Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315335
Shinta Amalia Kusuma Wardhani, A. P. Subriadi
Social commerce is a new trend in online shopping, which is different from e-commerce. Nowadays, social commerce is widely used because it complements the benefits of using traditional e-commerce with social interaction. Based on this condition, research on the adoption of social commerce has become the interest of new research increasingly being explored. Research on social commerce is novel and largely fragmented. It is theoretically important to evaluate what has been learned and gain meaningful insights through structured literature reviews. This study conducted a systematic literature review on the adoption of social commerce, analyzed based on the context, theories, and influencing factors. We identified 30 studies most relevant to the application of social commerce. The results of this systematic literature review have mapped the potential and direction of research related to the area of interest. Directions for further research will be discussed at the end of the paper.
{"title":"Consumer Behavior in Social Commerce Adoption: Systematic Literature Review","authors":"Shinta Amalia Kusuma Wardhani, A. P. Subriadi","doi":"10.1109/ISRITI51436.2020.9315335","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315335","url":null,"abstract":"Social commerce is a new trend in online shopping, which is different from e-commerce. Nowadays, social commerce is widely used because it complements the benefits of using traditional e-commerce with social interaction. Based on this condition, research on the adoption of social commerce has become the interest of new research increasingly being explored. Research on social commerce is novel and largely fragmented. It is theoretically important to evaluate what has been learned and gain meaningful insights through structured literature reviews. This study conducted a systematic literature review on the adoption of social commerce, analyzed based on the context, theories, and influencing factors. We identified 30 studies most relevant to the application of social commerce. The results of this systematic literature review have mapped the potential and direction of research related to the area of interest. Directions for further research will be discussed at the end of the paper.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134297802","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}
Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315510
Fauzi Dwi Setiawan Sumadi, Christian Sri Kusuma Aditya
Software Defined Network (SDN) allows the separation of a control layer and data forwarding at two different layers. However, centralized control systems in SDN is vulnerable to attacks namely distributed denial of service (DDoS). Therefore, it is necessary for developing a solution based on reactive applications that can identify, detect, as well as mitigate the attacks comprehensively. In this paper, an application has been built based on machine learning methods including, Support Vector Machine (SVM) using Linear and Radial Basis Function kernel, K-Nearest Neighbor (KNN), Decision Tree (DTC), Random Forest (RFC), Multi-Layer Perceptron (MLP), and Gaussian Naïve Bayes (GNB). The paper also proposed a new scheme of DDOS dataset in SDN by gathering considerably static data form using the port statistic. SVM became the most efficient method for identifying DDoS attack successfully proved by the accuracy, precision, and recall approximately 100% which could be considered as the primary algorithm for detecting DDoS. In term of the promptness, KNN had the slowest rate for the whole process, while the fastest was depicted by GNB.
软件定义网络(SDN)允许在两个不同的层分离控制层和数据转发。然而，SDN中的集中控制系统容易受到分布式拒绝服务(DDoS)攻击。因此，有必要开发基于响应性应用程序的解决方案，以全面识别、检测和减轻攻击。在本文中，基于机器学习方法建立了一个应用程序，包括使用线性和径向基函数核的支持向量机(SVM)， k -最近邻(KNN)，决策树(DTC)，随机森林(RFC)，多层感知器(MLP)和高斯Naïve贝叶斯(GNB)。本文还提出了一种在SDN中利用端口统计收集大量静态数据形式的DDOS数据集的新方案。支持向量机的准确率、精密度和召回率均接近100%，是最有效的DDoS攻击识别方法，可以作为DDoS检测的主要算法。在快速性方面，KNN在整个过程中速度最慢，GNB最快。
{"title":"Comparative Analysis of DDoS Detection Techniques Based on Machine Learning in OpenFlow Network","authors":"Fauzi Dwi Setiawan Sumadi, Christian Sri Kusuma Aditya","doi":"10.1109/ISRITI51436.2020.9315510","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315510","url":null,"abstract":"Software Defined Network (SDN) allows the separation of a control layer and data forwarding at two different layers. However, centralized control systems in SDN is vulnerable to attacks namely distributed denial of service (DDoS). Therefore, it is necessary for developing a solution based on reactive applications that can identify, detect, as well as mitigate the attacks comprehensively. In this paper, an application has been built based on machine learning methods including, Support Vector Machine (SVM) using Linear and Radial Basis Function kernel, K-Nearest Neighbor (KNN), Decision Tree (DTC), Random Forest (RFC), Multi-Layer Perceptron (MLP), and Gaussian Naïve Bayes (GNB). The paper also proposed a new scheme of DDOS dataset in SDN by gathering considerably static data form using the port statistic. SVM became the most efficient method for identifying DDoS attack successfully proved by the accuracy, precision, and recall approximately 100% which could be considered as the primary algorithm for detecting DDoS. In term of the promptness, KNN had the slowest rate for the whole process, while the fastest was depicted by GNB.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"76 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130604960","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}
Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315498
Ainul Fitriyah Lubis, Basari
COVID-19 contact tracing is one of preventive solution to slow down the spread of the virus. Some of countries have been implementing manual contact tracing and also digital tracing using smartphone application. The success of the digital tracing implementation requires cooperation from the community and firm leadership from the government as well as medical record reporting from the public health so that the data can be analyzed as soon as possible for the next preventive action required. However, for countries with large population like Indonesia, it is difficult to control the society while the health facilities are quite overwhelmed enough to cope with the number of infected, which has not decreased to date. Proximity-based COVID-19 contact tracing system devices using BLE (Bluetooth Low Energy) technology is focusing on tracing and controlling the spread of virus in local community. For example, the system devices will be implemented in a factory, the devices are put in front pocket of factory employee' shirt or hooked on the shirt. The devices will record the proximity between employees and the data is synchronized using their smartphone or via application to be stored in database. The proximity records will be used once there is an infected employee to obtain information of possibility of other employees are being infected, to avoid massive test and isolation. In addition, the use of this device can be expanded even further.
{"title":"Proximity-Based COVID-19 Contact Tracing System Devices for Locally Problems Solution","authors":"Ainul Fitriyah Lubis, Basari","doi":"10.1109/ISRITI51436.2020.9315498","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315498","url":null,"abstract":"COVID-19 contact tracing is one of preventive solution to slow down the spread of the virus. Some of countries have been implementing manual contact tracing and also digital tracing using smartphone application. The success of the digital tracing implementation requires cooperation from the community and firm leadership from the government as well as medical record reporting from the public health so that the data can be analyzed as soon as possible for the next preventive action required. However, for countries with large population like Indonesia, it is difficult to control the society while the health facilities are quite overwhelmed enough to cope with the number of infected, which has not decreased to date. Proximity-based COVID-19 contact tracing system devices using BLE (Bluetooth Low Energy) technology is focusing on tracing and controlling the spread of virus in local community. For example, the system devices will be implemented in a factory, the devices are put in front pocket of factory employee' shirt or hooked on the shirt. The devices will record the proximity between employees and the data is synchronized using their smartphone or via application to be stored in database. The proximity records will be used once there is an infected employee to obtain information of possibility of other employees are being infected, to avoid massive test and isolation. In addition, the use of this device can be expanded even further.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122094232","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}
Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315399
M. S. Gitakarma, T. K. Priyambodo, Y. Suyanto, R. Sumiharto, Danur Wijayanto
Microelectronic technology that supports the establishment of wireless sensor networks (WSN) has brought hope to the ease of Internet of Things (IoT) technology that can generate smart environments. A WSN consists of a collection of sensor nodes that are small, intelligent, and inadequate in storage, energy, and processing power. One of the well-known routing techniques in WSN is LEACH. There have been many LEACH studies and their development with random node distribution. Here we designed several scenarios in WSN routing with the position of the sensor nodes specified in the mapping area. MATLAB simulation results show network lifetime can be extended by reducing data packet size. In five experiments, the number of 40 nodes was the optimal number to extend network lifetime. Each scenario has advantages and disadvantages that can be referenced in developing the LEACH protocol.
