Asian Journal of Research in Computer Science
Not a member yet
792 research outputs found
Sort by
Veritas AI: The ChatGPT Polygraph
No full textAims: The objective of Veritas AI is to revolutionize the domain of lie detection through the deployment of a cutting-edge algorithm within the realms of computational linguistics and artificial intelligence.
Study Design: Veritas AI is conceptualized as a groundbreaking framework that integrates advanced syntactic and semantic analysis, leveraging generative pre-trained transformers to identify linguistic cues indicative of deception.
Place and Duration of Study: The research underpinning Veritas AI’s algorithm was meticulously executed at the Abacus CSE Lab over a period from December 2022 to March 2024, ensuring a robust empirical foundation for the system’s validation and optimization.
Methodology: Employing a deep learning neural network at its core, Veritas AI is trained on a diverse dataset comprising both truthful and deceptive dialogues. This training is complemented by multimodal biometric interrogation techniques and sophisticated natural language processing algorithms.
Results: The empirical results underscore Veritas AI’s unparalleled accuracy in discerning truth, marked by its ability to provide real-time adaptive feedback and maintain robust performance across various communication scenarios.
Conclusion: In conclusion, Veritas AI stands as a testament to the symbiotic potential of human ingenuity and machine learning. Its precision-engineered algorithm, underpinned by empirical validation, heralds a transformative leap in the field of automated veracity assessment, setting a new benchmark for truth analysis in the digital age
Combating the Challenges of False Positives in AI-Driven Anomaly Detection Systems and Enhancing Data Security in the Cloud
No full textAnomaly detection is critical for network security, fraud detection, and system health monitoring applications. Traditional methods like statistical approaches and distance-based techniques often struggle with high-dimensional and complex data, leading to high false positive rates. This study addresses the challenge by investigating advanced AI-driven techniques to reduce false positives and enhance data security within cloud computing environments. This study employs deep learning models, integrates contextual data, and incorporates comprehensive security measures to enhance anomaly detection performance. Data from synthetic sources, such as the NSL-KDD dataset and real-world cloud environments, were utilized to capture user behavior logs, system states, and network traffic. Over 50 academic journals were reviewed, and 21 were selected based on inclusion criteria, such as relevance to AI-driven anomaly detection, empirical performance metrics, and the focus on cloud environments, and exclusion criteria that filtered out studies lacking empirical data or not specific to cloud-based systems. Methodologically, the research involves a comparative analysis of different AI techniques and their impact on false positive rates, accuracy, precision, and recall. The findings demonstrate that deep learning techniques significantly outperform traditional methods, achieving a lower false positive rate and higher accuracy. The results underscore the importance of contextual data and robust security protocols in reliable anomaly detection. This research fills a gap by thoroughly evaluating advanced AI techniques for reducing false positives in cloud environments. The study\u27s significance lies in guiding the development of more effective anomaly detection systems, thereby enhancing security and reliability across various applications. Additionally, organizations should invest in continuously developing and integrating AI-driven anomaly detection systems with comprehensive security measures to improve their effectiveness the study suggests that further study be conducted with large datasets to evaluate the effectiveness of Hybrid anomaly detection systems in detecting and addressing false positives
Ga-RBP: A Rule-based Parser for the Syntactic Analysis of the Ga Language of Ghana
No full textThis research presents a Parts of Speech (POS) corpus and a static rule-based technique, which we refer to as Ga Rule-based Parser (Ga-RBP), for the syntactic analysis and the parsing of sentences for the Ga language of Ghana. The technique is developed to parse sentences by utilising the POS tagged corpus; the corpus was developed by manually tagging the Ga words with their corresponding POS tags following a standard Ga-English dictionary and custom Tagset for the language. The syntax rules were computationally defined using production rules, which establish how a word should follow the other in the right sequence to form a correct grammatical statement based on their POS. The model generally analyses the sentence structure of the language to assert its syntactic state for correctness or otherwise
Exploring Constraints and Catalysts: A Comprehensive Analysis of Technology Adoption in Sri Lankan Small and Medium Enterprises
No full textPurpose: Small and Medium Enterprises (SMEs) are considered as the backbone of the economy, however they face many difficulties and challenges for their survival. Adapting to changing technology is one of the primary challenges SMEs face. Globally new technologies such as social media and e-commerce have become the trend in contemporary business activities in Business to Consumer (B2C) communications for SMEs. The study aims to find the factors affecting to the adoption of technology in SME sector in an emerging economy, Sri Lanka.
