Bijendra Kumar
@nsut.ac.in
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Khushil Kumar Saini, Damandeep Kaur, Devender Kumar, and Bijendra Kumar
Springer Science and Business Media LLC
Deepti Singh, Bijendra Kumar, Samayveer Singh, Satish Chand, and Pradeep Kumar Singh
Springer Science and Business Media LLC
B. Arun Kumar, Sanjay B, Sri Kishore B, Yuvanesh R, and Sudharson D
IEEE
Hunger and insufficient diet cause reduced nutrients levels in an individual which is being the global issue. In ancient times people were exchanging products for survival, now every item is valued in terms of currency and supplied accordingly. Certain procedures lead to hoarding the products, making the food products unavailable in certain parts of the globe and in other parts it is of high cost to be affordable. Several technological processes were aligned with the notion of arriving increased productivity. This article analyzes the impact of Artificial Intelligence (AI), Machine Learning (ML), Internet of Things (IOT) for sustainable agriculture. Parameters such as humidity of air, strength of infrasonic sound gathered using IoT are categorized with respect to precision parameters through various existing ML models. Then it is reiterated and achieves 93.23% of accuracy by deploying Pareto Distribution based Gradient boosting algorithm. Finally, it uses other ML frameworks to support supply chain management.
Shilpi Sharma and Bijendra Kumar
Springer Nature Singapore
Pragya, Bijendra Kumar, and Gyanendra Kumar
Informa UK Limited
Vibha Jain and Bijendra Kumar
Springer Science and Business Media LLC
Vibha Jain and Bijendra Kumar
Springer Science and Business Media LLC
Sudharson D, D. Satheesh Kumar, Aman Kumar Dubey, B. Arun Kumar, Vaishali V, and Balavedhaa S
IEEE
In the food industry, allergen cross-contamination is a serious problem that necessitates innovative approaches to detection and prevention. In order to tackle this problem, this paper investigates the possibilities of machine learning (ML) techniques, focusing on CatBoost, XGBoost, and LightGBM in particular. Through an analysis of datasets from food processing establishments, the research develops prediction models that leverage on the distinct advantages of these machine learning methods. The models' comparative evaluations demonstrate how well they identify allergen cross-contamination risks, improving food safety protocols. This paper demonstrates the significant role of CatBoost, XGBoost, and LightGBM in strategically controlling allergen cross-contamination and offers insightful information about the applicability of ML. In the final analysis, these results provide a framework for the advancement of risk-mitigating intelligent systems that ensure consumer safety and support the industry’s broader food safety regulations.
Pragya and Bijendra Kumar
IEEE
IPv6 addressing has become increasingly important with the rapid emergence of the Internet of Things (IoT) due to the depletion of IPv4 addresses. Allocating IPv6 in the IoT is challenging because of the large number of devices with limited resources and the requirement for efficient and scalable addressing schemes. This paper comprehensively surveys the various IPv6 addressing strategies for IoT networks.This paper discusses the various factors involved in assigning IPv6 addresses to IoT nodes, including spatial information and allocation processes. The authors provide a detailed overview of existing IPv6 address assignment methods and the different types of IPv6 addresses used in IoT networks.The survey presents a tabular evaluation of the various addressing schemes based on different metrics, including address success rate (ASR), energy consumption,spatial information, communication overhead, and nature of deployment. Additionally, the paper highlights the advantages and disadvantages of different addressing schemes and discusses their areas of applicability.Furthermore, the survey highlights future research directions for addressing IoT, such as developing lightweight address generation schemes and better and secure addressing schemes to mitigate DOS and reconnaissance attacks.It also highlights the need for continued research to address the challenges associated with addressing IoT nodes.
