Pub Date : 2022-03-30DOI: 10.1109/dspa53304.2022.9790747
A. Alimuradov, A. Tychkov, P. Churakov, Bogdan A. Porezanov, Ilya O. Steshkin, Kirill E. Platonov, A. Baranova, D. S. Dudnikov
The article presents a novel technological procedure for speech signal processing based on the empirical mode decomposition, being an adaptive time-frequency analysis method. The proposed procedure is based on the uniform splitting of the original speech signal into fragments, the decomposition of fragments into empirical modes, and the formation of new mode speech signals. The goal of the technological procedure elaboration is to expand the space for informatively significant amplitude, time, frequency, and energy characteristics of the original speech signal. A brief description of various types of empirical mode decomposition has been presented, and their advantages and disadvantages have been revealed. The functionality of the proposed technological procedure has been detailed, and the research outcomes have been reported. An analysis of the research results has evidenced that the minimum time for the formation of a set of modal speech signals is afforded when analyzing 300–1000 ms fragments; the minimum error in the formation of a set of mode speech signals is obtained when the fragments are decomposed into 8–10 empirical modes, and the difference between the original and reconstructed signals being less than 0.001 V (0.1 %). It has been concluded that the proposed technological procedure actually provides an expansion of the space for informatively significant amplitude, time, frequency, and energy characteristics due to the formation of a set of new mode speech signals. Thus, it can be efficiently used in the formation of an optimal set of speech parameters relevant to naturally expressed human emotions.
{"title":"Novel EMD-Based Technological Procedure for Speech Signal Processing","authors":"A. Alimuradov, A. Tychkov, P. Churakov, Bogdan A. Porezanov, Ilya O. Steshkin, Kirill E. Platonov, A. Baranova, D. S. Dudnikov","doi":"10.1109/dspa53304.2022.9790747","DOIUrl":"https://doi.org/10.1109/dspa53304.2022.9790747","url":null,"abstract":"The article presents a novel technological procedure for speech signal processing based on the empirical mode decomposition, being an adaptive time-frequency analysis method. The proposed procedure is based on the uniform splitting of the original speech signal into fragments, the decomposition of fragments into empirical modes, and the formation of new mode speech signals. The goal of the technological procedure elaboration is to expand the space for informatively significant amplitude, time, frequency, and energy characteristics of the original speech signal. A brief description of various types of empirical mode decomposition has been presented, and their advantages and disadvantages have been revealed. The functionality of the proposed technological procedure has been detailed, and the research outcomes have been reported. An analysis of the research results has evidenced that the minimum time for the formation of a set of modal speech signals is afforded when analyzing 300–1000 ms fragments; the minimum error in the formation of a set of mode speech signals is obtained when the fragments are decomposed into 8–10 empirical modes, and the difference between the original and reconstructed signals being less than 0.001 V (0.1 %). It has been concluded that the proposed technological procedure actually provides an expansion of the space for informatively significant amplitude, time, frequency, and energy characteristics due to the formation of a set of new mode speech signals. Thus, it can be efficiently used in the formation of an optimal set of speech parameters relevant to naturally expressed human emotions.","PeriodicalId":428492,"journal":{"name":"2022 24th International Conference on Digital Signal Processing and its Applications (DSPA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130896197","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 : 2022-03-30DOI: 10.1109/dspa53304.2022.9790785
Andrey Mareev, A. Orlov
The paper considers an algorithm for localizing the markings of railway wheels. The parameters required for the operation of the algorithm have been selected. Research has been carried out to limit the shooting conditions. The functional model of the system is described. An example of using the developed software is given.
