Browse Items (2150 total)
Sort by:
-
Leveraging Deep Autoencoders for Security in Big Data Framework: An Unsupervised Cloud Computing Approach
Abnormalities recognition in bank transaction big data is the number one issue for stability of financial security system. Due to the rate digital transactions are increasing it is vital to have effective ways. Encryption with deep autoencoder model should be explored as it involves trained neural networks that learn such patterns from the complex transaction data. The following paper demonstrates application of anomaly detection using deep autoencoders in the banking big data transactions. It focuses on the theoretical bases, network design, preparedness and the testing measures for deep autoencoders. On the other hand, it solves problems such as high dimensionality and imbalanced dataset. This research paper shows deep autoencoders effectiveness in deep learning and how the network identifies different fraudulent big data transactions, money laundry and unauthorized access. It also encompasses recent developments of cloud environments and future methods using deep autoencoders including the fact that constant search for new possible solutions is a must. The insights delivered contribute to the discourse in financial security community, which incorporates researchers, practitioners, and policymakers involved in anomaly detection in cloud. 2024 IEEE. -
Leveraging Ensemble Methods for Accurate Prediction of Customer Spending Scores in Retail
This study primarily aims to estimate consumer spending trends in a retail context. The goal is to identify the best model for predicting Purchasing Scores, which indicate customer loyalty and potential income, using demographic and financial data. The dataset included information about customers' age, gender, and annual income, and the objective was to analyze their Spending Scores. Several regression models were tested, including Linear Regression, Random Forest, Gradient Boosting, K-Nearest Neighbors (KNN), and Lasso Regression. To improve the models, we engineered features like Age Squared, Income per Age, and Spending Score per Income. Each model was trained and tested using 3fold cross-validation. We evaluated their performance with Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R2) metrics. The results showed significant differences in model performance. The Random Forest model stood out, with the lowest Mean Absolute Error (MAE) of 0.33, Root Mean Square Error (RMSE) of 0.52, and the highest R-squared (R22) score of 0.9997. Gradient Boosting also performed well, achieving a Mean Absolute Error (MAE) of 1.77, Root Mean Square Error (RMSE) of 2.41, and an Rsquared (R2) score of 0.9930. While Linear Regression showed moderate accuracy, KNN and Lasso Regression had higher errors and lower R2 values, indicating less reliable predictions. The findings suggest that ensemble methods, particularly Random Forest, excel at predicting customer Spending Scores. The high accuracy and reliability of this model point to its potential for customer segmentation and targeted marketing strategies, ultimately enhancing customer relationship management and boosting business value. Further refinement and exploration of additional features could further improve these prediction capabilities. 2024 IEEE. -
Leveraging Model Distillation as a Defense Against Adversarial Attacks Based on Deep Learning
Adversarial attacks on deep learning models threaten machine learning system security and reliability. The above attacks use modest data alterations to produce erroneous model results while being undetected by humans. This work suggests model distillation to prevent adversarial perturbations. The student model is taught to emulate the teacher model in model distillation. This is done using teacher model soft outputs. Our idea is that this strategy organically strengthens the student model against adversarial assaults by keeping the teacher model's essential knowledge and generalization capabilities while reducing weaknesses. Distilled models are more resilient to adversarial assaults than non-distilled models, according to experiments. These models also perform similarly on undamaged, uncorrupted data. The results show that model distillation may be a powerful defense against machine learning adversaries. This method protects model resilience and performance. 2023 IEEE. -
Leveraging Robotic Process Automation (RPA) in Business Operations and its Future Perspective
