Innovative Computing and Communications

Table of Contents

1. Frontmatter

2. Cybersecurity Threats and Countermeasures for IoT Devices

   Sunidhi Yadav, Rohit Saini, Priyanka Sahu

   Abstract

   The Internet of Things (IoT) has indeed been a game changer, in today’s fast moving world where everything feels interconnected and technology keeps advancing. Take, for example, all those smart thermostats and the endless beep of sensors in factories; this is how IoT devices have become part and parcel of our daily lives and are key to mission-critical systems. However, as the numbers of these devices increase so is their associated risk. This research takes a plunge into IoT cyber security trying to figure out the many threats that these gadgets face. It is not just about defending our own personal information- it is also about ensuring that our networks are safe and our communities are healthy. This study aims at uncovering barriers and solutions in IoT cyber security. The hope by doing this is to refresh everybody’s mind on the pressing need for updated security measures in an interconnected world. Being one step ahead will definitely provide safety against any harm to us, our data or even our communities at large.

3. Relationship Between Website Atmospherics and Online Consumer Behavior

   Sunetra Saha, Arpita Srivastava, Nitish Pathak, Neelam Sharma

   Abstract

   A major component of internet marketing and e-commerce is the connection between website atmosphere and user behavior. A user’s experience and decision-making process can be significantly impacted by a website’s atmosphere, which can have an impact on a variety of factors. Keeping the website, internet, and online consumer behavior in the mind, this study was conducted. S-O-R framework was implemented in the study and used as a theoretical framework for conducting the research. The questionnaire was set with the help of this framework. One hundred and fifty-four responses were collected from various areas and demographics. The main aim of this paper is to explore the connection between ambience of website and the behavior of online consumer. The focus is to investigate how the various elements of a website, including design, layout, aesthetics, and user experience, influence the decision-making process of consumers in the online domain. By conducting a comprehensive analysis, the research aims to pinpoint and comprehend the main factors and attributes that notably impact consumer behavior in the digital environment. Through this investigation, the study seeks to provide valuable insights to the fields of digital marketing and online commerce, empowering businesses to better comprehend and optimize their online presence in order to effectively cater to consumer preferences. For data analysis and to test the hypothesis tools like factor analysis, correlation and regression were used. The finding of the study was that factors like website privacy, entertainment, technology adoption, information on website, and purchase intention are the essential factors on the website according to the respondents. The study indicates that information quality, website design, user flow, privacy, entertainment value, technology integration, and website content significantly influence online consumer behavior positively.

4. MIMO and Chaotic Communication: Systematic Literature Review

   S. J. Sheela, S. Y. Sonu, Virupaxi Dalal, Shankargoud Patil

   Abstract

   Owing to its low power consumption during chaotic signal production and reduced hardware implementation complexity, chaotic communications have attracted attention in the field of wireless communications. To enhance system efficiency in wireless networks, multiple transmit and/or multiple-input multiple-output (MIMO) systems leverage several receive antennas. The system is made resilient by the combination of MIMO and chaotic communication signals, which increases data throughput, capacity, ease of installation, and secure communication. In this regard, this article employed a standardized systematic literature review method to conduct a critical analysis of the selected papers. The study aimed to highlight the advantages of combination of MIMO and chaotic communication in enhancing the security of physical layer. The review selected and analyzed recent research papers disseminated between 2007 and 2023 and a total of 30 papers were reviewed. The review carried out a detailed evaluation of the selected papers with regard to the modulation techniques, channel coding techniques etc. The article concludes by highlighting the possible research directions preferred reporting items for systematic reviews and meta analyses (PRISMA) framework are used. Overall, this article provides a comprehensive summary of key improvements in enhancing the security through the use of MIMO and chaotic communication. However, there is no specific literature review article on combination of MIMO and chaotic communication.

