Asian Journal of Research in Computer Science
Not a member yet
792 research outputs found
Sort by
Data Mining in Environmental, Social, Governance (ESG) Analysis: An Overview
No full textESG (environmental, social, and governance) considerations are now essential standards for evaluating the ethical and sustainable effects of investments. This study examines data mining\u27s use in ESG analysis, emphasizing how it may be used to glean useful insights from sizable and varied datasets. It looks at data mining techniques, resources, and applications for trend identification, ESG compliance assessment, and decision support. Future directions, ethical issues, and difficulties in incorporating cutting-edge technologies into ESG analysis are also covered
IoT Assisted Optimization of Resources for Healthcare, Mining and Transportation Industry
No full textAims: The Internet of Things is a futuristic technology that creates a smart system of systems by connecting all electronic devices to one another over the Internet. The Internet of Things facilitates communication between individuals, devices, and other devices. There are numerous uses for this technology in e-Government, business, public administration, and industry. Every organization and industry aims to create its own Internet of Things application to enhance the production of goods and services, customer satisfaction, employee safety, and storage space. This paper explores the role of IoT in resource optimization for healthcare and transportation industries, The creation of IoT-enabled healthcare systems includes sophisticated data processing and large data storage capacities. this integration has been further felicitated by the integration of wireless sensor networks (WSNs) and the Internet of Things (IoT). The mining industry has a diverse setup, and because of infrastructure restrictions in communication, data management, storage, and information exchange, it might be challenging to identify areas where sensor-assisted IoT technology can be useful. While an overall IoT architecture appropriate for the general conditions in the mining industry is still in its early stages, the majority of research efforts to date on applying IoT in the mining industry concentrate on specific issues like ventilation monitoring, accident analysis, fleet and personnel management, tailing dam monitoring, and pre-alarm systems. In the automobile industry, integration of WSN within vehicles can be employed to harness sensor details for smart navigation, quick response, vehicle maintenance and interactive ambience. The logistics of transporting people and goods between cities and towns have been totally transformed by smart mobility. Modern technologies such as the Internet of Things (IoT), artificial intelligence (AI), data analytics, and networking are used in "smart" transportation to enhance many aspects of our transportation networks. These technologies\u27 real-time monitoring, analysis, and decision-making capabilities enable this ecosystem of interconnected automobiles, infrastructure, and customers. Work presents the present scenario of application of IoT in Healthcare and Transportation industry
The Role of Machine Learning in Enhancing Marketing Strategies within Cloud-based Enterprise Systems
No full textCombining cloud computing, digital technologies, and machine learning is changing organizational systems and marketing techniques. This paper explores how this is happening. Switching to cloud-based systems improves operational efficiency and collaboration by increasing scalability, lowering expenses, and enabling real-time data access. More individualized and focused marketing strategies are made possible by machine learning approaches, such as consumer segmentation and predictive analytics, improving decision-making and customer interaction. However, there are still issues with managing computing resources, guaranteeing strong data security, and offering enough staff training for smooth integration. New developments like edge computing and federated learning are emphasized as possible directions for future research. These convergent technologies\u27 digital transformation allows companies to stay flexible and competitive in a changing market
Leveraging Machine Learning for the Identification of Obfuscated JavaScript in Phishing Attacks
No full textJavaScript obfuscation has emerged as a pervasive tactic employed by cybercriminals to conceal malicious code and facilitate phishing attacks. As a language supported by over 95% of modern websites, JavaScript provides a fertile ground for exploitation due to its ubiquity and integration into nearly all web applications. Cyber attackers frequently rely on obfuscation techniques to disguise malicious scripts, thereby evading detection by traditional antivirus software and rendering manual code analysis exceedingly difficult. The complexity of modern obfuscation techniques demands advanced detection methodologies beyond signature-based tools. This research focuses on exploring the interplay between JavaScript obfuscation and phishing, identifying prevalent obfuscation methods, and deploying machine learning (ML) approaches to detect these threats. By leveraging supervised learning algorithms and semantic feature extraction, we demonstrate how ML can be utilized to distinguish between benign and malicious, obfuscated scripts. The study also conducts a comprehensive review of existing tools, methodologies, and academic research addressing this challenge. We propose a robust framework integrating abstract syntax tree (AST) analysis, lexical pattern recognition, and ensemble ML models for enhanced detection accuracy. Additionally, this study outlines key implementation strategies, challenges, and evaluation metrics while providing a critical outlook on future research pathways. The proposed approach promises significant advancements in cybersecurity by improving the precision of threat detection systems, thus reducing the risks posed by obfuscated phishing scripts in web applications
