Browse Items (11809 total)
Sort by:
-
Dictionary-Based BPT Compression with Trimodal Encryption for Efficient Fiber-Optic Data Management and Security
Fiber-optic transmission systems are capable of carrying tens of terabits per second of traffic and thereby form the core infrastructure for all Internet-based services and applications. While fiber-optic communication provides rapid data transfer, it faces the challenge of managing the substantial data volumes generated, stored, or transmitted. In the realm of fiber-optic communication, data interception is straightforward, necessitating robust security measures. One effective solution is compression-based encryption, which combines security with data compression benefits. Encryption safeguards data by transforming it into ciphertext during transmission, rendering it unreadable to attackers without knowledge of the encryption method. Data compression enhances bandwidth efficiency, enabling the efficient transmission of large data volumes using limited bandwidth. In the event of data compromise, attackers must grasp both compression and encryption methods to decipher the information, adding an additional layer of security. In this paper, an encoding technique named the Bounded Probability-Based Textual Data Compression (BPT) algorithm is introduced with trimodal encryption method for securing the short textual data while transferring from source to the destination. The BPT algorithm creates a codeword using a dictionary that assigns binary codes according to character occurrence probabilities in the input data. To decompress, the coding table must be transmitted alongside the compressed data. The trimodal encryption is used as a second tier for securing the data that was compressed using BPT algorithm. The trimodal encryption employs three encryption methods, and data is encrypted using one of these methods during transmission to the destination. The BPT algorithms performance is evaluated using benchmark textual datasets from the Calgary Corpus and the Canterbury Corpus. The experimental results demonstrate the unique characteristics of the BPT algorithm, including compression ratio (CR), compression factor (CF), bits per character (BPC), and space savings. Additionally, the Trimodal encryption algorithm (TME) method is evaluated using end-to-end delay analysis, packet loss analysis, and packet delivery ratio assessment. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
A Secure Deep Q-Reinforcement Learning Framework for Network Intrusion Detection in IoT-Fog Systems
IoT-Fog system security depends on intrusion detection system (IDS) since the growing number of Internet-of-Things (IoT) devices has increased the attack surface for cyber threats. The dynamic nature of cyberattacks often makes it difficult for traditional IDS techniques to stay up to date. Because it can adapt to changing threat landscapes, deep Q-reinforcement learning (DQRL) has become a potential technique for ID in IoT-Fog situations. In this paper, an IDS system for IoT-Fog networks based on DQRL is proposed. The suggested solution makes use of fog nodes' distributed computing power to provide real-time IDS with excellent accuracy and minimal latency. With feedback from the network environment, the DQRL agent learns to recognize and categorize network traffic patterns as either normal or intrusive. Adaptive exploration techniques, effective reward functions, and deep neural networks for feature extraction are adopted by the system to improve predictive performance. The evaluation findings show that, in terms of detection accuracy, precision, recall and f-measure, the proposed DQRL provides flexibility to changing threat patterns as compared to conventional IDS techniques. A vast array of cyberattacks, such as malware infections, denial-of-service (DoS) attacks, and command-and-control communications, are successfully recognized and categorized by the system. It is possible that the suggested solution will be crucial in safeguarding IoT-Fog networks and preventing cyberattacks 2024 IEEE. -
Enhanced Lumpy Cattle Skin Disease Prognosis via Deep Learning Methods
Animal illness is growing in importance. Identification of the illness is important since various diseases may affect different animals, and immediate guidance will be provided. Cows with lumpy skin issues are caused by the Neethling infection. The affection of these diseases causes lasting injury to the cattle's skin. Reduced Poor growth, reversal, milk production, gravidity, and, in severe cases, mortality are the most common adverse consequences of the illness. We developed a deep learning-based architecture that can predict or recognize disease. A deep literacy system is required to identify the microorganism causing the lumpy skin disease. This system collects diverse cattle electronic medical records and uses data analysis to create an intelligent diagnosis system for cattle diseases. It involves text preprocessing to enhance data quality, and the ECLAT algorithm correlates disease names with probabilities, providing tailored treatment plans. The system ensures timely disease treatment, reducing herders' losses and promoting scientific intelligence in animal husbandry. 2024 IEEE. -