{"title":"Development of a System for Localizing the Markings of Railway Wheels in a Video Stream","authors":"Andrey Mareev, A. Orlov","doi":"10.1109/dspa53304.2022.9790785","DOIUrl":"https://doi.org/10.1109/dspa53304.2022.9790785","url":null,"abstract":"The paper considers an algorithm for localizing the markings of railway wheels. The parameters required for the operation of the algorithm have been selected. Research has been carried out to limit the shooting conditions. The functional model of the system is described. An example of using the developed software is given.","PeriodicalId":428492,"journal":{"name":"2022 24th International Conference on Digital Signal Processing and its Applications (DSPA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122640723","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 : 2022-03-30DOI: 10.1109/dspa53304.2022.9790787
Dmitrii Maleev
Reasons for issues caused by latency spikes are described. Method of self-diagnostics of Internet Protocol (IP) audio codec software that is suitable for development, quality control, and operation and allows detecting these issues without external equipment and a special signal is demonstrated. The method of manual signal quality testing is mentioned. Based on that a method of automated testing using a second IP audio codec with specially modified software that allows detecting signal distortion in realistic network conditions is described. These methods simplify software quality control and accelerate the development of new versions of software, allowing detection of issues that are hard to detect with other methods.
{"title":"Quality Control Automation of IP Audio Codec Software","authors":"Dmitrii Maleev","doi":"10.1109/dspa53304.2022.9790787","DOIUrl":"https://doi.org/10.1109/dspa53304.2022.9790787","url":null,"abstract":"Reasons for issues caused by latency spikes are described. Method of self-diagnostics of Internet Protocol (IP) audio codec software that is suitable for development, quality control, and operation and allows detecting these issues without external equipment and a special signal is demonstrated. The method of manual signal quality testing is mentioned. Based on that a method of automated testing using a second IP audio codec with specially modified software that allows detecting signal distortion in realistic network conditions is described. These methods simplify software quality control and accelerate the development of new versions of software, allowing detection of issues that are hard to detect with other methods.","PeriodicalId":428492,"journal":{"name":"2022 24th International Conference on Digital Signal Processing and its Applications (DSPA)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130525571","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 : 2022-03-30DOI: 10.1109/dspa53304.2022.9790764
A. Degtyaryov, A. Kozhemyakin, I. Afonin, A. Polyakov
To lower the impact of non-linear distortions on the accuracy of reception of information under multipath signal transmission conditions it is proposed to use a technique involving orthogonalization of the useful and parasitic signals. The core of the technique is to determine such orthogonality weight that would minimize dispersion of the noise caused by parasitic signals.
{"title":"Technique for Lowering the Impact of Non-linear Distortions on Accuracy of Reception of Signals Transmitted in Multiple Paths","authors":"A. Degtyaryov, A. Kozhemyakin, I. Afonin, A. Polyakov","doi":"10.1109/dspa53304.2022.9790764","DOIUrl":"https://doi.org/10.1109/dspa53304.2022.9790764","url":null,"abstract":"To lower the impact of non-linear distortions on the accuracy of reception of information under multipath signal transmission conditions it is proposed to use a technique involving orthogonalization of the useful and parasitic signals. The core of the technique is to determine such orthogonality weight that would minimize dispersion of the noise caused by parasitic signals.","PeriodicalId":428492,"journal":{"name":"2022 24th International Conference on Digital Signal Processing and its Applications (DSPA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116796798","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 : 2022-03-30DOI: 10.1109/dspa53304.2022.9790766
Viktor F. Fedorov, V. Stolyar
This article is about the influence of the current level of the medical digital devices for personal use and the methods of distant diagnostics on the effectiveness of the most demanded and mass direction of telemedic technology implementation — personal telemedicine.