5. Crop-Recommendation in Spatial Clusters Using Meta-Heuristics and Machine Learning Techniques

   Manan Barwal, Paras Nath Barwal, Kamta Nath Mishra

   Abstract

   The crop is the baseline of the Indian economy. To ensure the actual variances of the crops, we need to analyze and further predict the best crop suitable for every spatial feature vector. In order to analyze the dataset, the authors in this paper implemented several machine learning and deep learning techniques upon which the predictions can be assumed. The authors in this paper analysed the meta-heuristic approaches such as particle swarm optimization, cuckoo search, ant colony optimization and in the presence of several factors, they also incorporated the machine learning techniques finding the spatial clusters of crops available to the farmers performing the agriculture on the land. The feature variables extracted from the standard dataset used in this project are Nitrogen, Potassium, Phosphorus, Temperature, Rainfall, and Humidity in the soil. The features are mapped using cuckoo search. The most appropriate features are then selected using Particle Swarm Optimization (PSO). These features are mapped using many machine language algorithms such as KNN (K-Nearest Neighbours) and Random Forest Optimization to provide a single class output. The results obtained are provided to deep learning neural network architecture to obtain multiclass output. The proposed model gives us an accuracy of 98.30% that is promising and higher than all the other algorithms used in the research.

6. Black Gram Leaf Disease Detection Model Using Combination of Hybrid-cnn Network and Transformer-based Classification Model

   Astha Sharma, Ashwni Kumar

   Abstract

   The king of pulses, black gram is also referred to as urad in India, where it has been grown since ancient times. The diseases that affect the leaves of the black gram plant are the reason behind the annual decrease in production of this crop, which is grown mostly in India. Therefore, detection of diseases in of utmost importance. Earlier detection and classification of plant leaf diseases utilized CNN based methods. These methods often constrained by economic losses making them less reliable. To overcome this issue, this paper presents a transformer-based model for identification of black gram leaves diseases. The proposed work utilized a hybrid CNN model which combines VGGNet and Inception-V3 for image feature extraction. The extracted features are further utilized by transformer-based classification network for efficient classification of plant leaf diseases for black gram. To validate the effectiveness of the proposed model extensive experiments on BPLD dataset are carried out. Further, to avoid data related and overfitting issues, the dataset was improved and increased to 15,000 images using different augmentation techniques. Also, the proposed hybrid CNN transformer model provided superior results on the BPLD dataset with an accuracy of 99.56%.

7. Multimodal Posture Monitoring and Eye Health Surveillance

   Abhishek Kutre, Arpit Pandey, B. V. Murali Sai, E. S. Ananth, K. N. Divyaprabha

   Abstract

   Addressing concerns that prolonged use of devices in today’s digital landscape has led to increased negative personal representation, leading to disruption and health issues, our research offers a new framework to enhance postural alignment and eye health is meant. Utilizing state-of-the-art Flex sensors and machine learning algorithms, our system delivers real-time feedback to users, designing an ergonomically sound work environment that integrates MQTT communication for Flex sensor data and imagery paragraph based webcam. We used a multimodal approach combining data from flex sensors and computer vision to perform a comprehensive postural analysis. In addition, the system monitors eye health by analyzing blink frequency and screen-to-screen distance. Our project shows promising results, helping to develop proactive solutions for continuous well-being in the digital age.

8. Efficient Feature Selection for IoT Security: A Comparative Analysis of Swarm Optimization Algorithms in Attack Detection

   S. Kumar Reddy Mallidi, Rajeswara Rao Ramisetty

   Abstract

   As the Internet of Things continues to expand, securing this interconnected space becomes increasingly critical. This research presents a wrapper-based approach to feature selection, utilizing swarm optimization algorithms to enhance intrusion detection systems in the IoT paradigm. We implemented and compared several swarm optimization techniques—gray wolf optimization, cuckoo search optimization, firefly optimization, whale optimization, and ant lion optimization—integrated with decision trees, light gradient boosting machine, and Gaussian Naive Bayes classifiers. These combinations were used to select optimal feature subsets, with the accuracy of the models serving as the fitness measure. Upon identifying the best feature subsets, we constructed detection models and compared their performance against models utilizing the complete feature set. This comparative analysis was conducted on a large-scale dataset, with over 46 million data points, ensuring robust evaluation. The selected feature subsets, particularly those derived from gray wolf optimization and cuckoo search optimization, exhibited exceptional performance, achieving high accuracy and weighted F1 scores. The findings of this study show the effectiveness of feature swarm optimization techniques in feature selection toward the development of lightweight intrusion detection systems for resource-constrained environments like IoT. While showcasing the importance of feature reduction, the study also discussed the trade-off between feature reduction and the model's accuracy. This study highlighted the future research direction in applying advanced feature engineering techniques and ensemble techniques for developing intrusion detection systems for IoT.

