Pub Date : 2013-11-01DOI: 10.1109/ICCSCE.2013.6720010
Golnoush Abaei, Z. Rezaei, A. Selamat
Predicting parts of the programs that are more defects prone could ease up the software testing process, which leads to testing cost and testing time reduction. Fault prediction models use software metrics and defect data of earlier or similar versions of the project in order to improve software quality and exploit available resources. However, some issues such as cost, experience, and time, limit the availability of faulty data for modules or classes. In such cases, researchers focus on unsupervised techniques such as clustering and they use experts or thresholds for labeling modules as faulty or not faulty. In this paper, we propose a prediction model by utilizing self-organizing map (SOM) with threshold to build a better prediction model that could help testers in labeling process and does not need experts to label the modules any more. Data sets obtained from three Turkish white-goods controller software are used in our empirical investigation. The results based on the proposed technique is shown to aid the testers in making better estimation in most of the cases in terms of overall error rate, false positive rate (FPR), and false negative rate (FNR).
{"title":"Fault prediction by utilizing self-organizing Map and Threshold","authors":"Golnoush Abaei, Z. Rezaei, A. Selamat","doi":"10.1109/ICCSCE.2013.6720010","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6720010","url":null,"abstract":"Predicting parts of the programs that are more defects prone could ease up the software testing process, which leads to testing cost and testing time reduction. Fault prediction models use software metrics and defect data of earlier or similar versions of the project in order to improve software quality and exploit available resources. However, some issues such as cost, experience, and time, limit the availability of faulty data for modules or classes. In such cases, researchers focus on unsupervised techniques such as clustering and they use experts or thresholds for labeling modules as faulty or not faulty. In this paper, we propose a prediction model by utilizing self-organizing map (SOM) with threshold to build a better prediction model that could help testers in labeling process and does not need experts to label the modules any more. Data sets obtained from three Turkish white-goods controller software are used in our empirical investigation. The results based on the proposed technique is shown to aid the testers in making better estimation in most of the cases in terms of overall error rate, false positive rate (FPR), and false negative rate (FNR).","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127171058","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719948
S. Sari, Sharifah Zahidah Hasan Al Fakkri, H. Roslan, Z. Tukiran
A good noise reduction is a method that can reduce the noise level and preserve the details of the image. This paper proposes the development of a denoising method through hybridization of bilateral filters and wavelet thresholding for digital images in low light condition.In the first stage, the noisy image is passed through Bilateral Filter. However, only some amount of noise gets reduced and the image gives a blurred appearance. Hence to preserve the edge details and reduce the blur effect, Wavelet Thresholding is applied and it is proved that the proposed method is more successful to preserve the edges while suppressing the noise.
{"title":"Development of denoising method for digital image in low-light condition","authors":"S. Sari, Sharifah Zahidah Hasan Al Fakkri, H. Roslan, Z. Tukiran","doi":"10.1109/ICCSCE.2013.6719948","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719948","url":null,"abstract":"A good noise reduction is a method that can reduce the noise level and preserve the details of the image. This paper proposes the development of a denoising method through hybridization of bilateral filters and wavelet thresholding for digital images in low light condition.In the first stage, the noisy image is passed through Bilateral Filter. However, only some amount of noise gets reduced and the image gives a blurred appearance. Hence to preserve the edge details and reduce the blur effect, Wavelet Thresholding is applied and it is proved that the proposed method is more successful to preserve the edges while suppressing the noise.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125507805","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719938
Sazianti Mohd Saad, Siti Sakira Kamarudin
The accuracy of similarity measurement between sentences is critical to the performance of several applications such as text mining, question answering, and text summarization. This paper focuses on calculating semantic similarities between sentences and performing a comparative analysis among identified similarity measurement techniques. Comparison between three popular similarity measurements which are Jaccard, Cosine and Dice similarity measures has been conducted. The performance of each identified measurement was evaluated and recorded. In this paper, we use a large lexical database of English known as WordNet to calculate the word-to-word semantic similarity. The result of this research concludes that the Jaccard and Dice performs better in measuring the semantic similarity between sentences.