{"title":"Digital Transformation is a Way to Increase the Effectiveness of Personal Telemedicine","authors":"Viktor F. Fedorov, V. Stolyar","doi":"10.1109/dspa53304.2022.9790766","DOIUrl":"https://doi.org/10.1109/dspa53304.2022.9790766","url":null,"abstract":"This article is about the influence of the current level of the medical digital devices for personal use and the methods of distant diagnostics on the effectiveness of the most demanded and mass direction of telemedic technology implementation — personal telemedicine.","PeriodicalId":428492,"journal":{"name":"2022 24th International Conference on Digital Signal Processing and its Applications (DSPA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115595607","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 : 2022-03-30DOI: 10.1109/dspa53304.2022.9790781
Y. Turovsky, A. Vakhtin, S. Borzunov, E. Martynenko
The paper presents a method for detecting evoked potentials from a background electroencephalogram based on one iteration of brain electrical activity in response to the stimulation process. The basis of the method is the formation of a quasi-periodic sequence of the component of the evoked potential (EP) of interest to the researcher, due to the addition of reference fragments of the EP with a given time shift. The resulting sequence is compared with the reference EP accumulated within the framework of the coherent accumulation approach and appropriately transformed so that the period of the desired component coincides with that in the signal under study. The comparison is carried out taking into account the Multivariate Synchronization Index (MSI) method, which is a further development of the canonical correlation method. The results obtained can be applied to the tasks of brain-computer interfaces (BCI) based on the P300 potential. In addition, this solution is applicable to the isolation of any biomedical signal containing single or non-periodic components.
{"title":"P300 Evoked Potential Detection Method Using the MSI Algorithm in the Problem of Human-Computer Interaction","authors":"Y. Turovsky, A. Vakhtin, S. Borzunov, E. Martynenko","doi":"10.1109/dspa53304.2022.9790781","DOIUrl":"https://doi.org/10.1109/dspa53304.2022.9790781","url":null,"abstract":"The paper presents a method for detecting evoked potentials from a background electroencephalogram based on one iteration of brain electrical activity in response to the stimulation process. The basis of the method is the formation of a quasi-periodic sequence of the component of the evoked potential (EP) of interest to the researcher, due to the addition of reference fragments of the EP with a given time shift. The resulting sequence is compared with the reference EP accumulated within the framework of the coherent accumulation approach and appropriately transformed so that the period of the desired component coincides with that in the signal under study. The comparison is carried out taking into account the Multivariate Synchronization Index (MSI) method, which is a further development of the canonical correlation method. The results obtained can be applied to the tasks of brain-computer interfaces (BCI) based on the P300 potential. In addition, this solution is applicable to the isolation of any biomedical signal containing single or non-periodic components.","PeriodicalId":428492,"journal":{"name":"2022 24th International Conference on Digital Signal Processing and its Applications (DSPA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122140080","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 : 2022-03-30DOI: 10.1109/dspa53304.2022.9790754
Kritiprasanna Das, Pankaj Verma, R. B. Pachori
Meditation is practiced since the old days and its popularity is growing in recent years to get better mental as well as physical health in a natural way. A rapidly increasing number of studies are involved in finding the biological mech-anism underlying the beneficial impacts of meditation. Surface electroencephalogram (EEG) is a non-invasive way to record the electrical activity of the brain which carries important signature about the different neural processing, going on inside the brain. EEG signals show oscillations at different frequency bands known as EEG rhythms which are associated with divergent neurophysiological states. In this paper, we have analyzed the effect of chanting 'Hare Krishna Mantra’ (HKM) on EEG rhythms. Relative band power of different rhythms, after and before one round (108 times) chanting HKM, are compared. A non-stationary signal decomposition tool, Fourier-Bessel series expansion is used to calculate the band power. After mediation, alpha band power has increased significantly which implies the relaxed and peaceful state of mind. This study on HKM chanting effects on EEG rhythms may show a simple but effective path to control stress, depression, tension, etc.
