Asian Journal of Research in Computer Science
Not a member yet
792 research outputs found
Sort by
Transforming Retail: Elevating Customer Experience and Efficiency with Generative AI Technique
No full textThis article examines the impact of generative artificial intelligence (AI) on the transformation of retail in the digital age. The author emphasizes that generative AI, by creating new content and providing personalized experiences, is becoming a key tool for retailers, allowing them not only to understand, but also to anticipate consumer preferences. Special attention is paid to changing the customer experience through innovative solutions such as smart chatbots that are able to adapt to user needs. The article also examines the impact of generative AI on operational efficiency, including inventory management and staff optimization, which helps reduce costs and increase profitability. The financial results of the AI implementation are supported by statistical data showing revenue growth and reduced operating costs. The conclusion emphasizes that generative AI will not only improve existing processes, but also change the very nature of interaction between retailers and consumers, opening up new horizons for business in the future
Smart and Sustainable City Experience on Smart Campus: A Case Study from Hassan Ist University
No full textThe desire to meet the demands of regional competition requires cities to adopt new patterns of urban management. In this sense, the trend at the global level is to use smart city standards by investing in the digital transformation of various public services in cities. In recent years, many efforts have been made in many Moroccan cities to improve their attractiveness by being part of the process of upgrading and enhancing their territories through the implementation of major infrastructure projects and the digitalization of urban administrations.
This study was conducted to examine the feasibility of a smart campus as a discounted smart city, and it relies on the dissemination of a quantitative survey, via a questionnaire (live and online), supplemented by a qualitative survey based on focus group methodology. We have gained a broader perspective that allowed us to understand the reality of things on campus. The study also showed that there are many efforts that the university must take in conjunction with developing its plan to advance Hassan I University to the ranks of smart universities.
This article is part of a study proposing a strategy for developing the campus of Hassan I University of Settat to be a smart one
First Fit Algorithm: A Graph Coloring Approach to Conflict-Free University Course Timetabling
No full textAims: Tackling scheduling issues with the most optimal graph coloring algorithm has consistently posed significant difficulties. The university scheduling problem can be expressed as a graph coloring problem, where courses are depicted as vertices and the connections between courses that have common students or teachers are represented as edges. Subsequently, the task at hand is to assign the vertices with the minimum number of colors. In order to accomplish this task, this paper present a graph coloring technique to conflict free university course timetabling using first fit algorithms.
Methodology: The conflict graph is partitioned into a set of independent color classes to be assigned time slots and transformed into a conflict-free timetable. The Ladoke Akintola University of Technology (LAUTECH) University Course Timetabling Data was adopted. The allocation of venue based on the allotted time slots is done using first fit packing algorithm. The proposed model is implemented using Python programming language. The developed model had courses being represented as vertices and edges. The course conflict graph was created based on the acquired dataset using vertices-edges relationship diagram. The implemented model is evaluated in terms of Halstead complexity metrics: Program Volume (PV), Program Length (PL), Program Effort (PE), Program Difficulty (PD) and Execution Time (ET). The PV, PL, PE, PD and ET values obtained for the implemented model are 18.45kbits, 0.51, 1037684, 1.97 and 20.45 secs, respectively.
Conclusion: The proposed model shows a significant improvement over the existing models by producing conflict-free course timetabling problem with better evaluation results. This work will be highly useful in solving various scheduling, optimization and NP-hard related computational problems
Exploring the Role of Dimensionality Reduction in Enhancing Machine Learning Algorithm Performance
No full textIn this study, we delve into the pivotal role of dimension reduction techniques in influencing the performance of machine learning algorithms for heart disease prediction. Through a comprehensive exploration of a dataset encompassing crucial features such as age, sex, chest pain type, blood pressure, cholesterol levels, and more, we investigate the impact of different techniques—namely, Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPCA), and Linear Discriminant Analysis (LDA) on classification algorithm effectiveness. The classification algorithms considered were Logistic Regression, Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Naive Bayes, and Deep Neural Network (DNN). We used K-fold cross validation to train and validate the classification algorithms. The performance of these algorithms was assessed using a range of key metrics including accuracy, F1-score, precision, recall, and specificity. The results reveals that Linear Discriminant Analysis consistently emerged as a potent method, remarkably enhancing algorithm performance across all assessed metrics. We also identified Naive Bayes and Logistic Regression as standout algorithms, demonstrating remarkable resilience and reliability across diverse scenarios. These findings collectively shed light on the intricate interplay between dimension reduction techniques and algorithm selection, offering critical insights for crafting more accurate and robust strategies in the prediction of heart disease.
