Pub Date : 2015-06-06DOI: 10.1109/ICCE-TW.2015.7216888
J. C. Yu, I-Cheng Chang, Yi-Jun Lin
With the popularization of mobile devices and cloud storages, people tend to store photos and videos through internet. Recently many cloud systems start providing functions to produce reviewing films from stored media files. However, the background music of the film usually does not match the video's emotion because the added music is usually selected randomly. This work proposed an emotion-based music adding cloud service that generates a reviewing film with the appropriate background music fitting the emotion of the corresponding video.
{"title":"A dynamic music adding system based on cloud computing","authors":"J. C. Yu, I-Cheng Chang, Yi-Jun Lin","doi":"10.1109/ICCE-TW.2015.7216888","DOIUrl":"https://doi.org/10.1109/ICCE-TW.2015.7216888","url":null,"abstract":"With the popularization of mobile devices and cloud storages, people tend to store photos and videos through internet. Recently many cloud systems start providing functions to produce reviewing films from stored media files. However, the background music of the film usually does not match the video's emotion because the added music is usually selected randomly. This work proposed an emotion-based music adding cloud service that generates a reviewing film with the appropriate background music fitting the emotion of the corresponding video.","PeriodicalId":340402,"journal":{"name":"2015 IEEE International Conference on Consumer Electronics - Taiwan","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125685055","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 : 2015-06-06DOI: 10.1109/ICCE-TW.2015.7216972
Chung-Yi Wu, J. Huang, Han-Yen Yu, Jiann-Jone Chen
With the prevalence of personal computer devices and Internet, it has to provide scalable video coding to serve users under heterogeneous network environments. We proposed to develop a cloud-based video transcoding system, in which a hierarchical scheduling algorithm has been developed to speed up the process. The efficiency can be maintained at 98% and processing time can be reduced to 13% smaller.
{"title":"Design and implementation of a video transcoding system in cloud computing platforms","authors":"Chung-Yi Wu, J. Huang, Han-Yen Yu, Jiann-Jone Chen","doi":"10.1109/ICCE-TW.2015.7216972","DOIUrl":"https://doi.org/10.1109/ICCE-TW.2015.7216972","url":null,"abstract":"With the prevalence of personal computer devices and Internet, it has to provide scalable video coding to serve users under heterogeneous network environments. We proposed to develop a cloud-based video transcoding system, in which a hierarchical scheduling algorithm has been developed to speed up the process. The efficiency can be maintained at 98% and processing time can be reduced to 13% smaller.","PeriodicalId":340402,"journal":{"name":"2015 IEEE International Conference on Consumer Electronics - Taiwan","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127623023","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}
One of the hardest parts of controlling asthma is making sure patients are getting the right does of medicine through their inhaler based on doctor's instructions. However, the patients, especially children, frequently miss doses or even forget to use it. In this study, our proposed electronic dose counter directly attached to pressurized metered dose inhaler without modification original inhaler structure, that is used to record the times and timestamps of doses actuated by patients. The dose information automatically uploads and displays in an inhaler APP ran on a smartphone. Moreover, the inhaler APP also reminds the patients when they forget to use it in right time. Overall cost of the electronics dose counter is ~$5. Our low-cost smart inhaler counter with inhaler APP could be lowered healthcare cost and saved lives.
{"title":"Low-cost electronic dose counter for pressurized metered dose inhaler","authors":"Chen-Chia Chen, Yi-Jun Liu, Shao-Min Wen, Chih-Chyau Yang, Jin-Ju Chue, Chieh-Ming Wu, Chun-Ming Huang","doi":"10.1109/ICCE-TW.2015.7216965","DOIUrl":"https://doi.org/10.1109/ICCE-TW.2015.7216965","url":null,"abstract":"One of the hardest parts of controlling asthma is making sure patients are getting the right does of medicine through their inhaler based on doctor's instructions. However, the patients, especially children, frequently miss doses or even forget to use it. In this study, our proposed electronic dose counter directly attached to pressurized metered dose inhaler without modification original inhaler structure, that is used to record the times and timestamps of doses actuated by patients. The dose information automatically uploads and displays in an inhaler APP ran on a smartphone. Moreover, the inhaler APP also reminds the patients when they forget to use it in right time. Overall cost of the electronics dose counter is ~$5. Our low-cost smart inhaler counter with inhaler APP could be lowered healthcare cost and saved lives.","PeriodicalId":340402,"journal":{"name":"2015 IEEE International Conference on Consumer Electronics - Taiwan","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126712196","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}
For depth-from-stereo vision applications such as driving assistance and object-size estimation, the accuracy of disparity estimation determines the precision of depth measurement. Conventional dense methods are hard to estimate disparity within a 0.1 pixel precision. In this paper, we present a novel object-based method to achieve robust and deep sub-pixel accurate disparity estimation. In our experimental system, it can provide depth measurement with less than 5% relative error within 150 m.
