Pub Date : 2018-06-01DOI: 10.1109/ICSSE.2018.8520239
Y. Chan, Meng-Hsun Tsai, Ping-Hsuan Sun, Ya-Lan Chang, Chwei-Shyong Tsaig
This study focused on ischemic stroke by using rats with middle cerebral artery occlusion (MCAO) as experimental subjects, and examining the images of their brains obtained from staining with 2, 3, 5-triphenyl tetrazolium chloride (TTC). The stroke rat brain infarct volume and atrophy volume computation system (SRBIAVC system) segmented the images via methods of background removal, gamma correction, brain center line detection, and genetic algorithm to yield a correct estimate on the volume of brain infarct and atrophy. This way, the SRBIAVC system can provide useful information in the development of new drugs for stroke treatment. As indicated by the experimental results, the estimates obtained by the SRBIAVC system were better than those by other methods and more closely approximated the estimates by experts.
{"title":"Ratio Computation of Stroke Rat Brain Infarct Volume and Atrophy Volume Relative to the Normal Brain Volume","authors":"Y. Chan, Meng-Hsun Tsai, Ping-Hsuan Sun, Ya-Lan Chang, Chwei-Shyong Tsaig","doi":"10.1109/ICSSE.2018.8520239","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520239","url":null,"abstract":"This study focused on ischemic stroke by using rats with middle cerebral artery occlusion (MCAO) as experimental subjects, and examining the images of their brains obtained from staining with 2, 3, 5-triphenyl tetrazolium chloride (TTC). The stroke rat brain infarct volume and atrophy volume computation system (SRBIAVC system) segmented the images via methods of background removal, gamma correction, brain center line detection, and genetic algorithm to yield a correct estimate on the volume of brain infarct and atrophy. This way, the SRBIAVC system can provide useful information in the development of new drugs for stroke treatment. As indicated by the experimental results, the estimates obtained by the SRBIAVC system were better than those by other methods and more closely approximated the estimates by experts.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127628728","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}
Currently, Android phones accounted for over 85 % of all smartphone sales as of 2017. Because the system allows users to install the unofficial apps, it will be targeted by malware easily. Using general anti-virus software to scan apps usually detected a known virus species only. As for new type of unknown variant, is not detectable normally. In this paper, we present a SVM-based mechanism to detect the malware and normal apps. The proposed idea scanning and recording features for both required and used permissions of the list. We adopt the LibSVM to classify the unknown apps. The experimental results indicate the accurate rate of 99% for the correct identification of both benign and malware even for the unknown applications. We propose not only a simple but also feasible approach to detect mobile apps.
{"title":"A SVM-Based Malware Detection Mechanism for Android Devices","authors":"Yung-Feng Lu, Chin-Fu Kuo, Hung-Yuan Chen, Chang-Wei Chen, Shih-Chun Chou","doi":"10.1109/ICSSE.2018.8520241","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520241","url":null,"abstract":"Currently, Android phones accounted for over 85 % of all smartphone sales as of 2017. Because the system allows users to install the unofficial apps, it will be targeted by malware easily. Using general anti-virus software to scan apps usually detected a known virus species only. As for new type of unknown variant, is not detectable normally. In this paper, we present a SVM-based mechanism to detect the malware and normal apps. The proposed idea scanning and recording features for both required and used permissions of the list. We adopt the LibSVM to classify the unknown apps. The experimental results indicate the accurate rate of 99% for the correct identification of both benign and malware even for the unknown applications. We propose not only a simple but also feasible approach to detect mobile apps.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132525770","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8520107
Jun-Lin Chen, Jing-Zhong Wang, Tsung-Ying Sun
This study mitigates the effect of sampling errors that comes from sampling rate in reality when localizing the sound source. In general, the sampling errors may make sound source localization that uses multi-hyperboloids method, for example, time difference of arrival (TDOA), have wrong sound source estimation or do not work. Due to alleviate the wrong source estimation, a geometric approach that transfers from multi-hyperboloids to multiplanes for sound source localization is proposed. This study also added a discriminant for check of different TDOAs conditions. Because of the easy realization for embedded systems, the closely spaced microphone array was used in this study. From experiments, the propose method successful improve the accuracy and validity of the source estimation.