{"title":"Designing Wireless Sensor Network Routing on Agriculture Area Using The LEACH Protocol","authors":"M. S. Gitakarma, T. K. Priyambodo, Y. Suyanto, R. Sumiharto, Danur Wijayanto","doi":"10.1109/ISRITI51436.2020.9315399","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315399","url":null,"abstract":"Microelectronic technology that supports the establishment of wireless sensor networks (WSN) has brought hope to the ease of Internet of Things (IoT) technology that can generate smart environments. A WSN consists of a collection of sensor nodes that are small, intelligent, and inadequate in storage, energy, and processing power. One of the well-known routing techniques in WSN is LEACH. There have been many LEACH studies and their development with random node distribution. Here we designed several scenarios in WSN routing with the position of the sensor nodes specified in the mapping area. MATLAB simulation results show network lifetime can be extended by reducing data packet size. In five experiments, the number of 40 nodes was the optimal number to extend network lifetime. Each scenario has advantages and disadvantages that can be referenced in developing the LEACH protocol.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124187931","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}
Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315503
Eny Sukani Rahayu, D. D. Ariananda, Risanuri Hidayat
Development of radar signal processing is still emerging until this age including its capability to detect targets. In this paper, spatial compressive beamforming (SCB) method based on compressive sensing (CS) is applied in spatial domain studied to improve the azimuth angle estimation (AAE) of received backscatter FMCW signals as well as beamforming algorithm. Since only few azimuth angles occupied by the signals, in single snapshot form, they present sparse signals that can be reconstructed using a sparse recovery method such as LASSO. The use of $M$ elements rather than $N$ element where $M < N$ is accomplished by applying compression matrix C from Gaussian matrix and yields a compressive array. The rffect of noise power to acuuracy of the reconstruction is investigated. Performance of SCB compared to classical beamforming is evaluated as well in case of close and far targets. Results show the azimuth resolution of SCB with 181 angular grid points can reach up to 2 degree accurately while classical beamforming gives lower resolution about 15 degree. By choosing the regularization parameter $lambda$ carefully in SCB, the replicated single snapshot backscatters are accurate enough since relative true error (RTE) achieves 0.85% for two closely adjacent targets less than 15 degree where classical beamforming presents 253.34%.
{"title":"Single Snapshot-Spatial Compressive Beamforming for Azimuth Estimation and Backscatter Reconstruction","authors":"Eny Sukani Rahayu, D. D. Ariananda, Risanuri Hidayat","doi":"10.1109/ISRITI51436.2020.9315503","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315503","url":null,"abstract":"Development of radar signal processing is still emerging until this age including its capability to detect targets. In this paper, spatial compressive beamforming (SCB) method based on compressive sensing (CS) is applied in spatial domain studied to improve the azimuth angle estimation (AAE) of received backscatter FMCW signals as well as beamforming algorithm. Since only few azimuth angles occupied by the signals, in single snapshot form, they present sparse signals that can be reconstructed using a sparse recovery method such as LASSO. The use of $M$ elements rather than $N$ element where $M < N$ is accomplished by applying compression matrix C from Gaussian matrix and yields a compressive array. The rffect of noise power to acuuracy of the reconstruction is investigated. Performance of SCB compared to classical beamforming is evaluated as well in case of close and far targets. Results show the azimuth resolution of SCB with 181 angular grid points can reach up to 2 degree accurately while classical beamforming gives lower resolution about 15 degree. By choosing the regularization parameter $lambda$ carefully in SCB, the replicated single snapshot backscatters are accurate enough since relative true error (RTE) achieves 0.85% for two closely adjacent targets less than 15 degree where classical beamforming presents 253.34%.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126285946","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}
Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315462
M. Muharram, S. Suyanto
Long-Term Evolution (LTE), also known as the 4th generation (4G) is a system currently seen as a development system of UMTS/HSPA, which is one of the 3rd generation (3G) evolutions. One of the supporting components of the LTE network is ENodeB. An ENodeB can be analogous to a Base Transceiver Station (BTS). As customer needs are increasing, the need for BTS (ENodeB) is also increasing. It causes a large number of base stations. On the other hand, the construction of new base stations will certainly cost a lot and cause temper the city's landscape. Therefore, it is necessary to optimize the BTS placement. Hence, in this research, we design a simulation of BTS placement optimization using the firefly algorithm (FA) with the parameter to be optimized is the coverage area and traffic. The fitness value obtained from this study reached 97.73% and reduced existing BTS by 50%. This fitness is comparable with the hybrid evolutionary FA (HEFA)-based model, which produces an average fitness of 98.62%.