句子间相似度度量的准确性对文本挖掘、问答和文本摘要等应用的性能至关重要。本文的重点是计算句子之间的语义相似度，并对现有的相似度测量技术进行比较分析。比较了三种流行的相似性度量，即Jaccard, cos和Dice相似性度量。评估和记录每一个确定的测量的性能。在本文中，我们使用一个叫做WordNet的大型英语词汇数据库来计算词与词的语义相似度。结果表明，Jaccard and Dice在句子间语义相似度的测量中表现较好。
{"title":"Comparative analysis of similarity measures for sentence level semantic measurement of text","authors":"Sazianti Mohd Saad, Siti Sakira Kamarudin","doi":"10.1109/ICCSCE.2013.6719938","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719938","url":null,"abstract":"The accuracy of similarity measurement between sentences is critical to the performance of several applications such as text mining, question answering, and text summarization. This paper focuses on calculating semantic similarities between sentences and performing a comparative analysis among identified similarity measurement techniques. Comparison between three popular similarity measurements which are Jaccard, Cosine and Dice similarity measures has been conducted. The performance of each identified measurement was evaluated and recorded. In this paper, we use a large lexical database of English known as WordNet to calculate the word-to-word semantic similarity. The result of this research concludes that the Jaccard and Dice performs better in measuring the semantic similarity between sentences.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127385719","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719971
F. M. Johar, F. A. Azmin, M. K. Suaidi, A. S. Shibghatullah, B. Ahmad, S. N. Salleh, M. Aziz, M. M. Shukor
Genetic Algorithms (GAs) is proven to be effective in solving many optimization tasks. GAs is one of the optimization tools used widely in solving problems based on natural selection and genetics. This paper is intended to cover the study of GA and parallel GA and analyses its usage in CPU and GPU. One of the popular ways to speed up the processing time was by running them as parallel. The idea of parallel GAs may refer to an algorithm that works by dividing large problem into smaller tasks. Broad literature review in this paper includes a categorization of the GA operations that involved with some theories and techniques used in GA, presented with the aid of diagrams. This review attempts to study and analyse the behaviour of GA and parallel GA categories to work in GPU depending on the type of genetic algorithm. Parallel GA for GPU covers the architecture of Compute Unified Device Architecture (CUDA).
{"title":"A review of Genetic Algorithms and Parallel Genetic Algorithms on Graphics Processing Unit (GPU)","authors":"F. M. Johar, F. A. Azmin, M. K. Suaidi, A. S. Shibghatullah, B. Ahmad, S. N. Salleh, M. Aziz, M. M. Shukor","doi":"10.1109/ICCSCE.2013.6719971","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719971","url":null,"abstract":"Genetic Algorithms (GAs) is proven to be effective in solving many optimization tasks. GAs is one of the optimization tools used widely in solving problems based on natural selection and genetics. This paper is intended to cover the study of GA and parallel GA and analyses its usage in CPU and GPU. One of the popular ways to speed up the processing time was by running them as parallel. The idea of parallel GAs may refer to an algorithm that works by dividing large problem into smaller tasks. Broad literature review in this paper includes a categorization of the GA operations that involved with some theories and techniques used in GA, presented with the aid of diagrams. This review attempts to study and analyse the behaviour of GA and parallel GA categories to work in GPU depending on the type of genetic algorithm. Parallel GA for GPU covers the architecture of Compute Unified Device Architecture (CUDA).","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"331 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132419505","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719952
S. Fadlallah, K. Goher
This paper presents a proposed design of a leg rehabilitation system. The system will be implemented on a reconfigurable wheelchair prototype in order to provide additional two rotational degrees of freedom (DOF) for serving more rehabilitation purposes. Lagrangian dynamic formulation is used to derive the system dynamics. Joints frictions based on Coulomb friction model are considered in the leg rehabilitation system. The system equations of motion are linearized since the model is dealt with in state space representation. LQR control approach is considered and derived for stabilization of the system. Simulation Results validating the model and the control approach are presented and discussed.
{"title":"Modelling and control of a leg rehabilitation system for a reconfigurable wheelchair","authors":"S. Fadlallah, K. Goher","doi":"10.1109/ICCSCE.2013.6719952","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719952","url":null,"abstract":"This paper presents a proposed design of a leg rehabilitation system. The system will be implemented on a reconfigurable wheelchair prototype in order to provide additional two rotational degrees of freedom (DOF) for serving more rehabilitation purposes. Lagrangian dynamic formulation is used to derive the system dynamics. Joints frictions based on Coulomb friction model are considered in the leg rehabilitation system. The system equations of motion are linearized since the model is dealt with in state space representation. LQR control approach is considered and derived for stabilization of the system. Simulation Results validating the model and the control approach are presented and discussed.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132462557","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719985
N. A. N. Mohamad, J. Jai, N. Arham, A. Hadi
With the emerging catalytic, optical and medical applications of nanoparticles, there is a growing demand for green synthesis methods to ensure consumer safety. Among bio-organisms, plants are the major source of reducing agents due to the simple procedures and inexpensive cost required. This paper presents a short review of bimetallic nanoparticle synthesis using several plant extracts. Biosynthesis studies examining pH and concentration of plant extract, reaction temperature, and ionic ratio are also presented to provide a clear understanding of how these parameters affect the formation of nanoparticles.
