JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
Visualization and Analysis of Safe Routes to School based on Risk Index using Student Survey Data for Safe Mobility
Get PDFRisk analysis is important in heterogeneous industrial domains to enable sustainable development. Data is the basis for emphasizing the potential risk elements for improving efficiency, quality, and safety. For supplying safe routes to schools based on risk analysis, the risk assessment of routes is one of the widely used and very effective methodologies to filter the most dangerous roads, intersections, or specific points on roads. This paper presents a visualization and analysis of the risk assessment approach based on the risk index model using geographical information, including routes, danger points, and student survey data. The proposed risk index model is used for deriving a risk index based on geographical information, including danger points and a route's path. The model includes an equation to calculate the distance of danger points to the path using the coordinates of each location. The survey data is mainly comprised of route and survey information that is analyzed and preprocessed for the input data of the risk index model. The survey mainly consists of basic information on the route, survey participants, school route information, and school route coordinates. The data is classified into the school route data set and the school route danger points data set, and these values are applied to the analysis and the risk index model. Also, the risk index model is designed and developed through the analysis of routes
The Effect of Layer Batch Normalization and Droupout of CNN model Performance on Facial Expression Classification
Get PDFOne of the implementations of face recognition is facial expression recognition in which a machine can recognize facial expression patterns from the observed data. This study used two models of convolutional neural network, model A and model B. The first model A was without batch normalization and dropout layers, while the second model B used batch normalization and dropout layers. It used an arrangement of 4 layer models with activation of ReLU and Softmax layers as well as 2 fully connected layers for 5 different classes of facial expressions of angry, happy, normal, sad, and shock faces. Research Metodology are 1). Data Analysis, 2). Preprocessing grayscaling, 3). Convolutional Neural Network (CNN), 4). Model validation Testing, Obtained an accuracy of 64.8% for training data and accuracy of 63.3% for validation data. The use of dropout layers and batch normalization could maintain the stability of both training data and validation data so that there was no overfitting. By dividing the batch size on the training data into 50% with 200 iterations, aiming to make the load on each training model lighter, by using the learning rate to be 0.001 which works to improve the weight value, thus making the training model work to be fast without crossing the minimum error limit. Accuracy results in the classification of ekp facial receipts from the distance of the camera to the face object about 30 cm in the room with the use of bright enough lighting by 78%
University Examination Timetabling Using a Hybrid Black Hole Algorithm
Get PDFUniversity timetabling construction is a complicated task that is encountered by universities in the world. In this study, a hybrid approach has been developed to produce timetable solution for the university examination timetabling problem. Black Hole Algorithm (BHA), a population-based approach that mimics the black hole phenomenon has been introduced in the literature recently and successfully applied in addressing various optimization problems. Although its effectiveness has been proven, there still exists inefficiency regarding the exploitation ability where BHA is poor in fine tuning search region in reaching for good quality of solution. Hence, a hybrid framework for university examination timetabling problem that is based on BHA and Hill Climbing local search is proposed (hybrid BHA). The aim of this hybridization is to improve the exploitation ability of BHA in fine tuning the promising search regions and convergence speed of the search process. A real-world university examination benchmark dataset has been used to evaluate the performance of hybrid BHA. The computational results demonstrate that hybrid BHA capable of generating competitive results and recording best results for three instances, compared to the reference approaches and current best-known recorded in the literature. Other than that, findings from the Friedman tests show that the hybrid BHA ranked second and third in comparison with hybrid and meta-heuristic approaches (total of 27 approaches) reported in the literature, respectively
Image Presentation Method for Human Machine Interface Using Deep Learning Object Recognition and P300 Brain Wave
