International Journal on Recent and Innovation Trends in Computing and Communication
Not a member yet
8613 research outputs found
Sort by
Advanced Contextual Integration and Millimeter Wave (mmWave) Technology for Optimizing 5G and Next-Generation Networks
Full text linkThis paper explores the enhancement of 5G and future generations of mobile networks through the integration of millimeter wave (mmWave) technology and advanced contextual awareness. It presents a comprehensive framework for embedding a sophisticated mmWave module within the ns-3 simulator, enhanced with detailed channel models to enable precise research and simulations. Additionally, it introduces the innovative Context Generation and Handling Function (CGHF), which leverages a publish-subscribe model to efficiently disseminate contextual data across network elements. This function is designed to bolster decision-making processes at various network points, including edges and data centers. The study further details the implementation of a context-aware Radio Access Technology (CRAT) selection strategy that optimizes connectivity and performance in complex scenarios characterized by ultra-dense networks and diverse Radio Access Technologies (RATs). By merging mmWave technology with enhanced contextual intelligence, the paper significantly advances Mobile Core Network (MCN) operations, promoting more reliable, efficient, and forward-thinking solutions in 5G and beyond. The outcomes provide a technological blueprint for improving network functionality and user experience, essential for the upcoming era of smart cities
Revolutionizing Construction: Harnessing IoT for Industry Remote Monitoring
Full text linkThe Construction Industry serves as a vital driver of national economic prosperity, yet it grapples with persistent challenges including low productivity and a lag in adopting cutting-edge technological advancements. Recognizing the imperative for modernization, there arises a pressing need to digitize operations within the construction sector. In today's technology-driven era, the Internet of Things (IoT) has become a driving force for transformation, leveraging sensors and actuators to digitize various tasks. This study explores integrating IoT technology into the realm of construction, promising the deployment of intelligent systems capable of enhancing operational efficiency and construction equipment productivity across construction projects. By delving into the myriad sensors available, it elucidates how these technologies automate tasks within construction sites, streamlining project execution. Furthermore, this study offers a concise overview of sensor-based IoT technologies and elucidates their profound impact on construction operations. It underscores the significance and urgency of embracing technological trends such as the Internet, wireless sensors, remote monitoring systems, and actuators, emphasizing the role of data acquisition in expediting the timely finalization of construction endeavors
Computational Prediction of Drug Toxicity and Binding Affinity
Full text linkThis study focuses on the computational prediction of drug toxicity and binding affinity, two critical aspects in the drug development process. Computational models offer a promising approach to predict these parameters accurately and efficiently, reducing the need for extensive in vitro and in vivo testing. This research leverages advanced machine learning algorithms and molecular docking simulations to predict the toxicity and binding affinity of drug candidates. By integrating various biochemical and pharmacological data, the study aims to develop robust predictive models that can identify potential toxic effects and optimal binding affinities early in the drug discovery pipeline. The results demonstrate that computational predictions can effectively complement traditional methods, offering significant advantages in terms of cost, time, and resource savings. This study provides valuable insights into the development of safer and more effective drugs, highlighting the potential of computational approaches in modern pharmacology
Advancing Machine Learning: Development, Evaluation, and Feature Engineering in Domain-Specific Applications
Full text linkThe rapid advancements in machine learning and the increasing availability of extensive datasets have significantly propelled the field of image classification. This study presents a comprehensive evaluation of three prominent machine learning models—Convolutional Neural Networks (CNNs), k-Nearest Neighbors (kNN), and Random Forest classifiers—on a specific image classification task. The research investigates the efficacy of these models through various performance metrics, examining their strengths and limitations. CNNs demonstrated superior accuracy and robustness, attributed to their ability to learn hierarchical features directly from image data. However, they require substantial computational resources and large datasets. The kNN classifier, while straightforward and easy to implement, exhibited limitations in handling high-dimensional data. The Random Forest classifier showed promise in structured data analysis but required effective feature engineering to enhance its performance with image data. The study also highlights the critical role of feature engineering techniques, data preprocessing, and hyperparameter tuning in optimizing model performance. Advanced CNN architectures, ensemble methods, and real-time deployment strategies are proposed as future research directions to further enhance image classification systems. This research provides valuable insights for developing more accurate and efficient image classification models, with potential applications across various domains.
