Pub Date : 2022-03-12DOI: 10.1109/ICIPRob54042.2022.9798723
S. Jayatilake, G. U. Ganegoda
Skin cancer is a form of cancer that is most common among Caucasians and is rapidly increasing year by year. Melanoma is the most dangerous type of skin cancer making it the world’s 17th most common cancer type which is 1.8% of all cancer patients globally. It is vital to detect Melanoma at its early stages to cure the patient without letting the cancer grow further. The proposed solution is to develop a system that can detect Melanoma by analysing the dermoscopic images while extracting Asymmetry, Border Irregularity, Colour, Diameter (ABCD) features and other salient dermoscopic features which are more often visible in Melanoma skin lesions. Different classification methods are also being evaluated to identify which classifier works best with the dermoscopic features extracted in the feature extraction stage so that the highest accuracy could be obtained when diagnosing Melanoma. Therefore, when a dermoscopic image is given to this proposed system it will output whether the patient is diagnosed with Melanoma along with the confidence level of the diagnosis result at which the model performed the diagnosis based on the various dermoscopic features extracted from the lesion.
{"title":"Melanoma Skin Cancer Detection from Dermoscopic Images using Computer Vision","authors":"S. Jayatilake, G. U. Ganegoda","doi":"10.1109/ICIPRob54042.2022.9798723","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798723","url":null,"abstract":"Skin cancer is a form of cancer that is most common among Caucasians and is rapidly increasing year by year. Melanoma is the most dangerous type of skin cancer making it the world’s 17th most common cancer type which is 1.8% of all cancer patients globally. It is vital to detect Melanoma at its early stages to cure the patient without letting the cancer grow further. The proposed solution is to develop a system that can detect Melanoma by analysing the dermoscopic images while extracting Asymmetry, Border Irregularity, Colour, Diameter (ABCD) features and other salient dermoscopic features which are more often visible in Melanoma skin lesions. Different classification methods are also being evaluated to identify which classifier works best with the dermoscopic features extracted in the feature extraction stage so that the highest accuracy could be obtained when diagnosing Melanoma. Therefore, when a dermoscopic image is given to this proposed system it will output whether the patient is diagnosed with Melanoma along with the confidence level of the diagnosis result at which the model performed the diagnosis based on the various dermoscopic features extracted from the lesion.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124572686","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 : 2022-03-12DOI: 10.1109/ICIPRob54042.2022.9798725
K. Sarankan, Surangani Bandara
In this paper, we have proposed a low-cost position tracking system for track indoor game players using minimal infrastructures with cost effective electronic components. Various positioning systems were introduced in previous to track game players, but they have complication due to time synchronization. To overcome this problem the proposed positioning system is constructed by using Ultrasonic (US) and Radio frequency (RF). This system uses open-source platforms with good user-friendly interface software, so the system can be operated by a user without prior knowledge of it. The system has two segments, which are transmitting unit and receiver unit. The transmitting unit has one RF transmitter and one ultrasonic Transmitter. The receiver unit has one RF receiver and three ultrasonic receivers. In this system the arduino module used to control the components and calculate the position estimation. The proposed system is using the theory of time difference of arrival for range measuring. The performance limitation of the system was also analyzed experimentally, such as a single range and positional accuracy in 2D & 3D space. Based on the results of analysis, major changes and substitutes in the circuits will improve the accuracy and performance limitation of the system such as making the circuits with high quality ICs & ultrasonic transducers, implementation of high pass or band pass filters in receiver circuits and integrating the receiver circuits with voltage regulators.