Get PDFWelfare robots, as a category of robotics, seeks to improve the quality of life of the elderly and patients by availing a control mechanism to enable the participants to be self-dependent. This is achieved by using man-machine interfaces that manipulate certain external processes like feeding or communicating. This research aims to realize a man-machine interface using brainwave combined with object recognition applicable to patients with locked-in syndrome. The system utilizes a camera with pretrained object-detection system that recognizes the environment and displays the contents in an interface to solicit a choice using P300 signals. Being a camera-based system, field of view and luminance level were identified as possible influences. We designed six experiments by adapting the arrangement of stimuli (triangular or horizontal) and brightness/colour levels. The results showed that the horizontal arrangement had better accuracy than the triangular method. Further, colour was identified as a key parameter for the successful discrimination of target stimuli. From the paper, the precision of discrimination can be improved by adopting a harmonized arrangement and selecting the appropriate saturation/brightness of the interface
Data Fairness Transmission and Adaptive Duty Cycle through Machine Learning in wireless Sensor Networks
Get PDFIn this paper, we propose the data fairness transmission and adaptive duty cycle through machine learning in wireless sensor networks. The mechanism of this paper is mainly composed of two parts. The proposed mechanism is based on the sleep-wake structure, which is one of the methods to increase the lifespan of the entire network by efficiently using the energy of the nodes. The first is a mechanism to support priority and data fairness. To this end, data input to the node is divided into priority classes according to transmission urgency and stored. Introduces the concept of cross-layer to rearrange data destined for the same destination. In addition, we propose a fair data transmission mechanism that allows even low-priority data to participate in transmission after a certain period. The second is an adaptive duty cycle mechanism through machine learning. For this purpose, public data related to forest fires are collected. The collected data is refined into data for each forest fire location and data for each forest fire time. For the refined data, an SVM (Support Vector Machine) model of supervised learning is used for machine learning, and a mechanism for adaptively adjusting the duty cycle of each node through the trained model is proposed. The computer language used for machine learning is Python language, and Google's Psychic Learn is used for the machine learning library. It was compared with the existing MAC protocol for evaluation, and it was confirmed that excellent energy efficiency results were obtained
Development of Early Startup Companies' Valuation Model Based on Android Mobile Application: The Angel Investor's Perspective
Get PDFThis research aims to develop a valuation model for early startup companies based on an Android mobile application (Valuasi app). This application aims to help early startups to evaluate their company performance. This research method uses the research development method. The first stage is to develop a startup valuation model by determining the criteria using the multi-criteria decision making (MCDM) method and weighting the criteria using the simple additive weighting (SAW) method. The instrument and the weight determination of the valuation model have been validated from the perspective of angel investors, practitioners, and academics. The second stage is developing an Android-based startup valuation model application. The third stage is an evaluation by the users of the application. Using the Unified Theory of Acceptance and Use of Technology (UTAUT) model, the results show that a potential user's intent to use the application is affected by the performance expectancy and social influence toward the application. This valuation model is expected to help early startup companies conduct business valuations, so they can attract investors, especially angel investors. In addition, the results showed that there was a positive response from users in using the 'Valuasi app', which was indicated by the positive and significant effect of performance expectations on usage intentions, and a positive and significant influence on social influence and behavioral intentions on user behavior. This research shows that 'Valuasi app' can be used to assess start up valuation. However, further improvements are needed to support application facilities so as to increase the ease of using the "Start Up Valuation App" applicatio
How to Deeply Analyze the Content of Online Newspapers Using Clustering and Correlation
Get PDFThe increase in the number of visitors is one of the keys to increasing income for online newspapers, whether to increase the number of ads, Google AdSense, or customer trust. Therefore, finding which news categories increase the number of visitors needs to be known and analyzed more deeply. Because it is very common to add content to online newspaper sites every day, even for hours, this pattern analysis is not the same as analyzing regular website content patterns. This study intends to add methods in the world of research on how to analyze website content, especially online news, by using the clustering method to classify what news categories bring high, medium, or a low number of visitors and then analyzing the correlation to explore the depth of the relationship between the variables, namely which parameters have a large or low effect on the increase in the number of visitors. A local Batam-based online newspaper company is used as a case study for this research. Data is collected, preprocessed first, and analyzed using the clustering and correlation method. This analysis of the news content readership suggests what news categories should be optimized because it provides an increase in the number of visitors. A summary of the analysis steps in this study is presented. We also provided some suggestions if other online newspaper owners or researchers are interested in a similar analysis of online news content