Exploring a Pragmatic and Exponential Advancement in the Use of Machine Learning and Artificial Intelligence Systems
No full textWith the advent of the Internet of Things (IoT) with sensors and connected devices, data generation is increasingly peaking at an unprecedented pace. However, energy consumption is also on the rise based on traditional energy sources, such as fossil fuels. This is not sustainable and could hurt the environment while being quite expensive to run e.g., empowering irrigation systems using sensors. In this context, using data as an energy source for future machines could be a promising solution to mitigate the energy crisis and reduce the carbon footprint. The concept of data as a new form of energy will be discussed, examining the benefits and challenges associated with this method. This paper also proposes other potential applications for using data as an energy source, including powering self-driving cars, drones, and smart irrigation systems a data-driven approach
Influence of AI: Robotics in Healthcare
No full textThe integration of artificial intelligence (AI) and robotics in healthcare has heralded a transformative era, offering unprecedented opportunities to enhance patient care, streamline processes, and augment medical professionals\u27 capabilities. This review article examines the burgeoning influence of AI robotics in healthcare, encompassing various applications, benefits, challenges, and future prospects. We delve into the role of AI robotics across medical diagnosis, surgical interventions, rehabilitation, patient monitoring, and drug discovery. Additionally, we explore the ethical considerations, regulatory frameworks, and societal implications shaping the adoption and advancement of AI robotics in healthcare. By synthesizing current research and real-world implementations, this review elucidates the profound impact of AI robotics, paving the way for a revolutionized healthcare landscape
Implementation of a Secured Scalable File Server System
No full textThis research paper proposed and developed a blueprint for a secured scalable file server system for organisations that can handle large volumes of data, accommodate numerous users with varying levels of access and permissions and adhere to all security and compliance standards of organisations. With the implementation of this secured and scalable file server system, users of all levels will be able to access, manipulate, transfer files easily devoid of any data lost, file corruption or fear of getting infested with virus when sharing using flash drives. System administrators will be able to backup files easily to forestall any unforeseen circumstances and finally the organisation’s Management will be able to have full control of all data that is used in the organisation. The proposed system is a scalable file server designed for digital file management. This secured and scalable file server system provided a secure and user-friendly interface allowing organisation\u27s staff to efficiently store, retrieve, and share files. The proposed system at its heart, provide strong data storage capabilities that will easily meet data growing needs
Automated Detection of Structural Change in Ethopia Gross Domestic Product (GDP) using Novel Algorithm
No full textThe target of this study is to use GFTSC (Group for time series modules/components) to classify the constituents components of time series existing in the Ethiopia Gross Domestic Product (GDP). This statistics is the GDP yearly data of Ethiopian Gross Domestic Product (GDP). The Gross fixed capital formation (% of GDP) was available. The (Ethiopia GDP) data for the period of twelve years. The GDP of Ethiopia is a secondary data obtained from the DataStream of National University Singapore Library. The softness of BFAST (Break for Additive/multiplicative Seasonal and Trend) were inspected by the extension of BFAST to GFTSC. GFTSC was created to involve the cyclical and irregular constituents that was not involved by BFAST technique. GFTSC is aimed to synchronous the image of all the 4 time series constituents. Experiential statistics of Ethiopia was employed to GFTSC and subsequently the next forecast was made. The simulated and real data findings suggested that BFTSC can provide a better time series components identification better than manual process and hence caution should be taken because Ethiopia GDP had only stationery trend, hence not really improving and not dropping, so caution should be taken less it got to ruin. Improvement in Ethiopia GDP is recommended
DevOps Implementation: Essential Tools, Best Practices, and Solutions to Overcome Challenges for Seamless Development and Operations Integration
No full textAims: This study aims to explore the core principles, tools, and best practices for implementing DevOps, emphasizing its benefits, such as enhanced efficiency, better collaboration, and faster time-to-market. It also seeks to identify common challenges in DevOps adoption and provide practical solutions.
Study Design: A qualitative research approach was used, incorporating case studies, industry reports, and expert interviews to analyze DevOps implementation across various industries.
Place and Duration of Study: Conducted across organizations in technology, finance, and healthcare sectors from 2022 to 2023 [1,2].
Methodology: The research utilized both primary and secondary data. Primary data were collected through interviews with DevOps experts and consultants, while secondary data included published case studies, industry white papers, and academic research. This comprehensive analysis identified recurring themes, challenges, and effective strategies in DevOps adoption. The study also examined successful case studies to illustrate best practices and drew insights from experts to address barriers and propose actionable recommendations.
Results: The analysis highlighted that strong leadership support (35%), continuous learning (30%), and effective communication (20%) are critical for successful DevOps implementation. Organizations that invested in automation tools such as Jenkins, Docker, Kubernetes, and GitLab experienced significant gains in workflow efficiency, continuous integration, and delivery. Cultural resistance (40%) and lack of expertise (25%) were the main barriers to DevOps adoption. A positive relationship was noted between cultural change initiatives and successful DevOps implementation (R = 0.85).
Conclusion: Effective DevOps adoption requires a cultural shift towards collaboration, shared responsibility, and continuous improvement, backed by strong leadership and strategic automation. To successfully implement DevOps, organizations should focus on cultivating a collaborative culture, ensuring leadership commitment, and investing in continuous learning and automation tools to overcome challenges and achieve their objectives
Election Voting Trend Prediction System
No full textThis paper presents the use of Bayesian networks and K-Nearest Neighbor algorithms for predicting election results. Our motivation stemmed from the complexities of the election data available, which spans over 120,000 voting locations across 36 states in Nigeria, and the requirement to develop a procedure that takes into consideration voter trends that are influenced by political parties seeking to win. The system architecture\u27s translation was utilised, and the prototyping methodology was adopted. In order to realize the requirements, the system was designed and implemented using Java and MySQL in accordance with specifications. Since the outcome is positive, it can serve as a benchmark for further study in this field, particularly when it comes to using data mining tools to analyze election results