Pragya and Bijendra Kumar
Wiley
AbstractIn resource‐constrained networks, IPv6 addresses are assigned to devices using SLAAC‐based EUI‐64, which generates unique addresses. However, the constant interface identifier (IID) across networks makes it vulnerable to reconnaissance attacks like location tracking, network activity correlation, address scanning, etc. This research work introduces a new addressing strategy that utilizes the Elegant Pairing function to guarantee the generation of nonpredictable unique IPv6 addresses, thereby mitigating different types of reconnaissance attacks. The proposed scheme achieves 100% address success rate (ASR) based on experimental evaluation while effectively thwarting reconnaissance attacks. Importantly, it achieves security enhancements without additional communication overhead and energy consumption.
C. Preethi, V.S. Shree Saran, M. Meikannan, S.Shahul Hammed, K. Haripriya, and B.Arun Kumar
IEEE
E-commerce, also known as electronic commerce or internet commerce, refers to the exchange of money and data for the purpose of business operations through the internet. The term “ecommerce” is commonly used to refer to the online sale of tangible goods, but it may also refer to any type of commercial transaction made possible via the internet. It is nowadays one of the most important components of the internet. Electronic commerce is the process of conducting business using computer networks. An individual sitting in front of a computer may use all of the Internet's resources to purchase or sell things. E-commerce, which began in the early 1990s, has made enormous strides in the world of computers. B2B e-commerce is used to increase the usage of e-commerce in developing nations by enhancing access to global markets for enterprises in developing countries. Regardless of the rapid growth of technology, e-commerce has reached its apex. This article proposes a novel application concept. It describes the public's needs for M-Commerce, as well as the analysis and literacy survey of essential components of mobile devices that use such apps. The design and security of the application are both carefully studied. This study examines the characteristics and possibilities of a mobile E-app for selling and purchasing fresh vegetables. The outcomes demonstrate how the application has impacted the public, employment, and long-term growth.
Sudharson D, Aman Kumar Dubey, Arun Kumar B, Sri Thrishna J, Neha F, and Kavinaya S K
IEEE
Businesses are looking for novel solutions to automate online shopping due to the worldwide rapid growth of online transactions which eventually results in Bigdata. The surviving retail operation of faring channels are not able to obtain a convenient successful collaboration between channels. Therefore, this article comes up with a novel solution of creating an Artificial Intelligence (AI) poweredshopbot. A shopbottracks the price of the product and compares it with the other E-commerce platforms and suggests customers the best platform to purchase the product that they desire to buy. This avoids wasting of additional time for looking up each retailer's price. By using this strategy customers may rapidly compare fares from several vendors for the same goods with the help of shopping bots through bigdata analysis.
Ritu Devi and Bijendra Kumar
Springer Nature Singapore
Manan Suri, Nalin Semwal, Divya Chaudhary, Ian Gorton, and Bijendra Kumar
ACM
One of the most common mental illnesses that affects 5% of adults globally is depression. The advancement of social media has meant that more and more people have gained a platform to voice their thoughts and beliefs. People’s social media interactions and posted content can be used to infer critical characteristics such as depressive tendencies which will allow for timely intervention and help. This paper describes a novel supervised approach to detect depressive tendencies in Twitter users using multimodal frameworks which account for user interaction and online behaviour in addition to the tweet content processed using transformers like BERT. The performance of three multimodal frameworks is described with different methods for combining modalities. The best result is obtained a cross-modality based model which improves the baseline by 12% points.
Vibha Jain and Bijendra Kumar
Wiley
With the recent advancements in the Internet of Things, cloud computing has emerged as an important industrial technology that assists in various data analysis operations. However, the remote locality of cloud servers and scalability issues of cloud computing make it unsuitable for real‐time computing‐intensive applications. Fog computing strives to support cloud computing in meeting scalability demands by providing location‐sensitive services closer to end devices. With decentralized heterogeneous resource capabilities, fog architecture can handle several computation‐intensive and delay‐sensitive user requests. Although deploying service providers in an untrustworthy environment makes it challenging to assess the trustworthy acquired services. Conspicuously, in this article, we present a trusted task offloading and resource allocation using blockchain technology. To start with, we analyze direct and indirect trust with a subjective logical aggregation approach using a distributed trust assessment approach. Additionally, we examined the various quality of service parameters and constructed a smart contract that utilizes the state‐of‐the‐art deep reinforcement learning algorithm, namely Deep Deterministic Policy Gradient, to maximize fog revenue while serving as many user requests as possible. The entire process from task generation to results calculation is assisted by blockchain and offloading task transactions are stored in the secure, immutable, and tamper‐resistant ledger. To assess the effectiveness of our proposed scheme, we compared the simulation results with other baseline schemes over different performance metrics in terms of reward, service latency, energy consumption, task drop ratio, and transaction success rate. The results suggest that enabling trust computation improves transaction success by 21%.