Safety of Unmanned Systems
The safety risk management process describes the systematic application of management policies, procedures and practices to the activities of communicating, consulting, establishing the context, and assessing, evaluating, treating, monitoring and reviewing risk. This process is undertaken to provide assurances that the risks associated with the operation of unmanned aircraft systems have been managed to acceptable levels. Active efforts should be made to develop rules to ensure the safe operation of unmanned aerial vehicles. For the safe integration of operations with unmanned aerial vehicles, it is important to take into account the influence of different levels of control and autonomous capabilities, as well as the source of movement monitoring in the system. This article discusses the security issues of unmanned systems, the main directions of ensuring the information security of unmanned systems, software and hardware vulnerabilities have been identified. The methods of information protection are given, the disadvantages are indicated. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Advancing Predictive Analytics in E-Learning Platform: The Dominance of Blended Models in Enrollment Forecasts
The rapid expansion of e-learning platforms has revolutionized the landscape of education, particularly highlighting the significance of online courses in contemporary learning environments. This research focuses on Udemy, a prominent online learning platform, and aims to enhance the predictability of course enrollments within its IT & Software category. The study's central purpose is to leverage advanced machine learning techniques to predict course subscriber numbers, a crucial indicator of a course's popularity and success. Employing an extensive dataset from (Kaggle DB)Udemy, encompassing various course attributes such as ratings, reviews, and pricing, the study explores multiple machine learning models. These include Linear Regression, Decision Tree, Random Forest, Gradient Boosting, and K-Nearest Neighbors Regression. A key innovation of this research is the application of ensemble methods, particularly a blended model approach, to integrate predictions from multiple models, thereby enhancing accuracy and reliability. The findings of this study are significant. The ensemble approach, notably the blended model, outperforms individual predictive models in accuracy. Among the single models, Gradient Boosting Regression shows the highest effectiveness in forecasting enrollments. The research highlights the vital role of course characteristics, including ratings and reviews, in determining course popularity. This study contributes to the field of e-learning by introducing a novel, data-driven approach to predict course enrollments. It offers valuable insights for educators, course creators, and platform developers, emphasizing the potential of machine learning in optimizing content strategy and marketing efforts in the digital education domain. The application of ensemble machine learning methods presents a new horizon in educational analytics, paving the way for more nuanced and effective strategies in online education delivery and promotion. 2024 IEEE. -
Transparency in Translation: A Deep Dive into Explainable AI Techniques for Bias Mitigation
In an era dominated by artificial intelligence (AI), concerns about bias and discrimination loom large. The quest for fairness and equity in AI-driven decision-making has led to the exploration of Explainable AI (XAI) as a viable solution. This paper undertakes a thorough examination of the bias ingrained within AI systems and posits XAI as a potent antidote. Beginning with an exploration of the origins and aftermath of bias in AI, the analysis traverses the evolution of XAI techniques, including SHAP, LIME, and counterfactual explanations, clearly stating their advantages and drawbacks. With each XAI method thoroughly inspected, the study unravels their applicability across diverse AI models and domains. Furthermore, a compelling case study is presented, showcasing XAI's practical application in a language translation app, where it guarantees transparency and equity in the translation process. This tangible example serves as a testament to XAI's efficacy in mitigating bias within real-world applications. As the analysis concludes, it underscores the pivotal role XAI plays in fostering accountability and trustworthiness in AI systems. By shedding light on how XAI mitigates bias and offering concrete examples of its utility, the paper advocates for its widespread adoption as an imperative step towards the development of ethically robust AI systems. In a landscape filled with concerns about bias, XAI emerges as a beacon of hope, promising a future where AI decisions are transparent, fair, and equitable for all. 2024 IEEE. -
