L. Nanni, Giovanni Faldani, S. Brahnam, Riccardo Bravin, Elia Feltrin
This paper presents a study of an automated system for identifying planktic foraminifera at the species level. The system uses a combination of deep learning methods, specifically convolutional neural networks (CNNs), to analyze digital images of foraminifera taken at different illumination angles. The dataset is composed of 1437 groups of sixteen grayscale images, one group for each foraminifera specimen, that are then converted to RGB images with various processing methods. These RGB images are fed into a set of CNNs, organized in an ensemble learning (EL) environment. The ensemble is built by training different networks using different approaches for creating the RGB images. The study finds that an ensemble of CNN models trained on different RGB images improves the system’s performance compared to other state-of-the-art approaches. The main focus of this paper is to introduce multiple colorization methods that differ from the current cutting-edge techniques; novel strategies like Gaussian or mean-based techniques are suggested. The proposed system was also found to outperform human experts in classification accuracy.
{"title":"Improving Foraminifera Classification Using Convolutional Neural Networks with Ensemble Learning","authors":"L. Nanni, Giovanni Faldani, S. Brahnam, Riccardo Bravin, Elia Feltrin","doi":"10.3390/signals4030028","DOIUrl":"https://doi.org/10.3390/signals4030028","url":null,"abstract":"This paper presents a study of an automated system for identifying planktic foraminifera at the species level. The system uses a combination of deep learning methods, specifically convolutional neural networks (CNNs), to analyze digital images of foraminifera taken at different illumination angles. The dataset is composed of 1437 groups of sixteen grayscale images, one group for each foraminifera specimen, that are then converted to RGB images with various processing methods. These RGB images are fed into a set of CNNs, organized in an ensemble learning (EL) environment. The ensemble is built by training different networks using different approaches for creating the RGB images. The study finds that an ensemble of CNN models trained on different RGB images improves the system’s performance compared to other state-of-the-art approaches. The main focus of this paper is to introduce multiple colorization methods that differ from the current cutting-edge techniques; novel strategies like Gaussian or mean-based techniques are suggested. The proposed system was also found to outperform human experts in classification accuracy.","PeriodicalId":93815,"journal":{"name":"Signals","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49048178","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}
We present an algorithm for extracting basis functions from the chaotic Lorenz system along with timing and bit-sequence statistics. Previous work focused on modifying Lorenz waveforms and extracting the basis function of a single state variable. Importantly, these efforts initiated the development of solvable chaotic systems with simple matched filters, which are suitable for many spread spectrum applications. However, few solvable chaotic systems are known, and they are highly dependent upon an engineered basis function. Non-solvable, Lorenz signals are often used to test time-series prediction schemes and are also central to efforts to maximize spectral efficiency by joining radar and communication waveforms. Here, we provide extracted basis functions for all three Lorenz state variables, their timing statistics, and their bit-sequence statistics. Further, we outline a detailed algorithm suitable for the extraction of basis functions from many chaotic systems such as the Lorenz system. These results promote the search for engineered basis functions in solvable chaotic systems, provide tools for joining radar and communication waveforms, and give an algorithmic process for modifying chaotic Lorenz waveforms to quantify the performance of chaotic time-series forecasting methods. The results presented here provide engineered test signals compatible with quantitative analysis of predicted amplitudes and regular timing.