{"title":"A Multiplanes Geometric Approach for Sound Source Localization with TDOA","authors":"Jun-Lin Chen, Jing-Zhong Wang, Tsung-Ying Sun","doi":"10.1109/ICSSE.2018.8520107","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520107","url":null,"abstract":"This study mitigates the effect of sampling errors that comes from sampling rate in reality when localizing the sound source. In general, the sampling errors may make sound source localization that uses multi-hyperboloids method, for example, time difference of arrival (TDOA), have wrong sound source estimation or do not work. Due to alleviate the wrong source estimation, a geometric approach that transfers from multi-hyperboloids to multiplanes for sound source localization is proposed. This study also added a discriminant for check of different TDOAs conditions. Because of the easy realization for embedded systems, the closely spaced microphone array was used in this study. From experiments, the propose method successful improve the accuracy and validity of the source estimation.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133112555","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8519972
Direselign Addis, Chuan-Ming Liu, Van-Dai Ta
Bidirectional Long Short-Term Memory (LSTM) networks have brought tremendous results on many machine learning tasks including handwritten and machine printed character recognition systems. The Ethiopic script uses a large number of characters in the writing and existence of visually similar character, which results in a challenge for OCR development. In this paper, we present application of bidirectional LSTM neural networks to recognize machine printed Ethiopic scripts. To train and test the model, we collect text files from different source written in Amharic, Ge’ ez and Tigrigna language and generate 96,000 artificial text line images by applying different degradation techniques. Additionally, to test the model with real scanned documents, we use real 12 page scanned images from Tsenat book. Without using any language modeling and any other post-processing, LSTM networks attain an average character error rate of 2.12%, and this indicates the proposed network achieves a promising result.
{"title":"Printed Ethiopic Script Recognition by Using LSTM Networks","authors":"Direselign Addis, Chuan-Ming Liu, Van-Dai Ta","doi":"10.1109/ICSSE.2018.8519972","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8519972","url":null,"abstract":"Bidirectional Long Short-Term Memory (LSTM) networks have brought tremendous results on many machine learning tasks including handwritten and machine printed character recognition systems. The Ethiopic script uses a large number of characters in the writing and existence of visually similar character, which results in a challenge for OCR development. In this paper, we present application of bidirectional LSTM neural networks to recognize machine printed Ethiopic scripts. To train and test the model, we collect text files from different source written in Amharic, Ge’ ez and Tigrigna language and generate 96,000 artificial text line images by applying different degradation techniques. Additionally, to test the model with real scanned documents, we use real 12 page scanned images from Tsenat book. Without using any language modeling and any other post-processing, LSTM networks attain an average character error rate of 2.12%, and this indicates the proposed network achieves a promising result.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131688922","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8519990
Li-Wei Cheng, J. Chang
With rapid development of assistive technologies, robots have been adopted to assist impaired persons to perform daily functions. To increase functionality of robotic arm in grasping, a universal robotic gripper consists of multiple degrees of freedom (DOF) is proposed and examined in this paper. Through modelling, simulation, and mechatronics integration, the proposed gripper design is validated to be able to morph its shape to adapt objects with various shapes. Compliance of the gripper in grasping is also validated, which can increase the safety should it be included in assistive devices.
{"title":"Design of a Multiple Degrees of Freedom Robotic Gripper for Adaptive Compliant Actuation","authors":"Li-Wei Cheng, J. Chang","doi":"10.1109/ICSSE.2018.8519990","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8519990","url":null,"abstract":"With rapid development of assistive technologies, robots have been adopted to assist impaired persons to perform daily functions. To increase functionality of robotic arm in grasping, a universal robotic gripper consists of multiple degrees of freedom (DOF) is proposed and examined in this paper. Through modelling, simulation, and mechatronics integration, the proposed gripper design is validated to be able to morph its shape to adapt objects with various shapes. Compliance of the gripper in grasping is also validated, which can increase the safety should it be included in assistive devices.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133378566","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8520207
Ta-Chung Wang, Cheng-Hsun Wu
This research is about building an input-output mathematical model for wind turbine that can be used for forecasting and monitoring. The proposed polynomial modeling of the wind turbine consists of monomials of wind speed and autoregressive terms of the produced power. The results indicate that the proposed approach is fast in computation while maintaining the accuracy of forecasting the generated power output. Moreover, the proposed model is robust in the sense that the model generated is statistically consistent in the presence of randomness of wind speed. A statistical method is also proposed so that the generated model can be used for wind turbine health monitoring.