{"title":"Real-Time Position Tracking of Indoor Games Player Based on Radio Frequency (RF) and Ultrasonic (US)","authors":"K. Sarankan, Surangani Bandara","doi":"10.1109/ICIPRob54042.2022.9798725","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798725","url":null,"abstract":"In this paper, we have proposed a low-cost position tracking system for track indoor game players using minimal infrastructures with cost effective electronic components. Various positioning systems were introduced in previous to track game players, but they have complication due to time synchronization. To overcome this problem the proposed positioning system is constructed by using Ultrasonic (US) and Radio frequency (RF). This system uses open-source platforms with good user-friendly interface software, so the system can be operated by a user without prior knowledge of it. The system has two segments, which are transmitting unit and receiver unit. The transmitting unit has one RF transmitter and one ultrasonic Transmitter. The receiver unit has one RF receiver and three ultrasonic receivers. In this system the arduino module used to control the components and calculate the position estimation. The proposed system is using the theory of time difference of arrival for range measuring. The performance limitation of the system was also analyzed experimentally, such as a single range and positional accuracy in 2D & 3D space. Based on the results of analysis, major changes and substitutes in the circuits will improve the accuracy and performance limitation of the system such as making the circuits with high quality ICs & ultrasonic transducers, implementation of high pass or band pass filters in receiver circuits and integrating the receiver circuits with voltage regulators.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130114794","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 : 2022-03-12DOI: 10.1109/ICIPRob54042.2022.9798724
Sagar Deep Deb, R. K. Jha
Breast Cancer is one of the most common forms of cancer occurring in women. According to GLOBCON, 24.2% of new cancer types are related to breast cancer. Early detection followed by a proper diagnosis can help to combat this kind of serious disease. Segmentation of mammography lesions has been proven to be a valuable source of information for the detection and classification of breast cancer. Segmentation can assist both in extracting shape-related features and providing accurate localization of the lesions. In this paper, detailed research on the segmentation of the mammography images using two different networks, namely U-Net and BCDU-Net is done. A comparison of the performance concerning Dice Coefficient and Jaccard Similarity is done on two subsets of the same dataset, one on the full mammogram image and another on the ROI extracted from the mammogram. The evaluation results of the proposed research achieve the highest Jaccard and Dice coefficient of 0.7872 and 0.8376 respectively on the full mammogram. Whereas the figures for ROI segmentation are 0.8098 and 0.8723 respectively. These results demonstrate that, with equal data size, both the network provides better segmentation performance on ROI than on full mammogram.
{"title":"Segmentation of Mammogram Images Using Deep Learning for Breast Cancer Detection","authors":"Sagar Deep Deb, R. K. Jha","doi":"10.1109/ICIPRob54042.2022.9798724","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798724","url":null,"abstract":"Breast Cancer is one of the most common forms of cancer occurring in women. According to GLOBCON, 24.2% of new cancer types are related to breast cancer. Early detection followed by a proper diagnosis can help to combat this kind of serious disease. Segmentation of mammography lesions has been proven to be a valuable source of information for the detection and classification of breast cancer. Segmentation can assist both in extracting shape-related features and providing accurate localization of the lesions. In this paper, detailed research on the segmentation of the mammography images using two different networks, namely U-Net and BCDU-Net is done. A comparison of the performance concerning Dice Coefficient and Jaccard Similarity is done on two subsets of the same dataset, one on the full mammogram image and another on the ROI extracted from the mammogram. The evaluation results of the proposed research achieve the highest Jaccard and Dice coefficient of 0.7872 and 0.8376 respectively on the full mammogram. Whereas the figures for ROI segmentation are 0.8098 and 0.8723 respectively. These results demonstrate that, with equal data size, both the network provides better segmentation performance on ROI than on full mammogram.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115827696","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 : 2022-03-12DOI: 10.1109/ICIPRob54042.2022.9798732
U. Manawadu, M. Deen, P. R. D. De Silva
Robots have been known to assist in making our lives more convenient in everyday situations by interacting with humans. Human-Robot Interaction is the area that focuses on developing methods that allow robots to interact with humans effortlessly. Humans may not be comfortable interacting or working together with robots in close proximity. However, the need for this close interaction with robots in situations such as escorting a group of people and guiding a group of people has led to situations where humans and robots are required to move and walk together. Research conducted into human walking behavior has shown that humans tend to walk in a side-by-side formation whenever possible. Therefore, the designers of new generational robots began to capture these qualities of humans when designing their robots. However, a major problem that arose when attempting to implement side-by-side motion models for robots was the fact that humans tend to have an intimate or personal space that is considered as a comfort zone for them. Therefore, the necessity arose to find a method that facilitates side-by-side walking for robots without invading human-personal space. As a remedy for this issue, a methodology was developed that was focused on exploring a comfort zone in side-by-side communication for human-robot interaction that allows the robot to walk side by side along with humans in a controlled environment without invading the human companion’s personal space. This research will attempt at bringing the human quality of companionship to robots to enhance human-robot interaction.
