Pub Date : 2015-12-01DOI: 10.7763/IJCTE.2015.V7.1007
Guoheng Huang, Chi-Man Pun
{"title":"Robust Interactive Segmentation Using Color Histogram and Contourlet Transform","authors":"Guoheng Huang, Chi-Man Pun","doi":"10.7763/IJCTE.2015.V7.1007","DOIUrl":"https://doi.org/10.7763/IJCTE.2015.V7.1007","url":null,"abstract":"","PeriodicalId":306280,"journal":{"name":"International Journal of Computer Theory and Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130818642","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 : 2015-12-01DOI: 10.7763/IJCTE.2015.V7.997
J. Mitrpanont, P. Chongcharoen
techniques, word forms, and even window sizes is proposed. The disambiguation techniques include path, vector, vector_pair and lesk. The 250 context words from four target words group which are วั ด (wat), หั ว (hua), เก็ บ (kep) and เกาะ (koh) from bi-text corpora of SEAlang and Concordance are studied. The experimental results show that using AWN with vector technique and PWN with path technique provides better accuracy. However, for Thai WSD included time consideration, the vector technique with AWN at five window size is suitable.
{"title":"TH_WSD: Thai Word Sense Disambiguation Using Cross-Language Knowledge Sources Approach","authors":"J. Mitrpanont, P. Chongcharoen","doi":"10.7763/IJCTE.2015.V7.997","DOIUrl":"https://doi.org/10.7763/IJCTE.2015.V7.997","url":null,"abstract":"techniques, word forms, and even window sizes is proposed. The disambiguation techniques include path, vector, vector_pair and lesk. The 250 context words from four target words group which are วั ด (wat), หั ว (hua), เก็ บ (kep) and เกาะ (koh) from bi-text corpora of SEAlang and Concordance are studied. The experimental results show that using AWN with vector technique and PWN with path technique provides better accuracy. However, for Thai WSD included time consideration, the vector technique with AWN at five window size is suitable.","PeriodicalId":306280,"journal":{"name":"International Journal of Computer Theory and Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116642970","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 : 2015-12-01DOI: 10.7763/IJCTE.2015.V7.1006
Abdul Razzaq, Zhongke Wu, Mingquan Zhou, Sajid Ali, Khalid Iqbal
Skeleton-base-animation methods have been commonly used in the character animations. The process of making skeleton for character animation is a long-winded task requiring manual tweaking. This paper presents a novel method to create an automatic animated skeleton from 3D human geometric model through mesh contraction. An automatically generated skeleton is animated by using Kinect captured human motion. The method first, extract a 1D curve-skeleton from the mesh through mesh contraction with constraints. Secondly, the hierarchical joint-based skeleton (armature) has been generated, using the extracted 1D curve-skeleton of the input mesh automatically. Third, the real-time human motion is captured by using the Kinect device. The Kinect captured motion also converts into a standard skeleton motion BVH (Biovision hierarchical) format. Finally, the Kinect motion is retargeted to animate the resulting skeleton of the mesh through joint mapping. The main objective of the proposed approach is to minimize labor-intensive process of skeleton adjustment for character animation. The results of a mesh generated skeleton and plausible skeleton animation to demonstrate the efficiency of the proposed work. The mesh generated skeleton and Kinect motion skeleton both can be directly useful for mesh skinning, mesh rigging, and motion retargeting to create satisfactory character animation. Studio and Blender. These packages require manual tweaking of the skeleton, such as bones and vertex weighting of character, manual creation of a skeleton hierarchy for getting desired animation effects. In present animation systems, object representation and its skeleton are disjointed, which often create problems in animation of the objects. The character animation based on skeleton still require experienced work and laborious process. To address these problems, a new framework has been proposed to generate an automatic animated skeleton from 3D human geometric mesh model. In this study, first extract a curve-skeleton from a polygon mesh by using mesh Laplican contractions. The extracted curve-skeleton is converted into a joint-based-skeleton automatically.This method is to make a skeleton, which has an accurate joint position, follow typology of the human skeleton. The flow of method divided into four phases. In first phase, mesh contraction has been applied to contract the given mesh model. The mesh contraction process preserves the original topology and connectivity of the mesh model. The mesh contraction process based on Laplacian smoothing with constraints. Contract the mesh iteratively until to obtain a 1D shape of that model. The 1D curve-skeleton is derived from the contracted mesh through edge contraction operation. The methods of Au et al. (4) used as starting point of the contracting mesh model. Second phase, present an automatic conversion of the refined curve-skeleton into a joint-based skeleton. Because the suitable extracted curve-skeleton should leave enough in
