Pub Date : 2020-06-01DOI: 10.1109/ECTI-CON49241.2020.9158110
Omer Ali, M. Ishak, Mohamad Adzhar Md Zawawi, Mohamad Tarmizi Abu Seman, Muhammad Kamran Liaquat Bhatti, Zainatul Yushaniza Mohamed Yusoff
Energy conservation and optimization remains the top researched field for wireless sensor networks, which is one of a subsets and the underlying communication medium for Internet of Things (IoT) devices. These constrained IoT devices are mostly battery operated and therefore requires robust and optimized algorithms to improve resources utilization which inherently increases the life-span for these devices without compromising Quality of Service (QoS). The communication radios on these nodes are the most power hogging components. Therefore, a major focus has always been on MAC and cross-layer protocols to optimize the duty cycle of radios for the conservation of energy. This paper presents a unique scheme for dynamically adjusting the duty cycle of nodes based on the arrival of incoming infrequent source node sensor data over which eliminates the need for frequent periodic channel assessment for network activity. The proposed scheme also makes use of ultra-low wakeUp receivers on the receiver nodes to further aid the node in energy conservation. In this paper, we describe the details of our design scheme, implementation and evaluation details in Contiki OS and Cooja simulator. The results are micro-benchmarked with ContikiMAC and X-MAC protocols, and an improvement in radio duty cycle is reported for lighter network traffic.
{"title":"A MAC Protocol for Energy Efficient Wireless Communication Leveraging Wake-Up Estimations on Sender Data","authors":"Omer Ali, M. Ishak, Mohamad Adzhar Md Zawawi, Mohamad Tarmizi Abu Seman, Muhammad Kamran Liaquat Bhatti, Zainatul Yushaniza Mohamed Yusoff","doi":"10.1109/ECTI-CON49241.2020.9158110","DOIUrl":"https://doi.org/10.1109/ECTI-CON49241.2020.9158110","url":null,"abstract":"Energy conservation and optimization remains the top researched field for wireless sensor networks, which is one of a subsets and the underlying communication medium for Internet of Things (IoT) devices. These constrained IoT devices are mostly battery operated and therefore requires robust and optimized algorithms to improve resources utilization which inherently increases the life-span for these devices without compromising Quality of Service (QoS). The communication radios on these nodes are the most power hogging components. Therefore, a major focus has always been on MAC and cross-layer protocols to optimize the duty cycle of radios for the conservation of energy. This paper presents a unique scheme for dynamically adjusting the duty cycle of nodes based on the arrival of incoming infrequent source node sensor data over which eliminates the need for frequent periodic channel assessment for network activity. The proposed scheme also makes use of ultra-low wakeUp receivers on the receiver nodes to further aid the node in energy conservation. In this paper, we describe the details of our design scheme, implementation and evaluation details in Contiki OS and Cooja simulator. The results are micro-benchmarked with ContikiMAC and X-MAC protocols, and an improvement in radio duty cycle is reported for lighter network traffic.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132764087","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}
A personalized recommendation has been an active area of research. Many companies such as Facebook, Amazon, and eBay have incorporated such functionality to enhance user experience and engagement. In today’s market, streaming digital contents (e.g., online movies) have become ubiquitous and accessi-ble from anywhere and anytime. The rapid growth of streaming market urges many providers to offer a personalized experience to capture customer loyalty. In this paper, we present a movie recommending system based on our proposed rating prediction algorithm using singular value decomposition (SVD). Empirical evaluation is conducted on two tasks: rating prediction and movie recommendation, using two case studies from MovieLens and Thaiware Movie.
