{"title":"Modeling Domestic Solar Generation Profiles Using Elbow and K-Means Clustering Techniques","authors":"Hanis Nasuha Binti Amer, M. Latip, N. Zaini","doi":"10.1109/ICSET57543.2022.10011009","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10011009","url":null,"abstract":"Solar photovoltaic (PV) power generation started growing at the second-fastest rate of all renewable energy technologies in 2020. Researchers and power generation industries are progressively interested in discussing the behavior analysis of solar energy to daily weather patterns over time. Previous research has often proposed clustering techniques to evaluate solar PV production profiles that are mainly focused on large-scale PV facilities. Therefore, this study explores domestic solar energy clustering techniques to develop a cluster-based representation of solar generation behavior profiles by using solar data collected from single-phase home solar panels of a residence located at Setia Alam, Selangor, Malaysia. Elbow and K-Means clustering approaches were used to classify the entire data into three clusters based on similar meteorological parameters developed using the Python programming language. Data analysis was then performed to determine the correlation coefficient between PV power output and weather conditions. Due to the high ambient temperature and low humidity, it is observed that March 2022 has the potential to produce the largest percentage value of clustered data in high solar generation, with a value of 25.27% ranging from 2839 to 4867W. The results of this study offer a technique that users can apply to evaluate the overall behavior profile of existing residential solar PV systems.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132596071","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}
Dhimas Bintang Kusumawardhana, B. Trilaksono, Harits Abdurrohman
{"title":"Panoptic Segmentation Datasets for Rail-based Autonomous Vehicle Under Mixed-traffic Scenario","authors":"Dhimas Bintang Kusumawardhana, B. Trilaksono, Harits Abdurrohman","doi":"10.1109/ICSET57543.2022.10010755","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10010755","url":null,"abstract":"The challenge of percept the complex environment through visual recognition has turned the tide of research on image recognition toward panoptic segmentation by unifying the distinct task of instance and semantic segmentation into a single architecture. This work applies panoptic segmentation for the inner-city tram in the environment where the railway intersects with the road. Our study on Cityscapes, COCO-Stuff, and RailSem19 public datasets has limitations due to unsuitable semantic and instance masks for our mixed traffic scenario. Thus, we consider creating our self-curated dataset, which was collected on the route of the Batara Kresna railbus, for the model to generalize our local context better. The data consists of a combination of 1000 frames of images with a dense-pixel panoptic annotation. Among those sets, 200 of them are specified and taken using the front camera to maximize the occurrence of the railway. We decided to calculate the occurrence of an object and class distribution as an initial data quality assessment.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129516593","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":"ICSET2022 COMMITTEE","authors":"","doi":"10.1109/icset57543.2022.10010977","DOIUrl":"https://doi.org/10.1109/icset57543.2022.10010977","url":null,"abstract":"","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115515454","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":"IoT Device Control with Offline Automatic Speech Recognition on Edge Device","authors":"Panji Setiawan, Rahadian Yusuf","doi":"10.1109/ICSET57543.2022.10010962","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10010962","url":null,"abstract":"Automatic speech recognition (ASR) on edge device still barely used in industry. Most of ASR such as speech-to-text commonly depend on the network presence. This is the disadvantages of using the server-based architecture that cannot always be reliable and available. In some conditions, the speech recognition need to be used in offline condition and edge-processing. Raspberry Pi, one of many edge devices will use offline ASR platform with only runs on python language. These platforms will encourage to do speech recognition in offline condition and edge device processing. Vosk, Picovoice/Cheetah, Sopare runs with python language and some of it required Word-Error-Rate (WER) on the result to validate result value. The 5 simple commands trained on each platform. Overall result, these 3 platforms are working well in offline environment with good accuracy (>80%). Vosk has around 84% accuracy, Picovoice/Cheetah has around 72% and Sopare has around 95% accuracy. Picovoice/Cheetah need an internet connection at first application startup.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114862530","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":"Online Learning Facial Expression Detection using Simplified AlexNet Deep Learning Architecture: Image Data Samples Comparison Experiment","authors":"Andhika Rahadian, Rahadian Yusuf","doi":"10.1109/ICSET57543.2022.10011131","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10011131","url":null,"abstract":"Online learning is one of the methods for students to interact with their teachers. However, interactivity aspects in online education should be evaluated. The method to automate the detection of students' enthusiasm when participating in online learning is still not much found. In this paper, we define the facial expressions that could show when students participate in online learning: bored, confused, and excited/delighted. We built a classifier system for these online learning face expressions. We collected a small dataset (for around 480 images) containing face images with these three facial expressions to be trained for the deep learning model. We proposed simplified AlexNet architecture as a deep learning model for a relatively small dataset, that is, AlexNet architecture with lower parameters (such as filters and the number of neurons in the fully connected layer). Image preprocessing methods such as resizing and augmentation are applied for the experiment. We also compare the model performance, given a distinct (three kinds) number of training data (480 samples, 1,500 samples, and 3,000 samples). When our proposed model is trained with these three kinds of training samples amount, the model performance consecutively has an average accuracy of 78.69%, 84.53%, and 90.80% in 5-Fold Cross Validation. Using ANOVA Test, we get a p-value of 0.00073, which is statistically significant to reject the null hypothesis that training samples do not affect our proposed model's accuracy.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115183948","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":"Deep Reinforcement Learning to Automate Cryptocurrency Trading","authors":"D. Mahayana, Elbert Shan, Muhammad Fadhl'Abbas","doi":"10.1109/ICSET57543.2022.10010940","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10010940","url":null,"abstract":"This research produces a deep reinforcement learning model for algorithmic trading of cryptocurrencies. The model aims to help traders earn greater profits than using traditional strategies. Although traditional strategies can generate profits, they require considerable knowledge, experience, and time to generate optimal profits. Models are trained to trade on the cryptocurrency market. Model inputs are 1 minute interval candlestick data and technical indicators for the BTC/USDT cryptocurrency pair. The model produces an output in the form of a buy, hold, or sell signal. Models are created with the PPO algorithm and a custom environment that follows the gym interface. The performance of the model is compared to the Buy and Hold strategy. The tests that have been carried out show that the model produced in this study still cannot beat the Buy and Hold strategy.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124680986","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}
