Pub Date : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708025
S. Bayraktar, B. Labitzke, J. Bader, R. Bornemann, P. Bolívar, A. Kolb
Raman spectroscopy is used to identify unknown constituent minerals and their abundances since Raman spectra convey characteristic information about the sample's chemical structure. We present a novel method to identify constituting pure minerals in a mixture by comparing the measured Raman spectra with a reference database. Our method comprises of two major components: A novel scale-invariant spectral matching technique, that allows to compare measured spectra with the reference spectra from the database even when the band intensities are not directly comparable and an iterative unmixing scheme to decompose a measured spectrum into its constituent minerals and compute their abundances.
{"title":"Efficient, robust, and scale-invariant decomposition of Raman spectra","authors":"S. Bayraktar, B. Labitzke, J. Bader, R. Bornemann, P. Bolívar, A. Kolb","doi":"10.1109/ICSIPA.2013.6708025","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708025","url":null,"abstract":"Raman spectroscopy is used to identify unknown constituent minerals and their abundances since Raman spectra convey characteristic information about the sample's chemical structure. We present a novel method to identify constituting pure minerals in a mixture by comparing the measured Raman spectra with a reference database. Our method comprises of two major components: A novel scale-invariant spectral matching technique, that allows to compare measured spectra with the reference spectra from the database even when the band intensities are not directly comparable and an iterative unmixing scheme to decompose a measured spectrum into its constituent minerals and compute their abundances.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129953587","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708001
Ahmed Asal Kzar, M. MatJafri, H. Lim, K. N. Mutter, S. Syahreza
The use of traditional ship sampling method of for environmental monitoring is time consuming, requires a high survey cost, and exert great efforts. In this study we classify one of the water pollutants which is the Total Suspended Solids (TSS) of polluted water in Penang strait, Malaysia by applying Modified Hopfield Neural Network Algorithm (MHNNA) on THEOS (Thailand Earth Observation System) image. The samples were collected from study area simultaneously with the airborne image acquisition. The samples locations were determined by using a handheld global positioning system (GPS), and the measurement of TSS concentrations was conducted in the lab as validation data (sea-truth data). By using algorithm (MHNNA) the concentrations of TSS have been classified according their varied values to produce the map. The map was colour-coded for visual interpretation. The investigation of efficiency of the proposed algorithm was based on dividing the validation data into two groups, the first group refers to standard samples for supervisor classification by the used algorithm. And the second group for test, where after classification we detect the second group data positions in the produced classes, then finding correlation coefficient (R) and root-mean-square-error (RMSE) between the first group data and the second group data according to their correspondence in the classes. The observations were high (R=0.899) with low (RMSE=17.687). This study indicates that TSS mapping of polluted water can be carried out using remote sensing technique by the application of MHNNA on THEOS satellite data over Penang strait, Malaysia.
{"title":"Modified Hopfield Neural Network Algorithm (MHNNA) for TSS mapping in Penang strait, Malaysia","authors":"Ahmed Asal Kzar, M. MatJafri, H. Lim, K. N. Mutter, S. Syahreza","doi":"10.1109/ICSIPA.2013.6708001","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708001","url":null,"abstract":"The use of traditional ship sampling method of for environmental monitoring is time consuming, requires a high survey cost, and exert great efforts. In this study we classify one of the water pollutants which is the Total Suspended Solids (TSS) of polluted water in Penang strait, Malaysia by applying Modified Hopfield Neural Network Algorithm (MHNNA) on THEOS (Thailand Earth Observation System) image. The samples were collected from study area simultaneously with the airborne image acquisition. The samples locations were determined by using a handheld global positioning system (GPS), and the measurement of TSS concentrations was conducted in the lab as validation data (sea-truth data). By using algorithm (MHNNA) the concentrations of TSS have been classified according their varied values to produce the map. The map was colour-coded for visual interpretation. The investigation of efficiency of the proposed algorithm was based on dividing the validation data into two groups, the first group refers to standard samples for supervisor classification by the used algorithm. And the second group for test, where after classification we detect the second group data positions in the produced classes, then finding correlation coefficient (R) and root-mean-square-error (RMSE) between the first group data and the second group data according to their correspondence in the classes. The observations were high (R=0.899) with low (RMSE=17.687). This study indicates that TSS mapping of polluted water can be carried out using remote sensing technique by the application of MHNNA on THEOS satellite data over Penang strait, Malaysia.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"05 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129315314","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707986
S. Ramamurthy, M. Raghavan
We present a fast and efficient method for feature-based synthesis of musical sounds that are perceptually close to an actual instrument, by designing filters that spectrally shape a chosen excitation signal. We have proposed a novel, multi-dimensional set of features for the Indian bamboo flute which has been used for the filter design. The filter design approach aims at providing a generic framework that can be used to obtain filters of appropriate orders to synthesize musical sounds of melodic instruments characterized by continuity in sound production, e.g., the bowed and woodwind classes of instruments. The designed filters are used for real time synthesis along with a harmonically rich excitation that can be generated with low complexity. The proposed approach of modeling and filter design is scalable in complexity and quality.