{"title":"Automatic Conversion of Human Mesh into Skeleton Animation by Using Kinect Motion","authors":"Abdul Razzaq, Zhongke Wu, Mingquan Zhou, Sajid Ali, Khalid Iqbal","doi":"10.7763/IJCTE.2015.V7.1006","DOIUrl":"https://doi.org/10.7763/IJCTE.2015.V7.1006","url":null,"abstract":"Skeleton-base-animation methods have been commonly used in the character animations. The process of making skeleton for character animation is a long-winded task requiring manual tweaking. This paper presents a novel method to create an automatic animated skeleton from 3D human geometric model through mesh contraction. An automatically generated skeleton is animated by using Kinect captured human motion. The method first, extract a 1D curve-skeleton from the mesh through mesh contraction with constraints. Secondly, the hierarchical joint-based skeleton (armature) has been generated, using the extracted 1D curve-skeleton of the input mesh automatically. Third, the real-time human motion is captured by using the Kinect device. The Kinect captured motion also converts into a standard skeleton motion BVH (Biovision hierarchical) format. Finally, the Kinect motion is retargeted to animate the resulting skeleton of the mesh through joint mapping. The main objective of the proposed approach is to minimize labor-intensive process of skeleton adjustment for character animation. The results of a mesh generated skeleton and plausible skeleton animation to demonstrate the efficiency of the proposed work. The mesh generated skeleton and Kinect motion skeleton both can be directly useful for mesh skinning, mesh rigging, and motion retargeting to create satisfactory character animation. Studio and Blender. These packages require manual tweaking of the skeleton, such as bones and vertex weighting of character, manual creation of a skeleton hierarchy for getting desired animation effects. In present animation systems, object representation and its skeleton are disjointed, which often create problems in animation of the objects. The character animation based on skeleton still require experienced work and laborious process. To address these problems, a new framework has been proposed to generate an automatic animated skeleton from 3D human geometric mesh model. In this study, first extract a curve-skeleton from a polygon mesh by using mesh Laplican contractions. The extracted curve-skeleton is converted into a joint-based-skeleton automatically.This method is to make a skeleton, which has an accurate joint position, follow typology of the human skeleton. The flow of method divided into four phases. In first phase, mesh contraction has been applied to contract the given mesh model. The mesh contraction process preserves the original topology and connectivity of the mesh model. The mesh contraction process based on Laplacian smoothing with constraints. Contract the mesh iteratively until to obtain a 1D shape of that model. The 1D curve-skeleton is derived from the contracted mesh through edge contraction operation. The methods of Au et al. (4) used as starting point of the contracting mesh model. Second phase, present an automatic conversion of the refined curve-skeleton into a joint-based skeleton. Because the suitable extracted curve-skeleton should leave enough in","PeriodicalId":306280,"journal":{"name":"International Journal of Computer Theory and Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133747429","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 : 2015-12-01DOI: 10.7763/IJCTE.2015.V7.1004
W. Ngongi, Jia-lu Du
Abstract—In this paper an output feedback controller for tracking control of surface ships based on Euler-Lagrange equations has been proposed. It has been assumed that a surface ship is moving in a horizontal plane and under-actuated in sway direction. The change of coordinate's method is applied to overcome the third order component that arises in the Lyapunov function derivatives due to Coriolis and centripetal forces term. The design of the controller is based on the backstepping control technique and Lyapunov stability theory. Firstly, the observer is derived using the change of coordinate method. Next, backstepping control technique is employed to derive the control law. Finally, a global asymptotic convergence is proven using Lyapunov stability theorems. Simulations are provided to demonstrate the performance of the designed controller and prove tracking error of the controller convergence.