{"title":"Extracting Communication, Ranging and Test Waveforms with Regularized Timing from the Chaotic Lorenz System","authors":"A. Beal","doi":"10.3390/signals4030027","DOIUrl":"https://doi.org/10.3390/signals4030027","url":null,"abstract":"We present an algorithm for extracting basis functions from the chaotic Lorenz system along with timing and bit-sequence statistics. Previous work focused on modifying Lorenz waveforms and extracting the basis function of a single state variable. Importantly, these efforts initiated the development of solvable chaotic systems with simple matched filters, which are suitable for many spread spectrum applications. However, few solvable chaotic systems are known, and they are highly dependent upon an engineered basis function. Non-solvable, Lorenz signals are often used to test time-series prediction schemes and are also central to efforts to maximize spectral efficiency by joining radar and communication waveforms. Here, we provide extracted basis functions for all three Lorenz state variables, their timing statistics, and their bit-sequence statistics. Further, we outline a detailed algorithm suitable for the extraction of basis functions from many chaotic systems such as the Lorenz system. These results promote the search for engineered basis functions in solvable chaotic systems, provide tools for joining radar and communication waveforms, and give an algorithmic process for modifying chaotic Lorenz waveforms to quantify the performance of chaotic time-series forecasting methods. The results presented here provide engineered test signals compatible with quantitative analysis of predicted amplitudes and regular timing.","PeriodicalId":93815,"journal":{"name":"Signals","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47798146","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}
Eduardo Arrufat-Pié, M. Estévez-Báez, José Mario Estévez-Carreras, Gerry Leisman, C. Machado, Carlos Beltrán-León
This study investigates the use of empirical mode decomposition (EMD) to extract intrinsic mode functions (IMFs) for the spectral analysis of EEG signals in healthy individuals and its possible biological interpretations. Unlike traditional EEG analysis, this approach does not require the establishment of arbitrary band limits. The study uses a multivariate EMD algorithm (APIT-MEMD) to extract IMFs from the EEG signals of 34 healthy volunteers. The first six IMFs are analyzed using two different methods, based on FFT and HHT, and the results compared using the ANOVA test and the Bland–Altman method for agreement test. The outcomes show that the frequency values of the first six IMFs fall within the range of classic EEG bands (1.72–52.4 Hz). Although there was a lack of agreement in the mean weighted frequency values of the first three IMFs between the two methods (>3 Hz), both methods showed similar results for power spectral density (<5% normalized units, %, of power spectral density). The HHT method is found to have better frequency resolution than APIT-MEMD associated with FTT that produce less overlapping between IMF3 and 4 (p = 0.0046) and it is recommended for analyzing the spectral properties of IMFs. The study concludes that the HHT method could help to avoid the assumption of strict frequency band limits, and that the potential impact of EEG physiological phenomenon on mode-mixing interpretation, particularly for the alpha and theta ranges, must be considered in future research.
{"title":"Beyond Frequency Band Constraints in EEG Analysis: The Role of the Mode Decomposition in Pushing the Boundaries","authors":"Eduardo Arrufat-Pié, M. Estévez-Báez, José Mario Estévez-Carreras, Gerry Leisman, C. Machado, Carlos Beltrán-León","doi":"10.3390/signals4030026","DOIUrl":"https://doi.org/10.3390/signals4030026","url":null,"abstract":"This study investigates the use of empirical mode decomposition (EMD) to extract intrinsic mode functions (IMFs) for the spectral analysis of EEG signals in healthy individuals and its possible biological interpretations. Unlike traditional EEG analysis, this approach does not require the establishment of arbitrary band limits. The study uses a multivariate EMD algorithm (APIT-MEMD) to extract IMFs from the EEG signals of 34 healthy volunteers. The first six IMFs are analyzed using two different methods, based on FFT and HHT, and the results compared using the ANOVA test and the Bland–Altman method for agreement test. The outcomes show that the frequency values of the first six IMFs fall within the range of classic EEG bands (1.72–52.4 Hz). Although there was a lack of agreement in the mean weighted frequency values of the first three IMFs between the two methods (>3 Hz), both methods showed similar results for power spectral density (<5% normalized units, %, of power spectral density). The HHT method is found to have better frequency resolution than APIT-MEMD associated with FTT that produce less overlapping between IMF3 and 4 (p = 0.0046) and it is recommended for analyzing the spectral properties of IMFs. The study concludes that the HHT method could help to avoid the assumption of strict frequency band limits, and that the potential impact of EEG physiological phenomenon on mode-mixing interpretation, particularly for the alpha and theta ranges, must be considered in future research.","PeriodicalId":93815,"journal":{"name":"Signals","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44474042","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}
Experimental data from the SACLANTCEN 1993 Mediterranean Experiment are reviewed to assess the reduction of the search space for the localization and tracking of an acoustic source in a three-dimensional environment. Key to this goal is the availability of an initial estimate of source range and depth (called the 2D initial guess); an ambiguous estimate of source bearing can be obtained from the 2D initial guess through Environmental Signal Processing, and the ambiguity can be removed by searching for the source only in the range/bearing regions where bearing estimates are higher. This search provides a new estimate of source range and a single bearing, which together with the estimate for source depth constitute the center of the reduced search space for source localization and tracking. The suggested approach is tested on experimental data from the SACLANTCEN experiment considering different frequencies, as well as a stationary and a moving source.