{"title":"SGD-Rec: A Matrix Decomposition Based Model for Personalized Movie Recommendation","authors":"Siripen Pongpaichet, Thatchapon Unprasert, Suppawong Tuarob, Petch Sajjacholapunt","doi":"10.1109/ecti-con49241.2020.9158308","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158308","url":null,"abstract":"A personalized recommendation has been an active area of research. Many companies such as Facebook, Amazon, and eBay have incorporated such functionality to enhance user experience and engagement. In today’s market, streaming digital contents (e.g., online movies) have become ubiquitous and accessi-ble from anywhere and anytime. The rapid growth of streaming market urges many providers to offer a personalized experience to capture customer loyalty. In this paper, we present a movie recommending system based on our proposed rating prediction algorithm using singular value decomposition (SVD). Empirical evaluation is conducted on two tasks: rating prediction and movie recommendation, using two case studies from MovieLens and Thaiware Movie.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131847932","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 : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158322
P. Kranoongon, B. Techaumnat
In recent years, the composite cross-arm is used in the transmission line system. The electric field analysis at the composite cross-arm is very important for the high voltage system. The electric field at corona rings and grading rings must be confirmed that can withstand the corona threshold field. But the geometry of cross-arm is very complicated for computing. Therefore, the objective of this paper is to compute the 3 phase electric field by using ANSYS Maxwell software base on the finite element method (FEM). We separately calculate in each phase in order to reduce the computation time. Firstly, the 3-dimensional (3D) model of composite crossarm is simulated in a close domain. Then the average potential from the 2-dimensional (2D) model is defined as a boundary condition in case of the 3-dimensional model. Finally, the maximum electric field values in each phase are compared. From the results, the highest electric field occurs at phase B, and the electric field of tension-type grading ring is slightly higher than other types of ring. However, all values are lower than the electric field criteria.
{"title":"Electric Field Analysis of the 230 kV AC Transmission Line System for an Limited Area","authors":"P. Kranoongon, B. Techaumnat","doi":"10.1109/ecti-con49241.2020.9158322","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158322","url":null,"abstract":"In recent years, the composite cross-arm is used in the transmission line system. The electric field analysis at the composite cross-arm is very important for the high voltage system. The electric field at corona rings and grading rings must be confirmed that can withstand the corona threshold field. But the geometry of cross-arm is very complicated for computing. Therefore, the objective of this paper is to compute the 3 phase electric field by using ANSYS Maxwell software base on the finite element method (FEM). We separately calculate in each phase in order to reduce the computation time. Firstly, the 3-dimensional (3D) model of composite crossarm is simulated in a close domain. Then the average potential from the 2-dimensional (2D) model is defined as a boundary condition in case of the 3-dimensional model. Finally, the maximum electric field values in each phase are compared. From the results, the highest electric field occurs at phase B, and the electric field of tension-type grading ring is slightly higher than other types of ring. However, all values are lower than the electric field criteria.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134164370","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 : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158286
W. Nuankaew, Jaree Thongkam
This paper presents methods to improve the prediction of student academic performance using feature selection by removing misclassified instances and Synthetic Minority Over-Sampling Technique. It compares the performance of seven students’ academic performance prediction models, namely Naïve Bayes, Sequential Minimum Optimization, Artificial Neural Network, k-Nearest Neighbor, REPTree, Partial decision trees, and Random Forest. The data were collected from 9,458 students at the Rajabhat Maha Sarakham University, Thailand during 2015 - 2018. The model performances were evaluated with precision, recall, and F-measure. The experimental results indicated that the Random Forest approach significantly improves the performance of students’ academic performance prediction models with precision up to 41.70%, recall up to 41.40% and F-measure up to 41.60%, respectively.
