Skip to main content

2024 | Buch

ICT: Smart Systems and Technologies

Proceedings of ICTCS 2023, Volume 4

herausgegeben von: M. Shamim Kaiser, Juanying Xie, Vijay Singh Rathore

Verlag: Springer Nature Singapore

Buchreihe : Lecture Notes in Networks and Systems

insite
SUCHEN

Über dieses Buch

This book contains best selected research papers presented at ICTCS 2023: Eighth International Conference on Information and Communication Technology for Competitive Strategies. The conference will be held in Jaipur, India during 8 – 9 December 2023. The book covers state-of-the-art as well as emerging topics pertaining to ICT and effective strategies for its implementation for engineering and managerial applications. This book contains papers mainly focused on ICT for computation, algorithms and data analytics and IT security. The work is presented in five volumes.

Inhaltsverzeichnis

Frontmatter
Digitalization of the Apparel Industry—The Impact of COVID-19

There is no denying that the outbreak of the COVID-19 pandemic affected all the industries, including the apparel industry leading to the closure of various apparel companies around the globe. Various lives were at stake due to factories’ shutdown, leading to the loss of bread for daily earners. However, digitalization played a crucial role in converting the situation into a better place over time. Digitalization changed the whole concept of selling during the pandemic, which led to the foundation of digital-based companies around the globe. Zara is one of the best examples of changing its working structure in a short period. Hence, people turned the pandemic ill-effects into their benefits due to technological advancement. Due to the outbreak, people faced many challenges like financial challenges, working structure challenges, hindrances in the application of digitalization, and many more. Nevertheless, it would be correct to state that digitalization opened the doors of various futuristic opportunities for the apparel industry.

Sunitha Ratnakaram, Vibhor Bansal, Venkamaraju Chakravaram, Hari Krishna Bhagavatham, Vidya Sagar Rao
Efficient Fire Detection and Automation Using Haar Cascade

In the current scenario breaking out fire is a common thing that occurs everywhere, and this may also cause many damages for both nature and humans. Here the system aims at the major role on detecting fire that provides more information which helps to compare using sensor. The detection process is done by using the method of image process. The prediction using image detection provides more accuracy rather than any other detection process. The dataset that is used for fire detection is totally to be about 1750 images. The images which are downloaded through internet are needed to be resized and reshaped. After detecting the fire, the system provides the alert through Blynk IoT app.

G. Sandhya, M. Harshavardhan, S. Inbasudan, S. Jayabal
Evolutionary Patterns in Modern-Era Cloud-Based Healthcare Technologies

Distributed computing plays a pivotal role in revolutionizing the management of clinical data within the healthcare sector. This technology facilitates the global exchange of healthcare documents through electronic commerce, contributing significantly to promoting overall well-being and advancing the field of medicine. Thanks to this groundbreaking innovation, seamless communication with healthcare networks worldwide becomes a reality. In the realm of healthcare, distributed computing has existed for some time and has continued to evolve in tandem with business development. This invention introduces standardized specifications for a wide range of applications within the medical field, enabling open access to various devices. The security of data is ensured through distributed computing and efficient cloud server management, safeguarding critical information. Medical professionals can now offer guidance to their patients on maintaining their health, discussing routine medical care, and ensuring overall physical and mental well-being. Video conferencing has become an invaluable tool for doctors and therapists, fostering a sense of comfort and connection with their patients. This white paper delves into the objectives of employing distributed computing in medical services, emphasizing the awareness of its benefits, limitations, and challenges within the healthcare domain. Additionally, we explore vital recent trends and developments in health and medicinal concern. The concerned can readily acquire equipments that are IoT devised from vast list of manufacturers providing health-concern equipments. Consequently, the convergence of rapidly evolving technologies such as Big Data analytics, computational thinking, and the IoT of health concern, in conjunction with distributed computing, presents numerous means to enhance efficiency and streamline health-service. Thus, we enhance interoperability, expands resource sharing with cost reduction.

Vishal Shrivastava, Vibhakar Pathak, Saumya Mishra, Ram Babu Buri, Sangeeta Sharma, Chandrabhan Mishra
The Development of the Semiconductor Supply Chain in India: Challenges and Opportunities

The semiconductor industry plays a pivotal role in driving technological advancements across various sectors, from consumer electronics to critical infrastructure. As India aims to establish itself as a global technology hub, the development of a robust semiconductor supply chain is of paramount importance. This research paper delves into the challenges and opportunities faced by India in its pursuit of building a competitive semiconductor supply chain. It examines the historical context, current state, and prospects, highlighting key challenges such as infrastructure, research and development, policy framework, and talent pool availability. The paper also explores potential strategies and opportunities for India to overcome these challenges and become a significant player in the global semiconductor ecosystem.

Manik Sadashiv Sonawane, Sanjay Shamrao Pawar, Jayamala Kumar Patil, Vikas Dattatray Patil
Water Quality Analysis of Major Rivers of India Using Machine Learning

Water is one of the most important natural resources. It is very crucial for the existence of life and nourishment of all living organisms living on earth. It is observed that over the years the river water quality is degrading at a very rapid rate because of the toxic waste and contaminants. This has made river water unsuitable for any usage. It becomes very important to analyze the water quality of various rivers as this river water is used for drinking and domestic purpose, irrigation and aquatic life as well as fish and fisheries. In-order to understand the quality of water that whether it clean or not we have to study and analyze various water quality parameters like Biochemical Oxygen Demand (BOD), temperature, Potential of Hydrogen (pH), Dissolved Oxygen (DO), and conductivity and to understand about the quality of water of various rivers of India that whether it is clean or not, a classification model using three different classifier is presented in the study. We used J48, LMT, and Naïve Bayes classification algorithm in-order to classify the water quality data. The WEKA tool was used for analyze the collected data of various rivers then classify as clean or not clean. Further the Exploratory Data Analysis (EDA) of the collected data was performed using python programming language in jupyter notebook and some of the python libraries which was used include NumPy, Pandas, matplotlib, seaborne. In this work we have studied 15 papers from various publishers and created a summary to study about how and why the water is classified as clean or not clean using various machine learning algorithms.