Comparative Analysis Study of 43-point and 27-point Buyoff Stations for Stressed Mirror Polishing (SMP) Metrology
As a collaborative effort within the Thirty Meter Telescope (TMT) project, India is committed to supplying 84 polished segments for the primary mirror, employing the innovative Stressed Mirror Polishing (SMP) technology obtained from Coherent Inc., USA. SMP allows for the efficient polishing of highly aspheric non-axisymmetrical glass blanks at an accelerated rate. India-TMT (I-TMT) successfully applied SMP to qualify three glass roundels at Coherent's facility in Richmond, CA. The study focuses on a comparative analysis of Buyoff Stations (BOS) used in the SMP process. It contrasts results from the 43-point hydraulic-based BOS at Coherent with simulated outcomes from the 27-point whiffletree-based BOS at I-TMT. This analysis assesses efficacy and performance differences between the two BOS configurations, involving a comprehensive examination of a 1520mm diameter polished glass roundel. The study integrates Finite Element Method (FEM) simulations with experimental data, providing insights into the efficiency of the respective BOS setups. 2024 SPIE. -
Enhancing Human-Computer Interaction with a Low-Cost Air Mouse and Sign Language Recognition System
The purpose of this study is to investigate the development of assistive technologies that are designed to empower people with disabilities by increasing their level of freedom and accessibility. Voice assistants, air mice, and software that recognizes sign language are some of the topics that are specifically covered in this. Those who have impaired fine motor skills can benefit from using air mice since they allow controls to be made by hand gestures. Using machine learning algorithms, sign language recognition software is able to decipher signs with an accuracy rate of over 90 percent, making it easier for people who are deaf or hard of hearing to communicate themselves. By relying solely on vocal instructions, voice assistants like Alexa make it possible to control devices without using your hands. Not only do these technologies have the potential to be revolutionary, but they also confront obstacles in terms of improving identification accuracy and integrating them into common gadgets. In this study, the development and impact of voice assistants, sign language software, and air mice are discussed. More specifically, the paper highlights the potential for these technologies to help millions of people with disabilities all over the world. Additionally, it examines potential enhancements that could be made to these technologies in the future in order to further improve accessibility and inclusivity. This research integrates computer vision and machine learning to create a multimodal system blending air mouse functionality with real-time sign language translation. Achieving 95% accuracy in gesture recognition for air mouse control and 98% accuracy in sign language letter classification using a basic webcam, the system promotes accessible interaction without specialized hardware. Despite limitations in vocabulary and lighting sensitivity, future efforts aim to broaden data training and explore mobile deployment. These advancements hold promise for enhancing natural human-computer interaction, particularly for users with disabilities, by enabling intuitive, hands-free control and communication. 2024 IEEE. -
Assessing and Exploring Machine Learning Techniques for Cardiovascular Disease Prediction using Cleveland and Framingham Datasets
Heart disease prediction using machine learning has garnered significant attention due to its potential for early diagnosis and intervention. This study presents an analysis of various machine learning algorithms applied to HD prediction across multiple research papers. The goal of this study is to analyze the performance and predictive capabilities of various machine learning algorithms in predicting heart disease across different datasets and research papers. Algorithms such as Logistic Regression, Random Forest, Support Vector Machine, Decision Tree, Naive Bayes, and Gradient Boosting were evaluated using diverse datasets and parameters. In the Cleveland dataset, both Random Forest and Decision Tree classifiers achieved perfect accuracy 100%. Conversely, in the Framingham dataset, Random Forest exhibited the highest accuracy at 94%, followed by SVM at 87.45%, and Decision Tree at 85.23%. While specific algorithm performance varies depending on the dataset and parameters considered, ensemble methods like Random Forest often demonstrate superior performance. These findings underscore the effectiveness of machine learning in HD prediction and emphasize the significance of algorithm selection in developing accurate predictive models for cardiovascular health. 2024 IEEE. -
Advancements in Sybil Attack Detection: A Comprehensive Survey of Machine Learning-Based Approaches in Wireless Sensor Networks
