Pub Date : 2016-11-01DOI: 10.1109/ICORAS.2016.7872623
S. S. Soh, T. Tan, T. A. I. T. Alang, E. Supriyanto
White Matter Hyperintensities (WMHs) are suspected to be a direct manifestation of microvascular ischemic injury in the distribution of the penetrating arteriolar vessels on magnetic resonance imaging (MRI) and usually seen in elderly persons. Further study on this issue is important as it might relate to other diseases. Early detection might be able to prolong brain health in people and prevent the fast progression on neurology illness. Segmentation of image is very useful in medical applications to diagnose any abnormalities in the image. There are three step involved in these process which are preprocessing, segmentation and volume quantification. Segmentation of WMH is done by using W2MHS toolbox and the result is then being compared with LST. The WMHs volume for W2MHS is 90.61.30ml and LST is 78.43ml.
{"title":"White matter hyperintensity segmentation on T2 FLAIR brain images using supervised segmentation method","authors":"S. S. Soh, T. Tan, T. A. I. T. Alang, E. Supriyanto","doi":"10.1109/ICORAS.2016.7872623","DOIUrl":"https://doi.org/10.1109/ICORAS.2016.7872623","url":null,"abstract":"White Matter Hyperintensities (WMHs) are suspected to be a direct manifestation of microvascular ischemic injury in the distribution of the penetrating arteriolar vessels on magnetic resonance imaging (MRI) and usually seen in elderly persons. Further study on this issue is important as it might relate to other diseases. Early detection might be able to prolong brain health in people and prevent the fast progression on neurology illness. Segmentation of image is very useful in medical applications to diagnose any abnormalities in the image. There are three step involved in these process which are preprocessing, segmentation and volume quantification. Segmentation of WMH is done by using W2MHS toolbox and the result is then being compared with LST. The WMHs volume for W2MHS is 90.61.30ml and LST is 78.43ml.","PeriodicalId":393534,"journal":{"name":"2016 International Conference on Robotics, Automation and Sciences (ICORAS)","volume":"330 9‐10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120838083","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 : 2016-11-01DOI: 10.1109/ICORAS.2016.7872620
Julia Löschel, Eko Syprianto, Amiliana Santoso, Habil Jens Haueisen, Manuela Aschoff, Dr. Saravana Kumar Jaganathan
The gold standard in determination of cardiac output is highly invasive and expensive in use. An accurate and reliable method, non-invasively and affordable, would improve hemodynamic management. This study is for validation of a new module in impedance cardiography to improve the accuracy in cardiac patients. Heart rate, Cardiac output/ index, and stroke volume have been determined simultaneously by thermodilution (Swan Ganz, right heart catheterisation) and impedance cardiography (VasoScreen3000 with integrated ACM module) from postoperative patients who underwent open heart surgery in intensive care unit. 34 measurements were successfully taken, on 22 patients. High agreement in heart rate and acceptable agreement with strong correlation in Cardiac output/ index and stroke volume was found. The mean difference in cardiac output was −0.44 (SD 1.06) L/min (−0.31 (SD 0.63) L/min/m2 for cardiac index), correlation after Pearson was rCO = 0.67 (p < 0.001). In this study, the appearance of mechanical ventilation affects the accuracy of impedance measurement. We concluded that impedance cardiography is a reliable and accurate method for determining cardiac performance, and is practical to use and without any discomfort to the patients.