{"title":"Filter design for synthesis of musical notes: A multidimensional feature-based approach","authors":"S. Ramamurthy, M. Raghavan","doi":"10.1109/ICSIPA.2013.6707986","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707986","url":null,"abstract":"We present a fast and efficient method for feature-based synthesis of musical sounds that are perceptually close to an actual instrument, by designing filters that spectrally shape a chosen excitation signal. We have proposed a novel, multi-dimensional set of features for the Indian bamboo flute which has been used for the filter design. The filter design approach aims at providing a generic framework that can be used to obtain filters of appropriate orders to synthesize musical sounds of melodic instruments characterized by continuity in sound production, e.g., the bowed and woodwind classes of instruments. The designed filters are used for real time synthesis along with a harmonically rich excitation that can be generated with low complexity. The proposed approach of modeling and filter design is scalable in complexity and quality.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131067183","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708027
Hussam M. M. Alhaj, N. M. Nor, V. Asirvadam, M. F. Abdullah
The widespread use of power electronics devises and nonlinear loads in power system grids is increasing in the last decades leads to rise of harmonic in power system signals. Great damage to power system gird can happen due to harmonics. Thus it is important to precisely estimate the harmonics components that may help to avoid its harmful effect of the electrical grid performance. The more common algorithm that has been used to estimate the harmonic component is the Fast Fourier Transform (FFT), however FFT has few limitations, furthermore, modern power system network getting complex and noisy. Therefore, fast and accurate harmonic estimation in the presence of noise is needed. Sliding window based least mean square (LMS) algorithm is introduced in this paper to estimate the harmonic components in noisy environment. The result shows that the sliding window method able to give a good estimation to the harmonic component even when the signal to noise ratio (SNR) is 0 dB.
{"title":"Power system harmonics estimation using sliding window based LMS","authors":"Hussam M. M. Alhaj, N. M. Nor, V. Asirvadam, M. F. Abdullah","doi":"10.1109/ICSIPA.2013.6708027","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708027","url":null,"abstract":"The widespread use of power electronics devises and nonlinear loads in power system grids is increasing in the last decades leads to rise of harmonic in power system signals. Great damage to power system gird can happen due to harmonics. Thus it is important to precisely estimate the harmonics components that may help to avoid its harmful effect of the electrical grid performance. The more common algorithm that has been used to estimate the harmonic component is the Fast Fourier Transform (FFT), however FFT has few limitations, furthermore, modern power system network getting complex and noisy. Therefore, fast and accurate harmonic estimation in the presence of noise is needed. Sliding window based least mean square (LMS) algorithm is introduced in this paper to estimate the harmonic components in noisy environment. The result shows that the sliding window method able to give a good estimation to the harmonic component even when the signal to noise ratio (SNR) is 0 dB.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131173200","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708045
Yan Ma, Rui Wang, Jinxiang Du
Parameter estimation of linear frequency modulation signal (LFM) is one of important problems of radar or sonar. Because the fractional Fourier transform (FRFT) can centralize the energy of LFM, FRFT became an important way to estimate the parameters of LFM. The location of the FRFT spectrum's peak was close relative with the chirp rate and central frequency of LFM. The finer we search the peak in FRFT domain the estimated parameter is more accurate. But the finer search results in the huge computation. In this paper, based on the definition and properties of FRFT, the amplitude characteristics of analytic LFM in FRFT domain was derived. According to those characters, the multi-resolution based-5 point was proposed for increasing the speed of search. It can speed up the search.
{"title":"Amplitude characteristics of linear frequency modulation signal in FRFT domain","authors":"Yan Ma, Rui Wang, Jinxiang Du","doi":"10.1109/ICSIPA.2013.6708045","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708045","url":null,"abstract":"Parameter estimation of linear frequency modulation signal (LFM) is one of important problems of radar or sonar. Because the fractional Fourier transform (FRFT) can centralize the energy of LFM, FRFT became an important way to estimate the parameters of LFM. The location of the FRFT spectrum's peak was close relative with the chirp rate and central frequency of LFM. The finer we search the peak in FRFT domain the estimated parameter is more accurate. But the finer search results in the huge computation. In this paper, based on the definition and properties of FRFT, the amplitude characteristics of analytic LFM in FRFT domain was derived. According to those characters, the multi-resolution based-5 point was proposed for increasing the speed of search. It can speed up the search.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130968717","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708043
Mohammed Hasan, S. Abdullah, Z. Othman
One of the most recently developed face recognition technique has utilized PSO-SVM, this method lacks in the initial phase of the PSO technique. That is in PSO; initially the populations are generated in random manner. Due to this random process, the population results may also be in random. Thus, it is not certain that this method will produce precise result. Hence to avoid this drawback, a modified face recognition method is proposed in this paper. Here, a new face recognition method based on Opposition based PSO with SVM (OPSO-SVM) is introduced. To accomplish the face recognition with our proposed OPSO-SVM, initially feature extraction process is carried out on the image database. In the feature extraction process, the efficient features are extracted and then given to the SVM training and testing process. In OPSO, the populations are generated in two ways: one is random population as same as the normal PSO technique and the other is opposition population, which is based on the random population values. The optimized parameters in SVM by OPSO efficiently perform the face recognition process. Two human face databases FERET and YALE are utilized to analyze the performance of our proposed OPSO-SVM technique and also this OPSO-SVM is compared with PSO-SVM and standard SVM techniques.