{"title":"Sub-pixel disparity estimation in continuous space","authors":"Li-De Chen, Jo-Jiun Yu, Wei-Han Cheng, Chao-Tsung Huang","doi":"10.1109/ICCE-TW.2015.7216807","DOIUrl":"https://doi.org/10.1109/ICCE-TW.2015.7216807","url":null,"abstract":"For depth-from-stereo vision applications such as driving assistance and object-size estimation, the accuracy of disparity estimation determines the precision of depth measurement. Conventional dense methods are hard to estimate disparity within a 0.1 pixel precision. In this paper, we present a novel object-based method to achieve robust and deep sub-pixel accurate disparity estimation. In our experimental system, it can provide depth measurement with less than 5% relative error within 150 m.","PeriodicalId":340402,"journal":{"name":"2015 IEEE International Conference on Consumer Electronics - Taiwan","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125064456","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 : 2015-06-06DOI: 10.1109/ICCE-TW.2015.7217025
Wen-Chuan Wu, HuaiChun Hsu, Pei-Yu Lin
This paper presents an active tamper detection and content recovery scheme for digital gray images. It mainly adopts vector quantization compression and treats the index codes as the authentication and recovery data of an image. In order to achieve the purpose of detecting and locating whether an image has been tampered with, this scheme embeds the essential information of authentication and recovery into each pixel value's LSB bit. In addition, this paper also utilizes Chan's LSB matching function to improve the quality of embedded image. Experimental results showed that the authentication data of index codes are able to detect those possible modified regions effectively and clearly. Moreover, the embedded image quality also improves nearly to 1.66dB.
{"title":"Active tamper detection of digital images using VQ compression","authors":"Wen-Chuan Wu, HuaiChun Hsu, Pei-Yu Lin","doi":"10.1109/ICCE-TW.2015.7217025","DOIUrl":"https://doi.org/10.1109/ICCE-TW.2015.7217025","url":null,"abstract":"This paper presents an active tamper detection and content recovery scheme for digital gray images. It mainly adopts vector quantization compression and treats the index codes as the authentication and recovery data of an image. In order to achieve the purpose of detecting and locating whether an image has been tampered with, this scheme embeds the essential information of authentication and recovery into each pixel value's LSB bit. In addition, this paper also utilizes Chan's LSB matching function to improve the quality of embedded image. Experimental results showed that the authentication data of index codes are able to detect those possible modified regions effectively and clearly. Moreover, the embedded image quality also improves nearly to 1.66dB.","PeriodicalId":340402,"journal":{"name":"2015 IEEE International Conference on Consumer Electronics - Taiwan","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125141957","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 : 2015-06-06DOI: 10.1109/ICCE-TW.2015.7216936
Wern-Yarng Shieh, Ti-Ho Wang, Chou-Jen Wang
Vehicle positioning in infrared vehicle-to-infrastructure communication systems can be realized with the aid of signal-direction discrimination. The coming direction of the infrared signal can be acquired with high precision by comparing the sgnal strengths received by different receiving modules in the signal-direction discriminator, provided that all the receiving modules together with their amplification circuits have the same characteristics. This can be fulfilled by a careful calibration. In this paper, the results of two different calibration methods are compared in order to obtain the coming direction of the signal with high accuracy for the aforementioned application.