{"title":"Search Space Reduction for Localization and Tracking of an Acoustic Source","authors":"O. Rodríguez, Lilun Zhang, Xinghua Cheng","doi":"10.3390/signals4030025","DOIUrl":"https://doi.org/10.3390/signals4030025","url":null,"abstract":"Experimental data from the SACLANTCEN 1993 Mediterranean Experiment are reviewed to assess the reduction of the search space for the localization and tracking of an acoustic source in a three-dimensional environment. Key to this goal is the availability of an initial estimate of source range and depth (called the 2D initial guess); an ambiguous estimate of source bearing can be obtained from the 2D initial guess through Environmental Signal Processing, and the ambiguity can be removed by searching for the source only in the range/bearing regions where bearing estimates are higher. This search provides a new estimate of source range and a single bearing, which together with the estimate for source depth constitute the center of the reduced search space for source localization and tracking. The suggested approach is tested on experimental data from the SACLANTCEN experiment considering different frequencies, as well as a stationary and a moving source.","PeriodicalId":93815,"journal":{"name":"Signals","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46996351","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}
M. Vieira, M. Vieira, P. Louro, P. Vieira, A. Fantoni
An innovative treatment for congested urban road networks is the split intersection. Here, a congested two-way–two-way traffic light-controlled intersection is transformed into two lighter intersections. By reducing conflict points and improving travel time, it facilitates smoother flow with less driver delay. We propose a visible light communication system based on Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I) and Infrastructure-to-Vehicle (I2V) communications able to safely manage vehicles crossing through an intersection, leveraging Edge of Things (EoT) facilities. Headlights, street lamps, and traffic signals are used by connected vehicles to communicate with one another and with infrastructure. Through internally installed Driver Agents, an Intersection Manager coordinates traffic flow and interacts with vehicles. For the safe passage of vehicles across intersections, request/response mechanisms and time and space relative pose concepts are used. A virtual scenario is proposed, and a “mesh/cellular” hybrid architecture used. Light signals are emitted by transmitters by encoding, modulating, and converting data. Optical sensors with light-filtering properties are used as receivers and decoders. The VLC request/response concept uplink and downlink communication between the infrastructure and the vehicles is tested. Based on the results, the short-range mesh network provides a secure communication path between street lamp controllers and edge computers through neighbor traffic light controllers that have active cellular connections, as well as peer-to-peer communication, allowing V-VLC ready cars to exchange information.
{"title":"Vehicular Visible Light Communication for Intersection Management","authors":"M. Vieira, M. Vieira, P. Louro, P. Vieira, A. Fantoni","doi":"10.3390/signals4020024","DOIUrl":"https://doi.org/10.3390/signals4020024","url":null,"abstract":"An innovative treatment for congested urban road networks is the split intersection. Here, a congested two-way–two-way traffic light-controlled intersection is transformed into two lighter intersections. By reducing conflict points and improving travel time, it facilitates smoother flow with less driver delay. We propose a visible light communication system based on Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I) and Infrastructure-to-Vehicle (I2V) communications able to safely manage vehicles crossing through an intersection, leveraging Edge of Things (EoT) facilities. Headlights, street lamps, and traffic signals are used by connected vehicles to communicate with one another and with infrastructure. Through internally installed Driver Agents, an Intersection Manager coordinates traffic flow and interacts with vehicles. For the safe passage of vehicles across intersections, request/response mechanisms and time and space relative pose concepts are used. A virtual scenario is proposed, and a “mesh/cellular” hybrid architecture used. Light signals are emitted by transmitters by encoding, modulating, and converting data. Optical sensors with light-filtering properties are used as receivers and decoders. The VLC request/response concept uplink and downlink communication between the infrastructure and the vehicles is tested. Based on the results, the short-range mesh network provides a secure communication path between street lamp controllers and edge computers through neighbor traffic light controllers that have active cellular connections, as well as peer-to-peer communication, allowing V-VLC ready cars to exchange information.","PeriodicalId":93815,"journal":{"name":"Signals","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42299389","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}
As radio frequency (RF) hardware continues to improve, two-way ranging (TWR) has become a viable approach for high-precision ranging applications. The precision of a TWR system is fundamentally limited by estimates of the time offset T between two platforms and the time delay τ of a signal propagating between them. In previous work, we derived a family of optimal “one-shot” joint delay–offset estimators and demonstrated that they reduce to a system of linear equations under reasonable assumptions. These estimators are simple and computationally efficient but are also susceptible to channel impairments that obstruct one or more measurements. In this work, we formulate an extended Kalman filter (EKF) for this class of estimators that specifically addresses this limitation. Unlike a generic KF approach, the proposed solution specifically integrates the estimation process to minimize the computational complexity. We benchmark the proposed first- and second-order EKF solutions against the existing one-shot estimators in a MATLAB Monte Carlo simulation environment. We demonstrate that the proposed solution achieves comparable estimation performance and, in the case of the second-order solution, reduces the computation time by an order of magnitude.
