International Journal on Recent and Innovation Trends in Computing and Communication
Not a member yet
8613 research outputs found
Sort by
DevOps for Telehealth Services: Accelerating Deployment and Scalability
Get PDFThe use of telehealth services is increasing rapidly to increase access and delivery of remote medical care. However, there are significant technical barriers to rapid and reliable deployment of these services and their ability to handle high patient volumes. This study looks at how DevOps approaches can benefit telehealth providers and let it to overcome this obstacle. To maximize software development and infrastructure management, DevOps focuses on collaboration between development and IT operations teams. Telehealth platforms can be deployed rapidly while leveraging key DevOps skills such as automation, infrastructure-to-code, monitoring, and continuous integration Studies show that these techniques also improve scalability to meet demand changes. This makes it possible for telehealth providers to deliver digitally enabled care to a larger patient base
The Importance of Educational Data Mining and Learning Analytics for Improving Teaching and Learning: An Issue Brief
Get PDF“The words educational data mining and learning analytics are frequently used interchangeably, despite their being an increase in their investigation and implementation. This may be as a result of the fact that both areas have similar conceptual components. One way to ensure precision, homogeneity, and consistency It aims to pinpoint themes that are similar to and different from one other in the two domains as they develop. This a topic modelling study of papers on educational data mining and learning analytics was carried out in the elucidate the two areas' respective themes. In particular, we used structural topic modelling to find the two domains' subjects from the abstracts. For instructional purposes, we use structural topic modelling on N 1 4192 articles. For both educational data and survey data, we infer five-topic models analytics for mining and learning. While there may be disciplinary variations in research, our findings show that beyond their various lineages, there is no evidence to indicate a clear separation between the two disciplines. the area of educational research on the uses of advanced statistical methods is trending toward convergence for improving teaching and learning, discover how to mine massive data streams for insights that may be put to use. Over the past five years, both areas have converged on a growing emphasis on student behaviour. This study topic has advanced greatly, and a variety of related words, including Academic Analytics, Institutional Analytics, Teaching Analytics, Data-Driven Education, Data-Driven Decision-Making in Education, Big Data in Education, and Educational Data Science, are now used in the paper. The main publications, significant turning points, cycle of knowledge discovery, primary educational settings, specialised tools, freely accessible datasets, widely used methodologies, primary goals, and anticipated trends in this field of study are reviewed to provide the state of the art at this time
Comparing Machine Learning Models for YouTube Movie Trailer Comments: An Approach for Accuracy and Overall Sentiment Prediction
Get PDFThis study compares multiple Machine Learning (ML) models for analyzing the sentiment of YouTube comments on movie trailers. The aim of this study is to determine which Machine Learning (ML) model can best accurately predict the overall sentiment of YouTube comments. We compiled a dataset of YouTube comments on a well-known movie trailer and labeled them based on their sentiment using a tokenizer. We then evaluated the performance of different ML models such as Naive Bayes, Support Vector Machine, k-Nearest Neighbors, Random Forest, and Bagging. Our findings show that the Naive Bayes model achieved the highest accuracy for sentiment analysis and provided the most accurate prediction for the overall sentiment of the comments
Deep Q-Learning on Internet of Things System for Trust Management in Multi-Agent Environments for Smart City
Get PDFSmart Cities are vital to improving urban efficiency and citizen quality of life due to the fast rise of the Internet of Things (IoT) and its integration into varied applications. Smart Cities are dynamic and complicated, making trust management in multi-agent systems difficult. Trust helps IoT devices and agents in smart ecosystems connect and cooperate. This study suggests using Deep Q-Learning and Bidirectional Long Short-Term Memory (Bi-LSTM) to manage trust in multi-agent Smart City settings. Deep Q-Learning and Bi-LSTM represent long-term relationships and temporal dynamics in the IoT network, enabling intelligent trust-related judgments. The architecture supports real-time trust assessment, decision-making, and response to smart city changes. The suggested solution improves dependability, security, and trustworthiness in the IoT system's networked agents. A complete collection of studies utilizing real-world IoT data from a simulated Smart City evaluates the system's performance. The Deep Q-Learning and Bi-LSTM technique surpasses existing trust management approaches in dynamic, complicated multi-agent environments. The system's capacity to adapt to changing situations and improve decision-making make IoT device interactions more dependable and trustworthy, helping Smart Cities expand sustainably and efficiently