{"title":"Validation study on cardiac output and index determination in impendence cardiography on postoperative cardiac patients in critical care","authors":"Julia Löschel, Eko Syprianto, Amiliana Santoso, Habil Jens Haueisen, Manuela Aschoff, Dr. Saravana Kumar Jaganathan","doi":"10.1109/ICORAS.2016.7872620","DOIUrl":"https://doi.org/10.1109/ICORAS.2016.7872620","url":null,"abstract":"The gold standard in determination of cardiac output is highly invasive and expensive in use. An accurate and reliable method, non-invasively and affordable, would improve hemodynamic management. This study is for validation of a new module in impedance cardiography to improve the accuracy in cardiac patients. Heart rate, Cardiac output/ index, and stroke volume have been determined simultaneously by thermodilution (Swan Ganz, right heart catheterisation) and impedance cardiography (VasoScreen3000 with integrated ACM module) from postoperative patients who underwent open heart surgery in intensive care unit. 34 measurements were successfully taken, on 22 patients. High agreement in heart rate and acceptable agreement with strong correlation in Cardiac output/ index and stroke volume was found. The mean difference in cardiac output was −0.44 (SD 1.06) L/min (−0.31 (SD 0.63) L/min/m2 for cardiac index), correlation after Pearson was rCO = 0.67 (p < 0.001). In this study, the appearance of mechanical ventilation affects the accuracy of impedance measurement. We concluded that impedance cardiography is a reliable and accurate method for determining cardiac performance, and is practical to use and without any discomfort to the patients.","PeriodicalId":393534,"journal":{"name":"2016 International Conference on Robotics, Automation and Sciences (ICORAS)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115075278","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 : 2016-11-01DOI: 10.1109/ICORAS.2016.7872616
M. Yuden, M. Ghazaly, I. W. Jamaludin, A. C. Amran, Z. Abdullah
This paper presents the optimization of three-dimensional (3D) Printed Underactuated Dexterous Robotic Hand (UDRH) design and the analysis of the UDRH material. The UDRH design consists of three fingers and a thumb at which each finger has two links and two degrees of freedoms (DOF) and each joint of the finger is actuated by the DC Micromotor. The thumb has 3DOF to allow for adduction and abduction of the thumb. The robot hand is designed to be like human hand whereby higher performances in accuracy, stability and consistency can be achieved. The actuators are placed directly in each finger link so that the robot hand has several degrees of freedoms to achieve dexterous grasping. The angular rotation, speed, and torque have to be controlled for each individual joint to enable a more precise control. The structure of the UDRH robot hand is printed by using Flashforge Creator Pro 3D printer machine. In this paper, the optimization and analysis of fused deposition modeling (FDM) printed materials which are Acrylonitrile Butadiene Styrene (ABS), Polylactid Acid (PLA), Nylon, and Polycarbonate (PC) plastic are accomplished by testing for their stress and deformation through finite element analysis by using Solidworks software. From the analysis, the critical points and the parts of the UDRH design that are prone to damage under high force and temperature can be detected. In this study, ABS plastic material is chosen for UDRH prototype due to its properties which are resistance to heat which is 5.47 × 106N/m2, and high melting point of 210°C compared to the other materials.
本文对三维打印欠驱动灵巧机械手进行了优化设计，并对欠驱动灵巧机械手材料进行了分析。UDRH设计由三个手指和一个拇指组成，每个手指有两个链接和两个自由度(DOF)，手指的每个关节由直流微电机驱动。拇指具有三维立体的功能，允许拇指内收和外展。机器人的手被设计成像人手一样，在精度、稳定性和一致性方面可以实现更高的性能。驱动器直接放置在每个手指环节，使机器人手具有多个自由度，以实现灵巧的抓取。为了实现更精确的控制，必须对每个单独的关节进行角旋转、速度和扭矩控制。利用Flashforge Creator Pro 3D打印机打印出UDRH机械手的结构。本文利用Solidworks软件对丙烯腈-丁二烯-苯乙烯(ABS)、聚乳酸(PLA)、尼龙(Nylon)和聚碳酸酯(PC)塑料等熔融沉积建模(FDM)打印材料的应力和变形进行了有限元测试，并对其进行了优化分析。通过分析，可以检测出在高强度和高温度下UDRH设计的关键点和容易损坏的部件。由于ABS塑料的耐热性为5.47 × 106N/m2，与其他材料相比，其熔点高达210℃，因此本研究选择ABS塑料作为UDRH原型材料。