Wireless Sensor Networks (WSNs) are used in various healthcare and military surveillance applications. As more sensitive data is transmitted across the network, achieving security becomes critical. Ensuring security is also challenging because most sensors are deployed in remote areas, making them vulnerable to many security attacks. Sybil attacks are one of the most destructive attacks. Security against Sybil attackers can be attained by implementing effective detection techniques to distinguish attackers from genuine nodes. This paper reviews existing machine learning-based approaches for detecting Sybil attacks, and their performance is compared based on different parameters. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Enhancing Patient Well-Being in Healthcare Through the Integration of IoT and Neural Network
This study analyses the revolutionary integration of Internet of Things (IoT) structures in healthcare through a complete examination of outstanding case research. The first case study focuses on real-time patient fitness monitoring in a clinic setting. The suggested device utilizes an Internet of Things-ready device that has many sensors, including oxygen, pressure, and temperature sensors. The issues of forecasting patient health in advance are handled with the deployment of machine learning models, notably Artificial Neural Networks (ANN), Decision Trees (DT), and Support Vector Machines (SVM). The second case study analyses IoT's effect on patient-precise medication identification and remote fitness monitoring, uncovering issues associated with accessibility, pricing, and human interfaces. Proposed alternatives, which incorporates greater education, increased accessibility, and user-pleasant interfaces with robust technical assistance, have been evaluated with 30 patients over a three-month duration. The results reveal a great growth in impacted person health, along with heightened attention of periodic health monitoring. The results highlight how IoT technologies may transform healthcare procedures by offering pro-active solutions for patients' well-being. This study offers insightful information that may be used to solve practical issues, promote patient-centered solutions, and broaden the scope of the healthcare period. A significant step towards a patient-centered and technologically advanced healthcare environment, the successful outcomes validate the capacity for sustained innovation, cooperation, and improvement in the integration of IoT systems for optimal patient care. 2024 IEEE. -
A Novel Technique for Magnetic Particle Separation Using Current-Carrying Slotted Plate
In this paper, a novel method for separating and trapping different magnetic particles is presented. Changes in the current-carrying structure yield disturbing the generated magnetic field. Here, slots were innovatively crafted on the current-carrying plate positioned beneath the microchannel, resulting in a non-uniform magnetic field distribution. This breakthrough enables the separation of different particle types using a constant and low electric current for the very first time, leading to a significant advancement in the field. More importantly, this proposed technique offers several advantages, including the generation of low levels of current and heat, ease of construction, and the ability to control the magnetic field produced by the electric current. In this study, the capability to effectively separate various particle types using a constant electric current was demonstrated with a remarkable separation efficiency of about 100%. By applying a 100[mA] electric current to the plate that carries electric current, the separation of two particle types M-450 and M-280 was achieved at a velocity of 2[?m/s]. 2024 IEEE. -
Impact of Corporate Announcement of Green Innovation on Automaker's Market Value -An Event Study Methodology
The aim of this paper is to analyse the effects of the Green Innovation event and corporate announcements regarding green innovation on the stock price of the Automobile Industry and the performance of firms. The authors also aim to assess the impact of these events on business performance and identify the effective innovation strategy influenced by the type of corporate announcement. The study focuses on the corporate announcements made by the automobile industry and their impact on company performance, specifically in relation to the application of green innovation methods. Furthermore, there is no universally agreed upon standard for defining and categorising corporate announcements. The writers also exclude the impact of media and other events that occur during the event window when categorising these announcements. The findings of this study have important practical consequences. They suggest that the release of green innovations, which aim to protect the environment, can have an impact on an organization's stock market success. Specifically, the type of innovation and the trade segment in which the organisation operates can influence its stock market performance. Grenze Scientific Society, 2024. -