Ashish Kumar Singh, Sanjay Patidar
Enhancing Trust in AI-Generated Medical Narratives: A Transparent Approach for Simplifying Radiology Reports

As advancements in artificial intelligence (AI) continue to permeate the medical field, the necessity for transparency in their decision-making becomes paramount. This work investigates how NLP models turn complex medical reports into simpler stories for patients from traditional radiology reports. Given the critical nature of medical information and its impact on patient care, merely producing accurate narratives is not sufficient. Patients, healthcare providers, and other stakeholders need to trust these AI-generated narratives, which comes from understanding how the AI arrived at its conclusions. This paper presents our work in integrating explainability into NLP models, ensuring that every step in the narrative generation process is interpretable and justifiable. Through our approach, we aim to bolster confidence in AI-generated medical narratives, bridging the gap between complex radiology jargon and clear, patient-friendly reports without compromising transparency. Our findings underscore the importance of making AI tools not just powerful, but also clear and trustworthy, especially in sensitive domains like healthcare.

Vivek Kumar Verma, Bhavna Saini
Green Construction Project Management: A Bibliometric Analysis

The construction industry has been one of the major influencers on our environment. Making it green by using renewable and recyclable resources can help maintain the sustainability of our planet. The construction industry has expanded rapidly in recent years. The impact of numerous elements on the sustainability of green construction has been the subject of extensive investigation. This paper aims to present a literature review of green construction project management and its environmental impact. Bibliometric analysis has been carried out to reveal emerging green construction project management trends. The study has been done on 30 research articles from various journals on sustainable construction. The findings of this study show that green construction can be an efficient way of preserving sustainability, how it impacts the project managers, and also it could improve the economic performance of the construction industry.

T. Gunanandhini, S. Sivakumar, Aswathy Sreenivasan, M. Suresh
Illuminating Agriculture: Crafting a Strategy IoT-Based Architectural Design for Future Growth

India is a nation of farmers, and it places a greater emphasis on farming since it is essential to the nation’s economic development. As agriculture’s share of the national economy is now shrinking, it is our obligation to boost agricultural output through efficient water and energy use. Improving agricultural water production and mitigating water scarcity frequently require optimizing irrigation schedule. However, there is a significant knowledge vacuum on the most effective strategies for optimizing and adapting irrigation choices in the face of weather and climatic variability. Furthermore, there is no understanding about the comparative benefits of adaptive irrigation scheduling vs the preset heuristics usually used by farmers. This vision creates the idea of intellectual farming which is obtained by using IoT. Evidently, in agriculture, IoT systems must frequently meet a number of functionalities as well as quality necessities, including deciding on connection routes, the speed of data processing, the level of security, the level of safety, and the execution in terms of time. This paper describes IoT architecture for intelligent farm automation in an agricultural area. Also, the procedures and modeling strategies for creating IoT-based architectures are described and a self-contained irrigation prototype is demonstrated at the research level.

M. Pavithra, S. Duraisamy, R. Shankar
Video-Based COVID-19 Monitoring System

This study introduces an innovative solution to address the ongoing COVID-19 pandemic challenges. With the importance of preventive measures like mask-wearing and social distancing in public places, our project aims to support these guidelines by using advanced machine learning and computer vision. We employ CCTV cameras and convolutional neural networks for precise mask adherence detection. Our goal is to develop a highly accurate and efficient system that can easily integrate into existing infrastructure, contributing to public health and safety during these unprecedented times….

Devesh Shetty, Fayeq Zaidi, Asfaq Parkhetiya, Abhishekh Gangwar, Deepali Patil
Analyzing User Profiles for Bot Account Detection on Twitter via Machine Learning Approach

Today social media platforms have become immensely popular. It is one of the ways in which we stay connected with our family and friends, thus making it an essential part of our lives. As the popularity of social media platforms increases, more and more users create their accounts and become a part of them. However, this popularity has also attracted many impersonators who create fake profiles and automated programs known as bots. These bots are involved in various malicious activities like directing users to spam websites, spreading false information about a person or organization, causing economic loss to society, and threatening the security and privacy of users. Such bots must be detected and removed. Thus, there is a need to design a system that can automatically analyze and detect such bots on social media platforms. In this paper, we have designed a system that can classify the bot and human accounts based on the user profile features. Machine learning algorithms like decision trees (DT), support vector machine (SVM), logistic regression (Log R), random forest, and neural networks are used for the classification task. Since the user profile features are huge, feature engineering and dimension reduction techniques like PCA are used. Inspired by the literature, new features are derived from existing features and used in the study. Finally, the comparative performance measure of accuracy, recall, precision, F1 score, and false positive rate of all the classifiers is presented.