{"title":"Controller Design for Tracking Control of an Under-Actuated Surface Ship","authors":"W. Ngongi, Jia-lu Du","doi":"10.7763/IJCTE.2015.V7.1004","DOIUrl":"https://doi.org/10.7763/IJCTE.2015.V7.1004","url":null,"abstract":" Abstract—In this paper an output feedback controller for tracking control of surface ships based on Euler-Lagrange equations has been proposed. It has been assumed that a surface ship is moving in a horizontal plane and under-actuated in sway direction. The change of coordinate's method is applied to overcome the third order component that arises in the Lyapunov function derivatives due to Coriolis and centripetal forces term. The design of the controller is based on the backstepping control technique and Lyapunov stability theory. Firstly, the observer is derived using the change of coordinate method. Next, backstepping control technique is employed to derive the control law. Finally, a global asymptotic convergence is proven using Lyapunov stability theorems. Simulations are provided to demonstrate the performance of the designed controller and prove tracking error of the controller convergence.","PeriodicalId":306280,"journal":{"name":"International Journal of Computer Theory and Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117086956","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 : 2015-12-01DOI: 10.7763/IJCTE.2015.V7.1002
Basma Basem, A. Ghalwash, R. Sadek
VoIP faces many emerging attacks and threats. securing SIP based VoIP is a major challenging task, hence confidentiality, integrity, availability, as well as authenticity must be provided. Focusing on three main critical attacks targeting SIP based VoIP infrastructure, which are Denial of service (DoS), man-in-the middle attack, and Authenticity based attacks. In this paper the main contribution is providing a secure efficient multilayer security architecture based on open source applications (snort, snortsam and iptables, as well as OPENVPN Tunnel), The architecture provides a secure reliable VoIP services for the enterprise network, that have been deployed based on asterisk PBX. The proposed security architecture aims to prevent the mentioned critical attacks, to provide CIAA security services, by proposing an adaptive rule based queuing polices. QoS is a major challenge, the paper also provides an enhancement for the proposed architecture to minimize the delay for more efficient secure communication, as well as preventing zero day attacks by exploiting method and updating Snort DB with attack signatures. QoS factors have been measured using OPNET simulators. The proposed architecture gives promising results when it comes to attacks prevention with 0.01% better performance results compared to previous work.
{"title":"Multilayer Secured SIP Based VoIP Architecture","authors":"Basma Basem, A. Ghalwash, R. Sadek","doi":"10.7763/IJCTE.2015.V7.1002","DOIUrl":"https://doi.org/10.7763/IJCTE.2015.V7.1002","url":null,"abstract":"VoIP faces many emerging attacks and threats. securing SIP based VoIP is a major challenging task, hence confidentiality, integrity, availability, as well as authenticity must be provided. Focusing on three main critical attacks targeting SIP based VoIP infrastructure, which are Denial of service (DoS), man-in-the middle attack, and Authenticity based attacks. In this paper the main contribution is providing a secure efficient multilayer security architecture based on open source applications (snort, snortsam and iptables, as well as OPENVPN Tunnel), The architecture provides a secure reliable VoIP services for the enterprise network, that have been deployed based on asterisk PBX. The proposed security architecture aims to prevent the mentioned critical attacks, to provide CIAA security services, by proposing an adaptive rule based queuing polices. QoS is a major challenge, the paper also provides an enhancement for the proposed architecture to minimize the delay for more efficient secure communication, as well as preventing zero day attacks by exploiting method and updating Snort DB with attack signatures. QoS factors have been measured using OPNET simulators. The proposed architecture gives promising results when it comes to attacks prevention with 0.01% better performance results compared to previous work.","PeriodicalId":306280,"journal":{"name":"International Journal of Computer Theory and Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132373496","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}
Abstract—Uncertainty is a major barrier in knowledge discovery from complex problem domains. Knowledge discovery in such domains requires qualitative rather than quantitative analysis. Therefore, the quantitative measures can be used to represent uncertainty with the integration of various models. The Bayesian Network (BN) is a widely applied technique for characterization and analysis of uncertainty in real world domains. Thus, the real application of BN can be observed in a broad range of domains such as image processing, decision making, system reliability estimation and PPDM (Privacy Preserving in Data Mining) in association rule mining and medical domain analysis. BN techniques can be used in these domains for prediction and decision support. In this article, a discussion on general BN representation, draw inferences, learning and prediction is followed by applications of BN in some specific domains. Domain specific BN representation, inferences and learning process are also presented. Building upon the knowledge presented, some future research directions are also highlighted.
