Asian Journal of Research in Computer Science
Not a member yet
792 research outputs found
Sort by
Implementation of a Neural Network Approach for Predicting Sales Profit
No full textThe term "artificial neural network" (ANN) refers, in the majority of cases, to a piece of computing hardware that is impacted by the process, function, and cognitive growth that are comparable to that of a human brain. It does this by simulating the way neurons in the human brain carry out their functions. It is able to solve complicated and dynamic issues in real time with some realistic probability constraints because it understands, observes, and recognises the patterns in the data. This paper implements the Microsoft neural network in Microsoft SQL Server Management using visual studio on a dataset that is accessible to the public in order to demonstrate the efficacy of neural networks in transforming raw data into an in-depth understanding of the trends in a dataset that is difficult to visualise. The dataset was chosen because it is readily available to the public. In addition to that, the error margin or standard deviation in the value prediction of the method that was carried out on the database is shown in this work. The selected dataset contains a significant volume of bike sale records from throughout Europe. As a result, it may be categorised as "big data," which cannot be resolved by utilising a standard paper record method or a typical data mining algorithm that is incapable of learning. Additionally, optimizers and modifiers that have an influence on the prediction value that is processed by the SQL database are investigated in this study. Traditional techniques of data analysis, on the other hand, are unable to correctly access or interpret data that is both so complicated and so dynamic as to be able to deliver quality forecasting. Neural networks, on the other hand, are able to resolve the information contained in big data into valuable knowledge in the form of predictions
Design of (3,2) and (4,2) CNTFET Ternary Counters for Multipliers
No full textThe reduction trees of combinational multipliers are widely applying counters. To be able to compare the ternary and the binary approaches, Nanotube Field-Effect Transistor (CNTFET) ternary (3,2) and ternary (4,2) counters have been designed. The ternary (4,2) counter is compared with the binary (7,3) counter as both compute approximately the same amount of information. The binary counter is more efficient. However, comparing counters is not enough: in the Wallace reduction tree of the ternary multiplier, there are two times more lines to reduce compared to the binary one, as a 1-trit multiplier generates both product and carry terms. Comparing the Wallace tree of an 8*8-trit multiplier and a 12*12-bit binary one also shows that the binary implementation is the most efficient
Detection of Fraudulent Health Insurance Claims Based on Decision Tree with Principal Component Analysis
No full textFraudulent health insurance claims pose a significant challenge to insurance companies and healthcare providers, leading to substantial financial losses and compromised service quality. In this study, we focused on detecting fraudulent health insurance claims using the decision tree algorithm and principal component analysis (PCA). The objective was to gain valuable insights and extract meaningful patterns from the dataset to enhance fraud detection capabilities. We developed a comprehensive method that employed the decision tree algorithm to build a decision tree-based model and the PCA for dimensionality reduction. By analyzing the data using these algorithms, we were able to capture important patterns and relationships within the dataset. The decision tree algorithm demonstrated reasonable performance, while the PCA exhibited even better results, leveraging the advantage of dimensionality reduction. The findings of this study have significant implications for fraud detection in the healthcare industry. The insights gained from applying the decision tree algorithms and PCA can aid in making informed decisions, identifying trends, and uncovering hidden patterns within the data. Our study recommends implementing advanced fraud detection systems that incorporate these algorithms, continuous monitoring and evaluation, collaboration and data sharing, further research and development, and adherence to regulatory compliance. By following these recommendations, stakeholders in the insurance and healthcare industries can strengthen their fraud detection capabilities, protect their organizations from financial losses, and maintain the integrity of their services. The use of decision tree algorithms and PCA, combined with effective strategies, can significantly contribute to the detection of fraudulent health insurance claims and the overall security and sustainability of the healthcare system
Streaming Data Processing
No full textAims: The data which is continuously being produced by hundreds of thousands of data sources is recognized as streamed data. The data which is processed via this kind of source is relatively smaller in size and is being sent at the same time it is generated.
Study Design: In streaming data, the data range is so wide like the telemetry from interconnected devices or other such forms of data with the inclusion of certain web applications. This information should be handled consecutively and steadily on a record-by-record premise or throughout sliding time windows and utilized for a wide assortment of examinations including relationships, totals, separating, and inspecting.
Place and Duration of Study: Service usage (for metering and billing), server activity, website clicks, and the geo-location of devices, people, and physical goods are just a few of the many aspects of a company\u27s business and customer activity that can be seen through this type of analysis. It also enables companies to respond quickly to new arising situations.
Methodology: The research methodology is used for the current research work is the qualitative method through which the research studies of a similar domain are studied thoroughly. It has been analyzed that the specified changes in the large volumes of data can better be managed through stream data processing.
Results: The flaws of batch data processing are better dealt with through the usage of streaming data processing agenda. Real-time monitoring as well as response functionality are the keys to success in the given method of data processing.