Deepti Nikumbh, Anuradha Thakare, Deep Nandu
Artificial Intelligence in Trucking Business Operations—A Systematic Review

If your company is involved in the transportation of goods, such as trucks or boats, you may want to gain a competitive advantage over others. Artificial intelligence (AI) can assist you in identifying the most efficient method to transport items, including finding the quickest route, avoiding traffic, and ensuring timely delivery. This technology also eases the jobs of technicians, managers, and dispatchers, resulting in faster response times, improved fix rates, and greater customer satisfaction by considering location, skill sets, and previous interactions. However, increasing the reliability of logistics on autonomous systems has presented new challenges for human–machine interaction concepts. Because of the lack of competent labor in some regions and the need for sustainability and efficiency enhancement, it is important for logistic operators to pursue automation in the process. This enables the optimization of orders and dynamic planning on the basis of integration with telecommunications facilities. Sustainability has become a mandate in the global corporate sector, with two factors impacting its implementation. Autonomous electric trucks are projected to revolutionize logistics over the next couple of years. In the past two decades, we have seen remarkable advancements in AI and machine learning applications. Using AI in warehouses will enhance efficiency, and the truck appointment scheduling problem can be solved by analyzing vast amounts of data to determine the best routes, schedules, and overall planning. Due to the ever-increasing movement of freight, the sustainability of road freight transportation is gaining importance. AI can satisfy customers with 24/7 virtual assistance through chatbots in vernacular languages. This technology can assist logistic operators in identifying more efficient transportation methods, leading to improved performance and increased customer satisfaction.

Yash Honrao, Shamla Mantri
Deep Learning Approach for Early Diagnosis of Alzheimer’s Disease

Alzheimer’s disease (AD) is a widespread neurological condition that affects millions of individuals worldwide. As a leading cause of dementia, AD is primarily marked by cognitive deterioration and the presence of various behavioral challenges that disrupt everyday activities. Drug trials for Alzheimer’s disease (AD) fail most of the time, probably due to the difficulty in identifying patients at an early stage. Efforts are being made to advance the understanding of the causal molecular processes involved in Alzheimer’s disease through non-invasive imaging modalities. With the boost in the field of big data, deep learning, and the advancement in computational capabilities, diagnosis and classification of various diseases have become easier. Convolutional Neural Networks have been found to be better at diagnosing Alzheimer’s disease through MRI than machine learning approaches using neuropsychological data. In this study, a big data framework based on Hadoop and deep learning approach is used to identify early diagnostic biomarkers of Alzheimer’s disease by integrating MRI and neuropsychological test results. Neuropsychological scores, MRI, and neurochemical scores are used to extract the brain’s structural, neurochemical, and behavioral features. A combination rule using XceptionNet and SVM classifier is then applied for accurate final classification and clinician validation. This includes feature selection and ensemble-based classification.

Vaishnav Chaudhari, Shreeya Patil, Yash Honrao, Shamla Mantri
Study of Key Agreement Protocol Implementation in Constraint Environment

The key establishment (agreement) protocol constructed using public key cryptography (like RSA, D–H key exchange, Elliptic Curve Cryptography) can deliver more confidence in a lesser amount of bit for secrete keys, condense the obligatory communication bandwidth considerably, and reduce the process of computational of the client-side and requirements of storage space considerably for constraint environment. Real and valid implementation of key agreement protocol must have well-built network security and cryptography problem-solving procedure which also safeguards privacy (confidentiality) and integrity of the message. Secure and authentic execution of ECC-based key agreement protocol with Elliptic Curve Cryptography (ECC) offers substantial progress in cryptographic algorithm to defend data integrity, user anonymity, and secrecy of data than other public key encryption schemes (RSA, DSA) and also towards inspection, at a necessary situation of existing secure and authenticated procedure for key agreement protocol execution. Therefore, elliptic curve cryptosystem (ECC) provides proper accomplishment of authenticated and secured key agreement protocol for constraint environment with improved security than RSA. Hence, suggested conventions for the proposed protocol can execute on a wireless communication network to summarize the data confidence, performance parameter necessity, and efforts of calculation (cost of computation).

Chandrashekhar Goswami, Amit K. Gaikwad, Ansar Sheikh, Swapnil Deshmukh, Jayant Mehare, Shraddha Utane
Covid-19 Disease Prediction System from X-Ray Images Using Convolutional Neural Network

Coronavirus has spread to in excess of 200 nations through immediate or auxiliary contact between individuals. Despite the fact that the Reverse Transcription-Polymerase Chain Reaction (RT-PCR) method has happened urged as a standard Coronavirus experiment action, it has many issues, like depressed openness, the necessity for a planned trained workers, and moment of truth span it takes. Covid presents an important evidence in chest X-beam (CX-Beam) pictures and, in this manner, they maybe an appropriate resolution for an alternate system for probing for Covid reactions. A Coronavirus register restraining foundation can find the contamination, that create the healing duties foundation less busy. In this review, a Convolutional Neural Network (CNN)-located action was urged for Coronavirus ailment anticipation from cloud-based CXR pictures. The recommended CNN model shows improvement over past deep learning models.(Names) DCCN, Which has 68 layers and the proposed model has 18 layers.

Basam Akshitha, A. Jagan
Liquidity Regulation and Bank Performance: The Industry Perspective

The present study examines the impact of the new liquidity framework on the performance of Indian banks by conducting in-depth interviews with industry experts. The study adopts a holistic performance framework by including both profitability measures and non-performing asset levels of banks. The study further investigates the role of bank-specific factors like ownership structure [promoters vs. institutional investors, Transparency and Disclosure Practices (T&D), and Information, Communication, and Technology (ICT)] in altering the association of liquidity ratios with bank performance. The industry experts highlight that initially, as banks begin to comply with the LCR standard and liquidity is low, banks’ profitability tends to suffer. However, as the LCR of banks increases further and banks hold sufficient liquid assets, the profits start improving. When analyzing the impact of NSFR on bank profitability, experts confirm that NSFR adversely impacts bank profits. On the NPA side, practitioners argue that though NSFR would have no bearing on the NPA levels of banks, LCR has a favorable influence on the same. The study provides crucial information that can be leveraged by national regulators/policymakers and bank strategists to re-align the regulation or compliance strategies to augment the outcome of the benefits of the new regulatory framework.

