{"title":"New Hybrid Deep Learning Method to Recognize Human Action from Video","authors":"M. Islam, Sunjida Sultana, Md Jabbarul Islam","doi":"10.26555/jiteki.v7i2.21499","DOIUrl":"https://doi.org/10.26555/jiteki.v7i2.21499","url":null,"abstract":"There has been a tremendous increase in internet users and enough bandwidth in recent years. Because Internet connectivity is so inexpensive, information sharing (text, audio, and video) has become more popular and faster. This video content must be examined in order to classify it for different purposes for users. Several machine learning approaches for video classification have been developed to save users time and energy. The use of deep neural networks to recognize human behavior has become a popular issue in recent years. Although significant progress has been made in the field of video recognition, there are still numerous challenges in the realm of video to be overcome. Convolutional neural networks (CNNs) are well-known for requiring a fixed-size image input, which limits the network topology and reduces identification accuracy. Despite the fact that this problem has been solved in the world of photos, it has yet to be solved in the area of video. We present a ten stacked three-dimensional (3D) convolutional network based on the spatial pyramid-based pooling to handle the input problem of fixed size video frames in video recognition. The network structure is made up of three sections, as the name suggests: a ten-layer stacked 3DCNN, DenseNet, and SPPNet. A KTH dataset was used to test our algorithms. The experimental findings showed that our model outperformed existing models in the area of video-based behavior identification by 2% margin accuracy.","PeriodicalId":244902,"journal":{"name":"Jurnal Ilmiah Teknik Elektro Komputer dan Informatika","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134343328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Muhamad Fariz Maulana, S. Sa'adah, Prasti Eko Yunanto
{"title":"Crude Oil Price Forecasting Using Long Short-Term Memory","authors":"Muhamad Fariz Maulana, S. Sa'adah, Prasti Eko Yunanto","doi":"10.26555/JITEKI.V7I2.21086","DOIUrl":"https://doi.org/10.26555/JITEKI.V7I2.21086","url":null,"abstract":"Crude oil has an important role in the financial indicators of global markets and economies. The price of crude oil influences the income of a country, both directly and indirectly. This includes affecting the prices of basic needs, transportation, commodities, and many more. Therefore, understanding the future price of crude oil is essential in helping to budgeting and planning for a better economy. The contribution of this research is in finding the best hyperparameters and using early stopping methods in the LSTM model to predict oil prices. This research implemented Long Short-Term Memory (LSTM), an artificial neural network that can handle long-term dependencies and the problems of time series data. The LSTM method will be used to predict Brent oil prices on daily and weekly time frames. The experiment has been conducted by tuning some parameters to obtain the best result. From the daily time frame experiment, the model obtained RMSE and MAE of 1.27055 and 0.92827, respectively, while the weekly time frame has RMSE and MAE of 3.37817 and 2.60603, respectively. The results show that the LSTM model can improve to the trends that occur in the original data.","PeriodicalId":244902,"journal":{"name":"Jurnal Ilmiah Teknik Elektro Komputer dan Informatika","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121304070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Naufal Fikri, Vito Louis Nathaniel, Muchamad Syahrul Gunawan, T. Abuzairi
{"title":"Design of Real-Time Aquarium Monitoring System for Endemic Fish on the Smartphone","authors":"Naufal Fikri, Vito Louis Nathaniel, Muchamad Syahrul Gunawan, T. Abuzairi","doi":"10.26555/JITEKI.V7I2.21137","DOIUrl":"https://doi.org/10.26555/JITEKI.V7I2.21137","url":null,"abstract":"The high rate of decreasing population of endemic fish species is becoming more severe over time. Therefore, it needed an effort to bring back the stability of the number. One of the reasons for the decreasing population is the changing environment due to climate change and the difficulty of treatment for this species. This research aims to design an aquarium monitoring system for endemic fish. The main components for this system are microcontroller ESP32 DOIT, Temperature Sensors DS18B20, DF Robot Analog pH Sensors, ESP32 Cam, UV Lamp, and Blynk server. The experiment was conducted by monitoring the aquarium environment using sensors and comparing it with the reference sensors. With a monitoring system, we can find out whether the current condition of the aquarium is in accordance with the fish's living environment or not. The monitoring results show that the average error for temperature is 0.14% and for pH is 0.67%. These results indicate that the prototype sensors are linear with reference sensors. Besides that, a real-time monitoring system is easy to use and more attractive because of smartphone utilization to monitor fish with a camera and lamp.","PeriodicalId":244902,"journal":{"name":"Jurnal Ilmiah Teknik Elektro Komputer dan Informatika","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123417372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Irwan Ismail, N. Iksan, S. K. Subramaniam, Azmi Shawkat Abdulbaqie, S. Pillai, I. Y. Panessai