Vibha Jain, Bijendra Kumar, and Aditya Gupta
Elsevier BV
Vibha Jain and Bijendra Kumar
Wiley
In the IoT‐cloud environment, the growing amount of spawn data may limit performance in terms of communication latency, network traffic, processing power, and energy usage. The introduction of fog computing extends the cloud services nearer to the edge of the network. Since these lightweight fog servers are not able to fulfill the demand of every user node and process each offloaded task due to the limited computation resources. Accordingly, an efficient resource management scheme is required to proficiently handle fog resources. The profit‐driven nature of both the fog service providers and user nodes increases the possibility of malicious activity while resource trading for their advantages or to privilege a bunch of devices. In this article, we designed a trusted and fair incentive mechanism that encourages buyers and sellers to trade by leveraging the benefits of blockchain and smart contracts. Especially, a combinatorial double auction employed market model is proposed which satisfies different economical properties such as individual rationality, budget balance, and truthfulness. Blockchain‐driven decentralized fog environments prevent the tampering of trade‐related information by the malicious nodes. Simulation results indicate that the proposed combinatorial double auction significantly improves the network utilization by improved winner determination and pricing model.
Shruti Sachdeva and Bijendra Kumar
Elsevier BV
Pragya and Bijendra Kumar
IEEE
IoT is a platform that allows various things to connect and communicate with one another. IPv6 is used to simplify the addressing process in order to address the IPv4 limitation. Each device needs an IPv6 address, which needs to be distinct and unique, in order to join a network. The DAD procedure is a useful tool for detecting address duplication in a network. It is necessary for each IoT object to create a unique IPv6 address when it joins the network in order to communicate with other nodes. The practice of detecting duplicate addresses is employed in order to ensure the unique address to each object before joining the network. This paper discusses the significance of the DAD process, potential dangers to the DAD process, and several author-provided solutions. This paper also presents different lessons learned from the literature and present future research directions towards the DAD process.
Vibha Jain and Bijendra Kumar
IGI Global
In recent years, the emergence of the internet of things (IoT) has accelerated the quality of day-to-day tasks. With the rapid development of IoT devices, the cloud computing paradigm has become an attractive solution by facilitating on-demand services. However, the remote location of third-party cloud reduces the overall user experience while increasing the latency involved. Fog computing has been introduced as a promising solution by improving the overall service quality. Fog computing comprises distributed and heterogeneous fog nodes with limited resource capabilities. Therefore, managing fog resources while satisfying users' service quality is a challenging task. This study attempts to conduct a systematic review by examining high-quality research papers published between 2018 and April 2022. This paper aims to address current trends, challenges, and theoretical gaps with a wide range of open issues to guide the researchers and practitioners interested in carrying out the further research in the current domain.
S. Pavalarajan, B.Arun Kumar, S.Shahul Hammed, K. Haripriya, C. Preethi, and T. Mohanraj
IEEE
Identification of dementia is an important concern in medical image processing. Alzheimer is a common kind of dementia. Four machine learning models were designed for identifying this disease. This is classified as a classification problem, and the classification algorithms tested include logistic regression, support vector classifier, decision tree, and random forest classifier. The models are fine tuned by choosing optimal values for parameters that influences the accuracy of the model. The optimal parameters are found using a K-fold cross validation score, and the models are generated using that. The dataset used in the model is longitudinal cross sectional data from OASIS. It has been inferred from the results that random forest classifier performs well than the other models.