Asian Journal of Research in Computer Science
Not a member yet
792 research outputs found
Sort by
Detection and Classification of Leukocytes in Leukemia using YOLOv2 with CNN
No full textThe development of machine learning systems that used for diagnosis of chronic diseases is challenging mainly due to lack of data and difficulty of diagnosing. This paper compared between two proposed systems for computer-aided diagnosis (CAD) to detect and classify three types of white blood cells which are fundamental of an acute leukemia diagnosis. Both systems depend on the You Only Look Once (YOLOv2) algorithm based on Convolutional Neural Network (CNN). The first system detects and classifies leukocytes at the same time called computer-aided diagnosis with one model (CADM1). The second system separates detection and classification by using two models called computer-aided diagnosis with two models (CADM2). The main purpose of the paper is proving the high performance and accuracy by fragmentation of the main task into sub-tasks through comparing between CADM1 and CADM2. Also, the paper proved that can be depending only on deep learning without any traditional segmentation and preprocessing on the microscopic image. The (CADM1) achieved average precision for detection and classification class1=56%, class2=69% and class3 72% while (CADM2) achieved average precision up to 94% for detect leukocytes and accuracy 92.4% for classification. The result of the second system is very suitable for diagnosis leukocytes in leukemia
A Comparative Analysis and Predicting for Breast Cancer Detection Based on Data Mining Models
No full textBreast cancer is one of the most common diseases among women, accounting for many deaths each year. Even though cancer can be treated and cured in its early stages, many patients are diagnosed at a late stage. Data mining is the method of finding or extracting information from massive databases or datasets, and it is a field of computer science with a lot of potentials. It covers a wide range of areas, one of which is classification. Classification may also be accomplished using a variety of methods or algorithms. With the aid of MATLAB, five classification algorithms were compared. This paper presents a performance comparison among the classifiers: Support Vector Machine (SVM), Logistics Regression (LR), K-Nearest Neighbors (K-NN), Weighted K-Nearest Neighbors (Weighted K-NN), and Gaussian Naïve Bayes (Gaussian NB). The data set was taken from UCI Machine learning Repository. The main objective of this study is to classify breast cancer women using the application of machine learning algorithms based on their accuracy. The results have revealed that Weighted K-NN (96.7%) has the highest accuracy among all the classifiers
Predicting Weather Forecasting State Based on Data Mining Classification Algorithms
No full textWeather forecasting is the process of predicting the status of the atmosphere for certain regions or locations by utilizing recent technology. Thousands of years ago, humans tried to foretell the weather state in some civilizations by studying the science of stars and astronomy. Realizing the weather conditions has a direct impact on many fields, such as commercial, agricultural, airlines, etc. With the recent development in technology, especially in the DM and machine learning techniques, many researchers proposed weather forecasting prediction systems based on data mining classification techniques. In this paper, we utilized neural networks, Naïve Bayes, random forest, and K-nearest neighbor algorithms to build weather forecasting prediction models. These models classify the unseen data instances to multiple class rain, fog, partly-cloudy day, clear-day and cloudy. These model performance for each algorithm has been trained and tested using synoptic data from the Kaggle website. This dataset contains (1796) instances and (8) attributes in our possession. Comparing with other algorithms, the Random forest algorithm achieved the best performance accuracy of 89%. These results indicate the ability of data mining classification algorithms to present optimal tools to predict weather forecasting
Leukemia Diagnosis using Machine Learning Classifiers Based on Correlation Attribute Eval Feature Selection
No full textLeukemia refers to a disease that affects the white blood cells (WBC) in the bone marrow and/or blood. Blood cell disorders are often detected in advanced stages as the number of cancer cells is much higher than the number of normal blood cells. Identifying malignant cells is critical for diagnosing leukemia and determining its progression. This paper used machine learning with classifiers to detect leukemia types as a result, it can save both patients and physicians time and money. The primary objective of this paper is to determine the most effective methods for leukemia detection. The WEKA application was used to evaluate and analyze five classifiers (J48, KNN, SVM, Random Forest, and Naïve Bayes classifiers). The results were respectively as follows: 83.33%, 87.5%, 95.83%, 88.88%, and 98.61%, with the Naïve Bayes classifier achieving the highest accuracy; however, accuracy varies according to the shape and size of the sample and the algorithm used to classify the leukemia types
The Impact of the COVID 19 Pandemic on the Digitalization of Municipal Administration, the Development of E-Governance
No full textThis paper essentially addresses the importance and contribution of digitalization in the creation and implementation of public policies, thus analyzing the activity of the Municipal Administration in Gjilan, Vitia, and Kamenica, the principles on which it relies and administrative bodies as an important part of administration. First, the importance of Public Administration and its principles is presented, then Municipal Administration and Ethics in Municipal Administration. It then analyzes E-Government and E-Kiosk as an important structure of the administration and the role it has given so far in administrative reform as one of the advantages for the integration of Municipal Administrations, strong management and use of information technology for a smooth-running of work quickly and accurately, especially in protecting the health of citizens from the Covid-19 Pandemic. To achieve the purpose of this paper, the method of surveying citizens directly through questionnaires was used. The questions are mostly qualitative and they are closed-type, open-type, but there are also Liker type. The questionnaire was used to survey 60 participants from the Municipality of Gjilan, 50 participants from the Municipality of Vitia and 50 participants from the Municipality of Kamenica. After completing the questionnaire, it was concluded that the digitalization of the Municipal Administration requires well-trained staff and continuous maintenance of information systems. E-Government should be the main goal in the reform of the municipal administration, which will promote radical changes such as: a new way of management, discussions and communication, more efficient and faster decision-making, access for all to services, elimination of corruption and administrative silence. It is a driving force for the reorganization and renewal of administration services. It also protects the health of citizens from contagious diseases, especially during the Covid-19 Pandemic