Navigating Secure Banking IT Landscapes: Insights for Solution Architects and Technical Leaders
Get PDFIn "Navigating Secure Banking IT Landscapes: Insights for Solution Architects and Technical Leaders," the authors examine the evolving strategies and intricate problems associated with banking IT infrastructure security. The purpose of this research is to offer technical professionals and solution architects useful information about the critical need for better cybersecurity measures. Examining new technology, industry standards, and innovative approaches tailored to the banking IT landscape, the study integrates theoretical frameworks with practical implications. Abstract: The study aims to empower banking sector leaders to make informed decisions, enhance technological foundations, and proactively navigate the ever-changing terrain of safe banking IT and persistent cyber threats. Research concludes that proactive incident response planning, frequent audits and continual monitoring are steps that IT executives may do to guarantee the long-term financial viability of the banking business. The auditor performed a thorough job of detecting cybersecurity occurrences, differentiating between genuine and fraudulent payment gateways, and determining the false positive rate ratio by applying networking theory
Hybrid Transform Technique for Robust Steganography on Red Component
Get PDFThe dynamic field of image steganography is witnessing remarkable advancements with the introduction of sophisticated techniques designed to bolster the security of digital data. A novel approach that has garnered attention involves leveraging grayscale picture steganography within the YIQ color space, aiming to provide a more secure method for protecting images. This innovative strategy necessitates the conversion of the carrier image from the conventional RGB color space to the YIQ color space, a process pivotal for the successful application of this steganographic method. The YIQ color space is particularly suited for this purpose due to its structure, which separates the luminance component (Y) from the chrominance components (I and Q). This separation is advantageous for steganography as it allows for the embedding of sensitive information within the luminance component, thus minimizing the impact on the image's color attributes. By converting sensitive information into a grayscale image, this method ensures that the data can be discreetly embedded into the Y component of the YIQ color space. The integrity of the I and Q components is preserved during this process, maintaining the original color characteristics of the carrier image while securely concealing the information. A crucial aspect of this approach is the use of a reliable steganographic technique during the embedding process. This technique must ensure that the grayscale image is seamlessly integrated into the Y component without compromising the quality of the carrier image. The effectiveness of this method is measured through two critical metrics: the Peak Signal to Noise Ratio (PSNR) and the Mean Square Error (MSE). High PSNR values indicate a high degree of similarity between the original and the stego image, suggesting that the embedding process has minimally affected the image quality. Simultaneously, minimal MSE values reflect the low error rate in the reconstructed image, further affirming the method's ability to maintain the integrity of the original image. The proposed algorithm, which utilizes grayscale image steganography within the YIQ color space, represents a significant advancement in enhancing the security of digital communications. By ensuring high PSNR and low MSE in the extracted image, this method demonstrates its efficacy in concealing sensitive information while preserving the visual quality of the carrier image. As such, it opens new avenues for the development of secure communication techniques, underscoring the potential for continued innovation in the field of steganography. This approach not only enhances current communication security protocols but also lays the groundwork for future exploration and development in this ever-evolving domain
Technical Analysis-Based Data Mining Strategies for Stock Market Trend Observation