{"title":"Accuracy and calibration of infrared signal-direction discriminator","authors":"Wern-Yarng Shieh, Ti-Ho Wang, Chou-Jen Wang","doi":"10.1109/ICCE-TW.2015.7216936","DOIUrl":"https://doi.org/10.1109/ICCE-TW.2015.7216936","url":null,"abstract":"Vehicle positioning in infrared vehicle-to-infrastructure communication systems can be realized with the aid of signal-direction discrimination. The coming direction of the infrared signal can be acquired with high precision by comparing the sgnal strengths received by different receiving modules in the signal-direction discriminator, provided that all the receiving modules together with their amplification circuits have the same characteristics. This can be fulfilled by a careful calibration. In this paper, the results of two different calibration methods are compared in order to obtain the coming direction of the signal with high accuracy for the aforementioned application.","PeriodicalId":340402,"journal":{"name":"2015 IEEE International Conference on Consumer Electronics - Taiwan","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124430253","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 : 2015-06-06DOI: 10.1109/ICCE-TW.2015.7216948
S. Tani, Y. Nogami, Masaru Fukushi
This paper addresses a job scheduling problem in Volunteer Computing (VC) systems, where some malicious participant may return incorrect results (sabotaging). Credibility-based job scheduling method, namely ENR-ECJ, is a promising approach to realize high-performance and sabotage-tolerant VC systems based on the credibility of each participant (worker). However, managing the credibility values in the management node may cause considerable performance degradation of whole the system. By implementing ENR-ECJ into a small scale VC system, this paper demonstrates the primacy of ENR-ECJ over existing methods and reveals its condition through the performance evaluation for various number of workers. The results show that ENR-EJC improves the overall performance about 10% when the access frequency of workers is less than 2 per second.
{"title":"An implementation of credibility-based job scheduling method in volunteer computing systems","authors":"S. Tani, Y. Nogami, Masaru Fukushi","doi":"10.1109/ICCE-TW.2015.7216948","DOIUrl":"https://doi.org/10.1109/ICCE-TW.2015.7216948","url":null,"abstract":"This paper addresses a job scheduling problem in Volunteer Computing (VC) systems, where some malicious participant may return incorrect results (sabotaging). Credibility-based job scheduling method, namely ENR-ECJ, is a promising approach to realize high-performance and sabotage-tolerant VC systems based on the credibility of each participant (worker). However, managing the credibility values in the management node may cause considerable performance degradation of whole the system. By implementing ENR-ECJ into a small scale VC system, this paper demonstrates the primacy of ENR-ECJ over existing methods and reveals its condition through the performance evaluation for various number of workers. The results show that ENR-EJC improves the overall performance about 10% when the access frequency of workers is less than 2 per second.","PeriodicalId":340402,"journal":{"name":"2015 IEEE International Conference on Consumer Electronics - Taiwan","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123215807","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 : 2015-06-06DOI: 10.1109/ICCE-TW.2015.7216861
Yu-Jie Jheng, Yu-Hua Yen, Tsung-Ying Sun
This study proposes a symmetry-based forward vehicle detection and collision warning system (FCW) on smartphone. The proposed system identifies forward vehicle by shadow with vehicular symmetry. Through Bayes classifier tracking approach, it can reduce the error detection of image processing. Shadow detection with symmetry-based approach could improve the robustness of identifying forward vehicle. The detection system is migrated the FCW algorithm to Android, and employs mobile camera embedded Android smartphone to capture image of road environment. The FCW kernel processes captured images to obtain vehicle-marking of forward vehicle.