{"title":"Optimization design and analysis of an underactuated dexterous robotic hand system","authors":"M. Yuden, M. Ghazaly, I. W. Jamaludin, A. C. Amran, Z. Abdullah","doi":"10.1109/ICORAS.2016.7872616","DOIUrl":"https://doi.org/10.1109/ICORAS.2016.7872616","url":null,"abstract":"This paper presents the optimization of three-dimensional (3D) Printed Underactuated Dexterous Robotic Hand (UDRH) design and the analysis of the UDRH material. The UDRH design consists of three fingers and a thumb at which each finger has two links and two degrees of freedoms (DOF) and each joint of the finger is actuated by the DC Micromotor. The thumb has 3DOF to allow for adduction and abduction of the thumb. The robot hand is designed to be like human hand whereby higher performances in accuracy, stability and consistency can be achieved. The actuators are placed directly in each finger link so that the robot hand has several degrees of freedoms to achieve dexterous grasping. The angular rotation, speed, and torque have to be controlled for each individual joint to enable a more precise control. The structure of the UDRH robot hand is printed by using Flashforge Creator Pro 3D printer machine. In this paper, the optimization and analysis of fused deposition modeling (FDM) printed materials which are Acrylonitrile Butadiene Styrene (ABS), Polylactid Acid (PLA), Nylon, and Polycarbonate (PC) plastic are accomplished by testing for their stress and deformation through finite element analysis by using Solidworks software. From the analysis, the critical points and the parts of the UDRH design that are prone to damage under high force and temperature can be detected. In this study, ABS plastic material is chosen for UDRH prototype due to its properties which are resistance to heat which is 5.47 × 106N/m2, and high melting point of 210°C compared to the other materials.","PeriodicalId":393534,"journal":{"name":"2016 International Conference on Robotics, Automation and Sciences (ICORAS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122709428","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 : 2016-11-01DOI: 10.1109/ICORAS.2016.7872605
I. Iszaidy, R. Ngadiran, R. B. Ahmad, M. Jais, D. Shuhaizar
Travel time is important information for traffic management system, which can help people to plan their travel schedule and improve their work efficiency. The development of smart travel time information system for multiple moving vehicle detection and tracking on highway composed of an embedded Linux platform and an image sensor. A low cost system with high resources is needed to capture an image of the monitoring area, analyze it and perform the vehicle detection and tracking process of the image to estimate the speed and time taken of moving vehicle from one point to another point on the scene. So, this paper will review some of embedded board that been used with image processing to find out which kind of platform that is suitable and possible to measure and estimate the travel time.
{"title":"Implementation of raspberry Pi for vehicle tracking and travel time information system: A survey","authors":"I. Iszaidy, R. Ngadiran, R. B. Ahmad, M. Jais, D. Shuhaizar","doi":"10.1109/ICORAS.2016.7872605","DOIUrl":"https://doi.org/10.1109/ICORAS.2016.7872605","url":null,"abstract":"Travel time is important information for traffic management system, which can help people to plan their travel schedule and improve their work efficiency. The development of smart travel time information system for multiple moving vehicle detection and tracking on highway composed of an embedded Linux platform and an image sensor. A low cost system with high resources is needed to capture an image of the monitoring area, analyze it and perform the vehicle detection and tracking process of the image to estimate the speed and time taken of moving vehicle from one point to another point on the scene. So, this paper will review some of embedded board that been used with image processing to find out which kind of platform that is suitable and possible to measure and estimate the travel time.","PeriodicalId":393534,"journal":{"name":"2016 International Conference on Robotics, Automation and Sciences (ICORAS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122749517","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 : 2016-11-01DOI: 10.1109/ICORAS.2016.7872618
M. Jais, T. Sabapathy, M. Jusoh, P. Ehkan, L. Murukesan, I. Ismail, R. Ahmad
Wireless sensor network (WSN) is commonly used for localization applications. Through sniffing receive signal strength indicator (RSSI) in WSN system, localization and connection to access point highest RSSI can be done automatically. In this paper, we propose Raspberry-Pi (RasPi), based best access point selection method utilizing RSSI metric. The RasPi brings the advantages of a personal computer (PC) to the domain of sensor network, which makes it the perfect platform for interfacing with a wide variety of external peripherals. This work aims to investigate various source codes deployed on RasPi for localization purpose by sniffing the RSSI metric. Consequently, comparative analysis of its key elements and performances with some of the currently available wireless sensor nodes have shown that despite few disadvantages, RasPi remains an inexpensive single board computer (SBC) which has been used very successfully in sensor network domain and diverse range of research applications.
