JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
An Efficient Approach for Uncertain Event Detection in RFID Complex Event Processing
Get PDFThe globalization of manufacturing has increased the risk of counterfeiting as the demand grows, the production flow increases, and the availability expands. The intensifying counterfeit issues causing a worriment to companies and putting lives at risk. Companies have ploughed a large amount of money into defensive measures, but their efforts have not slowed counterfeiters. In such complex manufacturing processes, decision-making and real-time reactions to uncertain situations throughout the production process are one way to exploit the challenges. Detecting uncertain conditions such as counterfeit and missing items in the manufacturing environment requires a specialized set of technologies to deal with a flow of continuously created data. In this paper, we propose an uncertain detection algorithm (UDA), an approach to detect uncertain events such as counterfeit and missing items in the RFID distributed system for a manufacturing environment. The proposed method is based on the hashing and thread pool technique to solve high memory consumption, long processing time and low event throughput in the current detection approaches. The experimental results show that the execution time of the proposed method is averagely reduced 22% in different tests, and our proposed method has better performance in processing time based on RFID event streams
Implementation of an Integrated Online Class Model using Open-Source Technology and SNS
Get PDFBefore Covid-19, the class model was divided into online, offline, and blended learning. Due to Covid-19, we have the only online class environment. We need a new online class model under the new circumstances. In the new model, all technology and educational methods need to be well-adapted, organized and harmonized to compensate for the absence of offline learning sessions. In this paper, we propose a new online class model. Because of the absence of offline sessions, the model emphasizes the integration of synchronous and asynchronous activities seamlessly and effectively. The model also emphasizes the instructor's role as a content prosumer because the instructor in the new model is either reusing other's and the one's own contents or supplying those contents for others. This model uses open-source solutions or free services like Moodle, OBS, Tubestory, and Snap Camera for both budget-saving and stability purposes. It actively uses Moodle's monitoring capability and adopts various learning technologies. It consists of three activity sessions: a pre-Zoom session, a Zoom session, and a post-Zoom session. Each session is composed of modules that describe the process and action for the class. The process, methods, and techniques for each module are explained in this paper. The official students survey for class evaluation held by Kongju national university showed that the new class model's application obtained a higher score than the same class of the previous year that is performed by conventional teaching
A Framework of Mutual Information Kullback-Leibler Divergence based for Clustering Categorical Data
Get PDFClustering is a process of grouping a set of objects into multiple clusters, so that the collection of similar objects will be grouped into the same cluster and dissimilar objects will be grouped into other clusters. Fuzzy k-means Algorithm is one of clustering algorithm by partitioning data into k clusters employing Euclidean distance as a distance function. This research discusses clustering categorical data using Fuzzy k-Means Kullback-Leibler Divergence. In the determination of the distance between data and center of cluster uses mutual information known as Kullback-Leibler Divergence distance between the joint distribution and the product distribution from two marginal distributions. Extensive theoretical analysis was performed to show the effectiveness of the proposed method. Moreover, the proposed method's comparison results with Fuzzy Centroid and Fuzzy k-Partition approaches in terms of response time and clustering accuracy were also performed employing several datasets from UCI Machine Learning. The experiment results show that the proposed Algorithm provides good results both from clustering quality and accuracy for clustering categorical data as compared to Fuzzy Centroid and Fuzzy k-Partition
Intelligence Eye for Blinds and Visually Impaired by Using Region-Based Convolutional Neural Network (R-CNN)
Get PDFIntelligence Eye is an Android based mobile application developed to help blind and visually impaired users to detect light and objects. Intelligence Eye used Region-based Convolutional Neural Networks (R-CNN) to recognize objects in the object recognition module and a vibration feedback is provided according to the light value in the light detection module. A voice guidance is provided in the application to guide the users and announce the result of the object recognition. TensorFlow Lite is used to train the neural network model for object recognition in conjunction with extensible markup language (XML) and Java in Android Studio for the programming language. For future works, improvements can be made to enhance the functionality of the Intelligence Eye application by increasing the object detection capacity in the object recognition module, add menu settings for vibration intensity in light detection module and support multiple languages for the voice guidance
Computational Thinking Evaluation Tool Development for Early Childhood Software Education
Get PDFThe early childhood software education is being actively conducted, but research on evaluation of computational thinking is in its infancy. The purpose of early childhood software education is to cultivate the computational thinking through activities centered on solving problems in everyday life. Evaluation in software education is very important in that it not only measures computational thinking simply but also improves computational thinking through evaluation. As such, guidelines for evaluating computational thinking that can be used in early childhood software education are needed, but they are very lacking. Therefore, in this study, the researcher developed an evaluation tool that can meet the ultimate purpose of software education, cultivating computational thinking. The developed evaluation tools are a software education effectiveness test tool and a computational thinking test tool. They were developed to the level of development and interaction of the early childhood. The developed evaluation tool has been validated by software experts, early childhood education experts, and early childhood teachers. As a result of the second step validity verification, all content validity was confirmed. Through this, it was confirmed that the evaluation tool developed in this study can be used as a tool for evaluating computational thinking. This study provides implications for evaluation of computational thinking for early childhood software education. In addition, it is meaningful that it has been suggested to be effectively used for proper evaluation in early childhood software education
Design of Personal Mobility Safety System Using AI