Residual-Based Statistical Process Control Charts in the Presence of Multicollinearity: an EWMA Framework with (RK) Estimator
Reliability monitoring of financial health requires strong control mechanisms, and the residual chart is an invaluable instrument to perform it. One of the key problems statisticians face while modeling is the problem of multicollinearity which arises when there is a strong correlation between independent variables leading to imprecise coefficient estimates and poor outcomes. To solve this problem and to make sure that the control chart works even with correlated data, we integrated a Weighted Moving Average Exponential smoothing chart within the modeling technique. The theoretical approach assures long-term variability and consistency of the residual control chart. These control charts are used to understand the process and the performances in various sectors. The charts can be used as analytical instruments to help recognize patterns, variations, or anomalies in economic indicators specifically in budget deficit data and facilitate rapid identification of any changes or inconsistencies in the fiscal deficit by policymakers. Further advances in statistical process control are rendered feasible by this study, which deepens the understanding and awareness of the potential uses and implications of the Weighted Moving Average Exponential smoothing chart for fiscal deficit data in the Economic realm. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Strategic Power Factor Management for Elevated Lift and Hoist Performance
The paper outlines the design and simulation of active power factor correction for a 100 hp induction motor using MATLAB/Simulink. In this system, the induction motor functions as the primary load, operating with a low power factor. Different load scenarios are simulated to examine the motor's performance. The current drawn from the supply is verified under varying conditions, both with and without the implementation of a variable capacitance bank. The power system network comprises apparatus such as Induction Motors, Power Transformers, and Induction Furnaces, contributing to a low power factor. The resultant low power factor leads to elevated energy consumption. To mitigate this, power factor correction is imperative. Utilizing a variable capacitance proves instrumental in enhancing the power factor. The capacitor compensates for a portion of the reactive power, consequently reducing the total reactive power drawn from the source. This reduction in reactive power contributes to an overall decrease in power consumption. The research focus is on the effective correction of the power factor for a 100 hp induction motor through comprehensive design and simulation using MATLAB/Simulink, providing valuable insights into the impact of variable capacitance on current draw under diverse load conditions. 2024 IEEE. -
An Optimal Load Balancing Framework for Fog-Assisted Smart Grid Applications
The growth of the Internet of Things (IoT) causes a significant amount of data to come in from physical devices and sensors, which adds to the latency and processing delays in smart grid applications. The pay-per-model method of transmitting gathered data that cloud computing offers improves scalability and functionality for end devices, which increases smart grid efficiency. Milliseconds matter in the crucial realms of load balancing, resource usage, and distribution systems, where any latency or jitter is unacceptable. By strategically positioning processing, networking, storage, and communication capabilities at the network edge, fog computing, an outgrowth of cloud technology, successfully addresses current issues in service groups. This paper introduces a unique hybrid framework on a highly virtualized platform and proposes three potential load balancing algorithms: throttled, Round Robin, and a novel Equilibrium Optimizer with Simulated Annealing (EO-SA). The article provides a comprehensive investigation on several load balancing techniques for obtaining optimized services in a smart grid environment thereby focusing on better utilization of network resources and reduction of costs. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Deep Learning Advancements in E-commerce Supply Chain Management in Forecasting and Optimization Strategies
In this study, the influence of deep learning technologies on the optimization of supply chain management in the context of the e-commerce industry is examined. Using a dataset of historical data of sales, inventories, market fluctuations, and customer and supplier details, I investigate the efficiency of different deep learning models to predict demand and facilitate the optimal balance of inventories. Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), and a model proposed by the authors are defined and applied, considering their accuracy, precision, recall, and F-1 score. The results show that the proposed model outperforms traditional products, achieving 97.5% of accuracy. In the context of the comparative analysis, the specific features of CNN, LSTM, and RNN are revealed, helping to understand the benefits and drawbacks of each recommendation. As a result, the proposed model proves that deep learning technologies have the power to change the approach to predictive analytics and supply chain management, allowing practitioners to focus on strengths and overcome the weaknesses of their structures. The impact of data preprocessing and hyperparameters is also considered along with the necessity to choose the most appropriate model evaluation technique. In the future, it is possible to implement other complex deep learning models, integrate additional data, and address the problem of data scaling and heterogeneity. In the era of modern technologies, e-commerce organizations should take these findings into consideration to discover the potential of deep learning, improve supply chain performance, reduce costs, and attract clients. This research contributes to the topic of using deep learning technologies in supply chain management, promoting innovation, and changes that may affect the industry drastically. 2024 IEEE. -
Python Driven Keyword Analysis for SEO Optimization
Every word or string of words a user types into a search engine has meaning. For example, a user might search for a 'hotel' or a 'hotel in New York City.' Keywords are the standard focus of search engine optimization (SEO), which offers a useful method of gauging demand for specific queries and aiding in a better understanding of how users look for goods, services, businesses, and, eventually, solutions. Any effective SEO strategy must include keyword research, and Python is a strong language that can be used to automate and accelerate the process. This project presents a Python-based keyword research tool that works on real-time data to identify the top searches over a user-specified domain to identify trends and customer needs. It does this by utilizing multiple Python libraries and Google Autocomplete. The Google Autocomplete results for the user-specified domain are first parsed by the tool before it can function. After that, unnecessary keywords are eliminated by filtering and cleaning the results. Subsequently, the remaining keywords are arranged for search volume and domain relevancy. The tool looks for trends by comparing the current keyword rankings with previous data. Thanks to this, users can see which keywords are growing in popularity. By identifying the most commonly asked questions and issues, the tool also offers insights into the needs of its users. The tool is simple and adaptable to each user's unique requirements. It can be used to create keyword lists for content marketing, SEO, and product development, among other uses. 2024 IEEE. -
Unveiling the Dynamics: A Performance Analysis of RPL under Congestion in IoT Network
The Routing Protocol for Low Power and Lossy Network (RPL) is a standardized routing protocol for resource constraint devices deployed in diverse applications in Internet of Things (IoT). RPL is the most efficient protocol which is carefully designed to meet energy efficiency of sensor nodes. However, this protocol is prone to network congestion which is one of most crucial bottlenecks of this protocol. In the current study a thorough analysis of effect of congestion on RPL routing metrics are analyzed. We have designed a congestion scenario using Cooja simulator and analyzed its effects on ETX, Power, Duty Cycle through graphs. The results of the experiments finally outline the critical parameters affected due to congestion in RPL. Grenze Scientific Society, 2024. -
AI-Powered IoT Framework for Enhancing Building Safety through Stability Detection
The rapid urbanization and increasing structural complexities of modern buildings have heightened the need for advanced monitoring systems to ensure building safety. The research presents an AI-powered IoT framework that enhances building safety through advanced stability detection mechanisms. The proposed framework employs a novel algorithm, Ensemble Learning with IoT Sensor Data Aggregation (EnIoT-SDA), which integrates ensemble learning techniques with aggregated sensor data to provide accurate and real-time stability assessments of building structures. The effectiveness of EnIoT-SDA was evaluated through a comprehensive simulation analysis, comparing its performance against existing algorithms, including Support Vector Machine (SVM), Gradient Boosting Machines (GBM), and Fuzzy Logic Systems (FLS). Simulation metrics, such as accuracy, false positive rate, computational time, and detection latency, were used to assess and compare the algorithms' performance. The results demonstrated that EnIoT-SDA outperformed the existing methods in several key areas, offering improved accuracy and reduced detection latency, thus establishing its potential as a robust solution for building safety monitoring. The study underscores the significant advancements brought by integrating ensemble learning with IoT sensor data and highlights areas for future research and development in this domain. 2024 IEEE.