Comparative Analysis of Res Net, Mobile Net, and Efficient Net Models for Lung Nodule Detection and Classification
No full textCancer is one of the most lethal diseases in the world. In a country as large as India, cancer has significantly burdened the medical infrastructure and the professionals. However, it has been proven that many forms of cancer could be treated, and the survival rate would be considerably higher if the diagnostics were performed accurately and at an earlier stage. In addition to the efforts of physicians and medical professionals, computer scientists have long contributed to the medical field by creating Computer Aided Diagnostics tools. In light of the recent strides made in the realm of Deep Learning, an international cohort of researchers has contributed to the development of a diverse array of neural models and architectures. These endeavors reflect the dynamic landscape of innovation within the field. Several aspects contribute to the effectiveness of Deep Learning computer-assisted diagnostics models; nonetheless, feature extraction plays a crucial part in defining the model's effectiveness. This research investigates the capacity of deep convolutional neural networks (DCNNs) to categorise lung cancer into three distinct groups. In this study, three cutting-edge computer vision architectures, namely ResNet50, MobileNet, and Google's EfficientNet, underwent fine-tuning for the task of classifying CT scans within the LIDC-IDRI dataset. This extensive dataset encompasses 244,527 CT scans categorized into groups denoting "nodule > or =3 mm," "nodule 3 mm," and "non-nodule > or =3 mm." The primary objective was to evaluate the efficiency of the EfficientNet model family, distinguished by substantial reductions in parameters and FLOPS, within the domain of lung nodule classification. This evaluation involved a comparative analysis against the ResNet50 and MobileNet architectures. The results distinctly demonstrated that the EfficientNet model, despite its economy in parameters, outperformed both the ResNet50 and MobileNet models. Notably, the EfficientNet model exhibited notably higher ROC AUC values across all classification categories, excelling in average AUC values for the comprehensive classification task, attaining scores of 0.922 (Micro AUC) and 0.956 (Macro AUC). These findings underscore the superior performance of EfficientNet in this critical medical imaging application
AI Model Lifecycle Management in Commercial Hardware
Full text linkThe rapid spread of AI across the commercial sector has bred the need for proper arsenal to manage AI models across the span of their lifecycle, especially given the deployment on hardware with various constraints. This paper looks at the pivotal processes concerning the life and death of an AI model, which is designing, training, deployment, monitoring, and continuous improvement, within the realm of commercial hardware systems. It pays special attention to the tension between hardware capabilities and model-level performance due to insufficient compute resources, power efficiency requirements, and real-time processing demands. In this vein, the study considers current tools, frameworks, and methodologies that aid lifecycle automation, model optimization, and standards compliance-including security and regulatory requirements. It also investigates futuristic trends such as federated learning, edge computing, and MLOps for advancing lifecycle workflows. Via thorough theoretical analysis coupled with experimental verification, it mounts an argument for best practice and a systematic approach to scalable, dependable, and secure management of AI models on commercial hardware. The findings put in place a strong argument for an integrated lifecycle strategy capable of keeping models performant, resilient, and ethically deployed in an increasingly AI-driven world
Service Discovery in a Complex Microservice Architecture
Full text linkModern enterprise systems increasingly adopt microservice architectures to achieve agility, scalability, and resilience. However, managing service discovery in a complex microservice environment presents substantial challenges due to dynamic service lifecycles, decentralized communication, and rapid scaling. This paper investigates how service mesh frameworks, such as Istio and Linkerd, provide foundational support for service discovery, beyond their traditional roles in observability, traffic management, and security. Through comparative analysis, architectural modeling, and real-world use cases, we highlight how service meshes simplify service discovery, improve reliability, and enhance operational efficiency in Kubernetes-based deployments
Electronic Health Record System using Blockchain Technology
Full text linkThe healthcare sector is frequently known for being delicate and intricate.Individuals' sensitive information must be kept safe, secure, and protected.Blocks of the blockchain are secured and bound to each other using cryptographic principles.
By maintaining the patient at the centre of the medical ecosystem system and establishing greater security, interoperability, and privacy of stored patient records, blockchain has the potential to eradicate the problems ailing the industry and transform healthcare.
By decentralizing and encrypting health records, blockchain ensures that patient data is securely stored and tamper-proof. Additionally, blockchain can facilitate the seamless exchange of medical information between different healthcare providers, leading to better coordination of care and reduced medical errors. By leveraging Ethereum's smart contract functionality, healthcare organizations can securely store and
share patient data, ensuring its integrity and confidentiality. Moreover, Ethereum's programmable nature allows for the development of decentralized applications (DApps) that can streamline various healthcare processes, such as medical record management, supply chain tracking, and clinical trials. Overall, the integration of blockchain in the healthcare industry has the potential to revolutionize the way healthcare data is managed, ensuring privacy, security, and efficiency in patient care
IoT and Machine Learning-Based Prediction of Smart Soil Moisture Monitoring and Irrigation System
Full text linkAbstract— A country like India faces an acute water shortage, with 35 million people lacking access to safe water. India is the world's largest groundwater user, as tube wells, the main source of irrigation for Indians, provide 46% of water for irrigation. IoT and machine learning can be vital in overcoming acute water shortages and achieving optimum water resource utilization. This paper aims to present an ML model to estimate the soil moisture level and IoT to act upon it. We are introducing a working plan to collect data on soil moisture, temperature, and humidity, utilizing sensor nodes deployed in the agricultural field to gather various sensor data. The gathered data is forwarded through IoT and stored in a cloud-based database like MongoDB. This data applies to machine learning techniques for classification. Several models, such as Naive Bayes (NB), Logistic Regression (LR), and Support Vector Machine models (SVM), are utilized. The experimental results, with accuracy rates of 98.8%, 99.0%, and 99.3% for Naive Bayes, Logistic Regression, and Support Vector Machine models respectively. The combination of IoT and machine learning helps to achieve environmental goals efficiently in water resource utilization and better crop yield
Design Methods of Hangeul Slanted Cursive Font
Full text linkThis study explores the absence of italics in Hangeul (Korean) fonts, a feature present in the Latin alphabet but lacking in Korean fonts. While italics provide emphasis in Latin text, Hangeul achieves similar effects using various font types, thicknesses, underlining, and emphasis points. However, these font variations and punctuation marks may disrupt reading flow. Existing methods, such as slanting options in editing software (“fake italic” when using Hangeul), may compromise visual aesthetics. To remedy this, like italics, Korean fonts need slanting and cursive elements. The study proposes a 6-step design method for slanted cursive Hangeul fonts, covering (1) skeleton extraction, (2) combining skeletons, (3) stroke weight, (4) slanted format, (5) cursive elements, and (6) visual flow adjustments. Applying this method to the design of Hangeul slanted cursive fonts, the study underscores the importance of determining optimal slant and cursive font degrees while considering subjective designer aesthetics