{"title":"Exploring a Comfort Zone in Side-by-Side Communication for Human-Robot Interaction","authors":"U. Manawadu, M. Deen, P. R. D. De Silva","doi":"10.1109/ICIPRob54042.2022.9798732","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798732","url":null,"abstract":"Robots have been known to assist in making our lives more convenient in everyday situations by interacting with humans. Human-Robot Interaction is the area that focuses on developing methods that allow robots to interact with humans effortlessly. Humans may not be comfortable interacting or working together with robots in close proximity. However, the need for this close interaction with robots in situations such as escorting a group of people and guiding a group of people has led to situations where humans and robots are required to move and walk together. Research conducted into human walking behavior has shown that humans tend to walk in a side-by-side formation whenever possible. Therefore, the designers of new generational robots began to capture these qualities of humans when designing their robots. However, a major problem that arose when attempting to implement side-by-side motion models for robots was the fact that humans tend to have an intimate or personal space that is considered as a comfort zone for them. Therefore, the necessity arose to find a method that facilitates side-by-side walking for robots without invading human-personal space. As a remedy for this issue, a methodology was developed that was focused on exploring a comfort zone in side-by-side communication for human-robot interaction that allows the robot to walk side by side along with humans in a controlled environment without invading the human companion’s personal space. This research will attempt at bringing the human quality of companionship to robots to enhance human-robot interaction.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124156264","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 : 2022-03-12DOI: 10.1109/ICIPRob54042.2022.9798745
S. A. I. P. Diddeniya, H. Gunasinghe, C. Premachandra
YouTube, owned by Google LLC, is the most widespread video platform. It has gained much popularity in Sri Lanka within the last couple of years. Youth has an interest of becoming full-time content creators, but lacks technical and marketing knowledge. In this paper, we present a computer aided analysis to provide insights of trending YouTube videos in Sri Lanka. The system gets YouTube trending video data of one and a half months in year 2021 as input and analyze them to report information on video title, description and thumbnail which are the main parameters of YouTube algorithm when deciding on a trending video. Particularly, the system uses YOLO and RetinaNet for detecting objects in thumbnails. Moreover, Sri Lankan video content mainly include Sinhala language which is the mostly used language in the country. We used Sinhala language processing techniques for reporting various information. In summary, using the provided information, a YouTuber can decide on the: (1) colors and objects to include in the thumbnail, (2) title and the description by considering word count and symbols, (3) number of tags, words and phrases to include in a tag and (4) date and time to publish the video. The results indicate that the proposed approach can significantly support an accurate decision of YouTube video upload with a little computational effort.
{"title":"YouTube Trending Video Analysis in Sri Lanka","authors":"S. A. I. P. Diddeniya, H. Gunasinghe, C. Premachandra","doi":"10.1109/ICIPRob54042.2022.9798745","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798745","url":null,"abstract":"YouTube, owned by Google LLC, is the most widespread video platform. It has gained much popularity in Sri Lanka within the last couple of years. Youth has an interest of becoming full-time content creators, but lacks technical and marketing knowledge. In this paper, we present a computer aided analysis to provide insights of trending YouTube videos in Sri Lanka. The system gets YouTube trending video data of one and a half months in year 2021 as input and analyze them to report information on video title, description and thumbnail which are the main parameters of YouTube algorithm when deciding on a trending video. Particularly, the system uses YOLO and RetinaNet for detecting objects in thumbnails. Moreover, Sri Lankan video content mainly include Sinhala language which is the mostly used language in the country. We used Sinhala language processing techniques for reporting various information. In summary, using the provided information, a YouTuber can decide on the: (1) colors and objects to include in the thumbnail, (2) title and the description by considering word count and symbols, (3) number of tags, words and phrases to include in a tag and (4) date and time to publish the video. The results indicate that the proposed approach can significantly support an accurate decision of YouTube video upload with a little computational effort.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123933051","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 : 2022-03-12DOI: 10.1109/ICIPRob54042.2022.9798729
Ken Nakahara, Y. Kobayashi
Learning approaches to robot control problems generally require a lot of trials, which is crucial to make the approaches available in wider applications. As a means to improve learning efficiency, it is promising to introduce methodologies and ideas developed in the control theory. Aiming at introducing an idea of nonlinear control method to learning approach, this paper presents an acquisition of a state space that allows control to reach a target for the two-wheeled mobile robot with non-holonomic constraints. In the proposed framework, it is assumed that knowledge of the sensor is not available in advance. An adaptive grid distribution algorithm to cope with a non-holonomic controller scheme is proposed. It was experimentally confirmed that the robot could reach the target point stably by the proposed method. The proposed method presents an idea to effectively integrate machine learning and control theory and it has the potential to become a unified learning method that can be applied to various control targets with fewer samples or trials.
