JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
Practical Evaluation of Federated Learning in Edge AI for IoT
Get PDFAI running locally on IoT Edge devices is called Edge AI. Federated Learning (FL) is a Machine Learning (ML) technique that builds upon the concept of distributed computing and preserves data privacy while still supporting trainable AI models. This paper evaluates the FL regarding practical CPU usage and training time. Additionally, the paper presents how biased IoT Edge clients affect the performance of an AI model. Existing literature on the performance of FL indicates that it is sensitive to imbalanced data distributions and does not easily converge in the presence of heterogeneous data. Furthermore, model training uses significant on-device resources, and low-power IoT devices cannot train complex ML models. This paper investigates optimal training parameters to make FL more performant and researches the use of model compression to make FL more accessible to IoT Edge devices. First, a flexible test environment is created that can emulate clients with biased data samples. Each compressed version of the ML model is used for FL. Evaluation is done regarding resources used and the overall ML model performance. Our current study shows an accuracy improvement of 1.16% from modifying training parameters, but a balance is needed to prevent overfitting. Model compression can reduce resource usage by 5.42% but tends to accelerate overfitting and increase model loss by 9.35%
(PANDEMIC Covid-19): A Shooter Game for Education - the Impact Measurement of War Games on Virus Eradication Lessons for Students
No full text(PANDEMIC Covid-19) is an educational shooter game inspired by the Covid-19 pandemic which occurred from the end of 2019 until early 2022. There are 2 game modes, namely Third-Person Shooter, or TPS, and First-Person Shooter, or FPS. This study was carried out to highlight the absence of a shooter genre game used in the student learning process. The research methodology in the development of this game applied the pressman method, and the stages include planning, analysis, game development and artificial intelligence, implementation, as well as  evaluation. Furthermore, the testing phase used software testing techniques based on the ISO 9126 standard and involved a total of 100 participants. The age range was between 17 and 20 years, while the participants' gender percentages were 55% male and 45% female. Some of the factors tested include functionality, reliability, portability, usability, efficiency, and maintainability. There were 2 choices only in this test, i.e. agree and disagree. The functionality factor had an agreed rate of 85%; reliability 79%, portability 86%, usability 83%, efficiency 79%, and maintainability 87%. Therefore, it was concluded that this game is suitable for use in student learning in the shooter genre. Furthermore, this research was inspired because shooter games have not been developed for the student learning process. This game genre is currently used for hobbies and for profit by developers and professional players. Further research should develop game levels, enable features to play online together with other users, and should be extended to Android and IOS.Â
Determining the Rice Seeds Quality Using Convolutional Neural Network
Get PDFSeed inspection is crucial for plant nurseries and farmers as it ensures seed quality when growing seedlings. It is traditionally accomplished by expert inspectors filtering samples manually, but there are some challenges, such as cost, accuracy, and large numbers. Speed and accuracy were the main conditions for increasing agricultural productivity. Machine learning is a sub-science of Artificial Intelligence that can be applied in research on the classification of rice seed quality. The pipeline of a machine learning system is dataset collection, training, validation, and testing. Model making begins with taking data on the characteristics of rice seeds based on physical parameters in the form of seed shape and color. The dataset used is two thousand images divided into two categories, namely superior seeds and non-superior seeds. Training and Validation was conducted using the Convolutional Neural Network (CNN) algorithm with the concept of cross-validation on Google Collaboratory notebooks. The ratio split of train data and validation data in modeling from a dataset is 80:20. The result of the model formed is a model with the development of a Deep Convolutional Neural Network (Deep CNN) that can classify the digital image data of rice seeds from the results of data calls uploaded into the system. The results of the experiment conducted on 30 test data can be analyzed so that the system can classify superior and non-superior seeds with a precision value of 93% and a recall of 95%
Implementation of CRNN Method for Lung Cancer Detection based on Microarray Data