{"title":"Improving Student Academic Performance Prediction Models using Feature Selection","authors":"W. Nuankaew, Jaree Thongkam","doi":"10.1109/ecti-con49241.2020.9158286","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158286","url":null,"abstract":"This paper presents methods to improve the prediction of student academic performance using feature selection by removing misclassified instances and Synthetic Minority Over-Sampling Technique. It compares the performance of seven students’ academic performance prediction models, namely Naïve Bayes, Sequential Minimum Optimization, Artificial Neural Network, k-Nearest Neighbor, REPTree, Partial decision trees, and Random Forest. The data were collected from 9,458 students at the Rajabhat Maha Sarakham University, Thailand during 2015 - 2018. The model performances were evaluated with precision, recall, and F-measure. The experimental results indicated that the Random Forest approach significantly improves the performance of students’ academic performance prediction models with precision up to 41.70%, recall up to 41.40% and F-measure up to 41.60%, respectively.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"42 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134287800","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 : 2020-06-01DOI: 10.1109/ECTI-CON49241.2020.9158220
S. Wilainuch, T. Kasetkasem, N. Sugino, T. Phatrapornnant, S. Marukatat
The use of machine learning technology with remote sensing image analysis, especially for the land cover mapping requires experts and huge resources because every pixel in the training set must be labeled. This task is time-consuming and tedious. Therefore, a better strategy is to only identify what classes are present in an image without specifying where they are. In this way, a large number of remote sensing images can be labeled quickly. To achieve this goal, we employed the attention layer to create the attention map. The attention map is then further segmented to produce the final l and c over m ap where every pixel in an image will be labeled. We have tested the performance of our proposed algorithm with UC Merced Dataset and achieved 79.7 % in identifying the presence of land cover classes and 71.2 % accuracy in the labeling of all pixels
{"title":"On the Use of Attention Map for Land Cover Mapping","authors":"S. Wilainuch, T. Kasetkasem, N. Sugino, T. Phatrapornnant, S. Marukatat","doi":"10.1109/ECTI-CON49241.2020.9158220","DOIUrl":"https://doi.org/10.1109/ECTI-CON49241.2020.9158220","url":null,"abstract":"The use of machine learning technology with remote sensing image analysis, especially for the land cover mapping requires experts and huge resources because every pixel in the training set must be labeled. This task is time-consuming and tedious. Therefore, a better strategy is to only identify what classes are present in an image without specifying where they are. In this way, a large number of remote sensing images can be labeled quickly. To achieve this goal, we employed the attention layer to create the attention map. The attention map is then further segmented to produce the final l and c over m ap where every pixel in an image will be labeled. We have tested the performance of our proposed algorithm with UC Merced Dataset and achieved 79.7 % in identifying the presence of land cover classes and 71.2 % accuracy in the labeling of all pixels","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133403420","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 : 2020-06-01DOI: 10.1109/ECTI-CON49241.2020.9158095
Thandar Htay, S. Phyu
Apache Hadoop is a widely used open-source distributed platform towards big data processing and provides YARN based distributed parallel processing framework on low cost commodity machines. However, YARN adopts static resource management (that is, the number of containers available per node and the size of each container are static in nature) depending on pre-configured default resource units called containers leading to poor performance to deal with various sort of MapReduce applications. In addition, during the last wave of a job, many available resources occur frequently being idle because YARN does not consider the wave behavior in tasks of MapReduce applications. To take advantage of idle resources resulting in performance improvement, the important parameter, the number of map tasks is needed to optimize based on the available resources and governed by split size. Therefore, this parameter is optimized through the split size tuning based on the available resources. To address the drawback of static resource management of yarn in Hadoop, the numbers of concurrent containers per machine are tuned to optimize the node performance for running each MapReduce application. As per experimental results, the proposed system that optimizes the selected parameter on optimized concurrent containers can achieve the performance gains of MapReduce applications while reducing the optimization overheads.
{"title":"Towards Performance Optimization for Hadoop MapReduce Applications","authors":"Thandar Htay, S. Phyu","doi":"10.1109/ECTI-CON49241.2020.9158095","DOIUrl":"https://doi.org/10.1109/ECTI-CON49241.2020.9158095","url":null,"abstract":"Apache Hadoop is a widely used open-source distributed platform towards big data processing and provides YARN based distributed parallel processing framework on low cost commodity machines. However, YARN adopts static resource management (that is, the number of containers available per node and the size of each container are static in nature) depending on pre-configured default resource units called containers leading to poor performance to deal with various sort of MapReduce applications. In addition, during the last wave of a job, many available resources occur frequently being idle because YARN does not consider the wave behavior in tasks of MapReduce applications. To take advantage of idle resources resulting in performance improvement, the important parameter, the number of map tasks is needed to optimize based on the available resources and governed by split size. Therefore, this parameter is optimized through the split size tuning based on the available resources. To address the drawback of static resource management of yarn in Hadoop, the numbers of concurrent containers per machine are tuned to optimize the node performance for running each MapReduce application. As per experimental results, the proposed system that optimizes the selected parameter on optimized concurrent containers can achieve the performance gains of MapReduce applications while reducing the optimization overheads.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131832228","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 : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158073
N. Supreeyatitikul, N. Teerasuttakorn
In this research, a miniaturized two-element multiple-input multiple-output (MIMO) antenna with high isolation by using metamaterial (MTM) has been presented for dual-band of millimeter-wave frequency (28 GHz and 38 GHz). The proposed MIMO antenna array has been etched on Rogers-5880 with an overall size of 23×10×0.787 mm3. The high isolation between two-element antennas was obtained by reducing the mutual coupling which employed the square split-ring resonators (S-SRRs). The S-SRRs can be achieved a low transmission coefficient of −34.56 dB and −49.85 dB at the entire operating frequency of 28 GHz and 38 GHz, respectively. The diversity performance of the proposed MIMO antenna array has been verified in order to prove the MIMO performance for mm-wave wireless communications.
