore, the objectives of this research paper are fourfolds. Firstly, to extensively review the literature for Geolocations and identify the existent clustering techniques. Secondly, to propose an algorithm for generating clusters for Geolocations. Thirdly, to implement and test the proposed algorithm on standard dataset pertaining to different clustering techniques and finally, to analyze and compare the results of the proposed algorithm for effective clustering of Geolocations.

People, these days, express their opinions regarding any particular topic or issue widely on social media. One such popular social media platform among masses is twitter with over 320 million monthly users. Users also express their thoughts on any political announcements or decisions taken by a particular party. Analyzing these tweets on a specific topic can help in determining what people think about measures undertaken by the government. It will give an idea on how many percent of people are in favor of any announcement, and how many of them stand against it. This will in turn provide areas of improvement for the ruling or opposition party. This paper thus aims on finding sentiments of tweets on a political leader, some party or announcements like a union budget. This can further be generalized to any particular measure undertaken by any organization.

Every year, an increasingly large number of neonatal deaths occur in India. Premature birth and asphyxia are being two of the leading causes of these neonatal deaths. A well-regulated thermal environment is critical for neonatal survival. In the current scenario, it is impossible for the health centers in the rural areas of India to afford a neonatal incubator for every newborn due to its price and transportability. The successful delivery of neonates is hampered in India due to its increasing population along with limited technology and resources. Thus, a prototype of an incubator has been designed that is affordable, transportable, and energy saving for the health centers in the rural regions, with an AI-based decision support system.

In recent times, social media has been used by people to participate in a particular event and has resulted in the generation of a large amount of data online. These data can be helpful for the decision-maker in promoting and devising necessary policies at the right time. The purpose of this paper is to understand the peoples’ sentiments and emotions about a recent social movement. Based on the result and analysis, the possible inferences have been presented.

This paper presents an automation system that mechanizes the post quality review of the weld which was performed by human welders already. A foundation is established to effectively extract information of the welded structure surface to facilitate quality check and inspection of the weld joint using different algorithms. The idea is to provide cost effective solution to the small scale manufacturing industries for robotizing there post welding activities, decrease the time required for these tasks, and increment the speed eventually. The proposed framework built up a GUI which can be utilized by nonspecialized laborers to make their work simple. The framework utilizes various algorithms like Otsu and BHT for estimation and examination of different geometric parameters of the weld which aided in post welding quality assessment of the welded structure. Results obtained from both the algorithms are compared and analyzed. Geometrical parameters thus calculated were then compared with the values of these parameters as specified by industry standards for accepting or declining the welded structure under inspection. Lot of research has been done in measuring characteristics of the welded structure. However, a limited research is done in the quality inspection and post welding operations efficiency performance check. The proposed system satisfies this necessity. In this system three things are remembered while building up the framework, i.e., cost proficiency, broadly utilized welding procedure, and industry interest for mechanization of post welding quality assessment. For actualizing a similar thought, Common CCD (Commercial charge coupled device) cameras are utilized to catch images, GTAW which is a broadly used welding procedure is used and simple to use however proficient GUI is built.

Shape memory alloys (SMAs) possess a certain extraordinary ability that is very attractive for several applications. Selecting a profile, configuration, size, cross-section, and material in order to meet the functions a structure has to perform is structural design. This paper describes the design considerations for actuating cantilever beam structures using shape memory alloy wire. An experimental arrangement for detecting the behavior of the cantilever beam and actuation properties of shape memory alloy (SMA) wire is presented in this work. The setup is incorporated with displacement and current sensors and the design is validated by computing the tip displacement of the cantilever beam for various dimensions of beam and shape memory alloy wire. Shape memory alloys can be effectively used to actuate the cantilever beam by introducing variable stiffness and providing push–pull effects due to the bias added with the structure. Some geometrical parameters such as thickness and length of the beam and, diameter and length of SMA wire are analyzed in this work. These investigations on the effect of the geometrical parameters are carried out experimentally. The information of beam displacement and the current required to excite SMA wire are communicated through suitable DAQ to the computer. The values of the response of the structure are presented and optimum structural configurations are to be considered to build a smart sensor in Intelligent Engineering.

The factors influencing the adoption of a cloud platform in the development of e-learning service is identified in this study. The e-learning service based on a cloud platform is analyzed from single/multiple data center dimensions. In spite of developing e-learning infrastructure, the service of the cloud platform is often adopted. The cloud-based e-learning simulation environment is created using CloudAnalyst tool. The efficiency of the cloud is analyzed based on e-learning hosted on a single data center and multiple data centers. The service time and overall response time of the datacenter are analyzed through CloudAnalyst. The infrastructure cost estimation for both models is also calculated. The study identifies that these factors influence the development of e-learning services in a cloud platform. Earlier studies less analyze the influencing factors of the online courses in the cloud environment. In future research, the cost factor can also be considered in the development of e-learning services. Fewer studies are reported on e-learning service based on a cloud platform in the Indian context. The current study demonstrates how cloud Infrastructure as a Service (IaaS) improves the performance of the e-learning system.