Adi Novitarini Putri, C. Machbub, D. Mahayana, E. Hidayat
{"title":"Linear Quadratic Gaussian using Kalman Network and Reinforcement Learning for Discrete-Time System","authors":"Adi Novitarini Putri, C. Machbub, D. Mahayana, E. Hidayat","doi":"10.1109/ICSET57543.2022.10010824","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10010824","url":null,"abstract":"A problem arises when implementing the control scheme into a system, the limitation of the number of sensors used causes not all state information from the plant can be obtained. In addition, the data measurement process also often contains noise. Therefore, implementing the optimal control scheme directly becomes difficult. The status estimation method proposed in this study utilizes the use of an Artificial Neural Network (ANN) as a function approximation. On the other hand, the development of optimal control implementation has also experienced a fairly massive increase. Some of the existing optimal control solutions can only be carried out offline and depend on the dynamics' model of the system to be controlled. The combination of KalmanNet and the Value Iteration (VI) algorithm is used to adapt the role of the Linear Quadratic Gaussian (LQG) method in designing control procedures to produce high performance. Tests were carried out on a cart-pole system in a discrete-time domain. The use of the combination of these methods could make the closed loop system towards a value of 0 and the evolution of the estimator gain is smoother, namely with the norm of 2.33S4E-04.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130083590","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}
Muhammad Ogin Hasanuddin, Hafizha Novianingrum, Eniman Yunus Syamsuddin
{"title":"Design and Implementation of Drowsiness Detection System Based on Standard Deviation of Lateral Position","authors":"Muhammad Ogin Hasanuddin, Hafizha Novianingrum, Eniman Yunus Syamsuddin","doi":"10.1109/ICSET57543.2022.10010991","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10010991","url":null,"abstract":"Drowsiness can decrease concentration while driving. The decreased concentration while driving makes a slower response in making decisions about road conditions. Roads with monotonous characteristics and low traffic density can also reduce driver alertness. This condition can lead to traffic accidents. However, drivers sometimes do not realize that they are sleepy. Therefore, a system is needed to detect drowsiness and provide warnings to drivers. To overcome that problem, we propose a system for detecting and alerting a driver's sleepiness based on the deviation from the lane. This system is designed using the Python programming language and the OpenCV library. Based on the results of experiments that we have done, the calculation of the Standard Deviation of the Lateral Position accuracy reaches 96.54% during the day and 91.08% at night.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131529400","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}
Muhammad Ogin Hasanuddin, Andaru Purwarangga Arham, Gotawa Aryo Prakoso, B. R. Hermanto
{"title":"Implementation of Progressive Web App-Based Applications for Vehicle Tracking Systems","authors":"Muhammad Ogin Hasanuddin, Andaru Purwarangga Arham, Gotawa Aryo Prakoso, B. R. Hermanto","doi":"10.1109/ICSET57543.2022.10010767","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10010767","url":null,"abstract":"The user has to be able to see the information from the server with ease, so the device's information sent from the server has to be easily accessed by the user. The application has to be made so that users across all platforms can easily access the application. Developing an application that can be accessed on all platforms can make the time to make the app a lot less consuming. Nowadays, web application development has supported web pages with capabilities close to natively developed applications. Progressive Web App, commonly known as PWA, allows for the integration of web-based applications with native applications. PWA is a web application that can enable native applications, especially in developing multi-platform applications that can be accessed by various platforms. In this project, the PWA application was developed in the form of a vehicle-based supporting device that can monitor car location from Internet-of-Things (IoT) devices and prevent an attempt to steal the vehicle. Two interfaces will be made in this project for the car's owner and the police. The car owner can access the car location, and the police can also access it when the car owner makes a report. The police interface is made so that it can track the stolen car with a legal approach. The car owner can access the web application and then change the desired device mode so that when there is a theft indication car owner can report it to the police, and the police can investigate it. The result of this implementation is that the user, who is a car owner and police, can both access the location visualization in the interface, and the interface can be accessed on all platforms.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"417 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132371569","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":"Improving Radar-Camera Fusion-based 3D Object Detection for Autonomous Vehicles","authors":"Irfan Tito Kurniawan, B. Trilaksono","doi":"10.1109/ICSET57543.2022.10011030","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10011030","url":null,"abstract":"Object detection is essential for autonomous driving as it provides knowledge of the state of the surrounding objects. Aside from the objects' 3D bounding boxes, 3D object detection also estimates the objects' velocity and attribute. Radar-camera fusion-based object detection methods have the potential to deliver accurate and robust results even in harsh conditions while being more affordable than lidar-based solutions. However, current radar-camera fusion-based methods are still significantly outperformed by their lidar-based counterparts, even when radar has access to direct velocity measurement which lidar lacks. In this work, we propose a feature-level radar-camera fusion-based object detection architecture. Our architecture associates preliminary detections produced by an image-based pipeline with radar detection clusters using a frustum-based association mechanism. By using radar detection clusters instead of individual points, we can extract features that allow the model to use the geometry of the clusters to refine the preliminary detections. We evaluated our architecture on the nuScenes dataset and achieved a nuScenes detection score (NDS) of 0.465. We also find that our architecture achieved significantly better objects' orientation, velocity, and attribute estimation results compared to other radar-camera fusion-based methods.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117012704","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}