Asian Journal of Research in Computer Science
Not a member yet
792 research outputs found
Sort by
A B+-Tree-Based Indexing and Storage of Numerical Records in School Databases
No full textThe need for effective indexing and retrieval of data is paramount in any contemporary organization. However, the use of tree data structure had been effective in this regard as evident in literature. This article gives an overview of B+-tree data structure, its indexing technique and application in indexing and retrieving students’ academic records in the school system in order to make such records flexible. The study demonstrates the indexing and arrangement patterns of some numerical data. In essence, it discusses how to adopt the use of B+-tree data structure to manage some numerical data in order to enhance indexing, retrieval and modifications of such record. It concludes that good record management results in more convenient indexing and retrieval of students’ academic records within the school system
Harnessing Machine Learning for Effective Cyber security Classifiers
No full textMachine learning has emerged as a transformative force, innovating diverse industries through its capacity to infuse meaningful insights from large datasets. It plays a pivotal role in powering data analysis, discover pattern matching, identifying hidden or evolving risks in securing systems. The ability of categorizing and behavior analysis is central to its efficacy in cybersecurity. This paper highlights the importance of machine learning in landscape of cyber threats. In this paper, we have identified few machine learning algorithms to categorize huge dataset. The complexities of identifying hidden risks increases by many folds, when the input data is voluminous. Evaluating and contemplating the underlying meaning of data is time-consuming and can be missed easily. We compared different types of machine learning algorithms. Each machine learning algorithm has its strength and weakness. It is found that, the TressJ48 algorithm is proficient in classifying the large dataset, better than Naive Bayes and Decision Stump algorithms. The efficient classifier helps to generate insight, which can be further used to make decisions in terms of cybersecurity
The Techniques Used in Mitosis Detection in Breast Cancer Histopathology Images: A Survey
No full textBreast cancer consider as the second cause of death around the world after heart disease, and it is the primary cause of death for women. Timely detection of breast cancer plays a crucial role in lowering mortality rates, as it enhances the patient\u27s prospects of survival through prompt diagnosis and appropriate treatment. The discovery of the mitotic number is one of the necessary procedures that must be performed for a person suffering from breast cancer because it is an important marker for determining the aggressiveness of the tumor. According to the Nottingham scale, it gives 3 degrees to determine the degree of the tumor, whether it is of the first degree, the second degree, or the third degree of seriousness. Deep learning algorithms have many contributions in the medical fields, including in the field of mitotic number discovery, as the mitotic number process is a difficult and tiring task that requires time and effort from pathologists (diagnostic doctors), because the work environment is under microscopes with high magnification degrees, for this reason deep learning techniques were used to reduce the burden on diagnostic doctors and save time for the patient to know the result of his examination, as the biopsy results in developed countries take from 10 days to two weeks for the results to appear. In this survey, we will evaluate the deep learning techniqus employed for mitotic number detection
Human Regular Activities Recognition Using Convolutional Neural Network
No full textCapturing commonly occurring behaviors is a tough issue in computer vision. A few of them are recreation, touring, leisure pursuits, and religious practice. A comprehensive effort has already been dedicated to this aspect to deal with this issue. In this work, we recreated a dataset with five categories, including household activities, farming, exercise, sports, and occupation, to identify human daily actions. This collection has 4328 colored images in total, among them 630 are set aside for testing, and 3698 for training. Deep learning and standard image-based strategies are being explored to address the issues. In this paper, we have designed a deep learning paradigm to classify the regular activities of human beings. To characterize people\u27s daily chores, we use the CNN model, one of the greatest tools for visual identification. We also have chosen two already-trained VGG16 and ResNet50 models. When we compare our model with the existing techniques, the investigation\u27s findings demonstrate that the suggested network has a better recognition accuracy of 91%. Additionally, we have observed that accuracy varies throughout different epochs, and after 25 epochs we got better stable results from our model. The reader may find this article instructive in grasping CNN models for various recognizing applications
.NET Tools for Software Development: Tool Selection, Key Benefits of .NET Web Applications
No full textAims: This report analysis the top 5 .NET tools that can be used to develop website and software.
Study Design: We have shortlisted the 5 .NET tools that can be used to design and implement website and software.
Methodology: According to Microsoft, .NET is a software-based approach for integrating information, users, technologies, and devices, and it encompasses everything that an organization requires to build and deploy an integrated data architecture: servers used to host services; development tools; and apps that utilize them. We have selected Web essential for Visual studio, Resharper, Ncrunch, NuGet and Elmah tools.
Results: The exposed qualities connect to modern emerging techniques such as components, allocation, software and services, and online redirection. As a result of the available options, .NET is recognized as one of the most extensively used software development platforms. The framework .NET\u27s of devices and technologies as well as their optimal usage in practice, need knowledge with its tool set.