{"title":"Verification and Analysist About Autoregressive Exogenous Model for Wind Power Forecasting","authors":"Ta-Chung Wang, Cheng-Hsun Wu","doi":"10.1109/ICSSE.2018.8520207","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520207","url":null,"abstract":"This research is about building an input-output mathematical model for wind turbine that can be used for forecasting and monitoring. The proposed polynomial modeling of the wind turbine consists of monomials of wind speed and autoregressive terms of the produced power. The results indicate that the proposed approach is fast in computation while maintaining the accuracy of forecasting the generated power output. Moreover, the proposed model is robust in the sense that the model generated is statistically consistent in the presence of randomness of wind speed. A statistical method is also proposed so that the generated model can be used for wind turbine health monitoring.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"349 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133078349","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8520157
Wei-chen Lee, Yu-Tzu Lee, Ching-chih Wei
To reduce the machining errors as much as possible is a goal for many machine shops. After a part is machined and measured, the errors are known but how to reduce them is still an issue. The objective of this research was to develop an automatic system, which can adopt the measured data to modify the original CAD model of the machined part so that the cutting tool paths can be regenerated based on the reconstruction of the CAD model. Then we can perform finish machining on the part by using the new tool paths to remove much of the remaining errors. We already completed the two-dimensional profile machining and found promising. The errors of three squares with different orientations can be controlled within 0.0065 mm. We are continuing to work on the three-dimensional free-form surfaces.
{"title":"Machining Error Compensation Based on the Reconstructed Free-Form Surfaces of CAD Models","authors":"Wei-chen Lee, Yu-Tzu Lee, Ching-chih Wei","doi":"10.1109/ICSSE.2018.8520157","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520157","url":null,"abstract":"To reduce the machining errors as much as possible is a goal for many machine shops. After a part is machined and measured, the errors are known but how to reduce them is still an issue. The objective of this research was to develop an automatic system, which can adopt the measured data to modify the original CAD model of the machined part so that the cutting tool paths can be regenerated based on the reconstruction of the CAD model. Then we can perform finish machining on the part by using the new tool paths to remove much of the remaining errors. We already completed the two-dimensional profile machining and found promising. The errors of three squares with different orientations can be controlled within 0.0065 mm. We are continuing to work on the three-dimensional free-form surfaces.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131322510","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8520151
Yu-Lin Jeng, Sheng-Bo Huang, Chin-Feng Lai
Road quality can be representative of a country's development status, affect transportation speeds and traveler safety. However, there is no standard or set of rules to protect people from the dangers of damaged roads. This study proposes a method for evaluating road quality, which has been made possible by the recent rapid development of information technology and machine learning algorithms, and the popularity and widespread use of smartphones. The proposed inspection method is a road quality inspection APP which collects raw data from smartphone sensors, including GPS and accelerator sensors. Once the data is collected, the server side of the proposed system runs an anomaly detection algorithm to interpret the recorded oscillating amplitude of a specific section of road. The calculated results are then added to the Google Maps app, and abnormal road sections are marked in different colors.