{"title":"Assessment of Chanting Effects Using EEG Signals","authors":"Kritiprasanna Das, Pankaj Verma, R. B. Pachori","doi":"10.1109/dspa53304.2022.9790754","DOIUrl":"https://doi.org/10.1109/dspa53304.2022.9790754","url":null,"abstract":"Meditation is practiced since the old days and its popularity is growing in recent years to get better mental as well as physical health in a natural way. A rapidly increasing number of studies are involved in finding the biological mech-anism underlying the beneficial impacts of meditation. Surface electroencephalogram (EEG) is a non-invasive way to record the electrical activity of the brain which carries important signature about the different neural processing, going on inside the brain. EEG signals show oscillations at different frequency bands known as EEG rhythms which are associated with divergent neurophysiological states. In this paper, we have analyzed the effect of chanting 'Hare Krishna Mantra’ (HKM) on EEG rhythms. Relative band power of different rhythms, after and before one round (108 times) chanting HKM, are compared. A non-stationary signal decomposition tool, Fourier-Bessel series expansion is used to calculate the band power. After mediation, alpha band power has increased significantly which implies the relaxed and peaceful state of mind. This study on HKM chanting effects on EEG rhythms may show a simple but effective path to control stress, depression, tension, etc.","PeriodicalId":428492,"journal":{"name":"2022 24th International Conference on Digital Signal Processing and its Applications (DSPA)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132079628","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 : 2022-03-30DOI: 10.1109/dspa53304.2022.9790784
I. Malay, Evgeniy U. Kharitonov, Anastasiya F. Kharitonova
The estimation and compensation method of the systematic measurement error terms, which are not removed by the one-port calibration of vector network analyzer, is proposed. The method is based on the well-known ripple methods, used to obtain the residual systematic measurement error terms estimates in the frequency domain by the insertion a regular transmission line section with characteristic impedance close to the reference impedance of the vector network analyzer port. By the using of the time domain analysis technics for the processing of the digitized ripple patterns allowed made to obtain the more accurate estimates of the residual systematic measurement error terms and to use them to correct the results of the measurements of the complex reflection coefficient and to correct the calibration standard models. The evaluation of the complex reflection coefficient systematic measurement error, achieved as a result of the proposed method usage, is also considered.
{"title":"Residual Systematic Error Terms Estimation Method by Digital Processing the Measurements Results of Complex Reflection Coefficient in Time Domain","authors":"I. Malay, Evgeniy U. Kharitonov, Anastasiya F. Kharitonova","doi":"10.1109/dspa53304.2022.9790784","DOIUrl":"https://doi.org/10.1109/dspa53304.2022.9790784","url":null,"abstract":"The estimation and compensation method of the systematic measurement error terms, which are not removed by the one-port calibration of vector network analyzer, is proposed. The method is based on the well-known ripple methods, used to obtain the residual systematic measurement error terms estimates in the frequency domain by the insertion a regular transmission line section with characteristic impedance close to the reference impedance of the vector network analyzer port. By the using of the time domain analysis technics for the processing of the digitized ripple patterns allowed made to obtain the more accurate estimates of the residual systematic measurement error terms and to use them to correct the results of the measurements of the complex reflection coefficient and to correct the calibration standard models. The evaluation of the complex reflection coefficient systematic measurement error, achieved as a result of the proposed method usage, is also considered.","PeriodicalId":428492,"journal":{"name":"2022 24th International Conference on Digital Signal Processing and its Applications (DSPA)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133840719","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 : 2022-03-30DOI: 10.1109/dspa53304.2022.9790751
A. Astafiev, A. Zhiznyakov, A. Zakharov, D. Privezentsev
The work is devoted to the development of an algorithm for preprocessing channel state information of the WIFI communication channel for building indoor positioning systems. The relevance of the work is associated with the rapid growth of the market for mobile smart devices. The use of such devices requires higher positioning accuracy than existing methods and approaches can provide. In this regard, the problem solved in the framework of the study is an urgent scientific and technical problem. The paper proposes consideration of information about the channel state information, as opposed to the method of measuring the RSSI signal level, adopted in most radio positioning algorithms. Unlike RSSI, the link state information includes information about the signal transmitted on each of the subcarriers. The paper considers the WiFi4 standard with 56 sub carriers. The data packet contains information about the phase and amplitude of the signal. The study considers a technique for obtaining data on the channel state information, its collection, preprocessing and synchronization. The algorithms considered in the article make it possible to prepare initial, raw data for use in practical indoor positioning algorithms using data mining methods.