Unifying DevOps and MLOps Pipelines Via AI-driven Observability: A Mixed-Methods Study
No full textThe analysis explores artificial intelligence-based observability as an operational solution to unite technological structures between Development and Operations systems and Machine Learning Operations systems. Enterprise environments that use machine learning require advanced strategies to manage the deployment and monitoring of ML models together with conventional software systems because they have become increasingly complex. The study investigates how artificial intelligence enables observable functions which support smooth integration of operations and automation between DevOps and MLOps development cycles. The research methodology includes a mixed approach that starts with a literature study which combines practitioner interviews with DevOps and MLOps professionals and a prototype AI observability framework development. The developed prototype utilizes machine learning analytics to detect anomalies along with roots cause identification and automated alert functions during evaluation on hybrid CI/CD and ML pipelines. AI-driven observability provides comprehensive application and model performance visibility while shortening the detection and resolution periods of system failures and making operations more effective through proactive monitoring and automated diagnosis and intelligent remedy strategies. The technology allows stakeholders to monitor dashboards which merge metrics and logs stemming from software applications and ML models therefore facilitating domain alignment between software developers and data scientists. This study demonstrates that AI observation solutions serve as vital infrastructure to unite MLOps practices with DevOps operations by connecting developers with data scientists and operators in their work. This solution solves the essential problems that stem from separated workflows in addition to unclear visibility and inconsistent operational performance. Organizations implementing intelligent observability measure in ML-integrated systems will accomplish faster deployment timelines along with model dependability maintenance and system stability which produces stronger and more scalable AI-driven production environments
Intelligent Cluster-Based Routing in Radio Network: Practice and Application
No full textOver the last two decades, wireless networks have been widely deployed in various regions because of their infrastructure-less nature. This paper presents an adaptive routing solution for radio and hybrid wireless networks using a mobile ad hoc link-cluster architecture with intelligent clustering mechanisms. It explores various routing strategies suited to intelligent radio-grid and ad hoc networks, supported by a systematic review of clustering approaches, link reconfiguration, and optimisation of data transmission. The study proposes a modular architecture for Mobile Intelligent Cluster Controllers (MICCs) and demonstrates real-time simulations of routing using MIDLinux/Raspberry Pi environments. The entire network is partitioned into several clusters employing a Distributed Mobility Adaptive Clustering Algorithm (DMAC) with the cluster-heads acting as gateways connecting clusters. The hybrid network combines high-capacity base stations and mobile ad hoc devices, emphasising efficient information dissemination and reduced uplink usage through dynamic, self-organising clustering. Analytical models are developed for delay analysis, reliability, and two-hop relaying mechanisms. Overall, the research contributes to the development of self-stabilising, adaptive routing strategies in heterogeneous ad hoc networks
Leveraging Big Data Analytics to Assess the Influence of Online Consumer Sentiment on Chery Omoda 5 Sales in Malaysia
No full textWith the rapid development of big-data technologies, the influence of online consumer sentiment on purchasing decisions has become increasingly significant, particularly within the automotive industry. This study systematically investigates the impact of negative online opinions on the sales of the Chery Omoda 5 in the Malaysian market by leveraging advanced data-mining, sentiment-analysis, and market-trend analysis techniques. Sales records and large-scale online content—including social-media posts, news articles, forums, and blogs—were collected from January 2024 to June 2024. Natural-language processing (VADER) was applied to quantify negative sentiment, and multiple linear-regression models—controlling for seasonality (month fixed effects) and macroeconomic indicators (fuel price index, consumer-price index)—were estimated to examine the relationship between sentiment fluctuations and monthly sales trends. The results demonstrate a strong negative correlation (r = −0.924) between the frequency of negative online mentions and Omoda 5 sales; peaks in negative sentiment, often triggered by product recalls or intensified media coverage, were temporally aligned with sharp declines in sales volume. These findings provide empirical evidence of the immediate and measurable adverse effects of online negativity on consumer purchasing behavior. The study concludes with recommendations for automotive manufacturers, urging marketing managers to integrate real-time social-listening dashboards into sales-forecasting workflows so that emerging reputation risks can be identified and addressed before they erode market performance, thereby underscoring the value of proactive crisis-communication strategies for protecting brand equity in an increasingly digital marketplace
