Pub Date : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923450
Median Hardiv Nugraha, Erdefi Rakun
SIBI is the standardized sign language system offi-cially used in Indonesia. The application of SIBI is often found to be a hindrance because there are too many gestures that must be memorized. A mobile-based application is needed as gesture-to-text translator. From Rakun et al., Skin Color Segmentation was used as a method to segment hand and facial features using greenscreen background as dataset (3.367% of WER and 80.180% of SAcc). When this application is used, the gesture video is recorded on complex background but performed poorly (135.180% of WER and 0% of SAcc score). The computational time using Skin Color Segmentation is 0.013 s per frame. OpenPose was used to locate hand and facial position. OpenPose can give better performance (6.312% of WER and 69.293% of SAcc score) compared to Skin Color Segmentation but cannot be implemented on mobile application. The computational time using OpenPose is 0.410 s per frame. The focus of this study is to find a model that can locate hand and facial position on complex background and also can be implemented on mobile application. The model we use is RetinaNet. RetinaNet is proven to locate hand and facial position much better (4,100% of WER and 78,990 % of SAcc score) than Skin Color Segmentation and OpenPose. The computational time using RetinaNet is 0.038 s per frame.
{"title":"Solving Complex Background Problem Using RetinaNet for Sign System for Indonesian Language (SIBI) Gesture-to-Text Translator","authors":"Median Hardiv Nugraha, Erdefi Rakun","doi":"10.1109/ICACSIS56558.2022.9923450","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923450","url":null,"abstract":"SIBI is the standardized sign language system offi-cially used in Indonesia. The application of SIBI is often found to be a hindrance because there are too many gestures that must be memorized. A mobile-based application is needed as gesture-to-text translator. From Rakun et al., Skin Color Segmentation was used as a method to segment hand and facial features using greenscreen background as dataset (3.367% of WER and 80.180% of SAcc). When this application is used, the gesture video is recorded on complex background but performed poorly (135.180% of WER and 0% of SAcc score). The computational time using Skin Color Segmentation is 0.013 s per frame. OpenPose was used to locate hand and facial position. OpenPose can give better performance (6.312% of WER and 69.293% of SAcc score) compared to Skin Color Segmentation but cannot be implemented on mobile application. The computational time using OpenPose is 0.410 s per frame. The focus of this study is to find a model that can locate hand and facial position on complex background and also can be implemented on mobile application. The model we use is RetinaNet. RetinaNet is proven to locate hand and facial position much better (4,100% of WER and 78,990 % of SAcc score) than Skin Color Segmentation and OpenPose. The computational time using RetinaNet is 0.038 s per frame.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130176894","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923485
Candra Dwi Nugraha, Deden Sumirat Hidayat, D. I. Sensuse, Nadya Safitri
Tacit knowledge such as regulatory understanding, practical skills to support daily work, and best practices are essential to support organizational knowledge. However, some government agencies in Indonesia do not yet have official guidelines and specific tools to manage this personal knowledge. The purpose of this study is to develop a bottom-up personal knowledge management system for the government institutions, namely BPS. The user-centered design (UCD) was used, along with the B-KIDE, to develop a knowledge management system model. The qualitative method was used through semi-structured interviews with 14 employees in the BPS regency/municipality. The evaluation of the prototype using the system usability scale resulted in an average score of 87.5, which means that the designed system is on grade scale B and indicated that the system can be accepted by users.
{"title":"Designing Personal Knowledge Management System to Support Knowledge Sharing in Government Organization: A Case study at the Indonesian Central Statistics Agency","authors":"Candra Dwi Nugraha, Deden Sumirat Hidayat, D. I. Sensuse, Nadya Safitri","doi":"10.1109/ICACSIS56558.2022.9923485","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923485","url":null,"abstract":"Tacit knowledge such as regulatory understanding, practical skills to support daily work, and best practices are essential to support organizational knowledge. However, some government agencies in Indonesia do not yet have official guidelines and specific tools to manage this personal knowledge. The purpose of this study is to develop a bottom-up personal knowledge management system for the government institutions, namely BPS. The user-centered design (UCD) was used, along with the B-KIDE, to develop a knowledge management system model. The qualitative method was used through semi-structured interviews with 14 employees in the BPS regency/municipality. The evaluation of the prototype using the system usability scale resulted in an average score of 87.5, which means that the designed system is on grade scale B and indicated that the system can be accepted by users.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134283104","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923500
Niken Ayu Firdayanti, Meylia Susiana Dewi Putri, Igara Triregina, Rahmat Sunarya, Kharismaji Kalasmoro, Teguh Budiman, Lily Harjanto, Andrian Andaya Lestari, R. Gultom, M. Supriyatno
The process of relocating the National Capital of Indonesia from its initial position on Jakarta (Java Island) to Kalimantan Island would cause a shift in Indonesia's Center of Gravity (CoG). Since there are now only two radars on Kalimantan and they are still unable to cover the entire territory of Kalimantan, air defense might be the primary concern that needs to be strengthened. The presence of a blank-spot area in the West Kalimantan region should be a consideration for placing radar in this region. The result of the study is coordinate point which is the exact location of the radar placement. This study aims to analyze the location of the GCI Radar placement in the West Kalimantan region using the Geographic Information System (GIS) and Radar Coverage methods, to ensure that air defense on Kalimantan Island is conducted as effectively as possible to detect and identify threats to COG of Indonesia. The data used for determining the location are altitude, radar coverage, road infrastructure, communication infrastructure, disasters, and land cover. Data processing using ArcGIS applications to help determine the appropriate location and test Radar coverage with the SPx Radar Coverage. The location with the best radar coverage is at coordinates 008'34.8”N 110032'34.8”E.