{"title":"Usefulness of Augmented Reality as a Tool to Support Online Learning","authors":"Irwan Ismail, N. Iksan, S. K. Subramaniam, Azmi Shawkat Abdulbaqie, S. Pillai, I. Y. Panessai","doi":"10.26555/JITEKI.V7I2.21133","DOIUrl":"https://doi.org/10.26555/JITEKI.V7I2.21133","url":null,"abstract":"The global crisis following the outbreak of the Covid-19 epidemic has had an impact on the teaching and learning process (PdP). The main problem with PdP during the Covid-19 epidemic was the limitation in conducting face-to-face activities in the classroom. Therefore, a learning aid is needed to enable PdP to run optimally even though there is no face-to-face interaction between teachers and students. The research contribution is to highlight the application of Augmented Reality to support distance learning in the Covid-19 epidemic situation, specializing in Wood Carving Art for the subject of Visual Arts Education Form 4. The AR Wood Carving Art mobile application uses the ADDIE design model based on five phases, namely Analysis, Design, Development, Implementation, and Testing. The AR Wood Carving Art mobile application is evaluated based on its usefulness. The AR Wood Carving Art mobile application was evaluated among 27 students from 4 of SMK Pasir Gudang (Johor, Malaysia) and registered to Visual Arts. Based on the result, 80% of respondents strongly agree that the AR Wood Craving Art mobile application help respondents be more effective. It helps users to be more productive and giving ideas to users to be creative and innovative. One hundred percent of respondents strongly agree that the AR Wood Craving Art mobile application makes things that users want to achieve easier to do, and the AR Wood Craving Art mobile application does what users want. Eighty percent of respondents strongly agree that the AR Wood Craving Art application is useful and the application saves time when users use it. Therefore, the AR Wood Craving Art application is effectively used in learning which makes users more productive, creative, and innovative. In addition, the AR Wood Craving Art mobile application makes it easy for users to understand wood carving topics in visual arts subjects, and users can carry out educational and teaching activities like in a classroom.","PeriodicalId":244902,"journal":{"name":"Jurnal Ilmiah Teknik Elektro Komputer dan Informatika","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128672073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Development of Laboratory Equipment Inventory System Using Radio Frequency and Internet of Things","authors":"M. F. Wicaksono, S. Syahrul, M. D. Rahmatya","doi":"10.26555/JITEKI.V7I2.21114","DOIUrl":"https://doi.org/10.26555/JITEKI.V7I2.21114","url":null,"abstract":"The purpose of this research is to create a laboratory equipment inventory system. With this system, users, namely lecturers, lab assistants, and final project students, can find out the borrower's data, borrowing time, return time, and the tool availability status. The research method used is experimental. This system is based on IoT technology. The main brain from the hardware side uses the NodeMCU ESP8266. NodeMCU, apart from being a controller, can also function as a WiFi module. On the server-side, PHP and MySQL are used. When the user wants to borrow a tool, the user can use an RFID tag to open the cupboard. Furthermore, the NodeMCU will continue to scan for the presence of items in the cupboard using a radio frequency with RF433MHz. This information is sent to the server when the cupboard is closed and locked automatically. The server will receive the information and decipher the information. As a result, the testing process in this study proved that the system has been able to detect the presence of items in the cupboard and track anyone who borrows laboratory equipment with a 100% success percentage.","PeriodicalId":244902,"journal":{"name":"Jurnal Ilmiah Teknik Elektro Komputer dan Informatika","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120984796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Riya Widayanti, Eka Purnama Harahap, Ninda Lutfiani, Fitra Putri Oganda, Ita Sari Perbina Manik
{"title":"The Impact of Blockchain Technology in Higher Education Quality Improvement","authors":"Riya Widayanti, Eka Purnama Harahap, Ninda Lutfiani, Fitra Putri Oganda, Ita Sari Perbina Manik","doi":"10.26555/JITEKI.V7I2.20677","DOIUrl":"https://doi.org/10.26555/JITEKI.V7I2.20677","url":null,"abstract":"The times have made technology increasingly developed that there are innovations as new media to make it easier for humans in everyday life. Blockchain technology is an innovation that has been applied in various fields such as education, health, economy, and other areas. In this study, researchers want to see the impact that blockchain technology has had on universities in technology and information to improve universities' quality. The methodology used is by reviewing previous research papers related to the research. So that this research is expected to contribute, which can overcome the problems being faced, such as the application of blockchain in universities, namely how to use the blockchain system, what blockchain is, and how to change existing technology into disruptive technology. The experimental results state that by using data from the previous paper, the aim is to reveal the impact that blockchain technology has had on technology and information that is useful for improving the quality of universities in encouraging human potential and improving quality so that they can compete both domestically and abroad.","PeriodicalId":244902,"journal":{"name":"Jurnal Ilmiah Teknik Elektro