Robotic Process Automation (RPA) is used to automate the business process operations including its capabilities to mimic the routine tasks, which requires less human intervention. RPA has seen crucial take-up practically throughout the last few years because of its capacity to reduce expenses and quickly associate heritage applications. Fundamentally RPA would perform automated tasks much like as an individual to accomplish objectives productively and adequately. This article analyses the features in current business conditions to comprehend the movement of RPA and automated interaction has carried to substitute the businesses with automated tasks. RPA is an innovative technology which utilizes software programming to execute enormous capacity assignments that are routine and time-consuming in the business cycle. RPA streamlines by playing out those undertakings proficiently as it reduces cost and saves assets of an association as programming works till the finishing of the assignment. This study aligns with the descriptive approach and leveraging Robotic Process Automation into business operations. This article also addresses the different players in the RPA Technological segment. This study also discussed and suggested selecting RPA Vendors in a future perspective. 2023 American Institute of Physics Inc.. All rights reserved. -
Leveraging the Synergy of Edge Computing and IoT in Supply Chain Management
This article investigates the possibilities of integrating edge computing and IoT in supply chain management, as well as the adoption of disruptive technologies such as blockchain integration, digital twins, robotics, and autonomous systems. Operational efficiency can be considerably enhanced by establishing a linked and intelligent supply chain ecosystem. The benefits of this technology include increased openness, efficiency, and resilience in supply chain processes. Among the benefits include real-time product tracking, environmental sustainability, enhanced production, and cost savings. The use of blockchain technology in a three-tiered Supply Chain Network (SCN) shows promise in terms of boosting supply chain transparency and security. The SCOR model is also discussed as a comprehensive framework for optimising supply chain processes. However, concerns such as data privacy, security, and employment displacement must be solved before firms can fully reap the benefits of new technologies. Overall, embracing these innovations has the potential to revolutionise supply chain management and create trust among stakeholders. 2023 IEEE. -
LGBT inclusion in UNSDGs - Has the Situation Improved for Sexual Minorities at Indian Workplaces?
In India, the acceptance of the sexual minorities has been considerably poor and challenging owing to societal biases and traditional misinformation. Speaking of workplaces in India, sexual minorities find it relatively difficult to have a complete breakthrough in these existing waves of biases as the policies are not that effective to help them survive in such competitive environment. The authors through this article have presented a qualitative account depicting an in-depth analysis of experiences that the sexual minorities have had in their workplaces. The paper examines the current situation of sexual minority employees at Indian workplaces after inclusion of the Universal value in UNSDGs. The authors in this paper have studied the existing issues that the sexual minorities are still facing in their respective workplaces further comparing it with the sustainable development goals on the grounds of the implicated hindrances that the practice imposes on the aim of United Nations. The Electrochemical Society -
Life Cycle Assessment of Battery Energy Storage Technologies for Vehicular Applications
The necessity of sustainable energy sources and storage technologies is emerging due to growing energy demands. Thus, it encourages the need to perform sustainability analysis in terms of energy efficiency. For battery technologies, energy production and recycling holds a significance. In this study, the direct and indirect requirements of various battery technologies including production to transportation. The five battery technologies taken into account for the analysis are Lithium ion, Nickel Metal Hydride, Lead acid, Valve Regulated lead Acid, and Nickel Cadmium. The characteristics analyzed here are cycle life, energy density and energy efficiency. The study also covers the life cycle assessment in an structured way from raw to evaluation of materials, energy flow, installation, usage to end of life. The Authors, published by EDP Sciences, 2024. -
Lifestyle Diseases Prevalent in Urban Slums of South India
Lifestyle diseases have always been considered to be a malady of the middle and upper classes of society. Recent findings indicate that these chronic non-communicable diseases are common among the lower socioeconomic classes as well. The objective of this study was to assess the prevalence of lifestyle diseases in three cohorts of urban slums, namely, waste pickers living in non-notified slums, communities living in notified slums, and BBMP Pourakarmikas, and to identify the risk factors among the three cohorts contributing to the common lifestyle diseases including hypertension, diabetes, and cardiovascular diseases. In this study, the data was collected by conducting health camps, followed by analysis of the data using logistic regression, HosmerLemeshow test and ROC Curve Analysis. The prevalence of hypertension was found 13.35%, diabetes-8.53% and cardiovascular disease-3.59%. These were significantly associated with substance abuse, high BMI, and age. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Lightweight Anti DDoS Security Tool: Edge Level Filtering in SDN using P4