{"title":"Automatic Generation of Feedback Stabilizable State Space for Non-holonomic Mobile Robots","authors":"Ken Nakahara, Y. Kobayashi","doi":"10.1109/ICIPRob54042.2022.9798729","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798729","url":null,"abstract":"Learning approaches to robot control problems generally require a lot of trials, which is crucial to make the approaches available in wider applications. As a means to improve learning efficiency, it is promising to introduce methodologies and ideas developed in the control theory. Aiming at introducing an idea of nonlinear control method to learning approach, this paper presents an acquisition of a state space that allows control to reach a target for the two-wheeled mobile robot with non-holonomic constraints. In the proposed framework, it is assumed that knowledge of the sensor is not available in advance. An adaptive grid distribution algorithm to cope with a non-holonomic controller scheme is proposed. It was experimentally confirmed that the robot could reach the target point stably by the proposed method. The proposed method presents an idea to effectively integrate machine learning and control theory and it has the potential to become a unified learning method that can be applied to various control targets with fewer samples or trials.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123351221","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 : 2022-03-12DOI: 10.1109/ICIPRob54042.2022.9798727
Bhavik Patel, Jyotindra Narayan, S. K. Dwivedy
Biological snakes can efficiently move from one place to another in different environmental conditions. Inspired by such locomotion behaviours, a biomimetic snake robot should have some adaptability features to foster several engineering applications. In this work, for energy-efficient locomotion, the optimal gait parameters of an underwater snake robot are investigated at the expense of different environmental drag force conditions and water current velocity. At first, mathematical modelling of underwater snake robot is briefly presented. Thereafter, a symbiotic organism search (SOS) algorithm is exploited to obtained the optimal gait parameters subjected to the cost function of maximum tangential velocity and minimum power consumption. The simulation runs have shown the potential of the proposed optimization algorithm for a cost effective locomotion of the underwater snake robot.
{"title":"Symbiotic Organism Search-based Locomotion of Underwater Snake Robot in various Environments","authors":"Bhavik Patel, Jyotindra Narayan, S. K. Dwivedy","doi":"10.1109/ICIPRob54042.2022.9798727","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798727","url":null,"abstract":"Biological snakes can efficiently move from one place to another in different environmental conditions. Inspired by such locomotion behaviours, a biomimetic snake robot should have some adaptability features to foster several engineering applications. In this work, for energy-efficient locomotion, the optimal gait parameters of an underwater snake robot are investigated at the expense of different environmental drag force conditions and water current velocity. At first, mathematical modelling of underwater snake robot is briefly presented. Thereafter, a symbiotic organism search (SOS) algorithm is exploited to obtained the optimal gait parameters subjected to the cost function of maximum tangential velocity and minimum power consumption. The simulation runs have shown the potential of the proposed optimization algorithm for a cost effective locomotion of the underwater snake robot.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129904628","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 : 2022-03-12DOI: 10.1109/ICIPRob54042.2022.9798720
Kuan-min Huang, H. Samani, Changguo Yang, Jie-Sheng Chen
The alternating direction method of multipliers (ADMM) is an important method to solve convex optimization problems. Due to the optimization tasks increased with the sort of machine learning applications, ADMM has gained much more attention recently. The principle of ADMM solves problems by breaking them into smaller pieces to specially limit the problem dimension. Each of the pieces are then easier to handle and speed up accordingly the total computational time to reach the optimum. With the speeding-up, it was widely adopted for optimization in a number of areas. In this paper, we start the explanation from the constrained convex optimization, and the relation between primal problem and dual problem. With the preliminary explanation, two optimization algorithms are introduced, including the dual ascent and the dual decomposition approaches. An introduction of augmented Lagrangian, the key to success ADMM, is also followed up ahead for elaboration. Finally, the main topic of ADMM is explained algorithmically based on the fundamentals, and an example code is outlined for implementation.