9. Analysis of Feature Extraction Technique LBP and Classification Model SVM for CECT Images

   Rituparna Sarma, Yogesh Kumar Gupta

   Abstract

   Extraction of various features from an image means identification of different attributes that characterize an image. This process is quite challenging because of the image resolution and its complexity. Medical field has been widely using image processing techniques for detection and diagnosis of diseases. Here we are trying to detect the cancerous tissues in the liver organ where the extraction of tissue features further requires differentiating between the cancerous and non-cancerous tissue patches. Also, it is necessary to achieve simpler computational complexity for an algorithm. In this paper, local binary pattern technique is used for identifying the texture characteristics of tumor in liver organ. This technique is a local descriptor of an image based on its neighborhood for any given pixel. The extracted features are then classified using SVM classifier. The accuracy of the model is satisfactory and effective for tumor diagnosis and decision-making process.

10. ADHD Scout: Mobile Application for Home-Based Screening to Facilitate Early Detection of ADHD in Children

    Kazi Hassan Robin, Md. Lutfor Rahman, Md. Habibur Rahman, Rajaul Karim

    Abstract

    This paper presents a novel framework and mobile application for detecting Attention-Deficit Hyperactivity Disorder (ADHD) in children. The app utilizes a combination of game-based assessments for children and parent and teacher feedback surveys to generate an accurate ADHD detection result. The framework aims to address the challenges of early detection, particularly for children by offering a cost-effective and accessible home-based screening tool. The application demonstrates how various technologies such as JavaScript, React.js, React Native, Tailwind CSS, Node.js, and MongoDB used to develop the application work together to form a seamless development stack that speeds up the development process and boosts code maintainability. Extensive testing confirmed the app's user-friendliness, accuracy, and reliable functionality across various network conditions. Rural user feedback further validated its feasibility and cultural sensitivity. This mobile app has the potential to transform early ADHD detection, improve access to care, and empower stakeholders (patients, parents, teachers, and doctors) to identify children with ADHD who may benefit from professional evaluation and treatment. Notwithstanding the app's shortcomings in terms of data quality and its inability to replace a medical diagnosis, it provides a viable tool for at-home ADHD screening that should improve results and the lives of people impacted. Future work will focus on fine-tuning the app's accuracy, conducting viability testing, and exploring integration with healthcare workflows and research initiatives.

11. Enhancing Solutions by Implementing Nash Equilibrium Strategies Using Python

    Ibrahim Saad Mohsin, Abdullah Ali Mohammed, Marwah Muataz Ismael, Noora H. Sherif

    Abstract

    Finding effective solutions is a never-ending mission. A basic idea in game theory, Nash equilibrium supports a theoretical framework for studying strategic interactions between many decision-makers. These works aim to improve traditional optimization techniques by applying NE principles, reaching better results in situations with complexly related variables. Game theory, especially Nash equilibrium, has become increasingly popular across diverse fields as an efficient tool for making strategic decisions. This study discusses the idea of Nash equilibrium and how it can be implemented to improve solutions in many fields. The basic idea of a Nash equilibrium, a fundamental idea in non-cooperative game theory, suggests a situation where, given the plans of other players, no one is motivated to unilaterally deviate from their preferred path of action. This balance provides us useful shrewdness toward maximizing outcomes in complex systems as well as being a theoretical idea. It is very important to know how game theory enters into many general applications and our daily lives and gives the simplest details. Every decision that is made daily is connected in one way or another to game theory. In this study, we will discuss how to solve game theory problems using linear programming. Detect the usefulness of Nash equilibrium and its basic impact on our routine lives and think of a simple practical application of Nash equilibrium. The study discusses the role of machine learning algorithms implemented by Nash equilibrium strategies and explains how Python programming language can be used in oracular modeling and for many strategic planning.