Software Defined Network (SDN) which has a promising future in satellite communication was first introduced as the solution to solve problems existing in the traditional network architecture. So far in SDN, mitigation strategies employed hardware installation or software solution which is heavily dependent on SDN controllers. The disadvantage of these approaches is the a) cost for implementation, b) intensive resource usage, and 3) costly optimization strategy necessary to enhance SDN performance. This research aims to fill the gap of the previously seen defense mechanism by enabling edge-level filtering without involving the control plane. By implementing filtering functions in edge switches, it can provide an efficient and effective defense layer in SDN network systems so that SDN switch can become the first line of defense against packet injection attacks. The proposed solution, Lightweight Anti-DDoS Software (LADS) focuses on lightweight workloads and provisioning of effective filtering mechanism to allow SDN switches to drop and block malicious packets sent by attackers. It utilizes Programming Protocol-independent Packet Processors (P4) programming language to create custom functionalities in SDN switches. P4 allows SDN switches to conduct host authentication and malicious packet filtering as well as blacklisting to isolate attackers. Simulation result proves that LADS efficiently manages malicious activities and maintains network performance during attacks at the data plane independent of SDN controller. 2023 IEEE. -
Lightweight Sybil attack detection framework for wireless sensor network with cluster topology
The development of communication and networking technology has made it possible for wireless sensor networks to play a significant role in many fields. Wireless sensor networks are vulnerable to a variety of security threats because of their remote hostile features. The Sybil attack, which generates several identities to gain access to wireless sensor networks, is one such devastating but simple to spread exploit. This Paper proposes a novel identity and trust-based system to ensure protection against Sybil attacks. Analysis of the RSSI and location parameter increases the accuracy. It recognises the attackers and broadcasts information about them to all adjacent sensor nodes. Additionally, it offers other crucial security features. 2025 Author(s). -
Linear and non-linear analysis of solute-magneto convection in a couple stress fluid with porous medium under concentration modulation
The effect of concentration modulation and magnetic field in a couple stress fluid with porous medium and salted from above is studied using linear and non-linear analysis. Venezian approach based on perturbation method is used to obtain the expression for solute Rayleigh number and correction solute Rayleigh number. The expression for correction solute Rayleigh number is obtained as a function of couple stress parameter, Chandrashekar number, Darcy number and Schmidt number. The effect of parameters on symmetric and asymmetric concentration modulation are discussed in the paper. A non-autonomous Ginzburg-Landau equation with time periodic co-efficient is obtained to study the effect of parameters on mass transfer. It is found that onset of convection and mass transfer can be delayed or advanced by varying the parameters of the problem. Asymmetric modulation is found to be more stable than the symmetric modulation. 2019 Author(s). -
Linear and non-linear magneto-convection in couple stress fluid with non-classical heat conduction law
A theoretical examination of the thermal convection for a couple stress fluid which is electrically conductive and possessing significant thermal relaxation time with an externally applied magnetic field is carried out. Fourier's law fails when fluids are subjected to rapid heating or when it is confined and in the case of nano-devices. A frame invariant constitutive equation for heat flux is considered. The linear analysis is carried out implementing a normal mode solution and the non-linear stability of the system is analyzed using a double Fourier series. The analysis of the transfer of heat is determined in terms of the Nusselt number. Published under licence by IOP Publishing Ltd. -
Linear Regression Tree and Homogenized Attention Recurrent Neural Network for Online Training Classification