Conclusion: The NET-framework offers a variety of software types, with a focus on producing apps for Windows, mobile devices, and the Internet. Windows applications can be terminal (text-based) or graphical, including drivers, libraries, and services. Applications for mobile devices are created for smartphones and tablets. ASP.NET web services and web applications written for the Internet
A Bibliometric Overview of IoT-Based Digital Voting
No full textAbstract: Several studies have empirically explored biometric voting using the IoT to transfer votes to the central system. There aren\u27t many bibliometric studies that categorize the output in this area, though. By keeping an eye on the papers posted on the Scopus platform, this study’s goal is to give research bibliometric analysis on biometric voting utilizing IoT to transfer votes to a central system, classifying trends, the state of the art, and other indications. 267 different materials made up the sample. Using the VOSviewer program, the data was processed and the outcomes graphically represented. According to the study, which examined publications’ simultaneous occurrence by year, trends of keyword, co-citations, coupling bibliographic, and co-authorship analysis, institutions, and countries, the body of knowledge on biometric voting that uses the Internet of Things to transfer votes to a central system is expanding quickly. More than 530 citations were found in just eight works. However, there are other industrious writers. The most significant of the 267 sources used in the review were published in 26.066 percent of the papers. China is the world\u27s leader in this field. This study offers knowledge about the current state of the art and indicates research opportunities and gaps in IoT-based biometric voting
Speed Analysis of Binary Search and Interpolation Search for Searching Identification Numbers on National Identity Cards
No full textAims: The purpose of the work is to make comparisons and find the best search algorithm between binary search and interpolation search algorithms for searching identity number on Indonesian identity cards.
Study Design: This study was designed by implementing binary and interpolation algorithms into C language, with a dataset of 5000.
Place and Duration of Study: Department of Informatic Universitas Multimedia Nusantara, between November 2022 until March 2023.
Methodology: Binary algorithms and interpolation search will be tested by searching for identity number on identity card data, totaling 5000 data. To measure the level of speed and effectiveness of the two algorithms, this will be done by trying to search for data in various amounts, namely 1000, 2000 and 5000 data, with the data sought between the two algorithms having the same value. Testing is carried out by implementing the two algorithms into C language to get the number of loops and execution time, and testing of the algorithms on each sample dataset is carried out five times to get the average value of the test results.
Results: The results of the tests that have been carried out between the binary search and interpolation search algorithms from the existing dataset, found that the number of loops in the interpolation loop is 36.57% better than the binary search algorithm, while for execution time, binary search has a faster execution speed of 12.43% than interpolation search.
Conclusion: It can be concluded that if the dataset is large enough, such as identity card data on Indonesian citizens, and if the computer specifications are adequate, binary search, which has a faster execution time, should be used; however, if the computer specifications are inadequate, interpolation search, which has a smaller number of loop processes, should be used
Generation and Evaluation of Tabular Data in Different Domains Using Gans
No full textDeep learning techniques like Generative Adversarial Networks (GANs) provide solutions in many domains where real data needs to be kept private. Synthesizing tabular data is difficult because of its high complexity. Tabular data usually contains a mixture of discrete and continuous data, which is not an easy model to build. The contributions made in this paper include training and generating data with the original Vanilla Gan, then CGan and WGan-Gp and WCGan-Gp which performs better than the former. The Adult Income Census dataset mainly focuses on predicting whether income exceeds 50,000 per year based on census data, then comparing the accuracy of machine learning models and calculating the F1 scores. Then the use of TimeGan on the stock dataset, comparing synthetic data vs real data. This paper will explore the use of GANs for generating and evaluating tabular data in different domains
Machine Learning Approach for House Price Prediction
No full textIn our ecosystem, real estate is clearly a distinct industry. Predicting house prices, significant housing characteristics, and many other things is made a lot easier by the capacity to extract data from raw data and extract essential information. Daily fluctuations in housing costs are still present, and they occasionally rise without regard to calculations. According to research, changes in property prices frequently have an impact on both homeowners and the real estate market.
To analyze the key elements and the best predictive models for home prices, literature research is conducted. The analyses\u27 findings supported the usage of artificial neural networks, support vector regression, and linear regression as the most effective modeling techniques. Our results also imply that real estate agents and geography play important roles in determining property prices. Finding the most crucial factors affecting housing prices and identifying the best machine learning model to utilize for this research would both be greatly aided by this study, especially for housing developers and researchers
Quantum Neural Networks: Bridging Quantum Computing and Machine Learning
No full textThe usage of QNNs is one approach that might be used to close the knowledge gap that exists between the domains of machine learning and quantum computing. As a result of this research, a full analysis of QNNs has been offered, covering a wide range of issues including their theoretical underpinnings, training techniques, benefits, limits, applications, and assessment methodologies. Quantum neural networks, also known as QNNs, are a type of artificial neural network that makes use of the power of quantum computing. These networks provide the promise for a significant improvement in processing speed as well as greater representation capabilities. On the other hand, in order to make full advantage of the benefits that QNNs give, obstacles such as scalability concerns and hardware restrictions need to be addressed and fixed. The fact that QNNs have the potential to be applied in such a broad range of different sectors is evidence of both the adaptability and the significance of this rapidly developing field of study. It will be necessary to do more study and investigation if there is to be any hope of making headway in the field of quantum machine learning with regard to the creation of QNNs and of realizing their full potential