{"title":"Improved Isolation of a Dual-Band MIMO Antenna Using Modified S-SRRs for Millimeter-Wave Applications","authors":"N. Supreeyatitikul, N. Teerasuttakorn","doi":"10.1109/ecti-con49241.2020.9158073","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158073","url":null,"abstract":"In this research, a miniaturized two-element multiple-input multiple-output (MIMO) antenna with high isolation by using metamaterial (MTM) has been presented for dual-band of millimeter-wave frequency (28 GHz and 38 GHz). The proposed MIMO antenna array has been etched on Rogers-5880 with an overall size of 23×10×0.787 mm3. The high isolation between two-element antennas was obtained by reducing the mutual coupling which employed the square split-ring resonators (S-SRRs). The S-SRRs can be achieved a low transmission coefficient of −34.56 dB and −49.85 dB at the entire operating frequency of 28 GHz and 38 GHz, respectively. The diversity performance of the proposed MIMO antenna array has been verified in order to prove the MIMO performance for mm-wave wireless communications.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134085160","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 : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158275
Pikkanate Angaphiwatchawal, Poowasarun Phisuthsaingam, S. Chaitusaney
With the development and low-cost trend of renewable energy technologies, particularly PV rooftop systems, energy consumers can produce electricity to self-consume and/or export the surplus energy into low-voltage (LV) distribution grids. The peer-to-peer (P2P) energy trading widely allows consumers with a generation role, called prosumers, to trade their surplus energy with other prosumers. The purpose of this study is to investigate how to impose the exchanged price between two P2P participants by using the k-factor continuous double auction (CDA) algorithm to scale up/down between seller’s offers and buyer’s bids submitted in the P2P energy trading. The k-factor is set to be varied between 0 and 1. The simulation results, based on the case study, show that the approximated value of k as of 0.6445 which is such that the benefits between sellers and buyers are equal is feasible. This states that the exchanged price between two participants can be formed with a combination between 64.45% and 35.55% of the buyer’s outstanding bid and the seller’s outstanding offer, respectively.
{"title":"A k-Factor Continuous Double Auction-Based Pricing Mechanism for the P2P Energy Trading in a LV Distribution System","authors":"Pikkanate Angaphiwatchawal, Poowasarun Phisuthsaingam, S. Chaitusaney","doi":"10.1109/ecti-con49241.2020.9158275","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158275","url":null,"abstract":"With the development and low-cost trend of renewable energy technologies, particularly PV rooftop systems, energy consumers can produce electricity to self-consume and/or export the surplus energy into low-voltage (LV) distribution grids. The peer-to-peer (P2P) energy trading widely allows consumers with a generation role, called prosumers, to trade their surplus energy with other prosumers. The purpose of this study is to investigate how to impose the exchanged price between two P2P participants by using the k-factor continuous double auction (CDA) algorithm to scale up/down between seller’s offers and buyer’s bids submitted in the P2P energy trading. The k-factor is set to be varied between 0 and 1. The simulation results, based on the case study, show that the approximated value of k as of 0.6445 which is such that the benefits between sellers and buyers are equal is feasible. This states that the exchanged price between two participants can be formed with a combination between 64.45% and 35.55% of the buyer’s outstanding bid and the seller’s outstanding offer, respectively.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"292 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134430695","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}
Software development is a team-based intensive activity where various skills (e.g. technical and analysis skills) are required to deliver high quality outcomes. An effective team member assignment is thus a crucial process. In this paper, we propose to adopt the existing machine learning approach for team recommendation to recommend software team members who are suitable for a given task. The approach take both individual strength and collaborative efficiency among team members into account to give a recommendation. We evaluate the approach on the Moodle project, well-known open source software project. The evaluation results show that the adopted approach yields a better recommendation performance compared to the baseline (i.e. random assignment approach).