Internet has become a vital part in people's life with the swift development of Information Technology (IT). Predominantly the customers share their opinions concerning numerous entities like, products, services on numerous platforms. These platforms comprises of valuable information concerning different types of domains ranging from commercial to political and social applications. Analysis of this immeasurable amount of data is both laborious and cumbersome to manipulate manually. In this work, a method called, Linear Regression Tree-based Homogenized Attention Recurrent Neural Network (LRT-HRNN) for online training is proposed. In the first step, a dataset consisting of student's reactions on E-learning is provided as input. A Linear Regression Decision Tree (LRT) - based feature (i.e., student's reactions and posts) selection model is applied in the second step. The feature selection model initially selects the commonly dispensed features. In the last step, HRNN sentiment analysis is employed for aggregating characterizations from prior and succeeding posts based on student's reactions for online training. During the experimentation process, LRT-HRNN method when compared with existing methods such as Attention Emotion-enhanced Convolutional Long Short Term Memory (AEC-LSTM) and Adaptive Particle Swarm Optimization based Long Short Term Memory (APSO-LSTM, performed better in terms of accuracy(increased by 6%), false positive rate (decreased by 22%), true positive rate (increased by 7%) and computational time (reduced by 21%). 2022 IEEE. -
Linking the Path to Zero Hunger: Analysing Sustainable Development Goals Within the Context of Global Sustainability
A global framework, the Sustainable Development Goals of the United Nations, are designed to tackle the most urgent global issues. SDG 2, which stands for Zero Hunger, demonstrates a robust interconnection with the remaining seventeen goals since achieving food security and improved nutrition requires an all-encompassing approach that addresses the interconnected challenges presented by poverty, health, education, gender equality, climate change, and sustainable resource management. Within this framework, the research endeavors to ascertain the interrelationships among SDG 2 and other goals and analyze the critical goals that drive the achievement of SDG 2. Furthermore, the study provides an exhaustive analysis of the positions adopted by different nations concerning SDG 2. The results indicate that the SDGs are interconnected; while SDG 2 is closely linked to several other SDGs, their respective impacts differ. Furthermore, it has been determined that policies are crucial to attaining the SDGs. Without a transformation in agri-food systems that enhances resilience and facilitates the provision of affordable, nutritious foods and healthy diets, the current state of affairs will persist. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Lithium photodisintegration with unpolarized photon beams at near threshold energies
The study of photonuclear reactions with lithium targets i.e. photodisintegration of lithium in addition to other photonuclear reactions is of considerable interest to the fields of nuclear physics, astrophysics, laser physics and several applications such as non - destructive testing of nuclear materials. We propose to study photodisintegration of lithium with unpolarized photon beams at near threshold energies. Our model independent theoretical approach, which makes use of irreducible tensor techniques, is well suited for making predictions on the spin observables as well as the differential cross section. In this paper we analyze the reaction channel 7Li + ? ? 6Li + n by using unpolarized photons. 2022 -
Load balancing with availability checker and load reporters (LB-ACLRs) for improved performance in distributed systems
Distributed system has quite a lot of servers to attain increased availability of service and for fault tolerance. Balancing the load among these servers is an important task to achieve better performance. There are various hardware and software based load balancing solutions available. However there is always an overhead on Servers and the Load Balancer while communicating with each other and sharing their availability and the current load status information. Load balancer is always busy in listening to clients' request and redirecting them. It also needs to collect the servers' availability status frequently, to keep itself up-to-date. Servers are busy in not only providing service to clients but also sharing their current load information with load balancing algorithms. In this paper we have proposed and discussed the concept and system model for software based load balancer along with Availability-Checker and Load Reporters (LB-ACLRs) which reduces the overhead on server and the load balancer. We have also described the architectural components with their roles and responsibilities. We have presented a detailed analysis to show how our proposed Availability Checker significantly increases the performance of the system. 2014 IEEE. -
Loan Default Prediction Using Machine Learning Techniques and Deep Learning ANN Model