Get PDFThis study introduces a comprehensive approach that utilizes technical analysis-based data mining strategies to observe and predict stock market trends, by leveraging historical trading data, technical indicators such as moving averages, RSI, and MACD, to systematically analyze and interpret market behavior, thereby providing investors and traders with actionable insights for making informed decisions in the volatile environment of stock trading. By integrating quantitative analysis with predictive modeling, the methodology aims to enhance the accuracy of trend forecasts and identify profitable trading opportunities. Through the application of cross-validation and backtesting techniques, the effectiveness of these strategies is rigorously evaluated against actual market movements, offering a robust framework for risk management and portfolio optimization. This interdisciplinary approach not only demystifies the complexities of the stock market but also opens new avenues for research and development in financial technology, promising a significant contribution to the field of economic forecasting and investment strategy
Measurement Based: 4G and 5G networks Analysis
Get PDFThe advancement of communications services requires the adoption of advanced technologies and the deployment of next generation networks. Nowadays, the Long-Term Evolution (LTE) standard is widely used. Conversely, an increasing number of mobile network operators (MNOs) are integrating the new fifth generation (5G) radio standard into their networks. This facilitates enhanced throughput, spectral and power efficiency and extended coverage, along with minimizing latency. The effectiveness of these developments is evaluated by evaluating the Quality of Service (QoS) in mobile networks. This study describes LTE-4G and NR-5G data measurements and key performance indicator (KPI) analysis based on information collected through a test drive (DT) process for two operators in Austria. Data measurements specifically target parameters that affect network strength and quality, including reference signal received power (RSRP), reference signal received quality (RSRQ), signal-to-interference-noise ratio (SINR), and received signal strength index (RSSI). And downlink - uplink data transfer rate (DL/UL throughput). Analysis of these parameters may reveal the presence of some errors when collecting data from the mobile phone network, such as errors from DT devices, errors from the network itself, errors due to weather conditions, geographical errors, etc. Identify areas of vulnerability for specialized attention to address network errors and maintain them to increase data accuracy and improve quality of services. Ultimately, analyzing KPIs and detecting errors within the collected data provides a simplified approach to managing and monitoring mobile network performance, reducing complexity, maintenance time and costs, thus enhancing customer satisfaction
Predictive Modelling for Medical Image Analysis Using Deep Learning Techniques
Get PDFRecent advancements in healthcare for the prediction of autosomal diseases have led to the usage of deep learning algorithms in analysing medical images. Autosomal diseases are an extensive group of illnesses that range from cardiovascular diseases to specific types of tumours. Leveraging Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) can forecast models accurately and then very efficiently, but it has limitations in finding autosomal chromosomes. The autosomal chromosome uses advanced deep-learning algorithms to analyse a database of medical images, including MRI and CT scans, to predict the onset and progression of inherited disorders. Predictive accuracy is maximized by the usage of data preparation, model training, and learning strategies. The prognosis and early finding of autosomal diseases can be greatly enhanced by algorithms for timely intervention and customized treatment for patients. Further integration of analysing medical images can give more patient care and improve disease prediction results, particularly in the case of autosomal disorders and diagnosis
Smart Roads, Smarter Cities: Machine Learning Integration for Dynamic Traffic Management
Get PDFAs the world's cities become more urbanised, traffic congestion becomes a major problem. Conventional approaches are unable to deliver timely insights, which impedes the application of efficient congestion control strategies. This study presents a novel machine learning-based traffic congestion control system that combines a Euclidean distance tracker with the YOLO (You Only Look Once) object recognition framework. As cities struggle with the intricacies of increasing traffic, the need for intelligent technologies capable of real-time vehicle surveillance and congestion analytics is highlighted. To address this, the suggested solution goes beyond traditional constraints by using machine learning to accurately detect and track automobiles in urban environments. Utilizing the YOLO object detection framework, which is renowned for its speed and accuracy, the study builds on prior research in computer vision and transportation engineering. By connecting object detections between frames, the Euclidean Distance Tracker improves performance and allows a continuous comprehension of vehicle motions. The system's effectiveness in real-world circumstances is demonstrated by the results, which offer high accuracy across a range of vehicle classes. A major advancement in the development of urban mobility has been made with the integration of YOLO and the Euclidean Distance Tracker, which offers a viable solution for intelligent traffic management