将印尼的国家首都从雅加达(爪哇岛)搬迁到加里曼丹岛的过程将导致印尼的重心(CoG)发生变化。由于现在加里曼丹只有两个雷达，它们仍然无法覆盖加里曼丹的整个领土，防空可能是需要加强的主要问题。在西加里曼丹地区存在一个空白区域，应该是在该地区部署雷达的一个考虑因素。研究的结果是坐标点，这是雷达放置的确切位置。本研究旨在利用地理信息系统(GIS)和雷达覆盖方法分析GCI雷达在西加里曼丹地区的位置，以确保加里曼丹岛上的防空尽可能有效地进行，以检测和识别对印度尼西亚COG的威胁。用于确定位置的数据包括海拔高度、雷达覆盖范围、道路基础设施、通信基础设施、灾害和土地覆盖。数据处理使用ArcGIS应用程序，以帮助确定适当的位置和测试雷达覆盖与SPx雷达覆盖。雷达覆盖最好的位置是坐标008'34.8 " N 110032'34.8 " E。
{"title":"Placement Analysis ofGCI Radar For Supporting Indonesia Air Defense Using Geographic Information System (Case Study: West Kalimantan)","authors":"Niken Ayu Firdayanti, Meylia Susiana Dewi Putri, Igara Triregina, Rahmat Sunarya, Kharismaji Kalasmoro, Teguh Budiman, Lily Harjanto, Andrian Andaya Lestari, R. Gultom, M. Supriyatno","doi":"10.1109/ICACSIS56558.2022.9923500","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923500","url":null,"abstract":"The process of relocating the National Capital of Indonesia from its initial position on Jakarta (Java Island) to Kalimantan Island would cause a shift in Indonesia's Center of Gravity (CoG). Since there are now only two radars on Kalimantan and they are still unable to cover the entire territory of Kalimantan, air defense might be the primary concern that needs to be strengthened. The presence of a blank-spot area in the West Kalimantan region should be a consideration for placing radar in this region. The result of the study is coordinate point which is the exact location of the radar placement. This study aims to analyze the location of the GCI Radar placement in the West Kalimantan region using the Geographic Information System (GIS) and Radar Coverage methods, to ensure that air defense on Kalimantan Island is conducted as effectively as possible to detect and identify threats to COG of Indonesia. The data used for determining the location are altitude, radar coverage, road infrastructure, communication infrastructure, disasters, and land cover. Data processing using ArcGIS applications to help determine the appropriate location and test Radar coverage with the SPx Radar Coverage. The location with the best radar coverage is at coordinates 008'34.8”N 110032'34.8”E.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114408937","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923475
Talitha Nabila Saifana, Nori Wilantika
Telemedicine provides various conveniences and solutions to several problems related to health services. The number of downloads of telemedicine apps has increased during the COVID-19 pandemic. However, the continuance mainly depends on user satisfaction associated with user perception of service quality. This study aims to figure out whether there are any changes in user perception toward telemedicine before and during the pandemic. This study proposes an approach that utilizes customer reviews of Halodoc and Alodokter from the Google Play Store. User perception extracted from user reviews includes sentiment polarity and the most discussed topics of telemedicine apps. Further analysis was conducted by mapping the most discussed topics to dimensions of service quality. The results show that the percentage of reviews with negative sentiment during the pandemic increased compared to before the pandemic. The highest percentage of topics discussed in negative nuance during pandemic is about system quality, which are payment methods, unauthorized deduction of user balances, and suspected leaks of users' private data. The findings of this research contribute to the preliminary information related to the sustainability of telemedicine usage. This research also extends the literature on the potential use of textual reviews in user perception on health platforms.