Design: The study utilized Technology, Organizational, and Environmental (TOE) model. The data was collected from 102 SME owners in Western province Sri Lanka who are registered as SME sectors with less than 50 employees. Qualitative data were collected from 7 SME owners through semi-structured interviews to evaluate new opportunities can gain via technology adaptation and to evaluate the impact of performance via technology adaptation in SME sector in Sri Lanka.
Findings: Descriptive statistics revealed that there are substantial disparities in how organizations and the environment adapt to new technologies. The ordinal regression analysis emphasised that organizational and environmental factors significantly influence on adaption of technology. Content analysis revealed that SMEs have gained many new opportunities via adaption of technology such as expand their businesses from local to global using e-commerce platform and online money transactions. Social media has made direct business to business instant contact. Further, transparency of business transactions increase trust with suppliers and customers.
Implications: The SME sector needs both new technology and updates existing technology status and guided towards modernization and continuous improvement process. Finding of this study will give policy makers and government officials on strengthening and arming SME sector with technology to face challenge and complete with local and international competition
Navigating the Docker Ecosystem: A Comprehensive Taxonomy and Survey
No full textThe cloud computing landscape is rapidly expanding and growing in complexity. It has witnessed the emergence of Cloud Computing as a widely adopted model for efficiently processing large volumes of data by harnessing clusters of commodity computers. This evolution enables the handling of massive data through on-demand services, relying on numerous microservices with diverse dependencies. The technology of containers ensures secure storage, allowing for large-scale data processing with high scalability and portability. Container technology, particularly exemplified by Docker in the last decade, plays a pivotal role in this scenario. It empowers microservices to process data swiftly, enabling developers to dynamically scale these services in real-time. This paper initiates by establishing a comprehensive taxonomy for delineating container architecture. Focusing specifically on Docker containers, we scrutinize various existing container-related literature. Through this taxonomy and survey, we not only discern similarities and disparities in the architectural approaches of Docker container technology but also pinpoint areas necessitating further research
Intelligent Phishing Website Detection Model Powered by Deep Learning Techniques
No full textPhishing websites or URLs differ from software flaws as they exploit human vulnerabilities rather than technical weaknesses. Various methods exist to undermine the security of an internet user, but the most prevalent approach is phishing. This sort of assault aims to acquire or exploit a user\u27s personal data, including passwords, credit card details, identity, and account information. Phishers gather user information by pretending to be authentic websites that are visually indistinguishable. Users\u27 confidential data can be potentially retrieved, exposing them to the possibility of financial detriment or identity fraud. Consequently, there is a pressing requirement to develop a system that efficiently identifies phishing websites. This research presents three discrete deep learning methodologies for identifying phishing websites, which involve the use of long short-term memory (LSTM) and convolutional neural network (CNN) for comparison, and ultimately an LSTM-CNN-based methodology. The experimental results confirm the precision of the proposed methods, specifically 99.2%, 97.6%, and 96.8% for CNN, LSTM–CNN, and LSTM, respectively. The CNN-based technology displayed a superior phishing detection mechanism
Data Governance in AI - Enabled Healthcare Systems: A Case of the Project Nightingale
No full textThe study investigates data governance challenges within AI-enabled healthcare systems, focusing on Project Nightingale as a case study to elucidate the complexities of balancing technological advancements with patient privacy and trust. Utilizing a survey methodology, data were collected from 843 healthcare service users employing a structured questionnaire designed to measure perceptions of AI in healthcare, trust in healthcare providers, concerns about data privacy, and the impact of regulatory frameworks on the adoption of AI technologies. The reliability of the survey instrument was confirmed with a Cronbach\u27s Alpha of 0.81, indicating high internal consistency. The multiple regression analysis revealed significant findings: a positive relationship between the awareness of technological projects and trust in healthcare providers, countered by a negative impact of privacy concerns on trust. Additionally, familiarity with and perceived effectiveness of regulatory frameworks were positively correlated with trust in data, while perceptions of regulatory constraints and data governance issues were identified as significant barriers to the effective adoption of AI technologies in healthcare. The study highlights the critical need for enhanced transparency, public awareness, and robust data governance frameworks to navigate the ethical and privacy concerns associated with AI in healthcare. The study recommends adopting flexible, principle-based regulatory approaches and fostering multi-stakeholder collaboration to ensure the ethical deployment of AI technologies that prioritize patient welfare and trust