Komputer dan Informatika","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133630702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Comparative Study of VGG16 and MobileNetV2 for Masked Face Recognition","authors":"Faisal Dharma Adhinata, Nia Annisa Ferani Tanjung, Widi Widayat, Gracia Rizka Pasfica, Fadlan Raka Satura","doi":"10.26555/JITEKI.V7I2.20758","DOIUrl":"https://doi.org/10.26555/JITEKI.V7I2.20758","url":null,"abstract":"Indonesia is one of the countries affected by the coronavirus pandemic, which has taken too many lives. The coronavirus pandemic forces us to continue to wear masks daily, especially when working to break the chain of the spread of the coronavirus. Before the pandemic, face recognition for attendance used the entire face as input data, so the results were accurate. However, during this pandemic, all employees use masks, including attendance, which can reduce the level of accuracy when using masks. In this research, we use a deep learning technique to recognize masked faces. We propose using transfer learning pre-trained models to perform feature extraction and classification of masked face image data. The use of transfer learning techniques is due to the small amount of data used. We analyzed two transfer learning models, namely VGG16 and MobileNetV2. The parameters of batch size and number of epochs were used to evaluate each model. The best model is obtained with a batch size value of 32 and the number of epochs 50 in each model. The results showed that using the MobileNetV2 model was more accurate than VGG16, with an accuracy value of 95.42%. The results of this study can provide an overview of the use of transfer learning techniques for masked face recognition.","PeriodicalId":244902,"journal":{"name":"Jurnal Ilmiah Teknik Elektro Komputer dan Informatika","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133705619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Performance Comparison Modeling Between Single-phase Cycloconverters and Three-phase Cycloconverters Using Matlab Simulink Tools","authors":"Setiyono Setiyono, Bambang Dwinanto","doi":"10.26555/JITEKI.V7I2.20225","DOIUrl":"https://doi.org/10.26555/JITEKI.V7I2.20225","url":null,"abstract":"This paper presents a performance comparison of a single-phase AC to AC converter (cycloconverter) and a three-phase converter circuit which divides the input wave frequency (fin) into a variable frequency with the frequency value of the AC output voltage waveform (alternating current) (f, fin/2, fin/3, fin/4, fin/5, fin/6, fin/7, fin/8, fin/9, fin/10. Cycloconvertor switches are built using a diode and a thyristor device. This research was conducted by modeling each cycloconverter circuit using Matlab Simulink tools. Modeling simulation parameters to be analyzed include the output waveform RMS (root mean square) value, frequency value, and Total Harmonic Distortion (THD) index for each wave. The output frequency voltage waveform of cycloconverter is affected by the variation of the trigger signal of the P-side (positive) converter and the N (negative) converter side switch. Simulation results show that adjusting the firing pulse width of the P converter and the N converter will produce an output voltage wave that has an index value of THD, Vrms, and form factor for each diode and thyristor cycloconverter circuit.","PeriodicalId":244902,"journal":{"name":"Jurnal Ilmiah Teknik Elektro Komputer dan Informatika","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133336064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Analysis of Random Forest, Multiple Regression, and Backpropagation Methods in Predicting Apartment Price Index in Indonesia","authors":"I. Saputra, S. Sa'adah, Prasti Eko Yunanto","doi":"10.26555/JITEKI.V7I2.20997","DOIUrl":"https://doi.org/10.26555/JITEKI.V7I2.20997","url":null,"abstract":"This study focuses on predicting the apartment price index in Indonesia using property survey data from Bank Indonesia. In the era of the Covid-19 pandemic, accurately predicting the sale and purchase price of apartments is essential to minimize the impact of losses, thus making apartment prices attractive to predict. The machine learning approach used to predict the apartment price index are the Random Forest method, the Multiple Regression method, and the Backpropagation method. This study aims to determine which method is more effective in predicting small amounts of data accuracy. The data used is apartment price index data from 2012 to 2019 in the JABODEBEK area. The research will produce prediction accuracy that will determine the effectiveness of the application of the method. The Random Forest method with parameters n_estimators=100 and max_features=”log2” produces an R2 accuracy of 0.977. The Multiple Regression method with a correlation between the selling price and rental price variables is 0.746, and the rental inflation variable is 0.042 produces an R2 accuracy of 0.559. The Backpropagation method with a 1000-4000-1 hidden scheme and 20000 iterations produces an R2 accuracy of 0.996. Therefore, the Backpropagation method is more suitable in this study compared to the other two methods. The Backpropagation method is suitable because it gets almost perfect accuracy, so this method will minimize losses in investing in buying and selling apartments in the Covid-19 pandemic era.","PeriodicalId":244902,"journal":{"name":"Jurnal Ilmiah Teknik Elektro Komputer dan Informatika","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131996376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}