Get PDFLung Cancer is one of the cancer types with the most significant mortality rate, mainly because of the disease's slow detection. Therefore, the early identification of this disease is crucial. However, the primary issue of microarray is the curse of dimensionality. This problem is related to the characteristic of microarray data, which has a small sample size yet many attributes. Moreover, this problem could lower the accuracy of cancer detection systems. Various machines and deep learning techniques have been researched to solve this problem. This paper implemented a deep learning method named Convolutional Recurrent Neural Network (CRNN) to build the Lung Cancer detection system. Convolutional neural networks (CNN) are used to extract features, and recurrent neural networks (RNN) are used to summarize the derived features. CNN and RNN methods are combined in CRNN to derive the advantages of each of the methods. Several previous research uses CRNN to build a Lung Cancer detection system using medical image biomarkers (MRI or CT scan). Thus, the researchers concluded that CRNN achieved higher accuracy than CNN and RNN independently. Moreover, CRNN was implemented in this research by using a microarray-based Lung Cancer dataset. Furthermore, different drop-out values are compared to determine the best drop-out value for the system. Thus, the result shows that CRNN gave a higher accuracy than CNN and RNN. The CRNN method achieved the highest accuracy of 91%, while the CNN and RNN methods achieved 83% and 71% accuracy, respectively
IP-Light Technologies Gen 2: Intervention Tools on IPLT for Trauma, Phobia, and Psychological Problems
Get PDFAs the fourth industrial revolution guides humanity toward the next stage of civilization, there have been various changes across multiple domains of life. The youngest generations now face a new era in which unexpected problems continuously arise and evolve. Consequently, innovation is needed, especially in psychology and technology. This innovation is important because of the increasing number of issues that plague human life, especially psychological problems, trauma, and phobias. However, modern psychology has not kept pace with these developments. Based on this, the researchers developed a tool called IP-Light Technologies. This tool was developed using a research and development approach. Product testing in the form of prototypes is limited and widely carried out in West Nusa Tenggara, West Sumatra, DKI Jakarta, and Bali. As a result of testing, the final prototype was widely produced. The perceptual light prototype comprises a set of lamps and a multiplicity of LED lights extending in horizontal wings spaced concerning the main handle; an elongated handle extending from the main handle in the opposite direction, vertically to horizontally; a linear array of illuminated displays located on the display surface of the handle; and numerous control switches mounted on the casing. The device further comprises a power supply, and control circuit wherein the LEDs on both wings are arranged in an array configured so that the combination of each bulb may project high-intensity light. A lamp clip with a spring design can be clipped on the edge of a table or any other surface
Design of Audio-Based Accident and Crime Detection and Its Optimization
Get PDFThe development of transportation technology is increasing every day; it impacts the number of transportation and their users. The increase positively impacts the economy's growth but also has a negative impact, such as accidents and crime on the highway. In 2018, the number of accidents in Indonesia reached 109,215 cases, with a death rate of 29,472 people, which was mostly caused by the late treatment of the casualties. On the other hand, in the same year, there were 8,423 mugs, and 90,757 snitches cases in Indonesia, with only 23.99% of cases reported. This low reporting rate is mostly caused by the lack of awareness and knowledge about where to report. Therefore, a quick response surveillance system is needed. In this study, an audio-based accident and crime detection system was built using a neural network. To improve the system's robustness, we enhance our dataset by mixing it with certain noises which likely to occur on the road. The system was tested with several parameters of segment duration, bandpass filter cut-off frequency, feature extraction, architecture, and threshold values to obtain optimal accuracy and performance. Based on the test, the best accuracy was obtained by convolutional neural network architecture using 200ms segment duration, 0.5 overlap ratio, 100Hz and 12000Hz as bandpass cut-off frequency, and a threshold value of 0.9. By using mentioned parameters, our system gives 93.337% accuracy. In the future, we hope to implement this system in a real environment
Geometry Representation Effectiveness in Improving Airfoil Aerodynamic Coefficient Prediction with Convolutional Neural Network
Get PDFMany applications use symmetric or asymmetric airfoils, such as aircraft design, wind turbines, and heat transfer. Each airfoil has different aerodynamic coefficients. Obtaining the aerodynamic coefficients is a must to optimize the airfoil design. Engineers use various methods to get the airfoil aerodynamic coefficients. A prediction method is an approximation approach that effectively reduces time and cost. This article uses convolutional neural networks (CNN) to get approximation values of those coefficients. In CNN, we collect 8920 aerodynamic coefficients for 223 NACA 4 as labels in datasets by using XFOIL at  and  with varying angles of attacks starting  to  with increment of . The simulation results are compared to the experiment using E387 airfoil for validation. Then, airfoil geometries as part of input datasets were transformed into Grayscale and RGB images using the signed distance function (SDF) and mesh algorithm. Each airfoil representation was trained using an 80% dataset and tested using a 20% dataset with Adam as an optimizer to generate each prediction model using modified LeNet-5. We use three different layer depths in modified LeNet-5 to obtain the optimal layer number. There is no remarkable improvement when varying the depth layers, so four layers are used instead. Simulation results show that using an SDF with Fast Marching Method on CNN predicts the most effective for the airfoil’s lift, drag, and pitch moment coefficient with varying angles of attack simultaneously. One can extend the method by using SDF to recognize different flow conditions