12. Target Specific Stance Detection from Social Media with Multilayer Perceptron

    Sayani Ghosal, Amita Jain

    Abstract

    Social media allows individual to share their judgment or standpoint towards any topic or news. People easily relies on the news that are circulated on social media. Generally, controversial political and social news can instigate people to react. So, automatic detection of stance towards any topic is very much essential that can help to detect rumor and fake news. Context identification and truthfulness of any post can improve the existing stance detection model. This research proposed a novel stance detection model that considers paragraph2vec embedding model for contextual analysis, TF-IDF for importance and relevance of each term and LIWC for emotion and psycholinguistic analysis with Multilayer Perceptron (MLP) classifier. This study considers English language standard dataset and achieved 10–35% improvement of F₁-score compared to baseline model. Among various combination of feature extraction method, the proposed stance detection model portrays achievable performance.

13. Web-Based Application for Medicinal Plant Identification Using Transfer Learning Approach

    Harsh Kukreja, Akash Saini, Dhruv Saluja, Devanshi Tegwal, Preeti Nagrath, Rachit Garg, Ashish Khanna

    Abstract

    This research addresses crucial challenges in identifying medicinal plants in India, essential for Ayurvedic Pharmaceutics. It proposes a pioneering approach using image processing, machine learning and a flask-based web solution allowing users to upload and analyze their own photos seamlessly. To conduct this study, a dataset from Kaggle featuring 40 medicinal plant classes is leveraged. Convolutional Neural Networks (CNNs) and transfer learning with DenseNet121 are employed for formulating deep learning model and class prediction. The CNN model achieves an accuracy of 69.58%, and transfer learning with DenseNet121 achieves 77.20%, both demonstrating high precision, recall, and F1-score. While acknowledging limitations in dataset scalability and potential biases, the study recommends future endeavors to focus on dataset expansion, real-time applications, integration of environmental data, continuous model optimization, validation, certification processes, educational initiatives, and global collaboration for conservation efforts. This research represents a significant advancement in ensuring the integrity of raw materials and building trust in traditional medicinal practices within the Ayurvedic Pharmaceutics domain. Such strides contribute to the broader landscape of holistic healthcare by combining traditional wisdom with cutting-edge technologies.

14. Navigating Challenges in India’s Milk Industry: An In-Depth Review on Cattle Healthcare, Technology, and Market Dynamics

    Aashi Gupta, Kritika, Prachi Yadav, Muskan, S. R. N. Reddy, Rishika Anand

    Abstract

    Milk has an ever-growing demand in the society being a necessity of a to infant to a full-grown adult. From the part of livestock care to distribution of the end product, each and every process plays a significance in the health of dairy products consumed. Availability of assured quality of these products is the biggest challenge faced by the consumer today. Verticals of the dairy industry: health care of livestock, technology involved, and market status are reviewed. Challenges in each vertical have been deduced and discussed. The adoption of various livestock management practices including breeding, feeding, and healthcare practices across various parts of India has been discussed. In some parts, lack of awareness is observed, while in others, ignorance is seen due to unavailability of resources and financial constraints. Technology acceptance, and its various factors, in the organized sector (20% of the whole) has worked toward effective utilization of milk production. Globally, various technological advancements are revolutionizing the dairy industry keeping in mind the goals of sustainability. India is the largest milk producer but still needs to import dairy products affecting the market. Socio-economical, technical, and operational reasons behind these are also deliberated upon.

15. Corpus-Based Machine Translation for English to Low-Resource Language Using OpenNMT

    Mohatesham Pasha Quadri, Pradeep Kumar

    Abstract

    One of the challenges in computational linguistics is the scope of Machine Translation (MT) for languages with few resources, specifically English to low-resource languages. Lack of parallel data in the majority of South-Asian languages prevents Machine Translation training. Computational linguistics plays a pivotal role in the storage of meaning and representation for specific object languages, and translation is a central component of language technology. This abstract explores the evolution of translation techniques, transitioning from direct word-to-word approaches to cutting-edge methods like Statistical Machine Translation (SMT) and Neural Machine Translation (NMT), enabled by neural networks and deep learning. However, despite these advancements, many South-Asian languages still face challenges due to the scarcity of parallel data for Machine Translation. This paper focuses on corpus-based machine translation and highlights various machine translation approaches. To address the issue of partial translations, an enhanced attention method is proposed, enhancing the decoder's ability to grasp contextual information. This abstract offers a glimpse into the significance of machine translation in the realm of computational linguistics and emphasizes the ongoing quest for more effective and accurate language translation solutions.