Anureet Virk Sidhu, Aman Pushp, Shailesh Rastogi
Enhancing Medical Education Through Augmented Reality

To perform at a professional level, medical professionals must develop complicated skills and undergo practical workplace training. Computer vision, computer graphics methods, and image processing are all used in augmented reality (AR) to seamlessly incorporate digital content into the natural environment. Real-time interactions between users, virtual things, and real items are made possible. AR gives the appearance that virtual objects are a real part of the environment by fusing 3D graphics into films. AR is being used more and more in the medical industry to support distant learning possibilities and interactive simulations. Due to their efficiency and engagement, AR-based teaching programs are being adopted by medical institutions all over the world.

Sumit Sawant, Pratham Soni, Ashutosh Somavanshi, Harsh Namdev Bhor
A Comprehensive Study on Plant Classification Using Machine Learning Models

Plant classification is a critical task with many practical applications, including agriculture, environmental management, and biodiversity conservation. Traditional methods of plant classification can be time-consuming and require considerable expertise. In recent years, machine learning models have shown great promise for automating the plant classification process. This paper provides a comprehensive survey of the existing literature on plant classification using machine learning models. This paper discusses the most commonly used machine learning algorithms, feature extraction and selection techniques, publicly available datasets, and evaluation metrics, also examines the potential applications of plant classification using machine learning models, and identifies the major challenges and future directions for research in this field. Overall, this review highlights the importance of machine learning methods for plant classification and their potential to revolutionize this field in the future.

A. Karnan, R. Ragupathy
Critical Analysis of the Utilization of Machine Learning Techniques in the Context of Software Effort Estimation

Software effort estimate is important today. All software development processes and lifecycles require an important step in the process is software effort estimating (SEE). Precision in software effort estimation is a vital figure compelling preparation, controlling, and delivering a fruitful software project inside budget and timetable. Over-estimation and underestimating are both essential challenges for future software development; therefore precision in software effort estimation (SEE) will be required indefinitely. Effort estimation is critical for an organization to perform since hiring more people than needed results in income loss and hiring fewer people than needed results in project delivery delays. The purpose of this research is to evaluate software effort objectively using machine learning approaches rather than subjective and time-consuming estimation methods. The cost-predicting procedure was employed, according on an analysis of the outcomes of the indicated approaches’ use. The K-Nearest Neighbors technique (KNN), Cascade Neural Networks (CNN), Logistic Regression (LR), Support Vector Machine (SVM), and Multilayer Perception (MLP) is all employed in the cost-predicting procedure. The primary goal of this paper is to thoroughly analyze the currently used software effort to determine approaches by examining estimating algorithms that match novel development methods. In this research, we employ machine learning techniques build a novel model for estimating the loss of software. In the early phases, using two open datasets, several machine learning methods are used to estimate the price of the software. This methodology will be helpful to make every accurate prediction about how much software will cost.

Chetana Pareta, Rajeev Mathur, A. K. Sharma
Review of Recent Research and Future Scope of Explainable Artificial Intelligence in Wireless Communication Networks

The concept of explainable artificial intelligence (XAI) has gained significant traction in recent times owing to its capacity to elucidate the decision-making mechanisms of intricate machine learning models. In the field of wireless communication networks, the application of XAI methods can improve the transparency, trust, and understanding of artificial intelligence (AI) algorithms used for various tasks such as interference management, resource allocation, and network optimization. This piece provides a comprehensive analysis of recent research efforts related to XAI in wireless communication networks and examines the potential opportunities in this emerging field.

Vijay, K. Sebasthirani, J. Jeyamani, M. Gokul, S. Arunkumar, Amal Megha John
Multi-core System Classification Algorithms for Scheduling in Real-Time Systems

This paper presents a technique for real-time scheduling of mixed task sets on a multi-core architecture. This work primarily focuses on the classification algorithms for scheduling in real-time systems within the context of multi-core systems. The utilization of the partitioned earliest deadline first (EDF) technique is employed in the scheduling of recurring jobs. Aperiodic jobs are allocated to many processor cores in a global manner and scheduled on each core via the total bandwidth server. The suggested technique involves assigning a periodic task to each core, so enabling the utilization of the idle processing power of the cores that are not occupied by these activities. This results in an overall improvement in the efficiency of each core.

Jyotsna S. Gaikwad
Transfer Learning Techniques in Medical Image Classification

Medical image classification is a critical task in modern health care that aids in diagnosis, treatment planning, and patient care. However, it is often challenged by limited annotated data, domain shifts, and the complex nature of medical images. Transfer learning has emerged as a pivotal approach to mitigate these challenges by leveraging knowledge from related domains and large-scale datasets. This study provides a comprehensive exploration of transfer learning techniques in the context of medical image classification. The paper commences by elucidating the foundational concepts of transfer learning, highlighting its relevance to medical image analysis. Various transfer learning paradigms, including fine-tuning, feature extraction, and domain adaptation, are meticulously discussed, offering insights into their mechanisms and applicability. Ethical considerations and potential biases intrinsic to transfer learning models in the medical domain are also deliberated upon. The survey emphasizes the necessity of rigorously validating these models to ensure reliable and safe integration into clinical practice.