{"title":"Face recognition based on opposition particle swarm optimization and support vector machine","authors":"Mohammed Hasan, S. Abdullah, Z. Othman","doi":"10.1109/ICSIPA.2013.6708043","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708043","url":null,"abstract":"One of the most recently developed face recognition technique has utilized PSO-SVM, this method lacks in the initial phase of the PSO technique. That is in PSO; initially the populations are generated in random manner. Due to this random process, the population results may also be in random. Thus, it is not certain that this method will produce precise result. Hence to avoid this drawback, a modified face recognition method is proposed in this paper. Here, a new face recognition method based on Opposition based PSO with SVM (OPSO-SVM) is introduced. To accomplish the face recognition with our proposed OPSO-SVM, initially feature extraction process is carried out on the image database. In the feature extraction process, the efficient features are extracted and then given to the SVM training and testing process. In OPSO, the populations are generated in two ways: one is random population as same as the normal PSO technique and the other is opposition population, which is based on the random population values. The optimized parameters in SVM by OPSO efficiently perform the face recognition process. Two human face databases FERET and YALE are utilized to analyze the performance of our proposed OPSO-SVM technique and also this OPSO-SVM is compared with PSO-SVM and standard SVM techniques.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114900604","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708014
Sanjay Saini, D. R. A. Rambli, S. Sulaiman, M. N. Zakaria
Tracking full articulated human body motion is a very challenging task due to the high dimensionality of human skeleton model, self-occlusion and large variety of body poses. In this work, we explore a novel Low-dimensional Manifold Learning (LDML) approach to overcome high dimensional search space of human model. Low-dimensional demonstration not only delivers a compact tractable search space, but it is efficient to capture general human pose variations. The key contribution of this work is an algorithm of Quantum-behaved Particle Swarm Optimization (QPSO) for pose optimization in latent space of human motion. Firstly, we learn the human motion model in low-dimensional latent space using nonlinear dimension reduction technique charting based on hierarchical strategy. Increased dependence provision is carried out using hierarchy strategic measures in charting, which improves accuracy in higher flexibility and adaptation. Then we applied QPSO algorithm to estimate the human poses in low-dimensional latent space. Preliminary experimental tracking results show that our approach is able to give good accuracy as compared to conventional state-of-the-arts methods.
{"title":"Human pose tracking in low-dimensional subspace using manifold learning by charting","authors":"Sanjay Saini, D. R. A. Rambli, S. Sulaiman, M. N. Zakaria","doi":"10.1109/ICSIPA.2013.6708014","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708014","url":null,"abstract":"Tracking full articulated human body motion is a very challenging task due to the high dimensionality of human skeleton model, self-occlusion and large variety of body poses. In this work, we explore a novel Low-dimensional Manifold Learning (LDML) approach to overcome high dimensional search space of human model. Low-dimensional demonstration not only delivers a compact tractable search space, but it is efficient to capture general human pose variations. The key contribution of this work is an algorithm of Quantum-behaved Particle Swarm Optimization (QPSO) for pose optimization in latent space of human motion. Firstly, we learn the human motion model in low-dimensional latent space using nonlinear dimension reduction technique charting based on hierarchical strategy. Increased dependence provision is carried out using hierarchy strategic measures in charting, which improves accuracy in higher flexibility and adaptation. Then we applied QPSO algorithm to estimate the human poses in low-dimensional latent space. Preliminary experimental tracking results show that our approach is able to give good accuracy as compared to conventional state-of-the-arts methods.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"s2-36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117122656","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708033
S. S. Chong, K. Sim, M. E. Nia
Magnetic resonance imaging (MRI) has higher sensitivity than mammography in breast cancer detection. However, the low contrast images produced often process difficulties in segmenting the images into regions of interest. There are various contrast enhancement techniques proposed over the years. Although these techniques shows evident contrast enhancement on general images, most of them are not suitable to apply to breast MRI images due to large portion of dark background and close gray levels between grandular tissues and fatty tissues. In this paper, a modified version of hyperbolic logarithm contrast enhancement technique is introduced. Comparisons are made visually and statistically with several existing contrast enhancement techniques.