{"title":"Inspect Road Quality by Using Anomaly Detection Approach","authors":"Yu-Lin Jeng, Sheng-Bo Huang, Chin-Feng Lai","doi":"10.1109/ICSSE.2018.8520151","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520151","url":null,"abstract":"Road quality can be representative of a country's development status, affect transportation speeds and traveler safety. However, there is no standard or set of rules to protect people from the dangers of damaged roads. This study proposes a method for evaluating road quality, which has been made possible by the recent rapid development of information technology and machine learning algorithms, and the popularity and widespread use of smartphones. The proposed inspection method is a road quality inspection APP which collects raw data from smartphone sensors, including GPS and accelerator sensors. Once the data is collected, the server side of the proposed system runs an anomaly detection algorithm to interpret the recorded oscillating amplitude of a specific section of road. The calculated results are then added to the Google Maps app, and abnormal road sections are marked in different colors.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116166356","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 : 2018-06-01DOI: 10.1109/ICSSE.2018.8520208
S. Doungpan, S. Moryadee, C. U-tapao, Z. Laokhongthavorn
This paper aims to provide a method for responding of natural disaster by applying the set facility location approach on disaster and emergency management in order to make an optimal location of emergency management facilities in pre-disaster phase. This paper presents and compares three models including maximal covering, p-median, and p-center models to determine an optimal location of emergency management facilities. These three models are applied to the case study of Chiang Rai province, Thailand. The model input data is generated from a geographic information system. The results show that a case study can be implemented with a real situation with comparison of an optimal solution from three models.
{"title":"Analysis of Three Emergency Medical Location Models: A Case Study of Thailand*","authors":"S. Doungpan, S. Moryadee, C. U-tapao, Z. Laokhongthavorn","doi":"10.1109/ICSSE.2018.8520208","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520208","url":null,"abstract":"This paper aims to provide a method for responding of natural disaster by applying the set facility location approach on disaster and emergency management in order to make an optimal location of emergency management facilities in pre-disaster phase. This paper presents and compares three models including maximal covering, p-median, and p-center models to determine an optimal location of emergency management facilities. These three models are applied to the case study of Chiang Rai province, Thailand. The model input data is generated from a geographic information system. The results show that a case study can be implemented with a real situation with comparison of an optimal solution from three models.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"33 1-2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120908880","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}
In the fast-paced modern life, everyone needs some time to relax. A good way to do it is through massage, it helps to get relief from body pain or eases stress and anxiety and then helps to lower blood pressure and more and more other health benefits. Nowadays, you can enjoy the professional massage machine without a therapist. The point and massage therapy machine will offer a more affordable and user-friendly alternative with the same benefits as the massage by the therapist. In this paper, a study of point and massage therapy using image processing is described and the information from image data also extracted to control automation machine or robot massage. After extracting the points from scanning images by a camera, the massage therapy trajectories were sent to master computer for intelligent control, the massage lines would be mapped to support for massage processes. It is not only suitable for every single person and save the time of but also be easy to be data retrieval and not depend on professional experts. This study is based on actual demand so practical application is very wide. Moreover, it will solve the time-consuming problem of experts. In addition to, with the automation, the quality of massage therapy is much higher and the process will be continuous.
{"title":"A Study of Predicting Human Points and Massage Therapy Lines Using Image Processing","authors":"Nguyen Thanh Phong, Vo Hung Phat, Truong Cong Toai, Nguyen Truong Thinh","doi":"10.1109/ICSSE.2018.8520142","DOIUrl":"https://doi.org/10.1109/ICSSE.2018.8520142","url":null,"abstract":"In the fast-paced modern life, everyone needs some time to relax. A good way to do it is through massage, it helps to get relief from body pain or eases stress and anxiety and then helps to lower blood pressure and more and more other health benefits. Nowadays, you can enjoy the professional massage machine without a therapist. The point and massage therapy machine will offer a more affordable and user-friendly alternative with the same benefits as the massage by the therapist. In this paper, a study of point and massage therapy using image processing is described and the information from image data also extracted to control automation machine or robot massage. After extracting the points from scanning images by a camera, the massage therapy trajectories were sent to master computer for intelligent control, the massage lines would be mapped to support for massage processes. It is not only suitable for every single person and save the time of but also be easy to be data retrieval and not depend on professional experts. This study is based on actual demand so practical application is very wide. Moreover, it will solve the time-consuming problem of experts. In addition to, with the automation, the quality of massage therapy is much higher and the process will be continuous.","PeriodicalId":431387,"journal":{"name":"2018 International Conference on System Science and Engineering (ICSSE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123420200","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：