D. S. Radhika Shetty, P. J. Antony
Integrating AI Tools into HRM to Promote Green HRM Practices

The image of Human Resource Management (HRM) is undergoing a drastic transformation. The conventional methods are evolving due to the emergence of technology, especially with the integration of Artificial Intelligence (AI) and data analytics into the HR processes. With the rapidly changing concept of the overall growth of an organization, AI is becoming a vital stimulant for sustainable growth. AI-powered tools promote data-driven decision-making for talent acquisition, performance management, workforce training and development, optimization of energy consumption and waste reduction. Green HRM aligns these efforts by integrating sustainability considerations into talent management strategies, nurturing employees’ eco-engagement, and promoting environmentally responsible practices within the workforce. This research paper aims to explore the synergies between AI tools and Green HRM practices, investigating how the integration of AI technologies into HR processes can contribute to the promotion of environmental sustainability. By examining real-world case studies, this study aims to investigate the potential of AI-powered solutions in shaping the future of HRM through the lens of sustainability.

Jasno Elizabeth John, S. Pramila
Archival of Rangabati Song Through Technology: An Attempt to Conservation of Culture

The Rangabati folk song, a cherished cultural gem of Odisha, India, holds immense historical and artistic significance. As with many traditional folk songs, there is a growing concern about its preservation and transmission to future generations. This abstract explores the inclusion of technology as a means to preserve and promote the Rangabati folk song. By harnessing the power of digital platforms, recording techniques, and interactive technologies, the traditional essence and cultural heritage of Rangabati can be safeguarded, while also fostering wider accessibility and appreciation among diverse audiences. This abstract examines the utilisation of technology-based interventions, such as audio and video recordings, digitisation, online archives, and virtual collaborations, to document, promote, and conserve the Rangabati folk song. Additionally, the abstract explores the ethical and cultural considerations surrounding the integration of technology and emphasises the importance of collaboration between technology experts, folk artists, and cultural preservationists in ensuring the authenticity and integrity of the song. The findings suggest that the strategic incorporation of technology can serve as a powerful tool in preserving the Rangabati folk song, facilitating its dissemination on a global scale, and fostering a renewed appreciation for this cultural treasure among both local and international audiences.

Jayasmita Kuanr, Deepanjali Mishra
Voice-Based Virtual Assistant for Windows Using ASR

Virtual assistant (VA) is one of the most rapidly expanding aspects in this modern developing world. It is a feature/device which helps the user in many ways such as searching content in the web, reminding about the tasks, calling someone in the contact, and other tasks which eases the user’s tasks. Virtual assistants incorporate artificial intelligence (AI) by using cloud computing which helps in communicating with users in natural language. The VA involves Natural Language Processing (NLP) and AI technology to understand the human language to perform tasks given by the user. In this work, the VA understands the human language using NLP and records using speech recognition. It gives replies using text to speech (TTS). TTS will convert the text into speech.

R. Adline Freeda, V. S. Krithikaa Venket, A. Anju, Gugan, Ragul, Rakesh
Music Recommendation Systems: Techniques, Use Cases, and Challenges

Music recommendation systems have become increasingly popular due to the massive amount of music data available on the internet. These systems aim to provide personalized and relevant music recommendations to users based on their listening history and preferences. This paper provides an overview of the techniques used in music recommendation systems, including clustering, classification, regression, matrix factorization, neural networks, association rules, and hybrid techniques. Moreover, the paper highlights the challenges faced by music recommendation systems, including the cold start problem, data sparsity, subjectivity, diversity, and scalability. The paper concludes by discussing the future scopes of music recommendation systems, including personalization, multimodal recommendation, explainability, interactivity, integration, real-time recommendation, and ethical considerations. Overall, this paper provides a comprehensive overview of the state-of-the-art in music recommendation systems, their applications, and the challenges that need to be addressed for their wider adoption.

Shaktikumar V. Patel, H. B. Jethva, Vishal P. Patel
Obstacle Detection Using Arduino Board and Bluetooth Control

An intelligent robotic vehicle with an ultrasonic sensor that can avoid obstacles in its path is the research idea. This sensor recognizes obstructions, permitting the vehicle to perform activities like halting, turning right or left, and going in reverse. The essential objective is to make a robot vehicle that can work independently or under client direction. The vehicle responds to avoid collision when the ultrasonic sensor detects an obstruction. The vehicle's development incorporates an Arduino UNO microcontroller, ultrasonic sensor, engines, and other electric parts. The microcontroller, which serves as the vehicle's brain, receives information about objects in the vehicle's path from the ultrasonic sensor. After that, the microcontroller issues commands to a servo motor that is connected to the wheels. This ensures that the vehicle comes to a stop in order to avoid colliding with anything. Moreover, the vehicle's usefulness incorporates Bluetooth availability for control. Bluetooth allows users to control the vehicle from a distance and even use voice commands to do so. The joining of a Bluetooth module empowers these control choices, upgrading the vehicle's flexibility and connection prospects.