{"title":"Firefly Algorithm-based Optimization of Base Transceiver Station Placement","authors":"M. Muharram, S. Suyanto","doi":"10.1109/ISRITI51436.2020.9315462","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315462","url":null,"abstract":"Long-Term Evolution (LTE), also known as the 4th generation (4G) is a system currently seen as a development system of UMTS/HSPA, which is one of the 3rd generation (3G) evolutions. One of the supporting components of the LTE network is ENodeB. An ENodeB can be analogous to a Base Transceiver Station (BTS). As customer needs are increasing, the need for BTS (ENodeB) is also increasing. It causes a large number of base stations. On the other hand, the construction of new base stations will certainly cost a lot and cause temper the city's landscape. Therefore, it is necessary to optimize the BTS placement. Hence, in this research, we design a simulation of BTS placement optimization using the firefly algorithm (FA) with the parameter to be optimized is the coverage area and traffic. The fitness value obtained from this study reached 97.73% and reduced existing BTS by 50%. This fitness is comparable with the hybrid evolutionary FA (HEFA)-based model, which produces an average fitness of 98.62%.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126324515","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}
Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315460
M. T. Anwar, W. Hadikurniawati, Edy Winarno, W. Widiyatmoko
Rain prediction is a crucial topic that continues to gain interest across the globe. Rain has a massive impact on various aspects of human life such as in agriculture, health, transportation, etc, and also some natural disasters. Various impacts of rain on human life prompts us to build a model to understand and predict rain to provide early warning for various use cases in various fields. Previous research on rain modeling using Data Mining (DM) techniques had suffered from low accuracy caused by the limited availability of the training data and their meteorological attributes. This research aims to address those issues by building the rain model using a richer and more abundant rain data in Indonesia. Four DM techniques are used and compared in this research i.e. the C4.5/J48, Random Forest (RF), Naïve Bayes (NB), and Multilayer Perceptron (MLP). The experimental results showed that the MLP and J48 algorithm can provide the best accuracy (up to 78,4%), which is better than previous research. Other key findings in this research include: (a) the selection of DM techniques has little effect on the model accuracy; (b) a larger training dataset generally improves model accuracy and a larger test dataset is necessary to get a representative realworld test accuracy, and (c) the two most influential attributes in rain modeling are the relative humidity and the minimum temperature, and we suggest to include cloud condensation nuclei in the next research to complete the model.
{"title":"Performance Comparison of Data Mining Techniques for Rain Prediction Models in Indonesia","authors":"M. T. Anwar, W. Hadikurniawati, Edy Winarno, W. Widiyatmoko","doi":"10.1109/ISRITI51436.2020.9315460","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315460","url":null,"abstract":"Rain prediction is a crucial topic that continues to gain interest across the globe. Rain has a massive impact on various aspects of human life such as in agriculture, health, transportation, etc, and also some natural disasters. Various impacts of rain on human life prompts us to build a model to understand and predict rain to provide early warning for various use cases in various fields. Previous research on rain modeling using Data Mining (DM) techniques had suffered from low accuracy caused by the limited availability of the training data and their meteorological attributes. This research aims to address those issues by building the rain model using a richer and more abundant rain data in Indonesia. Four DM techniques are used and compared in this research i.e. the C4.5/J48, Random Forest (RF), Naïve Bayes (NB), and Multilayer Perceptron (MLP). The experimental results showed that the MLP and J48 algorithm can provide the best accuracy (up to 78,4%), which is better than previous research. Other key findings in this research include: (a) the selection of DM techniques has little effect on the model accuracy; (b) a larger training dataset generally improves model accuracy and a larger test dataset is necessary to get a representative realworld test accuracy, and (c) the two most influential attributes in rain modeling are the relative humidity and the minimum temperature, and we suggest to include cloud condensation nuclei in the next research to complete the model.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124332346","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}
Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315480
Damai Bela Nusantara, L. M. Putranto, Sarjiya, S. Isnandar, Thomas Kristian Yudhantomo
Sulawesi's electricity system needs to maintain the sustainability of the electricity supply which is stable, reliable, safe, eco-friendly, and able to meet the needs of the community. For that reason, the transmission expansion-planning program 2018-2050 is proposed. Considering the load growth, primary energy, and the power flow, it is necessary to build the transmission backbone, which for Indonesian case maybe 275 kV or 500 kV. The determination of the backbone's voltage requires some criteria, one of them is to performing contingency analysis which can be obtained by performance index analysis. Performance index analysis, consist of voltage performance index and active power performance index, is simulated using the DIg-SILENT PowerFactory 15.1.7 software for two generation planning scenarios, regional balanced and resourced based. If the transmission system has exceeded the level of set severity of the contingency case, it is necessary to choose the 500 kV Extra High Voltage Overhead Transmission Line.