{"title":"Received signal strength indication (RSSI) code assessment for wireless sensors network (WSN) deployed Raspberry-Pi","authors":"M. Jais, T. Sabapathy, M. Jusoh, P. Ehkan, L. Murukesan, I. Ismail, R. Ahmad","doi":"10.1109/ICORAS.2016.7872618","DOIUrl":"https://doi.org/10.1109/ICORAS.2016.7872618","url":null,"abstract":"Wireless sensor network (WSN) is commonly used for localization applications. Through sniffing receive signal strength indicator (RSSI) in WSN system, localization and connection to access point highest RSSI can be done automatically. In this paper, we propose Raspberry-Pi (RasPi), based best access point selection method utilizing RSSI metric. The RasPi brings the advantages of a personal computer (PC) to the domain of sensor network, which makes it the perfect platform for interfacing with a wide variety of external peripherals. This work aims to investigate various source codes deployed on RasPi for localization purpose by sniffing the RSSI metric. Consequently, comparative analysis of its key elements and performances with some of the currently available wireless sensor nodes have shown that despite few disadvantages, RasPi remains an inexpensive single board computer (SBC) which has been used very successfully in sensor network domain and diverse range of research applications.","PeriodicalId":393534,"journal":{"name":"2016 International Conference on Robotics, Automation and Sciences (ICORAS)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124617120","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 : 2016-11-01DOI: 10.1109/ICORAS.2016.7872614
W. C. Tan, N. A. Mat-Isa
The study of sperm motility especially in sperm tracking has received increasing attentions. In this paper, we proposed an automated system to help in solving partial occlusion between sperms. Synchronous Pulse Coupled Neural Network (SPCNN) is employed to extract the centroid of the sperm from the occluded sperms. By using an optimization algorithm called Particle Swarm Optimization (PSO), the five unknown parameters were optimized. The proposed method has been evaluated with 500 sperm images. The proposed SPCNN method solved the partial occlusion problem by providing more accurate results. In future, SPCNN is expected to be implemented in sperm tracking algorithm.
{"title":"Potential use of synchronous pulse coupled neural network in partial occlusion","authors":"W. C. Tan, N. A. Mat-Isa","doi":"10.1109/ICORAS.2016.7872614","DOIUrl":"https://doi.org/10.1109/ICORAS.2016.7872614","url":null,"abstract":"The study of sperm motility especially in sperm tracking has received increasing attentions. In this paper, we proposed an automated system to help in solving partial occlusion between sperms. Synchronous Pulse Coupled Neural Network (SPCNN) is employed to extract the centroid of the sperm from the occluded sperms. By using an optimization algorithm called Particle Swarm Optimization (PSO), the five unknown parameters were optimized. The proposed method has been evaluated with 500 sperm images. The proposed SPCNN method solved the partial occlusion problem by providing more accurate results. In future, SPCNN is expected to be implemented in sperm tracking algorithm.","PeriodicalId":393534,"journal":{"name":"2016 International Conference on Robotics, Automation and Sciences (ICORAS)","volume":"29 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131178464","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 : 2016-11-01DOI: 10.1109/ICORAS.2016.7872603
N. Koh, K. Sim, C. Tso
Computed tomography (CT) images are vital in the diagnosis of ischemic stroke. However, CT images suffer from low contrast for lesion detection. There were many contrast enhancement techniques developed, but most of the techniques are not suitable for stroke detection in CT images due to poor lesion visualization. In order to overcome the problem, this paper introduces a contrast enhancement technique with combination of Recursive Sub-image Histogram Equalization (RSHIE) based discrete wavelet transform (DWT) and adaptive gamma correction with weighting distribution (AGCWD). It is proven from experimental results that our technique has better contrast and image quality for lesion detection compared to other contrast enhancement techniques such as extreme level eliminating histogram (ELEHE) and brightness preserving bi-histogram equalization (BBHE).