Enhancing Security Using GPS-GSM Motorcycle Tracking System
No full textMotorcycles are progressively becoming a well-known mode of transportation in Ghana, especially in the northern region. Their affordability and easy movement on our rough roads make them a choice many users prefer. Nonetheless, the increase in the number of these motorcycles brought some concerns connected with safety and security. To resolve these issues, the improvement of the security framework is fundamental. Real-time monitoring is part of the Internet of Things (IoT), which permits distance monitoring. Different tracking technologies such as RFID, Internet tracking, cellphone triangulation, GPS, and other technologies. This research work expects to plan a far-reaching motorcycle security and global positioning framework utilizing an Arduino microcontroller Uno r3, Neo-6mGPS, and GSM SIM800L modules. The GPS module obtains the location area while the GSM module works with interaction between the Arduino Uno and the client\u27s cell phone, showing the area on Google Maps. The framework comprises a locking component and a global positioning framework. The motorcycle\u27s ignition system is controlled by a locking mechanism that enhances protection against theft. Besides, the scarcity of these security systems and the existing motorcycle tracking systems are very costly to purchase and maintain. There is restricting openness for the overwhelming majority of bike users. This prompt is a high pace of bike theft, making recovery challenging. One of the project\u27s goals are to decrease power utilization in the global positioning framework, upgrade GPS following precision, and use SMS as the essential means of communication. This research work adopted the Agile Methodology of designing applications. While this research work presents various benefits, it additionally has limits. These incorporate the expenses of equipment parts. Restricted accessibility of Arduino components in the Ghanaian market and time. Regardless of these restrictions, the exploration attempts to create powerful and open bike security in the Ghanaian market
Design and Implementation of an Iot-Based Safety and Energy Efficient System
No full textThe paper provides a safe and power-efficient Internet of Things (IoT)-based solution. With the growing concerns about environmental sustainability and the demand for improved safety measures in today’s society, it has become critical to focus on building systems that decrease energy consumption and assure the safety of humans and the environment. The proposed system employs cutting-edge technologies and novel approaches that will result in optimal energy usage with minimal or no human involvement thereby assuring the safety of people. The proposed system leverages on existing IoT technologies and is comprised of smart sensors, energy-efficient gadgets, and a centralized control unit. Therefore, it is able to demonstrate cutting edge power control strategies including power gating and dynamic central power regulation which control the usage of gadgets to operate at optimal power levels vis-a-vis the real-time demand to achieve energy efficiency. The system is also able to collect data on occupancy, lighting, temperature, and power consumption trends which can assist in making data-driven choices that improve the usage of energy. The proposed system provides large energy savings without sacrificing user comfort by dynamically altering lighting, and cooling systems based on occupants and ambient factors. Multiple simulations and real-world trials in homes and institutions’ buildings were used to assess the efficacy of the suggested system. The findings revealed substantial reductions in energy consumption without jeopardizing safety
Sentiment Analysis by Hierarchical Deep Neural Networks for Audience Opinion Mining
No full textThe prominent applications of sentiment analysis encompass various fields, including marketing, customer service, and communication. The conventional bag-of-words approach for measuring sentiment only counts term frequencies, while neglecting the position of the terms within the discourse. As a remedy, this research aims to build a discourse-aware approach upon the discourse structure of documents. For this purpose, rhetorical structure theory (RST) is utilized to label (sub-) clauses according to their hierarchical relationships, and then polarity scores are assigned to individual leaves. To learn from the resulting rhetorical structure, a hierarchical category structure-based deep recurrent neural network is proposed to infer underlying tensors of salient passages of narrative materials to process the complete discourse tree. The significance of this study lies in enhancing the structure of exploding and vanishing gradients in deep recurrent neural networks and also improving evaluation criteria in text analysis using the structure of opinion mining. The proposed approach is RST-HRNN. Exploding gradients is a process in the backpropagation stage aimed at continuously sampling the gradient of the model parameter in the opposite direction based on the weight (w), which is continuously updated until reaching the minimum global function