{"title":"Analysis of Performance Index in Transmission Expansion Planning of Sulawesi's Electricity System","authors":"Damai Bela Nusantara, L. M. Putranto, Sarjiya, S. Isnandar, Thomas Kristian Yudhantomo","doi":"10.1109/ISRITI51436.2020.9315480","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315480","url":null,"abstract":"Sulawesi's electricity system needs to maintain the sustainability of the electricity supply which is stable, reliable, safe, eco-friendly, and able to meet the needs of the community. For that reason, the transmission expansion-planning program 2018-2050 is proposed. Considering the load growth, primary energy, and the power flow, it is necessary to build the transmission backbone, which for Indonesian case maybe 275 kV or 500 kV. The determination of the backbone's voltage requires some criteria, one of them is to performing contingency analysis which can be obtained by performance index analysis. Performance index analysis, consist of voltage performance index and active power performance index, is simulated using the DIg-SILENT PowerFactory 15.1.7 software for two generation planning scenarios, regional balanced and resourced based. If the transmission system has exceeded the level of set severity of the contingency case, it is necessary to choose the 500 kV Extra High Voltage Overhead Transmission Line.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121500658","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}
Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315434
R. Delfianti, A. Soeprijanto, A. Priyadi, Avian Lukman Setya Budi, I. Abadi
Renewable energy provides the healthiest options for generating electricity. On the on-grid and off-grid systems can be connected with renewable energy. The main problem in stand-alone off-grid photovoltaic systems is the stability of the power during sudden clouds. A grid system requires storage. Each storage has its positive and negative characteristics. The energy management system acts as a search for a more optimal combination of energy utilization. The main objective is to compare passive filter usage as components in an energy management system between battery and supercapacitor energy storage. The result is that a high-pass filter gives the best results. Undershoot has decreased by 26,464 Watts and overshoot by 10,586 Watts, but the power reserved is reduced by 81,083 Watts due to the large self-discharge effect supercapacitor and increased the steady-state time by 0.0241 seconds.
{"title":"Energy Management Efficiency and Stability Using Passive Filter in Standalone Photovoltaic Sudden Cloud Condition","authors":"R. Delfianti, A. Soeprijanto, A. Priyadi, Avian Lukman Setya Budi, I. Abadi","doi":"10.1109/ISRITI51436.2020.9315434","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315434","url":null,"abstract":"Renewable energy provides the healthiest options for generating electricity. On the on-grid and off-grid systems can be connected with renewable energy. The main problem in stand-alone off-grid photovoltaic systems is the stability of the power during sudden clouds. A grid system requires storage. Each storage has its positive and negative characteristics. The energy management system acts as a search for a more optimal combination of energy utilization. The main objective is to compare passive filter usage as components in an energy management system between battery and supercapacitor energy storage. The result is that a high-pass filter gives the best results. Undershoot has decreased by 26,464 Watts and overshoot by 10,586 Watts, but the power reserved is reduced by 81,083 Watts due to the large self-discharge effect supercapacitor and increased the steady-state time by 0.0241 seconds.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122705160","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}
Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315423
Máté Pethő, Ádám Nagy, T. Zsedrovits
Unmanned aerial vehicles (UAVs) becoming more and more common. They show excellent potential for multiple types of autonomous work, although they must achieve these tasks safely. For flight-safety, it must be assured that the UAV will avoid collision with any objects in its flight path during autonomous operations. Computer vision and artificial neural networks have shown to be effective in many applications. However, biological vision systems and the brain areas responsible for visual processing may hold solutions capable of acquiring information effectively. We are proposing a novel system, which performs visual cue extraction with algorithms based on the structure and functionality of the retina and the visual cortex of the mammalian visual system, and a convolutional neural network processing data to detect a predefined obstacle using the onboard camera of the UAV. We also examined the effect of preprocessing on calculation time and recognition effectiveness.
{"title":"A bio-motivated vision system and artificial neural network for autonomous UAV obstacle avoidance","authors":"Máté Pethő, Ádám Nagy, T. Zsedrovits","doi":"10.1109/ISRITI51436.2020.9315423","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315423","url":null,"abstract":"Unmanned aerial vehicles (UAVs) becoming more and more common. They show excellent potential for multiple types of autonomous work, although they must achieve these tasks safely. For flight-safety, it must be assured that the UAV will avoid collision with any objects in its flight path during autonomous operations. Computer vision and artificial neural networks have shown to be effective in many applications. However, biological vision systems and the brain areas responsible for visual processing may hold solutions capable of acquiring information effectively. We are proposing a novel system, which performs visual cue extraction with algorithms based on the structure and functionality of the retina and the visual cortex of the mammalian visual system, and a convolutional neural network processing data to detect a predefined obstacle using the onboard camera of the UAV. We also examined the effect of preprocessing on calculation time and recognition effectiveness.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115552235","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：