{"title":"Algorithm for Preliminary Processing Channel State Information of the WIFI Communication Channel for Building Indoor Positioning Systems","authors":"A. Astafiev, A. Zhiznyakov, A. Zakharov, D. Privezentsev","doi":"10.1109/dspa53304.2022.9790751","DOIUrl":"https://doi.org/10.1109/dspa53304.2022.9790751","url":null,"abstract":"The work is devoted to the development of an algorithm for preprocessing channel state information of the WIFI communication channel for building indoor positioning systems. The relevance of the work is associated with the rapid growth of the market for mobile smart devices. The use of such devices requires higher positioning accuracy than existing methods and approaches can provide. In this regard, the problem solved in the framework of the study is an urgent scientific and technical problem. The paper proposes consideration of information about the channel state information, as opposed to the method of measuring the RSSI signal level, adopted in most radio positioning algorithms. Unlike RSSI, the link state information includes information about the signal transmitted on each of the subcarriers. The paper considers the WiFi4 standard with 56 sub carriers. The data packet contains information about the phase and amplitude of the signal. The study considers a technique for obtaining data on the channel state information, its collection, preprocessing and synchronization. The algorithms considered in the article make it possible to prepare initial, raw data for use in practical indoor positioning algorithms using data mining methods.","PeriodicalId":428492,"journal":{"name":"2022 24th International Conference on Digital Signal Processing and its Applications (DSPA)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130099392","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 : 2022-03-30DOI: 10.1109/dspa53304.2022.9790762
P. Chaudhary, Sujay Jain, Tina Damani, Shirali Gokharu, R. B. Pachori
This paper presents a framework for the automatic classification of Primary Angle-Closure Glaucoma (PACG), Pri-mary Open-Angle Glaucoma (POAG), and secondary Glaucoma from a normal subject. Order-one two-dimensional-Fourier-Bessel series expansion-empirical wavelet transform (2D-FBSE-EWT) based fusion ensemble ResNet-50 model is used in this work. Order-one 2D-FBSE-EWT decomposes the fundus images into sub-images. Subsequently, each sub-image is fed to the ResNet-50 model for extraction of deep features. Thereafter, deep features from each sub-images are ensembled. The ensembled features are then reduced using principal component analysis, and finally the reduced features are fed to a Softmax classifier for classification. Besides this approach, 4-channel, 3-channel (diagonal-wise grouping), and 2-channel (diagonal-wise grouping and neglecting diagonal detail component) sub-image groupings are also compared at 5-fold and 10-fold cross-validation. The 3-channel order-one 2D-FBSE-EWT based fusion ensemble ResNet-50 model provided an accuracy of 93% for the balanced database whereas it was limited to an accuracy of 78.3% for the unbalanced database at 10-fold cross-validation.
{"title":"Automatic Diagnosis of Type of Glaucoma Using Order-One 2D-FBSE-EWT","authors":"P. Chaudhary, Sujay Jain, Tina Damani, Shirali Gokharu, R. B. Pachori","doi":"10.1109/dspa53304.2022.9790762","DOIUrl":"https://doi.org/10.1109/dspa53304.2022.9790762","url":null,"abstract":"This paper presents a framework for the automatic classification of Primary Angle-Closure Glaucoma (PACG), Pri-mary Open-Angle Glaucoma (POAG), and secondary Glaucoma from a normal subject. Order-one two-dimensional-Fourier-Bessel series expansion-empirical wavelet transform (2D-FBSE-EWT) based fusion ensemble ResNet-50 model is used in this work. Order-one 2D-FBSE-EWT decomposes the fundus images into sub-images. Subsequently, each sub-image is fed to the ResNet-50 model for extraction of deep features. Thereafter, deep features from each sub-images are ensembled. The ensembled features are then reduced using principal component analysis, and finally the reduced features are fed to a Softmax classifier for classification. Besides this approach, 4-channel, 3-channel (diagonal-wise grouping), and 2-channel (diagonal-wise grouping and neglecting diagonal detail component) sub-image groupings are also compared at 5-fold and 10-fold cross-validation. The 3-channel order-one 2D-FBSE-EWT based fusion ensemble ResNet-50 model provided an accuracy of 93% for the balanced database whereas it was limited to an accuracy of 78.3% for the unbalanced database at 10-fold cross-validation.","PeriodicalId":428492,"journal":{"name":"2022 24th International Conference on Digital Signal Processing and its Applications (DSPA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122804525","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：