A Study of Database Connection Pool in Microservice Architecture
Get PDFThe growing number of Internet presents a higher requirement to backend application systems nowadays to be designed to handle thousands of users traffic concurrently. Microservice architecture is also in a rising trend which they allow for each service to scale horizontally by their throughput and load helps to scale the system efficiently without waste of resources like in the traditional monolithic application system. Among the many strategies to optimize delivery, database connection pool helps backend systems to access databases efficiently by reusing database connections, thus eliminating the computationally expensive need to open and close connections with new requests. Additionally, database connection pools can also help improve the connection reliability for applications. This paper aims to determine the most suitable maximum amount of database connections in a microservice setting, where multiple instances of the service are used for scalability and high availability purposes of the system. To tackle the issue of scalability and to achieve high availability of our services, we propose running multiple instances of each of our services in production, especially for services that we anticipate will be hit the most during runtime. This is to allow load balancing of request load between multiple instances and having backup instances to serve HTTP requests when one of the instances is down. The result obtained in this experiment shows that 5 database connections give the best result in microservice settings as described in our methodology
The Relevance of Bibliometric Analysis to Discover the Area’s Research Efforts: Root Exploit Evolution
Get PDFMalware steals, encrypts, and damages data of the targeted machines for private, money, or fame purposes. The types of malware are root exploit, cryptojacking, Trojan, worms, viruses, spyware, ransomware, and adware. Among these types, root exploit is one of the most destructive malware types since it disguises and obscures all types of malware and provides a mechanism for other malware to carry out malicious acts invisibly. In the interest to review the progress of root exploit efforts globally, there is a need to inspect all publications that involve root exploit. Among all malware reviews previously, to date, there is still no trace of any bibliometric analysis that demonstrates the research impacts of root exploit and trends in bibliometric analysis. Hence, this paper adopts bibliometric analysis specifically on root exploit studies which evaluate: (1) Wordcloud; (2) WordTreeMap; (3) Three fields plot; (4) Thematic evolution; (5) Thematic maps; (6) Correspondence analysis (CA); (7) Dendrogram; and (8) Multiple correspondence analysis (MCA). To conclude, our bibliometric discovers that; 1) Linux and Android become main interest in root exploit studies. 2) Types of root exploit in virtualization layer and studies to detect on this area are increasing. 3) USA and China have become the leaders in root exploit research. 4) Research studies are more towards memory forensics to detect root exploit, which is more promising. 5) Instead of researching new methods of root exploit in compromising victims, root exploit researchers were more focused on detecting root exploits
Smartphone-based Indoor Navigation for Guidance in Finding Location Buildings Using Measured WiFi-RSSI
Get PDFThis study investigates a Wi-Fi-based indoor navigation system to determine building locations. The system was developed using the fingerprint method from the Received Signal Strength Indication (RSSI) of each Access Point (AP). The main components of a smartphone-based system use data from Wi-Fi and the Global Positioning System (GPS). The system developed for navigation is designed and implemented as an element of a dynamic, seamless mobility planning and building location route guidance application. Building map data is collected from Google Map data and enhanced by coloring the geographic location of buildings displayed on mobile devices. Navigational aids collected from sensors provide trip orientation and position updates. The approach of measuring the distance between known positions is compared to those displayed in the application with the haversine formula to measure the accuracy of the position displayed. A series of experiments were conducted in the Politeknik Negeri Semarang area, Indonesia. The experiment results showed that the Wi-Fi-based indoor positioning system was accurate within 7.050 meters of the error for that location, thus proving the system's usefulness for determining the location of buildings in the campus area. The measurement has not adopted the maximum APs placement for signal coverage and strength, only using the existing APs positions. The temperature nor humidity was neither measured in each area where the AP was installed, which is discussed later. This system can help visitors without asking, even though they have only visited once