Loan default prediction is a critical task in the financial sector, aimed at assessing the creditworthiness of borrowers and minimizing potential losses for lending institutions. Online loans continue to reach the public spotlight as Internet technology develops, and this trend is expected to continue in the foreseeable future. In this paper, the authors proposed loan default loan prediction system based on ML and DL models. This work makes use of the information on loan defaults provided by Lending Club. The dataset is preprocessed by applying various data preprocessing techniques and preprocessed dataset is generated. Later, we proposed four ML algorithms decision tree, random forest, logistic regression, K-NN and Feed forward neural network. The experimental results shown that proposed feed forward neural network achieved good accuracy for loan default prediction with an accuracy of 99%. 2023 IEEE. -
Log-Base2 of Gaussian Kernel for Nuclei Segmentation from Colorectal Cancer H and E-Stained Histopathology Images
Nuclei Segmentation is a very essential and intermediate step for automatic cancer detection from H and E stained histopathology images. In the recent advent, the rise of Convolutional Neural Network (CNN), has enabled researchers to detect nuclei automatically from histopathology images with higher accuracy. However, the performance of automatic nuclei segmentation by CNN is fraught with overfitting, due to very less number of annotated segmented images available. Indeed, we find that the problem of nuclei segmentation is an unsupervised problem, because still now there is no automatic tool available which can make annotated images (nuclei segmented images) accurately, to the best of our knowledge. In this research article, we present a Logarithmic-Base2 of Gaussian (Log-Base2-G) Kernel which has the ability to track only the nuclei portions automatically from Colorectal Cancer H and E stained histopathology images. First, Log-Base2-G Kernel is applied to the input images. Thereafter, we apply an adaptive Canny Edge detector, in order to segment only the nuclei edges from H and E stained histopathology images. Experimental results revealed that our proposed method achieved higher accuracy and F1 score, without the help of any annotated data which is a significant improvement. We have used two different datasets (Con-SeP dataset, and Glass-contest dataset, both contains Colorectal Cancer histopathology images) to check the effectiveness and validity of our proposed method. These results have shown that our proposed method outperformed other image processing or unsupervised methods both qualitatively and quantitatively. 2023 SPIE. -
Low cost ANN based MPPT for the mismatched PV modules
Due to manufacturing dispersal, the photovoltaic (PV) panels of similar rating and manufacturer have distinctive characteristics in practical. As the maximum power point tracking (MPPT) becomes essential to optimally utilize the solar PV panel, distributed maximum power point tracking (DMPPT) is considered in this paper to follow the MPP of each panel. As the common MPP value is used in the existing DMPPT method to control all the panels, it fails to consider the uniqueness of each panel. By considering the uniqueness of each panel, the ANN based MPPT is implemented in this paper. As the ANN is trained using the actual characteristics of each panel based on the operating current, voltage and temperature, it is able to track the actual MPP. Due to the solar irradiance free MPPT, the costly pyranometer is not required in the actual PV system for MPPT. It reduces the cost of the system and also provides the interruption free tracking due to its independent nature on Voc and Isc values. Also, because of the looping free behaviour of the proposed algorithm, it is capable of following the MPP at rapidly varying condition. The proposed technique and the verified outcomes are discussed here in detail. Published under licence by IOP Publishing Ltd. -
Low cost energy management for demand side integration
Numerous batteries are outfitted with a state ofcharge (SoC) demonstrating the relaxation about the charge. Building a beneficial BMS is to check while thinking about, to that amount regardless we work now not holds a reliable method in imitation of study condition state of-charge, the nearly imperative measurement concerning a battery. Perusing the relaxation about the vigour of a battery is more unpredictable than administering thin fuel as in automobiles. An electrochemical cell diminishes its greatness and the in-and-streaming coulombs are counted for SOC. The BMS together which offers commitment while charging yet releasing; that detaches the battery if the SOC is below certain percentage. Various laws like Peukerts Law for battery capacity have been employed to determine the discharge rate of the battery. Arduino Uno is used for the input parameters required for Peukerts Law and various other calculations for significant monitoring. To address the existing complicated BMS, a new approach has been provided using IoT platform and making the understanding of BMS in much similar perspective. 2018 IEEE.