{"title":"CT brain lesion detection through combination of recursive sub-image histogram equalization in wavelet domain and adaptive gamma correction with weighting distribution","authors":"N. Koh, K. Sim, C. Tso","doi":"10.1109/ICORAS.2016.7872603","DOIUrl":"https://doi.org/10.1109/ICORAS.2016.7872603","url":null,"abstract":"Computed tomography (CT) images are vital in the diagnosis of ischemic stroke. However, CT images suffer from low contrast for lesion detection. There were many contrast enhancement techniques developed, but most of the techniques are not suitable for stroke detection in CT images due to poor lesion visualization. In order to overcome the problem, this paper introduces a contrast enhancement technique with combination of Recursive Sub-image Histogram Equalization (RSHIE) based discrete wavelet transform (DWT) and adaptive gamma correction with weighting distribution (AGCWD). It is proven from experimental results that our technique has better contrast and image quality for lesion detection compared to other contrast enhancement techniques such as extreme level eliminating histogram (ELEHE) and brightness preserving bi-histogram equalization (BBHE).","PeriodicalId":393534,"journal":{"name":"2016 International Conference on Robotics, Automation and Sciences (ICORAS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123921009","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 : 2016-11-01DOI: 10.1109/ICORAS.2016.7872621
N. N. N. Nazirun, E. Supriyanto, D. Baumgarten, J. Haueisen, C. Pohl, A. Omar
The combination of different medical modalities from single or multiple sensors produces higher reliability in diagnosis, pre-surgical planning and surgical intervention. Multimodal fusion is an option to exploit medical images in the context of coronary plaques detection. It is most sensible to detect the vulnerability of plaque as diseases related to it are among the leading cause of death. CTA and ICA were chosen as both modalities can visualize the blood vessel anatomically and functionally in the images, which were taken at a certain point in time and during the angioplasty intervention. The cross-sectional diameter of the blood vessel in an ICA was measured thus detecting vessel narrowing due to stenosis. Meanwhile, the high intensity pixels in CTA image, which indicated the calcification of plaque, were calculated after applying multilevel threshold. The severity of stenosis in ICA correlating to the pixel coverage in CTA was investigated. Compared to the diagnosis from one modality alone, the feature correlation delivered more information and consumes less time. The research results will support cardiologists by providing enhanced diagnosis capabilities of cardiovascular vulnerable plaques to improve the quality of data interpretation.