Get PDFIn this paper, we propose the implementation of a safety device that generates an alarm sound or braking operation to reduce the risk of accidents. It reduces the exposure of risks due to non-wearing by supplementing the function of the helmet for safety. For machine learning, the safety state is learned by using two types of sensing data, and when an abnormal helmet use or speed or drinking driving is detected, an alarm sound is generated and motion is broken to maintain the safe state. By measuring data using a gas sensor, alcohol is checked and this is used as abnormal data. Users form a habit of wearing safety equipment with continuous safety alarm sound and speed braking and proper driving habit by driving in a normal state without drinking alcohol. In addition, the proposed system enables real-time monitoring, thereby reducing risks by continuously maintaining safe driving and wearing protective equipment. The proposed system uses artificial intelligence to discriminate data related to helmet wearing, speed, and drinking in making an electric kickboard for safety, and triggers an alarm or operates the brake to prevent abnormal driving. If the design and function are supplemented, it will become a basic function that can be applied to various equipment of transportation
Improving the Response Time of Online Letter Management Application Users: an Application of Social Representation Theory of Shame
Get PDFOne of the most important and potential problems encountered in an official online letter management application is the recipients' late response. This action research aims to improve the recipients' response time and determine the central core of shyness according to response time categories: less than 24 hours (green zone); between 24 hours to 48 hours (orange zone); and more than 48 hours (red zone) in managing formal online letter management system at Jambi University. Using the social representation theory of shyness as the basis of action adopted from Moscovici theory [1], it is hypothesized that response time displaying will impact response time improvement. A survey questionnaire distributed to 129 respondents showed a significant improvement in the participants' response time, respectively, in cycles 1 and 2. The zone group increased percentage sed from 22.44% to 52.49 % in the first cycle, and it ultimately raised to 62.38% at the end of the second cycle. Such an increase might be due to the users' efforts to avoid the level of shyness, which were classified into: (1) slow to respond and (2) personal or work unit late response time – both marked in red. It is recommended that social shyness incorporated in improving response time in a formal online letter can be further implemented with other social and psychological parameters. The application will illustrate computer systems' interaction on social society to implement regulations both in institutions and in government
Hesitant Fuzzy-Stochastic Data Envelopment Analysis (HF-SDEA) Model for Benchmarking
Get PDFThe Data Envelopment Analysis (DEA) method is a method commonly used in benchmarking. The Dynamic Data Envelopment Analysis (DDEA) method was proposed to improve the DEA method in the benchmarking process. The DDEA method proposed can determine the effectiveness of the Decision Making Unit (DMU). The disadvantage of the DDEA model is that it cannot handle problems that involve benchmarking for stochastic data. To improve the DDEA method, the Stochastic Data Envelopment Analysis (SDEA) method is proposed which can be used for benchmarking involving stochastic data. The SDEA method itself has weaknesses in dealing with noise and uncertainty problems that will appear in the assessment process. The purpose of the research conducted by the researcher was to use the Hesitant Fuzzy method in optimizing the SDEA method so that the Hesitant Fuzzy model - Stochastic Data Envelopment Analysis (HF-SDEA) could be carried out benchmarking process in a situation where the assessment contained many elements of uncertainty. The results of this study are benchmarking methods that can do benchmarking for stochastic data on conditions that contain elements of uncertainty
Teler Real-time HTTP Intrusion Detection at Website with Nginx Web Server
Get PDFWeb servers and web-based applications are now widely used, but in this case, the crime rate in cyberspace has also increased. Crime in cyberspace can occur due to the exploitation of how a system works. For example, the way HTTP works are exploited to weaken the webserver. Various tools for attacking the internet are also starting to be easy to find, but so are the tools to detect these attacks. One of the useful tools for detecting attacks and sending warnings against threats is based on the weblogs on the webserver. Many have not reviewed Teler as an intrusion detection system on HTTP on web servers because the existing tools are relatively new. Teler detecting the weblog and run on the terminal with rule resources collected from the community. So here, the researcher tries to implement the use of Teler in detecting HTTP intrusions on a Nginx-based web server. Intrusion is carried out in attacks commonly used by attackers, for example, port scanning and directory brute force using the Nmap and OWASP ZAP tools. Then the detection results will be sent via the Telegram bot to the server admin. From the results of the experiments conducted, it has been found that Teler is still classified as being able to send warning notifications with a delay between the time of detection and the time when the alert is received, no more than 3 seconds
Early Dropout Prediction in Online Learning of University using Machine Learning
Get PDFRecently, most universities plan to open or open online learning courses, but the problem of dropout of online learning is still a problem for universities. Online learning has the advantage of being able to receive education anytime, anywhere, but it is true that the dropout rate is higher than offline classes because you have to manage and control your own study time without the help of a professor or manager. Therefore, it is very important for professors and managers to support students in a timely act to avoid the risk of dropout of university online classes. This study used the access log data recorded in the Learning Management System (LMS) and the learner's statistical information and calculated data, and aims to present predictive algorithms suitable for online learning dropout early prediction systems at universities. This study features a 7-year online learning history log data recorded in the Cyber University LMS system to overcome the data count limitations of existing studies and predict the risk of drop-out during the learning period. The characteristics of the data you utilized were used to validate the availability of predictive models by applying learner statistical information, number of system connections, number of lectures, previous semester grade data, machine learning based decision tree, arbitrary forest (RF), support vector machine (SVM) and deep learning (DNN). Studies show that random forest (RF) algorithms have the best prediction and performance, and deep learning algorithms also apply to learning management (LMS) systems