N. Pavitha, Rohit Dardige, Vaibhav Patil, Ameya Pawar, Bhavesh Shah
Green ICT: Exploring the Role of IoT-Enabled Technologies in Small-Scale Businesses

The optimisation of energy utilisation is of paramount importance for enterprises to augment their operational efficacy, curtail expenses, and foster ecological sustainability. Green Communication and Network Systems cover a diverse array of techniques, which entail the advancement of network protocols that are energy-efficient, the incorporation of renewable energy sources into network operations, and the implementation of network virtualisation technologies to enhance resource utilisation. Conventional energy management methodologies frequently suffer from a dearth of contemporaneous data, leading to suboptimal utilisation of resources and inordinate energy consumption. The integration of Information and Communication Technology (ICT) and the Internet of Things (IoT) into Green Communication and Network Systems facilitates environmental sensing and data collection, thereby empowering stakeholders to make educated decisions regarding energy use and resource distribution. This research delves into the prospective employment of the Internet of Things (IoT) in revolutionising energy management for small-scale businesses. Additionally, the paper also expounds upon the significance of proficient communication and marketing strategies in advancing environmentally conscious behaviours to enhance customer involvement and loyalty. The present study examines the principal obstacles encountered by small-scale enterprises in the domain of resource consumption and deliberates on the potential of Green IoT-based systems to facilitate real-time monitoring, automation, and prognostic analytics for the purpose of optimising energy consumption. By leveraging IoT-enabled communication and network systems, small-scale businesses can attain substantial energy conservation, augment sustainability, and amplify their competitive edge.

Subhashree Rout, Swati Samantaray
Unravelling Obfuscated Malware Through Memory Feature Engineering and Ensemble Learning

Memory analysis is an essential step in the process of identifying malicious programs since it can capture a variety of traits and behaviours. Malware detection faces a number of severe challenges, including a low detection rate and increasingly sophisticated methods of obfuscation, despite the fact that extensive research is being conducted in this area. Given the evasion techniques employed by advanced malware, a pressing need arises for a robust framework specialized in detecting concealed and obfuscated malware. To address this challenge, the VolMemLyzer, an advanced memory feature extractor tailored for machine learning systems, has been enhanced. An integrated stacked ensemble machine learning model complements this improved tool to establish an effective malware identification framework. Supporting the evaluation of this system is the MalMemAnalysis2022, a dedicated malware memory dataset with the primary aim of faithfully simulating real-world obfuscated malware scenarios for comprehensive testing and analysis. According to the findings, the proposed solution has an accuracy of 91.25% and an F1 score of 95.45%, indicating that it is able to detect obfuscated and concealed malware utilizing memory feature engineering in an incredibly short amount of time.

K. M. Yogesh, S. Arpitha, Thompson Stephan, M. Praksha, V. Raghu
Quad-Port MIMO Antenna System for n79-5G and WLAN Wireless Communication Applications

The MIMO communication and Wireless LAN antenna operational in 4.6 GHz n79 5G communication band (4.51–4.63 GHz) and 5 GHz (4.97–5.04) WLAN frequency band is presented. The equal and symmetrical four-element four-port antenna has been strip line excited. The slotted structure of the antenna is responsible for the generation of a second resonance in addition to the fundamental mode. The radiation characteristics of the resonator have been optimized through iteration in the patch and slot dimensions. The engineered MIMO antenna has mechanical dimensions of 90 mm × 90 mm etched on an FR4 laminate having a depth of 1.6 mm. The ground plane of the antenna is made defective to improve the antenna bandwidth. The antenna presents an efficiency of 81.24% and 79.34% and a gain of 2.88 dBi and 2.31 dBi at the first and second frequency bands, respectively. The performance validation of simulated results is done by fabrication and measurement through a vector network analyzer in an anechoic chamber environment.

Trushit Upadhyaya, Killol Pandya, Upesh Patel, Jinesh Varma, Rajat Pandey, Poonam Thanki
Socio-technical Approaches to Solid Waste Management in Rural India: A Case Study of Smart Pipe Composting in Raichur District, Karnataka

Rural areas in developing countries are plagued with complex, intricate challenges. In India, rural communities are seriously lagging regarding Sanitation and Waste management facilities. The majority of communities lack the resources to address those issues. Government programs have partly been able to address those issues, but much still needs to be done to solve the challenges completely. This study aimed to understand better the challenges associated with Solid Waste Management in rural India. It specifically explores how technology can help to complete the last mile of sustainability through a user-centered and participatory problem-solving approach. Taking the case of a community in Raichur district, Karnataka, a smart pipe composting design is proposed to address the Solid Waste Management challenges in the community.

R. K. Chethan, Aniketh V. Jambha, Chirag Pathania, Mutyala Sai Sri Siddhartha, Sanjay, Arifuzzaman, K. Darshan, Souresh Cornet, Sajithkumar K. Jayaprakash
Attendance System Using Face Detection and Face Recognition

In today’s era, world is growing very fast but still in some fields improvement is required. As we know that attendance is very crucial part of student and employee’s life. Many institutes and collages uses some way to mark the attendance of student and many collages still uses that old paper work to mark the attendance of student. However, it is not efficient way to store the data through year and wastage of paper is very high and it is time consuming too because teacher have to call the student by their name or ID and according to response of student, he/she will be marked present or absent. Therefore, to reduce this thing we have implemented a system, which takes attendance automatically in digital way. It will help teachers to save their time. In addition, we can organize the data in efficient manner.

Harsh N. Chavda, Sakshi P. Bhavsar, Jaimin N. Undavia, Kamini Solanki, Abhilash Shukla
Smart Health with Medi2Home: Redefining Medicine Delivery for a Safer Tomorrow

The progress of monitored medicine delivery technology and its importance to healthcare is significantly noticeable. It draws attention to the expansion of the market for these systems, especially oral controlled-dose different versions. These innovations give patients more complete and precise control over the administration of medications, which lowers negative consequences. The proposed system, “Medi2Home” mobile application, is a revolutionary solution for medication collection and delivery. It allows patients to upload doctor’s prescriptions, which are reviewed by experts for precise selection and dosage determination. The system directs the delivery process, ensuring the authenticity of the medication and preventing the distribution of fake pharmaceuticals. The application also enhances patient observance to their prescribed medicines, providing timely notifications and encouraging prescription refills. This approach could significantly improve health outcomes and overall well-being. By combining technology and a patient-centric focus, “Medi2Home” could transform medication appropriation and commitment, fostering a healthier and more obedient patient population.