Improvement of Starling Image Classification with Gabor and Wavelet Based on Artificial Neural Network
Get PDFIndonesia is a country that has a diversity of animal species with the top 10 predicate in the world. The population of animal species, including starlings, is very widely known in the country. Starlings currently in Indonesia are diverse, ranging from standard to rare in Indonesia. This starling has its characteristics based on the type, color, sound, etc. In the first problem, the first accuracy performance when using the GLCM texture feature with Artificial Neural Network is 68%. Furthermore, the second problem is the accuracy performance of typing using the GLCM texture feature with a Decision Tree of 50%. This research aims to improve the starling classification system accuracy using Gabor and Wavelet texture features with artificial Neural Networks. Based on testing in the classification of starlings using the GLCM, Gabor, and Wavelet features, the highest degree of precision can, therefore, be concluded to be at the GLCM and Wavelet feature levels. The GLCM and Wavelet level accuracy results reached 83% at a rate of learning 0.9. In the experiments that have been done, the GLCM and Wavelet levels can increase accuracy using Artificial Neural Networks. In the classification process, the type of starlings also shows that the computational time in testing is much faster in producing accuracy values. In addition, the accurate accuracy while testing the starling category also increases
Software Quality Measurement for Functional Suitability, Performance Efficiency, and Reliability Characteristics Using Analytical Hierarchy Process
Get PDFThe quality model used in this paper is ISO 25010. Functional Suitability, Performance Efficiency, and Reliability are the characteristics to be used. The case study used is the ITS Academic Information System, and the method used for the basis of calculation is the AHP (Analytical Hierarchy Process) method. The initial stage is to make a list of questionnaire questions, which are then filled out by three stakeholders: experts, students, and developers. With the AHP method, experts will analyze the questionnaire results to determine the required weight. This weight is used to calculate the quality of the software. There are two types of software measurements: student questionnaires and developer questionnaires. These two questionnaires become data input. Automatic measurements are carried out on Time Behavior aspects, namely Response Time Testing. In the automatic measurement stage, the URL to be tested by the tester is used as data input. From this automatic measurement, we experimented with the response time of the destination URL to respond to requests and conversion results on a scale of one hundred. The final value of these two types of measurements will be used in several equations to get the final value of the quality of the software. The study results are in the form of automatic measuring instruments of software quality. The measurement results can be used as feedback in making improvements so that the quality value increases when measured. Regarding Functional Suitability, the ITS Academic Information System has provided features according to user needs. In the aspect of Performance Efficiency, the ITS Academic Information System can provide performance and performance according to user needs. Meanwhile, regarding reliability, the ITS Academic Information System can carry out a function under certain conditions and time
Assessing Rural Community Empowerment through Community Internet Centre: Using Asset Mapping and Surveys Method
Get PDFThis paper assesses community empowerment through Community Internet Centre. Community empowerment is a process of the outcome made by the community to take action and change or improve the community's quality of life. Hence, adopting Information and Communication Technology would bridge the digital divide in rural areas. The digital divide affected rural community development through numerous barriers that widened the gap between urban and rural communities, consequently generating an imbalance in community development. The community internet center can bridge the digital divide among urban and rural communities. Asset mapping and surveys have been measured to assess rural community empowerment dimensions through distributed questionnaires to eight Community Internet Centres in rural areas of Kelantan. The findings indicate that the Internet Centre is a medium to encourage community empowerment. The Internet Centre bridges the digital divide among communities by providing Information and Communications Technology community building in rural areas. Hence, the center drives community empowerment and improves the quality of life in rural communities. Thus, Community Internet Centre prepared an appropriate platform for empowering the rural community. This is evidence based on the outcome of findings which resulted in three domains of community empowerment: (1) community participation, (2) ownership, and (3) information services. Nevertheless, community participation determined the outcomes of the roles played by the center to empower a community. Further study needs to be conducted in other groups of samples and gaining other perspectives from managerial of the internet center to get different views of the internet center program