An Enhanced K-NN Algorithm Leveraging BERT Techniques for Resume Parsing System
No full textThe increasing volume of job applications has created significant challenges for organizations in efficiently screening and ranking candidate resumes. Manual and keyword-based automated systems often struggle with accuracy, and contextual understanding. The study introduced an experimental design that develops a hybrid ensemble model for resume parsing and ranking, combining k-nearest neighbors (KNN) and Bidirectional Encoder Representations from Transformers (BERT). The enhancement lies in BERT\u27s ability to generate deep contextual embeddings that are integrated into KNN’s distance-based classification and keyword matching to improve contextual accuracy, a combination not commonly explored in previous resume parsing systems. The research involved stages such as data cleaning, preprocessing, feature extraction using named entity recognition (NER), model development and training. The system achieved 96.91% parsing accuracy and 100% ranking accuracy across 962 resumes, demonstrating strong performance with precision, recall, and F1-score of 97.0% and allows resumes in DOCX, PDF, or image formats as input. Using Natural Language Processing (NLP) techniques, term frequency- inverse document frequency (TF-IDF) vectorization, and cosine similarity, the system processes resume and ranks them based on relevance to job descriptions with a similarity score. The study was conducted at Air Force Institute of Technology within the time frame of December 2024 and June 2025. The system built highlighted the importance of automated resume parsing systems in recruitment processes
Enhancing Cybersecurity: Zero-Day Attack Detection in Network Traffic with Deep Learning Model
No full textA big risk to networks comes from zero-day attacks since no patches are available until after the attack takes place. Such attacks can escape detection by traditional, signature-based IDSs. Therefore, better analysis methods are needed to catch threats that examining data has not revealed before. A zero-day hack is the most dangerous thing that can happen to network security. Zero-day attacks are hard to spot because they act in ways that haven\u27t been seen before. A lot of people are interested in intrusion detection systems (IDS) because they can find these kinds of threats. Machine learning (ML) and deep learning (DL) are being used a lot more in intrusion monitoring systems. It has been shown that these methods can find zero-day risks. The study aims how to detect Zero-Day Attack in network traffic with deep learning model and to enhancing cybersecurity. This study shows a way to find cyberattacks using deep learning and a Convolutional Neural Network (CNN) trained on the UNSW-NB15 dataset. Adopted the UNSW-NB15 dataset to reflect real-world and comprehensive cyber-attack patterns. The collection has a lot of different types of real-world network attacks. Support Vector Machine and Random Forest are not as good as the CNN model that was mentioned. The CNN model achieved the highest accuracy at 93.8%, demonstrating its superior capability in capturing complex patterns in network traffic data. A score of 95.1% means it is mostly correct, 93.8% means it is mostly precise, 96.5% means it remembers things, and 94.6% means it is most likely correct. Experiments show that the model is good at learning, generalising, and being sturdy without becoming too perfect. This proves that it can find complex zero-day attacks. This study contributes to enhancing cybersecurity through an efficient and reliable deep learning framework for network traffic analysis. The power grid and other similar systems play a big role in keeping cyber-physical systems safe. When someone breaks the control code in a power grid system, it could cause a lot of damage. If the issue is found early, it will do less damage in the future. Future tasks involve collecting more diverse datasets, building combinations of existing approaches and validating the model directly on-site during real cyber-attacks
Design and Implementation of an IoT-Based Smart Shoe with Blynk–Twilio Emergency Alerts to Enhance Independence of the Visually Impaired
No full textThe work designs and implements a low-cost Internet of Things smart shoe to enhance safety and independence for visually impaired users by unifying ultrasonic obstacle sensing, Global Positioning System (GPS) geolocation, audio–haptic feedback, and multi-channel emergency alerts through Blynk and Twilio. The platform centers on an ESP32 microcontroller that interfaces with an ultrasonic sensor, a GPS receiver, an emergency push button, a buzzer, and a vibration motor. Firmware developed in the Arduino IDE parses GPS data and manages sensing, actuation, and cloud notifications. Functional verification under indoor and outdoor conditions evaluates threshold-based obstacle warnings and the end-to-end alert pipeline that delivers GPS-tagged push or email notifications and short message service (SMS). The prototype consistently triggered audio–haptic cues when distance fell below a 40 cm safety threshold and sent alerts with coordinates when the emergency button was pressed, demonstrating a coherent device-to-cloud-to-caregiver flow without reliance on vision-based sensing. The findings indicate that an ESP32–ultrasonic–GPS architecture with Blynk–Twilio alerts is feasible and replicable for assistive footwear, advancing user safety and independence while keeping complexity and bill of materials practical. Future development should add detection of holes and elevation changes, improve robustness in obstructed environments, and optimize energy use to extend operating time