{"title":"A symmetry-based forward vehicle detection and collision warning system on Android smartphone","authors":"Yu-Jie Jheng, Yu-Hua Yen, Tsung-Ying Sun","doi":"10.1109/ICCE-TW.2015.7216861","DOIUrl":"https://doi.org/10.1109/ICCE-TW.2015.7216861","url":null,"abstract":"This study proposes a symmetry-based forward vehicle detection and collision warning system (FCW) on smartphone. The proposed system identifies forward vehicle by shadow with vehicular symmetry. Through Bayes classifier tracking approach, it can reduce the error detection of image processing. Shadow detection with symmetry-based approach could improve the robustness of identifying forward vehicle. The detection system is migrated the FCW algorithm to Android, and employs mobile camera embedded Android smartphone to capture image of road environment. The FCW kernel processes captured images to obtain vehicle-marking of forward vehicle.","PeriodicalId":340402,"journal":{"name":"2015 IEEE International Conference on Consumer Electronics - Taiwan","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131393800","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 : 2015-06-06DOI: 10.1109/ICCE-TW.2015.7216852
Yi-Chen Lu, Feng-Yuan Tai, Hsiao-Ping Tsai
Other than some driving assistant systems that can automatically avoid accidents, providing a driver with highly relevant and real-time traffic information is useful in attracting a driver's attention and striving more reaction time to possible dangers. In this paper, we propose an intelligent traffic information extraction system that explores a vehicle's trajectories to discover its driver's movement patterns and use the discovered patterns to predict the most likely locations that the driver will go in the near future. Based on the proper locations in the near future, our system extract the top-k correlated traffic messages that are situated on the proper way of the driver. To validate our design, we implement the intelligent traffic information extraction system as an Android app and run the app on a car to test the system. The results show the discovered movement patterns can help in extracting highly correlated traffic messages and as the movement routes of a driver are of high regularity, more percentage of the extracted traffic events are situated on the way of the driver.
{"title":"An intelligent personalized traffic information extraction system for road traffic safety","authors":"Yi-Chen Lu, Feng-Yuan Tai, Hsiao-Ping Tsai","doi":"10.1109/ICCE-TW.2015.7216852","DOIUrl":"https://doi.org/10.1109/ICCE-TW.2015.7216852","url":null,"abstract":"Other than some driving assistant systems that can automatically avoid accidents, providing a driver with highly relevant and real-time traffic information is useful in attracting a driver's attention and striving more reaction time to possible dangers. In this paper, we propose an intelligent traffic information extraction system that explores a vehicle's trajectories to discover its driver's movement patterns and use the discovered patterns to predict the most likely locations that the driver will go in the near future. Based on the proper locations in the near future, our system extract the top-k correlated traffic messages that are situated on the proper way of the driver. To validate our design, we implement the intelligent traffic information extraction system as an Android app and run the app on a car to test the system. The results show the discovered movement patterns can help in extracting highly correlated traffic messages and as the movement routes of a driver are of high regularity, more percentage of the extracted traffic events are situated on the way of the driver.","PeriodicalId":340402,"journal":{"name":"2015 IEEE International Conference on Consumer Electronics - Taiwan","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130475484","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 : 2015-06-06DOI: 10.1109/ICCE-TW.2015.7216928
Yi-Zeng Hsieh, Chen-Hsu Wang, M. Su, Ching-Hu Lu, Jen-Chih Yu, Yi Min Chiang
One important factor for the patients in a postoperative recovery is hypothermia. The doctor must decide whether the patients should be sent to another place with better medical therapy. We therefore adopt the proposed PSO (particle swarm optimization) based Fuzzy classifier to retrieve the crisp rules from the postoperative given medical data from UCI machine learning database, where the rules can be used to assist in doctor diagnosis. The average correct ratio of our prediction for the postoperative recovery is about 84%.
{"title":"Prediction of postoperative recovery based on a computational rules extractor","authors":"Yi-Zeng Hsieh, Chen-Hsu Wang, M. Su, Ching-Hu Lu, Jen-Chih Yu, Yi Min Chiang","doi":"10.1109/ICCE-TW.2015.7216928","DOIUrl":"https://doi.org/10.1109/ICCE-TW.2015.7216928","url":null,"abstract":"One important factor for the patients in a postoperative recovery is hypothermia. The doctor must decide whether the patients should be sent to another place with better medical therapy. We therefore adopt the proposed PSO (particle swarm optimization) based Fuzzy classifier to retrieve the crisp rules from the postoperative given medical data from UCI machine learning database, where the rules can be used to assist in doctor diagnosis. The average correct ratio of our prediction for the postoperative recovery is about 84%.","PeriodicalId":340402,"journal":{"name":"2015 IEEE International Conference on Consumer Electronics - Taiwan","volume":"341 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121119859","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：