远程医疗为与卫生服务有关的若干问题提供了各种便利和解决方案。在2019冠状病毒病大流行期间，远程医疗应用程序的下载量有所增加。然而，持续与否主要取决于用户满意度与用户对服务质量的感知。这项研究的目的是弄清楚用户对远程医疗的认知在大流行之前和期间是否有任何变化。本研究提出了一种利用来自Google Play Store的Halodoc和Alodokter的用户评论的方法。从用户评论中提取的用户感知包括情感极性和远程医疗应用中讨论最多的话题。通过将讨论最多的主题映射到服务质量的维度，进行了进一步的分析。结果显示，与疫情前相比，疫情期间负面评价的百分比有所增加。在大流行期间，以负面细微差别讨论的话题比例最高的是系统质量，即支付方式、未经授权扣除用户余额以及可疑的用户私人数据泄露。本研究的结果有助于提供与远程医疗使用的可持续性有关的初步信息。本研究还扩展了关于文本评论在健康平台用户感知中的潜在用途的文献。
{"title":"User Perception towards Telemedicine Before and During COVID-19","authors":"Talitha Nabila Saifana, Nori Wilantika","doi":"10.1109/ICACSIS56558.2022.9923475","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923475","url":null,"abstract":"Telemedicine provides various conveniences and solutions to several problems related to health services. The number of downloads of telemedicine apps has increased during the COVID-19 pandemic. However, the continuance mainly depends on user satisfaction associated with user perception of service quality. This study aims to figure out whether there are any changes in user perception toward telemedicine before and during the pandemic. This study proposes an approach that utilizes customer reviews of Halodoc and Alodokter from the Google Play Store. User perception extracted from user reviews includes sentiment polarity and the most discussed topics of telemedicine apps. Further analysis was conducted by mapping the most discussed topics to dimensions of service quality. The results show that the percentage of reviews with negative sentiment during the pandemic increased compared to before the pandemic. The highest percentage of topics discussed in negative nuance during pandemic is about system quality, which are payment methods, unauthorized deduction of user balances, and suspected leaks of users' private data. The findings of this research contribute to the preliminary information related to the sustainability of telemedicine usage. This research also extends the literature on the potential use of textual reviews in user perception on health platforms.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125860071","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923446
Nur Hamid, Willy Dharmawan, Hidetaka Nambo
The evacuation process in a flood disaster environment faces some challenges when exploring the affected area. During a flood situation, the boat must quickly determine the shortest path to save as many flood victims as possible. In this research, we proposed an adaptively rotatable distance sensor implemented in an evacuation boat. The single sensor conducts either early rotation (with a specific initial rotation angle) for early detection of the obstacles or wider rotation to determine the way-out point using the greedy principle. The proposed methodology is implemented in three-dimensional simulation, containing static and dynamic for both water wave environment and obstacles. The obstacles are limited to some exact cube shape with an exact size, and they are linearly moving for the dynamic ones. By adapting the greedy principle, the boat agent can successfully move on the water surface to avoid static and dynamic obstacles. This achievement cannot be reached by the previous path planning method.
{"title":"Autonomous Evacuation Boat in Dynamic Flood Disaster Environment","authors":"Nur Hamid, Willy Dharmawan, Hidetaka Nambo","doi":"10.1109/ICACSIS56558.2022.9923446","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923446","url":null,"abstract":"The evacuation process in a flood disaster environment faces some challenges when exploring the affected area. During a flood situation, the boat must quickly determine the shortest path to save as many flood victims as possible. In this research, we proposed an adaptively rotatable distance sensor implemented in an evacuation boat. The single sensor conducts either early rotation (with a specific initial rotation angle) for early detection of the obstacles or wider rotation to determine the way-out point using the greedy principle. The proposed methodology is implemented in three-dimensional simulation, containing static and dynamic for both water wave environment and obstacles. The obstacles are limited to some exact cube shape with an exact size, and they are linearly moving for the dynamic ones. By adapting the greedy principle, the boat agent can successfully move on the water surface to avoid static and dynamic obstacles. This achievement cannot be reached by the previous path planning method.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129316346","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923490
Muchammad Choirur Rizqi Anwar, P. W. Handayani
Digitalization is an effort to increase oil and gas production in the upstream sector to become more effective and efficient. Digital transformation in the primary upstream oil and gas operations to monitor drilling activities, production operations, shipping, lifting, and inventory monitoring through the Integrated Operation Center (IOC). IOC is Business Intelligence (BI) to produce information for executives and decision-makers of the organization. IOC's evaluation result showed the number of IOC access of business users was only 31 %, while the IT team reached 69%; there are differences in expectations and reality from management needs regarding continuous use of IOC as BI. The study aimed to identify important factors contributing to the continuous use of IOC in PHE. The study adopts DeLone & McLean. A quantitative study was conducted in a survey of 30 IOC users to determine the essential factors for the continuity of IOC use. The results showed that seven continuous factors use of IOC had significant relationships. Information Quality correlated with User Satisfaction, System Quality correlated with System Use, System Use correlated with Net Benefits and User Satisfaction, User Satisfaction correlated with System Use, and Net Benefits Net Benefits User Satisfaction and System Use. This study provides input for organizations on essential factors in evaluating and improving the continuous use of IOC as BI.