Conclusion: Stream data processing connects analytics and applications. Because multiple systems can be constructed using the same architecture, this makes the construction of the infrastructure a similar architecture. It additionally allows designers to fabricate applications that utilize scientific outcomes to straightforwardly answer information experiences and make a move
Development of a Web-Based Kasem Language Learning System
No full textThe concept of language involves using words in an organized and traditional way, be it through speaking, writing, or gesturing, as a means of human communication. The inability to communicate efficiently in a specific language is known as language barrier. Such limitation can result in difficulties performing everyday tasks and create challenges on a global levels, such as when businesses move to other nations or on a local level, like when a family or student moves to a region where English is not the primary language. The effects of linguistic barriers can negatively impact the quality of life for everyone involved, regardless of the context. In this paper, the researchers have designed and implemented a web-based Kasem language learning system (KLLS). The technology provides audio output, with corresponding text in the Kasem language to the end user, allowing them to study and become fluent in it. High-level Python web framework, Django, was used to develop and implement the system. Finally, a series of tests were conducted by different levels of users. Each end user reported a high level of satisfaction with the system after navigating through and receiving a clear audio output
Statistical Properties of Buys-Ballot Estimates for Multiplicative Model with the Error Terms
No full textIn this study, we discuss statistical properties of Buys-Ballot estimates for multiplicative model with their error terms. The aim of this study is to characterize the properties of the row, column and overall means and variances of the Buys-Ballot table for multiplicative model with the error terms. The properties of Buys-Ballot estimates in this study are used for (1) estimation of trend parameters (2) estimation of seasonal effect (3) choice of model for decomposition. The results indicate that (1)
the column variance (σ2j) of the Buys-Ballot depends on the seasonal indices (S2j) of the jth seasons. (2) the model that best describe the pattern in the transformed series is additive. This further confirms that the appropriate model of the original series is multiplicative
Comparative Evaluation of Machine Learning Algorithms for Intrusion Detection
No full textThis study undertakes a comparative examination of machine learning algorithms used for intrusion detection, addressing the escalating challenge of safeguarding networks from malicious attacks in an era marked by a proliferation of network-related applications. Given the limitations of conventional security tools in combatting intrusions effectively, the adoption of machine learning emerges as a promising avenue for bolstering detection capabilities. The research evaluates the efficacy of three distinct machine learning algorithms—Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Naive Bayes—in identifying diverse attack categories, including Denial of Service, Probe, Remote to Local, and User to Root.
Conducted on the NSL-KDD dataset, the analysis unveils CNN and RNN as superior performers compared to Naive Bayes, particularly in terms of detection accuracy. These findings extend value to both researchers and practitioners in the realm of intrusion detection systems, offering insights into optimal algorithmic choices. Furthermore, the study\u27s implications resonate within broader contexts, such as the advancement of secure automation in industrial environments and the realm of automobile automation. Overall, this research contributes to the ongoing efforts to fortify network security and promote the development of safer technological landscapes
Software Defect Prediction System Based on Decision Tree Algorithm
No full textSoftware defect prediction plays a crucial role in ensuring software quality and minimizing the potential risks associated with defects. This study aims to develop a comprehensive software defect prediction system that utilizes tree-based algorithms to enhance accuracy, feature selection, and evaluation metrics. The study addresses the limitations of previous research by considering a broader range of datasets, comparing computational efficiency with other ensemble techniques, and examining the impact of hyperparameters on model performance. The implemented system consists of three stages: dataset loading, processing, and result presentation. The dataset loading page allows users to upload their datasets in CSV format, simplifying the prediction process. The processing page performs essential tasks such as feature engineering, normalization using minimax normalization, and training the model with the decision tree algorithm. These steps ensure the extraction of relevant features, transformation of data, and learning of patterns and correlations for accurate software defect prediction. The study emphasizes the practical implementation of the developed system, going beyond model evaluation. By providing a fully functional and integrated system, this study bridges the gap between research and real-world application. The findings of this study contribute to the field of software defect prediction by offering an improved system that enhances accuracy, feature selection, and evaluation metrics. This has implications for software development and quality assurance processes, ultimately leading to higher software quality and increased productivity
Optimizing Business Potential: A Framework for the Implementation of Cloud Computing by SMEs in the Bolgatanga Municipality, Ghana
No full textCloud computing has significantly impacted businesses across different scales, presenting advantages that can be harnessed by small and medium enterprises (SMEs) in Bolgatanga. However, the effective adoption of cloud services requires a well-defined strategy. SMEs in the Bolgatanga Municipality face challenges in implementing cloud computing due to limited knowledge of its applicability, a lack of expertise, and concerns about perceived high costs, among other factors. It was therefore necessary to develop a framework that can be utilized by SMEs in Bolgatanga to implement cloud solutions. The design science research methodology was employed where an extensive evaluation of existing cloud frameworks was performed. The findings suggest that although current cloud transition models have potential value, their complexity and lack of context applicability make them less suitable. The application of the design science research methodology paved way for the development of a practical framework for successful cloud computing implementation by SMEs in Bolgatanga, Ghana. The newly developed framework would enable SMEs to embrace the benefits of the emerging cloud computing era, reducing costs, and gaining a larger market share. Beyond the immediate benefits, leveraging cloud computing will promote collaboration, agile decision-making, and innovation. Cloud solutions provide scalability and accessibility, allowing SMEs to adapt quickly to market changes, improve customer experiences, and make significant progress in their industries. Implementing cloud computing strategically by SMES in Bolgatanga is therefore not just a technological upgrade but a crucial step towards unlocking substantial business advancements for SMEs
An Electronic Payment System for Revenue Collection in the Kassena Nankana Municipality
No full textTraditionally, revenue collection in Kassena-Nankana Municipal Assembly (KNMA), as in Ghana, was manual, with some ICT systems employed recently.This study designed an E-payment system for revenue collection in the KNMA. The research focused on the development and implementation of an electronic payment system, to facilitate revenue mobilization. The study utilizes tools such as HTML, CSS, PHP, JavaScript, MYSQL, SQL, and other resources like VS Code, and payment APIs for the development of the system as well as azure key vaut and secureauth for incription and muti-factor authentication( MFA).As part of the research, it is revealed that, there is a strong willingness among people to embrace electronic payment methods for their taxes, finding it convenient to pay via the internet from anywhere. The E- system developed during this study demonstrated the flexibility expected of an Electronic Payment System, allowing users to create and update accounts, make payments in instalment or in full in any location using their phones. The study establishes a positive impact between the electronic systems and improved revenue generation processes which support the notion that there is indeed a correlation between ICT systems and revenue generation processes, against the notion that there is no correlation