The identification and removal of a stopword is a common preprocessing task in many natural language processing implementations. The morphologically parsed information of stopword is also relevant in analysis of various NLP tasks. The list of most common seventy-five Sanskrit stopwords are evaluated using rule-based morphological analyzer. Most stopwords were classified as indeclinables and pronouns. The Gujarati equivalent of stopwords is retrieved using bilingual dictionary so as to cache the data for faster retrieval during MT process.

In this work, we discuss about the issues raised due to the high-dimensional data in real-life scenario and present a novel approach to overcome the high dimensionality issue. Principal Component Analysis (PCA) based dimension reduction and clustering are considered as promising techniques in this field. Due to computational complexities PCA fails to achieve the desired performance for high-dimensional data whereas, subspace clustering has gained huge attraction from research community due to its nature of handling the high-dimensional data. Here, we present a new approach for subspace clustering for computer vision based applications. According to the proposed approach, first all subspace clustering problem is formulated which is later converted into an optimization problem. This optimization problem is resolved using a diagonal optimization. Further, we present a Lagrange Multiplier based optimization strategy to reduce the error during reconstruction Low-level data from high-dimension input data. Proposed approach is validated through experiments where face clustering and motion segmentation experiments are conducted using MATLAB simulation tool. A comparative analysis is presented shows that the proposed approach achieves better performance when compared with the existing subspace clustering techniques.

Integration of information communication technology (ICT) with the judicial system has recently brought new opportunities in courts toward improved efficiency, quality, and transparency of court cases; better management of cases from registration through case disposal; and extended availability of the judiciary. This paper reflects on the implementation of the e-court system in the Sulaimaniyah Appellate Court in the region of Kurdistan in Iraq. The analysis is based on expert interviews of different stakeholders in the appellate court. The results show significant improvements in terms of the court case management workflow in the following four areas: improved internal daily operations, the security of court cases, concurrent extended access to the judiciary, and transparency. The research aims at extending the body of knowledge for judiciaries, who are on the way to start integrating technology to courts.

Working with cross-linguistic environments where lexico-semantic features are vital, the use of digitized bilingual dictionary cannot be overlooked. Here, Sanskrit-Gujarati bilingual dictionary design, contents and its applicability is discussed. The Sanskrit-Gujarati lemmas are correspondingly mapped so as to facilitate use-cases like machine translation, cross-lingual information retrieval, stemming, lemmatization, and other related task. The dictionary design and implementation is through Comma Separated Verbose (CSV) format and Relational Database Management System (RDBMS), but also convertible to formatted tag-based form for better portability. It is usual to have bilingual dictionary for scarce resourced languages prepared manually as opposed to automated and aligned bilingual corpora method for several Natural Language Processing (NLP) related task.

A myriad of infotainment systems has found its applications in the automobile industry with the burgeoning demand for user comfort and interaction. However, operating such infotainment systems entertain secondary tasks to be carried out at the expense of the primary task of driving. This can increase the cognitive load on the driver and has the potential to keep road safety at stake. This paper presents an intelligent interactive head-up display (HUD) on the windscreen of the driver that does not require them to take eyes off the road while undertaking secondary tasks like playing music, operating vent controls, watching navigation map, and so on. The interactive HUD allows the user to navigate and make selections using eye gaze. The HUD also incorporates provisions to estimate driver’s cognitive load and distraction level. User studies show that the system improves driving performance in terms of mean deviation from lane in an ISO 26022 lane changing task compared to touch screen system and participants can undertake ISO 9241 pointing tasks in less than 2 s on average inside a car.

In this paper, effect of the mutual and gap coupling on patch antenna characteristics is studied in detail. The study is carried out by placing two patches that are parasitic in nature on both non-radiating sides of Rectangular Microstrip Antenna (RMSA). Gap coupling is examined by altering the distance between the parasitic patch and radiating patch, while mutual coupling can be analysed by altering the width parasitic patch. Mutual coupling and gap coupling contributes to the decrease in overall size of the antenna, increase in gain with a slight decrease in bandwidth. The observations obtained by simulation are confirmed experimentally.

Mobile phones are widely used digital devices among young learners. Although it is evident that students use mobile phones for their learning process, until recently it was not recognized as a learning tool, especially in Interior Architecture pedagogy. This article aims to explore the research gap in finding the impacts of using mobile phones as a learning tool in nature inspired furniture design project. The research was conducted using qualitative methodology through observation and interviews which were carried out among 12 selected students in the interior architecture degree program. In this article, we will explore the impacts of using mobile phones, throughout the product development process and how it has affected the students creative design ability. This is an exploratory study conducted within 5 weeks and the design process has been observed as a fly on wall observer throughout the given duration. The research is based on observational notes and open-ended questions given to participants. The results were analyzed through thematic analysis and it reflects on how the exposure of the mobile phones have affected the design ability of the students.