16. Optimizing Energy Trade in Virtual Power Plants with Lstm, Representative Houses and Dynamic programming

    Hartej Singh, Pallavi Chauhan, R. Padma Priya

    Abstract

    The radical change of the global energy system causes the development of Virtual Power Plants and microgrids in energy trading. Since the consumer behavior is volatile and not easily predictable, load forecasting is becoming a serious problem, also due to the influence of holidays and seasonal and special events that may affect energy demand in general. Virtual Power Plants and microgrids require precise load forecasting for real-time trading to ensure the balance between supply and demand. Thus, this paper proposes innovative forecasting techniques using Long Short-Term Memory and machine learning to address these challenges. New forecasting techniques would help to improve resource management and enhance the stability of the energy system while improving the integration of renewable energy and the efficiency of distributed energy resources. The use of a multivariate LSTM load forecasting model in this small work aims at making the energy supply and demand process more optimal between producers and consumers. For more accurate assessment of constantly changing customer attitudes to control the energy distribution process, virtual energy groups have been prepared aimed at clustering residential homes based on energy usage and weather forecasting pattern. Since the most similar homes are clustered according to their energy consumption, the most similar resident homes within such groups were selected, which was the basis for multivariate LSTM load forecasting. In the following study, such virtual consumer groups and the study of homes as a separate group will be analyzed based on the different ways of energy distribution on the needs of such virtual energy groups. This study provides the importance of virtual organizations and homes for load forecasting, increasing the efficiency of energy supply, network survivability, costs, and environmental protection. Efficient energy trading, guided by advanced forecasting techniques like LSTM, representative houses, and dynamic programming, is essential for optimizing Virtual Power Plants, ensuring precise resource allocation, and enhancing grid resilience, cost-effectiveness, and sustainability in the modern energy ecosystem. The study not only delves into the current challenges and methodologies, but also provides a trajectory for future work, envisaging continued advancements in optimizing energy trading systems.

17. An AI-Powered Personalised Badminton Training System with Frame-by-Frame Correction

    Atharv Anant Athavale, Anish Cherekar, B. K. Aditi, Ananya Prabhakar, Gauri Sameer Rapate

    Abstract

    Excellence in badminton demands a combination of mental toughness, strategic insight and technical skill in strokes, footwork, and physical fitness. The proposed work provides an AI-based solution to enhance the performance of the badminton players. Proposed work identifies the flaws in the postures of players and provides feedback. The proposed badminton training system extracts frames from the uploaded video, extracts keypoints from the frames using the Mediapipe library, classifies frames into different poses/shots, identifies areas of improvement and provides feedback for the pose by performing an angle-based comparison. The proposed approach is implemented using a web user interface. It works on commodity personal computing hardware, which makes it accessible and user-friendly for a broad audience without the need for high-end equipment. A shot classification accuracy of 97.3% is achieved using a random forest model.

18. Integration of AI with BlockChain Toward Authentication of Testimonials and Transcripts in Academic Institutions

    Anant Jain, Gauranshi Gupta, Rahul Johari, Deo Prakash Vidyarthi

    Abstract

    This research paper investigates the fusion of Artificial Intelligence (AI) and BlockChain technologies to enhance the authentication of testimonials and transcripts in a certificate verification system. The motive behind this study was addressing the limitations of traditional certification processes, necessitating a shift toward more secure, transparent, and efficient methods. The proposed research approach utilizes Artificial Intelligence for candidate verification, via facial recognition and Optical Character Recognition (OCR). Afterward, digital certificates are generated and securely stored on the BlockChain, using smart contracts for transparency. The result of AI and BlockChain provides an efficient verification process that ensures security and efficiency by verifying candidate credentials. Verified certificates are provided to recruiters or receiving parties, that show the effectiveness of this proposed approach in certificate authentication system. This system not only ensures the security of candidate credentials but also enhances the verification experience for the receiving parties.