{"title":"Towards Team Formation in Software Development: A Case Study of Moodle","authors":"Noppadol Assavakamhaenghan, Ponlakit Suwanworaboon, Waralee Tanaphantaruk, Suppawong Tuarob, Morakot Choetkiertikul","doi":"10.1109/ecti-con49241.2020.9158078","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158078","url":null,"abstract":"Software development is a team-based intensive activity where various skills (e.g. technical and analysis skills) are required to deliver high quality outcomes. An effective team member assignment is thus a crucial process. In this paper, we propose to adopt the existing machine learning approach for team recommendation to recommend software team members who are suitable for a given task. The approach take both individual strength and collaborative efficiency among team members into account to give a recommendation. We evaluate the approach on the Moodle project, well-known open source software project. The evaluation results show that the adopted approach yields a better recommendation performance compared to the baseline (i.e. random assignment approach).","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134414729","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 : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158104
Pornphom Piraintorn, V. Sa-Ing
Stroke rehabilitation is an important requirement of patient treatment after recovering from stroke disease. However, a physical therapist can only observe once a patient at a time. Moreover, it takes a lot of time to suggest and evaluate the correction. From this problem, this research will develop the new rehabilitation guidance systems that assist the physical therapist and medical doctor. The intelligence interaction system is proposed for detection and monitoring the rehabilitation of the stroke patient who stays on the bed. The proposed system detects a stroke patient by using a 3D camera, which is the Intel Realsense D415, to place at the end of the patient bed for extracting the patient from the bed by measuring the distance between the patient and bed. From the segmentation result of the patient, the proposed system evaluates the rehab posture of the patient by detection from the simulated skeleton to calculate from the changing degree of the shoulder joint, elbow joint, and wrist joint. In addition, the proposed system uses the capabilities of artificial intelligence to check the accuracy of physiotherapy patients and show to the patients how to perform physical therapy correctly. From the experiment results, the proposed system represents the effective monitoring and evaluation of the stroke rehabilitation that the program can accurately count the arm flexion gesture therapy. Therefore, the intelligence interaction system can usefully help the physical therapist to monitor and evaluate the rehabilitation of stroke on the bed.
{"title":"Stroke Rehabilitation based on Intelligence Interaction System","authors":"Pornphom Piraintorn, V. Sa-Ing","doi":"10.1109/ecti-con49241.2020.9158104","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158104","url":null,"abstract":"Stroke rehabilitation is an important requirement of patient treatment after recovering from stroke disease. However, a physical therapist can only observe once a patient at a time. Moreover, it takes a lot of time to suggest and evaluate the correction. From this problem, this research will develop the new rehabilitation guidance systems that assist the physical therapist and medical doctor. The intelligence interaction system is proposed for detection and monitoring the rehabilitation of the stroke patient who stays on the bed. The proposed system detects a stroke patient by using a 3D camera, which is the Intel Realsense D415, to place at the end of the patient bed for extracting the patient from the bed by measuring the distance between the patient and bed. From the segmentation result of the patient, the proposed system evaluates the rehab posture of the patient by detection from the simulated skeleton to calculate from the changing degree of the shoulder joint, elbow joint, and wrist joint. In addition, the proposed system uses the capabilities of artificial intelligence to check the accuracy of physiotherapy patients and show to the patients how to perform physical therapy correctly. From the experiment results, the proposed system represents the effective monitoring and evaluation of the stroke rehabilitation that the program can accurately count the arm flexion gesture therapy. Therefore, the intelligence interaction system can usefully help the physical therapist to monitor and evaluate the rehabilitation of stroke on the bed.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132163393","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：