{"title":"The correlation of features in detecting cardiovascular vulnerable plaque","authors":"N. N. N. Nazirun, E. Supriyanto, D. Baumgarten, J. Haueisen, C. Pohl, A. Omar","doi":"10.1109/ICORAS.2016.7872621","DOIUrl":"https://doi.org/10.1109/ICORAS.2016.7872621","url":null,"abstract":"The combination of different medical modalities from single or multiple sensors produces higher reliability in diagnosis, pre-surgical planning and surgical intervention. Multimodal fusion is an option to exploit medical images in the context of coronary plaques detection. It is most sensible to detect the vulnerability of plaque as diseases related to it are among the leading cause of death. CTA and ICA were chosen as both modalities can visualize the blood vessel anatomically and functionally in the images, which were taken at a certain point in time and during the angioplasty intervention. The cross-sectional diameter of the blood vessel in an ICA was measured thus detecting vessel narrowing due to stenosis. Meanwhile, the high intensity pixels in CTA image, which indicated the calcification of plaque, were calculated after applying multilevel threshold. The severity of stenosis in ICA correlating to the pixel coverage in CTA was investigated. Compared to the diagnosis from one modality alone, the feature correlation delivered more information and consumes less time. The research results will support cardiologists by providing enhanced diagnosis capabilities of cardiovascular vulnerable plaques to improve the quality of data interpretation.","PeriodicalId":393534,"journal":{"name":"2016 International Conference on Robotics, Automation and Sciences (ICORAS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125176000","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 : 2016-11-01DOI: 10.1109/ICORAS.2016.7872630
W. Ong, A. Tan
Voice activity detector (VAD) is used to detect the presence or absence of human voice in a signal. A robust VAD algorithm is essential to distinguish human voice in a noisy acoustic signal. There were many recent works in development of robust VAD which focus on unsupervised features extraction such as temporal variation, signal-to-noise ratio in [1] and etc. However, these methods are typically sensitive to nonstationary noise especially under low SNR. To overcome these problems, this paper presents a robust voice activity detection (VAD) method via a combination of gammatone filtering and entropy as an information-theoretic measure in the detection algorithm. The performance of the proposed algorithm is tested using speech signals from TIMIT test corpus with additive noise at varying degrees of signal-to-noise ratio. The results show that the proposed robust VAD outperforms other existing methods in terms of detection accuracy.
{"title":"Robust voice activity detection using gammatone filtering and entropy","authors":"W. Ong, A. Tan","doi":"10.1109/ICORAS.2016.7872630","DOIUrl":"https://doi.org/10.1109/ICORAS.2016.7872630","url":null,"abstract":"Voice activity detector (VAD) is used to detect the presence or absence of human voice in a signal. A robust VAD algorithm is essential to distinguish human voice in a noisy acoustic signal. There were many recent works in development of robust VAD which focus on unsupervised features extraction such as temporal variation, signal-to-noise ratio in [1] and etc. However, these methods are typically sensitive to nonstationary noise especially under low SNR. To overcome these problems, this paper presents a robust voice activity detection (VAD) method via a combination of gammatone filtering and entropy as an information-theoretic measure in the detection algorithm. The performance of the proposed algorithm is tested using speech signals from TIMIT test corpus with additive noise at varying degrees of signal-to-noise ratio. The results show that the proposed robust VAD outperforms other existing methods in terms of detection accuracy.","PeriodicalId":393534,"journal":{"name":"2016 International Conference on Robotics, Automation and Sciences (ICORAS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121761346","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 : 2016-11-01DOI: 10.1109/ICORAS.2016.7872604
D. W. Y. Tan, H. Ting, S. B. Y. Lau
Badminton is one of the most popular racket sports in Malaysia. In the past, badminton player movement analyses such as smashing, service, racket swing and shuttle trajectory etc. were mainly carried out qualitatively with substantial human involvement. In recent time, there is increasing assimilation of computer technology in badminton movement analysis as revealed by our review of the state-of-the-art researches. This paper aims to lay a solid foundation for the exploration of further research on badminton movement analysis. Three key areas reviewed were badminton smashing analysis, badminton service recognition, and badminton swing and shuttle trajectory analysis.
{"title":"A review on badminton motion analysis","authors":"D. W. Y. Tan, H. Ting, S. B. Y. Lau","doi":"10.1109/ICORAS.2016.7872604","DOIUrl":"https://doi.org/10.1109/ICORAS.2016.7872604","url":null,"abstract":"Badminton is one of the most popular racket sports in Malaysia. In the past, badminton player movement analyses such as smashing, service, racket swing and shuttle trajectory etc. were mainly carried out qualitatively with substantial human involvement. In recent time, there is increasing assimilation of computer technology in badminton movement analysis as revealed by our review of the state-of-the-art researches. This paper aims to lay a solid foundation for the exploration of further research on badminton movement analysis. Three key areas reviewed were badminton smashing analysis, badminton service recognition, and badminton swing and shuttle trajectory analysis.","PeriodicalId":393534,"journal":{"name":"2016 International Conference on Robotics, Automation and Sciences (ICORAS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127858869","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：