{"title":"Continuous Use Evaluation of Business Intelligence Implementation in Energy Company","authors":"Muchammad Choirur Rizqi Anwar, P. W. Handayani","doi":"10.1109/ICACSIS56558.2022.9923490","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923490","url":null,"abstract":"Digitalization is an effort to increase oil and gas production in the upstream sector to become more effective and efficient. Digital transformation in the primary upstream oil and gas operations to monitor drilling activities, production operations, shipping, lifting, and inventory monitoring through the Integrated Operation Center (IOC). IOC is Business Intelligence (BI) to produce information for executives and decision-makers of the organization. IOC's evaluation result showed the number of IOC access of business users was only 31 %, while the IT team reached 69%; there are differences in expectations and reality from management needs regarding continuous use of IOC as BI. The study aimed to identify important factors contributing to the continuous use of IOC in PHE. The study adopts DeLone & McLean. A quantitative study was conducted in a survey of 30 IOC users to determine the essential factors for the continuity of IOC use. The results showed that seven continuous factors use of IOC had significant relationships. Information Quality correlated with User Satisfaction, System Quality correlated with System Use, System Use correlated with Net Benefits and User Satisfaction, User Satisfaction correlated with System Use, and Net Benefits Net Benefits User Satisfaction and System Use. This study provides input for organizations on essential factors in evaluating and improving the continuous use of IOC as BI.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130960378","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923439
Agus Kurniawan, M. Kyas
LoRaWAN provides a long-range communication among IoT devices. Since a LoRaWAN gateway becomes a bridge between LoRaWAN nodes and back-end server, it could has potential security risks. We present an anomaly detection system to secure LoRa Wangateway devices by evaluating incoming packet data. To evaluate our proposed system, we build machine learning models using various outlier detection algorithms. We construct and evaluate LoRaWAN dataset from LoRaWAN gateway devices. The simulation and experimental results show that machine learning to address anomaly detection on constrained LoRa Wandevices guarantees feasibility, accu-racy and performance.
{"title":"Machine Learning Models for LoRa Wan IoT Anomaly Detection","authors":"Agus Kurniawan, M. Kyas","doi":"10.1109/ICACSIS56558.2022.9923439","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923439","url":null,"abstract":"LoRaWAN provides a long-range communication among IoT devices. Since a LoRaWAN gateway becomes a bridge between LoRaWAN nodes and back-end server, it could has potential security risks. We present an anomaly detection system to secure LoRa Wangateway devices by evaluating incoming packet data. To evaluate our proposed system, we build machine learning models using various outlier detection algorithms. We construct and evaluate LoRaWAN dataset from LoRaWAN gateway devices. The simulation and experimental results show that machine learning to address anomaly detection on constrained LoRa Wandevices guarantees feasibility, accu-racy and performance.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123200870","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923528
Zhanyu Guo, Peng Wang
Locating exactly where a train is on a track is now a major concern for railway companies. By training the charac-teristic objects from the picture samples along the railway with YOLO v5 to generate the recognition template, the characteristic images containing characteristic objects can be selected as the positioning points. Then Compile the identity code (ID code) of the positioning points' pictures by using the location information of the characteristic objects. Match the detected pictures' ID code with positioning pictures' ID code through similarity, and the recognition can be completed if the similarity is higher than the set threshold. Finally, by fetching the location information of the positioning point, the train can identify it position. Through a series of methods such as changing the shooting angle, sharpness and contrast of the positioning point images, the testing set is expanded, and the YOLO v5 based positioning algorithm can be measured its optimal model. The experimental results show that when the similarity threshold is 0.58 and the confidence limit is 0.6, the train positioning model has the best performance, and the success rate of positioning is 97.6 %.