Sahal Bin Saad, Anatte Rozario, Sadi Mahmud Sagar, Nafees Mansoor
Sentiment Analysis of Product Reviews from Amazon, Flipkart, and Twitter

Social networking services are used by millions of people to share details about their daily lives and express their emotions. People also write on a variety of topics, including social events and product reviews. Through the participatory forums offered by online communities, users can inform and influence others. Additionally, social media gives businesses a chance to engage with their customers by offering them a platform to do so, such as social media for advertising or speaking directly to customers for engaging with customer's perspective on goods and services. In contrast, customers have complete control over what they want to see and how they react. This results in the company's success and failure being made public and spreading by word of mouth. However, social media can affect how consumers behave and make decisions. The Sentiment Analysis of Product Reviews from Amazon, Flipkart, and Twitter plans to apply sentiment analysis on customer tweets from Twitter and reviews from popular e-commerce platforms, such as Amazon and Flipkart, for any product.

Padma Adane, Avanti Dhiran, Shruti Kallurwar, Sushmita Mahapatra
Arithmetic Optimization Algorithm: A Review of Variants and Applications

In this paper, we reviewed the potential of one of the latest metaheuristic algorithms called arithmetic optimization algorithm (AOA) which is based on four basic mathematical functions like addition, subtraction, division, and multiplication to solve the optimization problems. Firstly, the primary inspiration, principles, the basic concepts, and mathematical model of AOA are presented followed by the intense analysis and enquiry of variants and applications published over years listed along with tools used for research. This study intends to encourage researchers for further exploring the opportunities AOA in tackling existing and new practical optimization problems.

Shivani Thapar, Amit Chhabra, Arwinder Kaur
Dark Channel Prior-Based Single-Image Dehazing Using Type-2 Fuzzy Sets for Edge Enhancement in Dehazed Images

The process of image dehazing is known to have a significant impact in the field of computer vision. It has been found to have practical applications in various real-world scenarios, such as autonomous driving, surveillance, and the enhancement of outdoor images. This study tackles the challenge of image dehazing by introducing an approach that combines the dark channel prior (DCP) technique with type-2 fuzzy set theory. The objective of the proposed methodology is to improve the image quality by utilizing the I-Haze and O-Haze datasets, which encompass a compilation of hazy images captured under diverse environmental circumstances. In order to assess the efficacy of our approach, we employ various quality assessment metrics including Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), Lightness Order Error (LOE), and Naturalness Image Quality Evaluator (NIQE). Our research contributes to advancing image dehazing techniques and their practical applications, across domains.

Nisha Amin, B. Geeta, R. L. Raibagkar, G. G. Rajput
ECO-Guard: An Integrated AI Sensor System for Monitoring Wildlife and Sustainable Forest Management

In India, 12% of wild animals are threatened with extinction, and human activity threatens more than 80% of East and Southeast Asia's wetlands. Every year, an estimated 400 people are killed by wildlife in India, with Maharashtra alone seeing 88 human deaths and 9258 cattle killings by tigers in 2020. The ECO-Guard is an intelligent device which uses the You Only Look Once (YOLO) model and various sensors and machine learning models with algorithms that support and promote forest monitoring and tourist guidance in forest areas addressing Sustainable Development Goal (SDG) 12 (Life on Land). The paper presents a linear chain-like mesh of devices speeded across bio-area which are used in correlation for intended surveillance. Each device can multimodule apps and tally their sightings automatically to analyze coherence of the situation with the forest rangers, organizations, and figures. It catches from the information, the ill substitutes like human spotting with beasts. It suggests that the advice can be further put into practice by constantly monitoring any closeness of alternatives that match to create an unfavorable combination. Also having to help detect many forest crimes, some including illegal logging, preventing, and deforestation on a large scale. This paper highlights a novel ECO-Guard, an intelligent and autonomous monitoring system which includes artificial intelligence (AI)-enhanced strategies and algorithms to conserve wildlife and forest ecosystems by integrating various hardware and software components.

Ch. Nikhilesh Krishna, Avishek Rauniyar, N. Kireeti Sai Bharadwaj, Sujay Bharath Raj, Vipina Valsan, Kavya Suresh, V. Ravikumar Pandi, Soumya Sathyan
Machine-Learning-Based Diagnosis of Mental Health Issues

Preventing common mental diseases like anxiety as well as depression have grown into a worldwide priority. Therefore, there is a need to develop effective solutions to such issues. For serving such needs, machine learning methods have been integrated into medical facilities for the identification as well as forecasting of treatment results for illnesses related to mental well-being. The previous literature focuses on such mental well-being like suicidal thoughts, stress, anxiety, depression, and bipolar disorder along with minor aspects like mixed reality, emotional states (moods), mental health education, pharmacogenomics, precision psychiatry, chronic disease contracting, body mass index, and wearable sensors were chosen and subsequently classified into the various grounds of comparison for making the survey more comprehensive. Finally, the future directives for the research on mental health goodness are presented.