Calculating Feeder Fault Current with MATLAB Software Program
No full textThe aim of this article describes the program of computerized how to calculate the feeder fault current in a distribution substation. This article adopts Thevenin theory as the basis of calculation, and narrates them in two ways: the artificial and the computerized algorithm. It leaves aside the artificial and delves the computerized algorithm. The latter is divided for two computerized algorithm - separate and all of equipment. In the computerized algorithm, all data inputting, procedure steps, and report form were carefully been designed by MATLAB application software. As for data Inputting refers to the specification parameters of equipment component. The characteristics of this article are described with both text and Fig. to achieve operation simple and understanding easy. References include a representative textbook and several journal articles. Verify with real cases and reveal the pros and cons of artificial and program algorithms. The purpose of this article is to discard waste - an artificial calculation that is time - consuming, cumbersome and prone to clerical errors. The computer programs algorithm can compensates for defects and improves accuracy and timeliness. This method has been proven to be an economical design aid tool that is of great help to maintenance or designers in the field of electrical engineering
Usability, Security and Trust of E-commerce Websites: The effect on the Nigerian E-shopper
No full textWith the internet fast-penetrating the Nigerian populace, e-commerce businesses have become commonplace, this has given rise to an increase in the number of Nigerians shopping online. However, there is a growing concern that most Nigerian e-shoppers prefer foreign to local online shops, resulting in an online fund-leak from the local economy. This work presents a comparative analysis of the usability of e-commerce websites in Nigeria, highlights the key findings viz: security and lack of trust. The findings were then related to why Nigerians prefer shopping from foreign rather than local e-commerce websites. We argued that for e-commerce to thrive; usability should be given prime consideration, security should be guaranteed and trust-building ethos is practiced. We conclude that despite the ‘pay on delivery’ mode applied by e-commerce websites to woo customers and gain trust, the insecurity posed by the prevalence of online fraud in Nigeria has created apprehension and distrust among Nigerians towards local e-commerce websites and is contributing to why Nigerians prefer to buy from foreign rather than local e-commerce websites
Securing Logins in Electronic Examination Systems for Tertiary Institutions Using Quick Response Code (QR) Technology and Multiple Hashing Algorithms
No full textThis work is aimed at adding an extra layer of security to the login process of an electronic examination system as security has been identified as one of the critical success factors in the management of such exams. It proposes to secure the login process of an e-exam system through authentication and encryption to control access and avoid impersonation. A model of the e-exam system with Quick Response (QR) code generation capability was designed where a student’s matriculation number is accepted as input which is then converted into a two-dimensional bar code using a QR generator. Outputs from the QR code generator are then secured by encryption using MD5 and SHA-224 encryption algorithms. MD5 algorithm produces a 32-bit hash value which is further encrypted using SHA-224 that produces a resulting 56-bit hash value that is then saved in the password column of the user table in the database. This research resulted in a secure and web-based electronic examination authentication system implemented and tested on a client-server architecture. Performance evaluation of the developed system revealed that it is fast and effective, capable of authenticating students in an average of 0.624 seconds when the smartphone flashlight is off, and 0.318 seconds with flashlight turned on and consequently, resistant to brute force attacks. This paper fulfils an identified need to develop an electronic exam system that not only secures the question bank but equally ensures the security of the login process as well as the login details using a combination of two security techniques
Scheduling Algorithms Implementation for Real Time Operating Systems: A Review
No full textThe term "Real-Time Operating System (RTOS)" refers to systems wherein the time component is critical. For example, one or more of a computer\u27s peripheral devices send a signal, and the computer must respond appropriately within a specified period of time. Examples include: the monitoring system in a hospital care unit, the autopilot in the aircraft, and the safety control system in the nuclear reactor. Scheduling is a method that ensures that jobs are performed at certain times. In the real-time systems, accuracy does not only rely on the outcomes of calculation, and also on the time it takes to provide the results. It must be completed within the specified time frame. The scheduling strategy is crucial in any real-time system, which is required to prevent overlapping execution in the system. The paper review classifies several previews works on many characteristics. Also, strategies utilized for scheduling in real time are examined and their features compared
Mobile Sensor Networks: What Can Underground Electric Transport Vehicles do in Underground Mine Monitoring?
No full textAccording to our previous work, we have found that the ZigBee WSN technology and sensors are actually suitable for the underground monitoring, but there are still many problems. So in this viewpoint paper, we showed our viewpoint that the underground driver-less electric transport vehicles could also play an important role in the underground monitoring, that is, underground electric transport vehicles running in the mine roadway could carry mobile sensors to monitor the environmental conditions in the transport roadway. If it could be realized, it will save the number of sensors installed around the mine so as to reduce costs. If it could be realized, the monitoring of underground mines will become more convenient