摘要-不确定性是从复杂问题领域中发现知识的主要障碍。这些领域的知识发现需要定性分析而不是定量分析。因此，定量度量可以用来表示不确定性与各种模型的集成。贝叶斯网络(BN)是一种广泛应用于表征和分析现实世界领域不确定性的技术。因此，在图像处理、决策制定、系统可靠性估计以及关联规则挖掘和医疗领域分析中的PPDM (Privacy Preserving in Data Mining，数据挖掘中的隐私保护)等广泛领域中可以看到BN的实际应用。BN技术可以用于这些领域的预测和决策支持。在本文中，讨论了BN的一般表示，得出推论，学习和预测，然后是BN在一些特定领域的应用。还介绍了特定领域的BN表示、推理和学习过程。在此基础上，展望了未来的研究方向。
{"title":"An Overview of Bayesian Network Applications in Uncertain Domains","authors":"Khalid Iqbal, Xu-Cheng Yin, Hongwei Hao, Qazi Mudassar Ilyas, Hazrat Ali","doi":"10.7763/IJCTE.2015.V7.996","DOIUrl":"https://doi.org/10.7763/IJCTE.2015.V7.996","url":null,"abstract":" Abstract—Uncertainty is a major barrier in knowledge discovery from complex problem domains. Knowledge discovery in such domains requires qualitative rather than quantitative analysis. Therefore, the quantitative measures can be used to represent uncertainty with the integration of various models. The Bayesian Network (BN) is a widely applied technique for characterization and analysis of uncertainty in real world domains. Thus, the real application of BN can be observed in a broad range of domains such as image processing, decision making, system reliability estimation and PPDM (Privacy Preserving in Data Mining) in association rule mining and medical domain analysis. BN techniques can be used in these domains for prediction and decision support. In this article, a discussion on general BN representation, draw inferences, learning and prediction is followed by applications of BN in some specific domains. Domain specific BN representation, inferences and learning process are also presented. Building upon the knowledge presented, some future research directions are also highlighted.","PeriodicalId":306280,"journal":{"name":"International Journal of Computer Theory and Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126797205","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 : 2015-12-01DOI: 10.7763/IJCTE.2015.V7.999
Jamilu Awwalu, A. Garba, A. Ghazvini, Rose Atuah
{"title":"Artificial Intelligence in Personalized Medicine Application of AI Algorithms in Solving Personalized Medicine Problems","authors":"Jamilu Awwalu, A. Garba, A. Ghazvini, Rose Atuah","doi":"10.7763/IJCTE.2015.V7.999","DOIUrl":"https://doi.org/10.7763/IJCTE.2015.V7.999","url":null,"abstract":"","PeriodicalId":306280,"journal":{"name":"International Journal of Computer Theory and Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134070648","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 : 2015-12-01DOI: 10.7763/IJCTE.2015.V7.1005
Wiwik Wiharti, S. Anggraini, I. Rimra
One of the gunboat weapons that need to stay stable is the cannon. Its unbalance position that caused by pitch and roll disturbance will influence the target accuracy, target detection, tracking system, object identification and the ability to counter the threat. In order to determine this disturbance, the balancing control on the movement platform can be solved by using neural network control and sliding mode control methods. To make an approach, the cannon movement system can be modeled in training and elevation movements and the disturbances are modeled through pitch and roll mechanisms. The variations in obtained parameters of training and elevation (moment of inertia) are the non-linearity result of the moving cannon. The system is simulated to verify the error in the controller's output processed using the neural network coordination system control and sliding mode control. The learning process in the neural network is made using back propagation method in order to get the weight value at the different disturbances which their results are given in the simulation of coordination models. On the other hand, the free chattering of sliding mode control is implemented in order to make the movement of training and elevation can be controlled for having the desired angle position in the disturbance of pitch and roll. This paper is based on the study to compare the performance of neural network control and sliding mode control on the moving platform.