{"title":"A short review on the synthesis of bimetallic nanoparticles using plant extract","authors":"N. A. N. Mohamad, J. Jai, N. Arham, A. Hadi","doi":"10.1109/ICCSCE.2013.6719985","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719985","url":null,"abstract":"With the emerging catalytic, optical and medical applications of nanoparticles, there is a growing demand for green synthesis methods to ensure consumer safety. Among bio-organisms, plants are the major source of reducing agents due to the simple procedures and inexpensive cost required. This paper presents a short review of bimetallic nanoparticle synthesis using several plant extracts. Biosynthesis studies examining pH and concentration of plant extract, reaction temperature, and ionic ratio are also presented to provide a clear understanding of how these parameters affect the formation of nanoparticles.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132931694","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719981
K. K. Hasan, U. K. Ngah, M. Salleh
In this paper, flexible hardware architecture of multi-level decomposition Discrete Wavelet Transform (DWT) is proposed for image compression applications to eliminate redundant information from the transmitted images or video frames over the wireless channel. This architecture of DWT is described and synthesized with the Very High Speed Integrated Circuit (VHSIC) Hardware Description Language (VHDL) based methodology. The design can be accommodated on any targeting Field Programmable Gate Array (FPGA) device with slight changes. It facilitates to images of size 64×64, 128×128, 256×256, and 512× 512 pixels and capable of seven levels of decomposition. In order to reduce computational complexities, Fast Haar Wavelet Transform (FHWT) is used. The reduction in the resource usage of this 2D DWT multilevel FPGA core can be used to counter severe hardware constraints of various wireless and mobile device applications.
{"title":"Multilevel decomposition Discrete Wavelet Transform for hardware image compression architectures applications","authors":"K. K. Hasan, U. K. Ngah, M. Salleh","doi":"10.1109/ICCSCE.2013.6719981","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719981","url":null,"abstract":"In this paper, flexible hardware architecture of multi-level decomposition Discrete Wavelet Transform (DWT) is proposed for image compression applications to eliminate redundant information from the transmitted images or video frames over the wireless channel. This architecture of DWT is described and synthesized with the Very High Speed Integrated Circuit (VHSIC) Hardware Description Language (VHDL) based methodology. The design can be accommodated on any targeting Field Programmable Gate Array (FPGA) device with slight changes. It facilitates to images of size 64×64, 128×128, 256×256, and 512× 512 pixels and capable of seven levels of decomposition. In order to reduce computational complexities, Fast Haar Wavelet Transform (FHWT) is used. The reduction in the resource usage of this 2D DWT multilevel FPGA core can be used to counter severe hardware constraints of various wireless and mobile device applications.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"256 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122651477","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719933
Amir Mukhtar, L. Xia, T. Tang, K. A. A. Kassim
Driver Assistance System (DAS) plays a vital and promising role in most intelligent vehicles technologies by alerting the motorists about any possible collision. In such systems robustness, reliability and real-time detection are critical. This paper focused on on-road detection of approaching motorcycles, where sensor is preferably attached on the rear side of vehicle. More attention is given to the applicability of methods and technologies on motorcycle detection and recognition, as motorcycles are smaller and harder to be noticed by vehicle driver. First we discuss the problem of on-road motorcycle detection using different sensors followed by review of motorcycle detection research. Then, we discuss types of sensor to set the stage for vision-based motorcycle detection. Methods used for hypothesis generation (HG) and hypothesis verification (HV) are mentioned before the integration of detection and tracking systems. Finally, we present a critical overview of the methods discussed and assess the potential of these methodologies for the future research and applications.