{"title":"Research on Train Positioning Algorithm with Special Rail Characters","authors":"Zhanyu Guo, Peng Wang","doi":"10.1109/ICACSIS56558.2022.9923528","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923528","url":null,"abstract":"Locating exactly where a train is on a track is now a major concern for railway companies. By training the charac-teristic objects from the picture samples along the railway with YOLO v5 to generate the recognition template, the characteristic images containing characteristic objects can be selected as the positioning points. Then Compile the identity code (ID code) of the positioning points' pictures by using the location information of the characteristic objects. Match the detected pictures' ID code with positioning pictures' ID code through similarity, and the recognition can be completed if the similarity is higher than the set threshold. Finally, by fetching the location information of the positioning point, the train can identify it position. Through a series of methods such as changing the shooting angle, sharpness and contrast of the positioning point images, the testing set is expanded, and the YOLO v5 based positioning algorithm can be measured its optimal model. The experimental results show that when the similarity threshold is 0.58 and the confidence limit is 0.6, the train positioning model has the best performance, and the success rate of positioning is 97.6 %.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116645175","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923496
Surbhi Kakar, Deepali Dhaka, Monica Mehrotra
This work aims to predict retweet popularity of covid19 tweet corpus. Our work fuses unsupervised and supervised learning techniques to create retweet popularity model. In the first phase, we use a Clustered Bert model, which works on clustering the Bert embeddings using clustering algorithms on the textual data to generate novel and meaningful feature set for our model. In the second phase, we use the output of Clustered Bert model as an input to the Supervised Regression models intending to predict retweet popularity. Our work also draws a comparison between features from numeric model; emotions/sentiment model; and Clustered Bert model. Three different Regression models, belonging to different categories: Nearest Neighbors, Ensemble and Stacked models are then tested on the final feature-set to generate predictions for our model. The results show higher accuracy when the Clustered Bert model is used in combination with numerical and emotion/sentiment model. The experiment shows better results for Stacked Regression models out of all the three regressors used for our study.
{"title":"Clustered Bert Model for predicting Retweet Popularity","authors":"Surbhi Kakar, Deepali Dhaka, Monica Mehrotra","doi":"10.1109/ICACSIS56558.2022.9923496","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923496","url":null,"abstract":"This work aims to predict retweet popularity of covid19 tweet corpus. Our work fuses unsupervised and supervised learning techniques to create retweet popularity model. In the first phase, we use a Clustered Bert model, which works on clustering the Bert embeddings using clustering algorithms on the textual data to generate novel and meaningful feature set for our model. In the second phase, we use the output of Clustered Bert model as an input to the Supervised Regression models intending to predict retweet popularity. Our work also draws a comparison between features from numeric model; emotions/sentiment model; and Clustered Bert model. Three different Regression models, belonging to different categories: Nearest Neighbors, Ensemble and Stacked models are then tested on the final feature-set to generate predictions for our model. The results show higher accuracy when the Clustered Bert model is used in combination with numerical and emotion/sentiment model. The experiment shows better results for Stacked Regression models out of all the three regressors used for our study.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114262673","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923501
Zafira Binta Feliandra, Siti Khadijah, M. F. Rachmadi, D. Chahyati
This study covers a pilot study on developing a tele-health system for detection and classification of stroke and non-stroke patients from human body movements using smartphone videos. Human body poses are extracted from smartphone videos which are then transformed into RGB images and classified into either stroke (positive) or non-stroke (negative) labels. We tested PoseNet, BlazePose, and MoveNet for human body pose detection and AlexN et and SqueezeN et for classification. From this pilot study, we found that MoveNet is the best human body pose detection while AlexNet is the best for classification.
{"title":"Classification of Stroke and Non-Stroke Patients from Human Body Movements using Smartphone Videos and Deep Neural Networks","authors":"Zafira Binta Feliandra, Siti Khadijah, M. F. Rachmadi, D. Chahyati","doi":"10.1109/ICACSIS56558.2022.9923501","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923501","url":null,"abstract":"This study covers a pilot study on developing a tele-health system for detection and classification of stroke and non-stroke patients from human body movements using smartphone videos. Human body poses are extracted from smartphone videos which are then transformed into RGB images and classified into either stroke (positive) or non-stroke (negative) labels. We tested PoseNet, BlazePose, and MoveNet for human body pose detection and AlexN et and SqueezeN et for classification. From this pilot study, we found that MoveNet is the best human body pose detection while AlexNet is the best for classification.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"357 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115852314","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：