{"title":"The Performance of Controlling Cannon Barrel Position on the Moving Platform Using Neural Network Control and Sliding Mode Control","authors":"Wiwik Wiharti, S. Anggraini, I. Rimra","doi":"10.7763/IJCTE.2015.V7.1005","DOIUrl":"https://doi.org/10.7763/IJCTE.2015.V7.1005","url":null,"abstract":"One of the gunboat weapons that need to stay stable is the cannon. Its unbalance position that caused by pitch and roll disturbance will influence the target accuracy, target detection, tracking system, object identification and the ability to counter the threat. In order to determine this disturbance, the balancing control on the movement platform can be solved by using neural network control and sliding mode control methods. To make an approach, the cannon movement system can be modeled in training and elevation movements and the disturbances are modeled through pitch and roll mechanisms. The variations in obtained parameters of training and elevation (moment of inertia) are the non-linearity result of the moving cannon. The system is simulated to verify the error in the controller's output processed using the neural network coordination system control and sliding mode control. The learning process in the neural network is made using back propagation method in order to get the weight value at the different disturbances which their results are given in the simulation of coordination models. On the other hand, the free chattering of sliding mode control is implemented in order to make the movement of training and elevation can be controlled for having the desired angle position in the disturbance of pitch and roll. This paper is based on the study to compare the performance of neural network control and sliding mode control on the moving platform.","PeriodicalId":306280,"journal":{"name":"International Journal of Computer Theory and Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117077305","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 : 2015-12-01DOI: 10.7763/IJCTE.2015.V7.998
H. Saboohi, A. Amini, T. Herawan, S. A. Kareem, Nooshin Anari, Gholamreza Ahakian
There are numerous methods which are proposed to mediate semantic Web services. The mediations of semantic services include their discovery, composition, execution, and monitoring. These are performed on both atomic and composite services. Newly proposed methods are required to be evaluated on a dataset. Despite the existence of atomic test collections of semantic services, the number of publicly available test collections containing composite services is not comparable. In this paper, we propose an approach to enlarge the number of composite services in a test collection. We generate new composites by calculating subdigraphs of available composite services. We evaluated our approach on a number of composite services and we could exponentially enlarge the size of test collections.
{"title":"Enlarging Test Collections of Composite Semantic Services","authors":"H. Saboohi, A. Amini, T. Herawan, S. A. Kareem, Nooshin Anari, Gholamreza Ahakian","doi":"10.7763/IJCTE.2015.V7.998","DOIUrl":"https://doi.org/10.7763/IJCTE.2015.V7.998","url":null,"abstract":"There are numerous methods which are proposed to mediate semantic Web services. The mediations of semantic services include their discovery, composition, execution, and monitoring. These are performed on both atomic and composite services. Newly proposed methods are required to be evaluated on a dataset. Despite the existence of atomic test collections of semantic services, the number of publicly available test collections containing composite services is not comparable. In this paper, we propose an approach to enlarge the number of composite services in a test collection. We generate new composites by calculating subdigraphs of available composite services. We evaluated our approach on a number of composite services and we could exponentially enlarge the size of test collections.","PeriodicalId":306280,"journal":{"name":"International Journal of Computer Theory and Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133141246","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 : 2015-12-01DOI: 10.7763/IJCTE.2015.V7.1001
Thaweewong Akkaralaertsest, T. Yingthawornsuk
The procedure of this research was carried out in order to investigate the discriminative property of the focused vocal parameters mainly between depressed speakers and high-risk suicidal speaker groups. The result revealed that MFCC and GSS parameters are slightly high effective in term of vocal indicator corresponding to severe depression with fairly high performance in between-group separation.
{"title":"Comparative Analysis of Vocal Characteristics in Speakers with Depression and High-Risk Suicide","authors":"Thaweewong Akkaralaertsest, T. Yingthawornsuk","doi":"10.7763/IJCTE.2015.V7.1001","DOIUrl":"https://doi.org/10.7763/IJCTE.2015.V7.1001","url":null,"abstract":"The procedure of this research was carried out in order to investigate the discriminative property of the focused vocal parameters mainly between depressed speakers and high-risk suicidal speaker groups. The result revealed that MFCC and GSS parameters are slightly high effective in term of vocal indicator corresponding to severe depression with fairly high performance in between-group separation.","PeriodicalId":306280,"journal":{"name":"International Journal of Computer Theory and Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114300850","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：