{"title":"On-road approaching motorcycle detection and tracking techniques: A survey","authors":"Amir Mukhtar, L. Xia, T. Tang, K. A. A. Kassim","doi":"10.1109/ICCSCE.2013.6719933","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719933","url":null,"abstract":"Driver Assistance System (DAS) plays a vital and promising role in most intelligent vehicles technologies by alerting the motorists about any possible collision. In such systems robustness, reliability and real-time detection are critical. This paper focused on on-road detection of approaching motorcycles, where sensor is preferably attached on the rear side of vehicle. More attention is given to the applicability of methods and technologies on motorcycle detection and recognition, as motorcycles are smaller and harder to be noticed by vehicle driver. First we discuss the problem of on-road motorcycle detection using different sensors followed by review of motorcycle detection research. Then, we discuss types of sensor to set the stage for vision-based motorcycle detection. Methods used for hypothesis generation (HG) and hypothesis verification (HV) are mentioned before the integration of detection and tracking systems. Finally, we present a critical overview of the methods discussed and assess the potential of these methodologies for the future research and applications.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115466479","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719955
A. Jaber, M. F. Zolkipli
Cloud computing is a platform for expanding capabilities and developing potentialities dynamically without employing new infrastructure, personnel, or software systems. In Addition, cloud computing originated from a commercial enterprise concept, and developed into a flourishing IT invention. However, given that considerable information on individuals and companies are identified in the cloud, concerns have been raised regarding the safety of the cloud environment. Despite the hype surrounding cloud computing, customers remain reluctant to deploy their commercial enterprise into the cloud. Nevertheless, lack of protection is the only major concern that hinders increased use of cloud computing. Furthermore, the complexity with which cloud computing manages data secrecy, and information security makes the market hesitant about cloud computing. The architecture of cloud models threatens the security of existing technologies when deployed in a cloud environment. Thus, users of cloud services should know the dangers of uploading data into this new environment. Therefore, in this paper different cryptography aspects that pose a threat to cloud computing are reviewed. This paper is a survey of specific security issues brought by the use of cryptography in a cloud computing system.
{"title":"Use of cryptography in cloud computing","authors":"A. Jaber, M. F. Zolkipli","doi":"10.1109/ICCSCE.2013.6719955","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719955","url":null,"abstract":"Cloud computing is a platform for expanding capabilities and developing potentialities dynamically without employing new infrastructure, personnel, or software systems. In Addition, cloud computing originated from a commercial enterprise concept, and developed into a flourishing IT invention. However, given that considerable information on individuals and companies are identified in the cloud, concerns have been raised regarding the safety of the cloud environment. Despite the hype surrounding cloud computing, customers remain reluctant to deploy their commercial enterprise into the cloud. Nevertheless, lack of protection is the only major concern that hinders increased use of cloud computing. Furthermore, the complexity with which cloud computing manages data secrecy, and information security makes the market hesitant about cloud computing. The architecture of cloud models threatens the security of existing technologies when deployed in a cloud environment. Thus, users of cloud services should know the dangers of uploading data into this new environment. Therefore, in this paper different cryptography aspects that pose a threat to cloud computing are reviewed. This paper is a survey of specific security issues brought by the use of cryptography in a cloud computing system.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"18 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120985880","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6720016
J. Saraswathy, M. Hariharan, W. Khairunizam, S. Yaacob, N. Thiyagar
Acoustic analysis of infant cry has been the subject of a number of researchers since half decades ago. This paper addresses a simple time-frequency analysis based signal processing technique using short-time Fourier transform (STFT) for the investigation and classification of infant cry signals. A cluster of statistical features are derived from the time-frequency plots of infant cry signals. The extracted feature vectors are used to model and train two types of radial basis neural network namely Probabilistic Neural Network (PNN) and General Regression Neural Network (GRNN) in classification phases. Three classes of infant cry signals are considered such as normal cry signals cry signals from deaf infants and infants with asphyxia. Promising classification results above 99% reveals that the proposed features and classification technique can effectively classify different infant cries.
{"title":"Infant cry classification: Time frequency analysis","authors":"J. Saraswathy, M. Hariharan, W. Khairunizam, S. Yaacob, N. Thiyagar","doi":"10.1109/ICCSCE.2013.6720016","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6720016","url":null,"abstract":"Acoustic analysis of infant cry has been the subject of a number of researchers since half decades ago. This paper addresses a simple time-frequency analysis based signal processing technique using short-time Fourier transform (STFT) for the investigation and classification of infant cry signals. A cluster of statistical features are derived from the time-frequency plots of infant cry signals. The extracted feature vectors are used to model and train two types of radial basis neural network namely Probabilistic Neural Network (PNN) and General Regression Neural Network (GRNN) in classification phases. Three classes of infant cry signals are considered such as normal cry signals cry signals from deaf infants and infants with asphyxia. Promising classification results above 99% reveals that the proposed features and classification technique can effectively classify different infant cries.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125912754","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：