{"title":"Modified HL contrast enhancement technique for breast MR images","authors":"S. S. Chong, K. Sim, M. E. Nia","doi":"10.1109/ICSIPA.2013.6708033","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708033","url":null,"abstract":"Magnetic resonance imaging (MRI) has higher sensitivity than mammography in breast cancer detection. However, the low contrast images produced often process difficulties in segmenting the images into regions of interest. There are various contrast enhancement techniques proposed over the years. Although these techniques shows evident contrast enhancement on general images, most of them are not suitable to apply to breast MRI images due to large portion of dark background and close gray levels between grandular tissues and fatty tissues. In this paper, a modified version of hyperbolic logarithm contrast enhancement technique is introduced. Comparisons are made visually and statistically with several existing contrast enhancement techniques.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123441109","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708021
R. Diao, Qingfeng Meng, Yumei Liang
An algorithm for the estimation of parameters that characterize a multi-frequency damped sinusoidal signal is presented. At first, the signal is weighted by using the Hanning window before the fast Fourier transform (FFT), then the frequencies, amplitudes, phases and damped factors of the signal are obtained by frequency domain interpolation. It is shown that the purpose of improving the accuracy of parameter estimation is achieved by using the Hanning window which reduces the long-range leakage and by frequency domain interpolation which eliminates the short-range leakage. The sensitivity analysis of changing of the parameters, noise effect and sampling length show that, both the noise effect and spectrum interference are considered, proving the reliability and high accuracy parameter estimation in a number of engineering applications. Otherwise, the characteristics of efficient computational and low memory demands are advantageously adopted for the poor computing resources situations.
{"title":"An windowed frequency domain interpolation algorithms for damped sinusoidal signals","authors":"R. Diao, Qingfeng Meng, Yumei Liang","doi":"10.1109/ICSIPA.2013.6708021","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708021","url":null,"abstract":"An algorithm for the estimation of parameters that characterize a multi-frequency damped sinusoidal signal is presented. At first, the signal is weighted by using the Hanning window before the fast Fourier transform (FFT), then the frequencies, amplitudes, phases and damped factors of the signal are obtained by frequency domain interpolation. It is shown that the purpose of improving the accuracy of parameter estimation is achieved by using the Hanning window which reduces the long-range leakage and by frequency domain interpolation which eliminates the short-range leakage. The sensitivity analysis of changing of the parameters, noise effect and sampling length show that, both the noise effect and spectrum interference are considered, proving the reliability and high accuracy parameter estimation in a number of engineering applications. Otherwise, the characteristics of efficient computational and low memory demands are advantageously adopted for the poor computing resources situations.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129893180","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707989
H. Jaafar, D. A. Ramli, S. Shahrudin
Identification of frog sound is useful tool and competent in biological research and environmental monitoring. In contrast with traditional methods that not practical due to the time consuming, expensive or detrimental to the animal's welfare, this study proposes an automatic frog call identification system. 750 data species that recorded from Malaysia forest is used as data signals and have been corrupted by 10dB and 20dB noise to determine the performance of accuracy in noisy environment. MFCC parameter is employed as feature extraction. An analysis of signals for different number of MFCCs (8, 12, 15, 20 and 25) is presented and the results are provided using MFCC, Delta Coefficients (ΔMFCC) and Delta Delta Coefficients (ΔΔMFCC). Subsequently, kNN classifier is applied to evaluate the performance in the frog identification system. The results show the accuracy range from 84.67% to 85.78%, 61.33% to 68.89% and 59.33% to 67.33% in clean environment, 10dB and 20dB, respectively.
{"title":"MFCC based frog identification system in noisy environment","authors":"H. Jaafar, D. A. Ramli, S. Shahrudin","doi":"10.1109/ICSIPA.2013.6707989","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707989","url":null,"abstract":"Identification of frog sound is useful tool and competent in biological research and environmental monitoring. In contrast with traditional methods that not practical due to the time consuming, expensive or detrimental to the animal's welfare, this study proposes an automatic frog call identification system. 750 data species that recorded from Malaysia forest is used as data signals and have been corrupted by 10dB and 20dB noise to determine the performance of accuracy in noisy environment. MFCC parameter is employed as feature extraction. An analysis of signals for different number of MFCCs (8, 12, 15, 20 and 25) is presented and the results are provided using MFCC, Delta Coefficients (ΔMFCC) and Delta Delta Coefficients (ΔΔMFCC). Subsequently, kNN classifier is applied to evaluate the performance in the frog identification system. The results show the accuracy range from 84.67% to 85.78%, 61.33% to 68.89% and 59.33% to 67.33% in clean environment, 10dB and 20dB, respectively.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130679898","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：