{"title":"Alternating Direction Method of Multipliers for Convex Optimization in Machine Learning - Interpretation and Implementation","authors":"Kuan-min Huang, H. Samani, Changguo Yang, Jie-Sheng Chen","doi":"10.1109/ICIPRob54042.2022.9798720","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798720","url":null,"abstract":"The alternating direction method of multipliers (ADMM) is an important method to solve convex optimization problems. Due to the optimization tasks increased with the sort of machine learning applications, ADMM has gained much more attention recently. The principle of ADMM solves problems by breaking them into smaller pieces to specially limit the problem dimension. Each of the pieces are then easier to handle and speed up accordingly the total computational time to reach the optimum. With the speeding-up, it was widely adopted for optimization in a number of areas. In this paper, we start the explanation from the constrained convex optimization, and the relation between primal problem and dual problem. With the preliminary explanation, two optimization algorithms are introduced, including the dual ascent and the dual decomposition approaches. An introduction of augmented Lagrangian, the key to success ADMM, is also followed up ahead for elaboration. Finally, the main topic of ADMM is explained algorithmically based on the fundamentals, and an example code is outlined for implementation.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125257580","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 : 2022-03-12DOI: 10.1109/ICIPRob54042.2022.9798716
Sittichai Wangwiwattana, Koike Yoshikazu
In this research, we devised a low cost and low voltage arc-fault detector. The circuit detection method is to measure peak current from the current transformer and make the comparison between non-arc-fault state and arc-fault state. Since the output current peak created by the current sense transformer in arc-fault state has certain jagged edge, voltage output from the transformer is substantially lower than that of normal state. Such a voltage variation causes into changes of magnetic flux in the current transformer. It is expected that the large voltage difference between arc fault and non-arc fault state appears. It can be used to detect and identify the arc-fault even if arc-fault influence on the supplied voltage is quite low. In this report, we are able to detect the direct pattern difference between non-arc fault and arc fault state. The detection setup for proposed method can be created successfully.
{"title":"Arc-Fault Detection method with Saturated Current Transformer","authors":"Sittichai Wangwiwattana, Koike Yoshikazu","doi":"10.1109/ICIPRob54042.2022.9798716","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798716","url":null,"abstract":"In this research, we devised a low cost and low voltage arc-fault detector. The circuit detection method is to measure peak current from the current transformer and make the comparison between non-arc-fault state and arc-fault state. Since the output current peak created by the current sense transformer in arc-fault state has certain jagged edge, voltage output from the transformer is substantially lower than that of normal state. Such a voltage variation causes into changes of magnetic flux in the current transformer. It is expected that the large voltage difference between arc fault and non-arc fault state appears. It can be used to detect and identify the arc-fault even if arc-fault influence on the supplied voltage is quite low. In this report, we are able to detect the direct pattern difference between non-arc fault and arc fault state. The detection setup for proposed method can be created successfully.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114917713","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 : 2022-03-12DOI: 10.1109/ICIPRob54042.2022.9798744
Md. Hasibur Rahman, Mazharul Islam, Md. Fayed Al Monir, S. Alam, Ruzbelt, Md. Mijanur Rahman, M. Shidujaman, Rubaiyat Islam
Kinematics analysis is essential for finding the robot manipulator's joint motions. Using kinematics, we can determine how the robot's arms will move and the possible direction of that arm's end-effector. Kinematics analysis is split into two parts forward Kinematics and Inverse Kinematics. Forward Kinematics measure the positions and orientations of the robot's end-effector, and we can calculate the joint angles by using inverse kinematics. This study provided mathematical derivation for forward and Inverse kinematics to determine our robots’ positions and joint angles briefly. To implement different walking motions in a quadruped robot, firstly, we need to analyze the single-leg structure. In this study, we analyzed and derived the forward and inverse kinematics of the quadruped robots and verified their correlation. We used python and Pybullet physics engines to analyze our robot leg motions for mathematical programming.
{"title":"Kinematics analysis of a quadruped robot: Simulation and Evaluation","authors":"Md. Hasibur Rahman, Mazharul Islam, Md. Fayed Al Monir, S. Alam, Ruzbelt, Md. Mijanur Rahman, M. Shidujaman, Rubaiyat Islam","doi":"10.1109/ICIPRob54042.2022.9798744","DOIUrl":"https://doi.org/10.1109/ICIPRob54042.2022.9798744","url":null,"abstract":"Kinematics analysis is essential for finding the robot manipulator's joint motions. Using kinematics, we can determine how the robot's arms will move and the possible direction of that arm's end-effector. Kinematics analysis is split into two parts forward Kinematics and Inverse Kinematics. Forward Kinematics measure the positions and orientations of the robot's end-effector, and we can calculate the joint angles by using inverse kinematics. This study provided mathematical derivation for forward and Inverse kinematics to determine our robots’ positions and joint angles briefly. To implement different walking motions in a quadruped robot, firstly, we need to analyze the single-leg structure. In this study, we analyzed and derived the forward and inverse kinematics of the quadruped robots and verified their correlation. We used python and Pybullet physics engines to analyze our robot leg motions for mathematical programming.","PeriodicalId":435575,"journal":{"name":"2022 2nd International Conference on Image Processing and Robotics (ICIPRob)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114409401","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：