Sonali Chopra, Parul Agarwal, Jawed Ahmed, Ahmed J. Obaid
Hybrid CPU Scheduling Algorithm for Operating System to Improve User Experience

The operating system employs CPU scheduling algorithms to allocate the CPU or system resources among the jobs that the job scheduler schedules to run. The goal of the operating system is to divide the resources in a manner that takes into account system objectives such as response times, throughput, and efficiency. Through the use of CPU scheduling algorithms, tasks are distributed to the CPU, ensuring optimal resource allocation and achieving the desired system objectives. Traditional CPU scheduling methods like FCFS, SJF, and RR have limitations like starvation and suboptimal CPU utilization. Modern operating systems have adopted hybrid scheduling techniques to overcome these limitations and improve the system’s performance. These techniques combine multiple algorithms, which resulted in improved efficiency, reduced starvation, and better CPU utilization. By utilizing hybrid scheduling techniques, modern operating systems optimize resource allocation and enhance system performance. The proposed algorithm presents a hybrid scheduling technique, which exploits a Red–Black Tree structure for efficient job selection with a time complexity of (Log2n), that prioritizes jobs and executes them within a specified time period using the Incremental Time Quantum Round Robin (ITQRR) method. This approach improves user experience and CPU performance, combining the Red–Black Tree (RBT) with a multi-queue strategy. The “Time Quantum Incremental” concept of Multilevel Queue (MQ) scheduling algorithms dynamically adjusts the time quantum for subsequent processes. The algorithm outperforms previous algorithms in response time, average completion time, and resource utilization. It excels at prioritizing critical tasks, making it suitable for real-time systems. These enhancements result in notable outcomes, including a remarkable 50% reduction in CPU idle time and a significant 42% improvement in turnaround time.

Ankit Saha, Tushar Mulwani, Neelu Khare
AI-Enable Heart Sound Analysis: PASCAL Approach for Precision-Driven Cardiopulmonary Assessment

A large number of medical professionals depended on manual methods to assess the features of heart sounds. Because of the hands-on nature of this method, it was necessary for them to generate waveforms representing heart sounds and then carefully analyses the various components of these sounds. In contrast, the findings of our most recent research provide an improved methodology that automates the process of separating heart sound data and extracting the relevant factors from those signals. This update is very helpful for applications of machine learning in thoracentesis, and it aligns well with the developments of the most recent clinical imaging technologies. A novel “accordion” approach is presented in our methodology, which we have dubbed PASCAL. This method not only makes use of reference data that is determined by sudden shifts, but it also incorporates an improved classification model that has been customised for the highest possible level of precision. This is particularly clear when looking at the Dataset that We Have for Characterising Heart Rate. It is of the utmost importance to emphasise the fact that the performance as well as the false positive ( $$F_{p}$$ F p ) rates of our classification phase were thoroughly evaluated. While this was going on, we looked at how the features of the ECG signal changed over time. The findings of our investigation are really positive. A fantastic F1-score of 94.38% and a respectable accuracy rate of 93.52% were reached by our suggested technique for identifying and classifying the capabilities of a healthy cardiopulmonary system. The primary sound ( $$S_{1}$$ S 1 duration), the subsequent sound ( $$S_{2}$$ S 2 duration), the overall cardiac cycle, the duration of ventricular systole, the time taken for ventricular contraction, and the ratio between the systolic and diastolic phases were some of the aspects of heart sounds that we examined in great detail. This ground-breaking method makes it possible to conduct an accurate study of the two most important peaks of heart sounds, which are $$S_{1}$$ S 1 and $$S_{1}$$ S 1 . It is important to note that these peaks may demonstrate significant changes from one individual sample to the next. This is mostly because of the different positions that the sphygmomanometer is placed.

Ankit Kumar, Kamred Udham Singh, Gaurav Kumar, Tanupriya Choudhury, Teekam Singh, Ketan Kotecha
Sentiment Analysis in Social Media Marketing: Leveraging Natural Language Processing for Customer Insights

In this day and age of online marketing, social media platforms have evolved into essential tools for companies to use in order to communicate with their consumers, as well as to advertise the goods and services they provide. Understanding client emotion, tastes, and views may be significantly aided by perusing the vast amounts of user-generated information that can be found on these many platforms. This study investigates the use of sentiment analysis, a branch of natural language processing (NLP), as a potent instrument for gleaning useful consumer insights from data collected from social media platforms like as Facebook and Twitter. The application of computer methods in the process of automatically determining and categorising the sentiment that is represented in textual data, such as tweets, Facebook posts, and online reviews, is what is known as sentiment analysis. In this article, the primary methodology and techniques used in sentiment analysis, such as lexicon-based, machine learning, and deep learning approaches, are dissected and discussed. In addition to this, it sheds light on the difficulties and factors to take into account that are unique to sentiment analysis when applied to the context of data from social media, such as the management of noisy and unstructured language, the management of sarcasm, and the management of context-dependent sentiment.

Kamred Udham Singh, Ankit Kumar, Gaurav Kumar, Tanupriya Choudhury, Teekam Singh, Ketan Kotecha
Correction to: Smart Health with Medi2Home: Redefining Medicine Delivery for a Safer Tomorrow
Sahal Bin Saad, Anatte Rozario, Sadi Mahmud Sagar, Nafees Mansoor
Backmatter
Metadaten
Titel
ICT: Smart Systems and Technologies
herausgegeben von
M. Shamim Kaiser
Juanying Xie
Vijay Singh Rathore
Copyright-Jahr
2024
Verlag
Springer Nature Singapore
Electronic ISBN
978-981-9994-89-2
Print ISBN
978-981-9994-88-5
DOI
https://doi.org/10.1007/978-981-99-9489-2