Human activity recognition is the task of recognizing activities of any given subject in a scene, from a set of observation over time, taking into consideration the environmental and behavioral factors. It has application in a lot of fields including surveillance, assistance system, threat identification. Human activity recognition plays a vital role in human computer interaction, as it is very important that a computer correctly identifies human activity to really understand the human behavior and learn what the human is trying to convey through their action as more than 50% of communication humans do is through body language. In this paper, we propose a system for identifying activities of pedestrians on road using pose estimation to give the autonomous vehicles a better understanding of the humans’ actions and get better at driving and also provide a safer environment for the humans.

Sarcasm is rapidly becoming prevalent in all forms of communication today. Each person has a different way of exploiting and understanding sarcasm. It is difficult for even humans to interpret sarcastic texts, as it depends on a lot of things like perspective, context and tone. This makes it a challenging task to train a machine to distinguish sarcastic text from non-sarcastic text. As there are no concrete rules upon which a model to detect sarcasm can be built, we must resort to promising and upcoming techniques to do so. In this paper, we have reviewed the works done in sarcasm detection using deep learning in combination with the natural language processing techniques. We have also proposed an outline of our own system based on current gaps in literature and challenges in the field.

This proposed device uses urine to predict the glucose level present in the patient using non-invasive technique with a high level of accuracy for detection of diabetes. The paper presents a urine glucose level diagnosing and prediction using a computer-based polarimeter held in a portable device, to provide a fast and accurate on-field result. The instrument consists of an LCD screen, optical sensor, Benedict’s reagent, a detachable tank, and an embedded system-on-chip (SoC).

Clustering is grouping of similar data points in clusters. Clustering has many applications, particularly in big data analytics. In data mining, traditional algorithm are used for clustering. These algorithms are inefficient in terms quality of cluster. This paper attempts to improvise the traditional K-mean by adding the Ant Colony Optimization algorithm (ACO) for improving the centroid for better clustering. This combination of ACO in K-mean and IACO in K-mean is experimented on iris and skin segmentation supervised datasets. Experimental results show that the performance in terms of F-measure for IACO in K-mean is better than ACO in K-mean and traditional K-means for iris and skin segmentation datasets.

The paper presents Devanagari Character Segmentation and Recognition using neural networks. The hybrid features extraction technique which is the combination of geometric and statistical features is implemented. The geometric feature extraction technique uses directional features of Skeletonized Character image, whereas the statistical feature technique uses distribution of pixel density and Euclid features of the skeletonized character image. For classification, SVM (Support Vector Machine) and MLP (Multi Layer Perceptron) are used as classifiers. The Support Vector Machine has more accuracy as compare to MLP.

Sugarcane is a major contributing component in the economy of tropical and subtropical countries like India, Brazil and China. Sugarcane agriculture is empowered with the advancements in the remote sensing technology because of its timely, non invasive, and labor and cost effective capability. Remote sensing data with machine learning algorithms like Support Vector Machine, Artificial Neural Network and Random Forest are proven to be suitable in sugarcane agriculture. The aim of this paper is to present a review of studies that implemented various machine learning algorithms based on remote sensing data in sugarcane crop mapping and classification.

The twenty-first century has given birth to a virtual networking where humans are interconnected via different modes of social media, paying less preference to more active forms of communication. So the people tend to use social media and become more and more obsessed by its use which results in various kinds of cyber attacks as well as many health issues like anxiousness, feeling low, mental instability, etc. This paper focuses on the adverse effects of social media obsession by conducting survey in 5 rural and urban areas of Gujarat. The samples were asked to fill the questionnaire in both the modes, i.e., online as well as offline. On the basis of the results of the outputs obtained from the questionnaire the various aspects of the samples were known and it was found whether they were obsessed with the use of social media. An online system is developed to find the intensity of obsession with social media.

Development and sustainability both are crucial parts of any economy. Developing countries are working for sustainability development whereas developed countries are focused on growth and developments. The Indian economy stands in stable economies worldwide. There are various sectors that provide their contribution to the GDP growth. The IT sector in India plays a significant role in development as well as sustainability development during the slowdown in economy. At present the Indian IT industries and support services are leading industries. With the slogan of “Digital India” rapid development in this sector take place now. At present Indian IT industries’ participation in GDP is 7.7% approx and till 2025 it is expected to reach 10%. The present paper is an effort to depict a view of Indian IT industries and its role and presence in national development and sustainability. The study focuses on the current slight economy slowdown and position of IT industries.