{"title":"Extended Kalman Filter Design for Tracking Time-of-Flight and Clock Offsets in a Two-Way Ranging System","authors":"S. Srinivas, A. Herschfelt, D. Bliss","doi":"10.3390/signals4020023","DOIUrl":"https://doi.org/10.3390/signals4020023","url":null,"abstract":"As radio frequency (RF) hardware continues to improve, two-way ranging (TWR) has become a viable approach for high-precision ranging applications. The precision of a TWR system is fundamentally limited by estimates of the time offset T between two platforms and the time delay τ of a signal propagating between them. In previous work, we derived a family of optimal “one-shot” joint delay–offset estimators and demonstrated that they reduce to a system of linear equations under reasonable assumptions. These estimators are simple and computationally efficient but are also susceptible to channel impairments that obstruct one or more measurements. In this work, we formulate an extended Kalman filter (EKF) for this class of estimators that specifically addresses this limitation. Unlike a generic KF approach, the proposed solution specifically integrates the estimation process to minimize the computational complexity. We benchmark the proposed first- and second-order EKF solutions against the existing one-shot estimators in a MATLAB Monte Carlo simulation environment. We demonstrate that the proposed solution achieves comparable estimation performance and, in the case of the second-order solution, reduces the computation time by an order of magnitude.","PeriodicalId":93815,"journal":{"name":"Signals","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49218983","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}
D. Anyfantis, A. Koutras, G. Apostolopoulos, Ioanna Christoyianni
Breast cancer is the most common cancer in women, a leading cause of morbidity and mortality, and a significant health issue worldwide. According to the World Health Organization’s cancer awareness recommendations, mammographic screening should be regularly performed on middle-aged or older women to increase the chances of early cancer detection. Breast density is widely known to be related to the risk of cancer development. The American College of Radiology Breast Imaging Reporting and Data System categorizes mammography into four levels based on breast density, ranging from ACR-A (least dense) to ACR-D (most dense). Computer-aided diagnostic (CAD) systems can now detect suspicious regions in mammograms and identify abnormalities more quickly and accurately than human readers. However, their performance is still influenced by the tissue density level, which must be considered when designing such systems. In this paper, we propose a novel method that uses CycleGANs to transform suspicious regions of mammograms from ACR-B, -C, and -D levels to ACR-A level. This transformation aims to reduce the masking effect caused by thick tissue and separate cancerous regions from surrounding tissue. Our proposed system enhances the performance of conventional CNN-based classifiers significantly by focusing on regions of interest that would otherwise be misidentified due to fatty masking. Extensive testing on different types of mammograms (digital and scanned X-ray film) demonstrates the effectiveness of our system in identifying normal, benign, and malignant regions of interest.
{"title":"Breast Density Transformations Using CycleGANs for Revealing Undetected Findings in Mammograms","authors":"D. Anyfantis, A. Koutras, G. Apostolopoulos, Ioanna Christoyianni","doi":"10.3390/signals4020022","DOIUrl":"https://doi.org/10.3390/signals4020022","url":null,"abstract":"Breast cancer is the most common cancer in women, a leading cause of morbidity and mortality, and a significant health issue worldwide. According to the World Health Organization’s cancer awareness recommendations, mammographic screening should be regularly performed on middle-aged or older women to increase the chances of early cancer detection. Breast density is widely known to be related to the risk of cancer development. The American College of Radiology Breast Imaging Reporting and Data System categorizes mammography into four levels based on breast density, ranging from ACR-A (least dense) to ACR-D (most dense). Computer-aided diagnostic (CAD) systems can now detect suspicious regions in mammograms and identify abnormalities more quickly and accurately than human readers. However, their performance is still influenced by the tissue density level, which must be considered when designing such systems. In this paper, we propose a novel method that uses CycleGANs to transform suspicious regions of mammograms from ACR-B, -C, and -D levels to ACR-A level. This transformation aims to reduce the masking effect caused by thick tissue and separate cancerous regions from surrounding tissue. Our proposed system enhances the performance of conventional CNN-based classifiers significantly by focusing on regions of interest that would otherwise be misidentified due to fatty masking. Extensive testing on different types of mammograms (digital and scanned X-ray film) demonstrates the effectiveness of our system in identifying normal, benign, and malignant regions of interest.","PeriodicalId":93815,"journal":{"name":"Signals","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45831094","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}
In this work, an effective Fault Detection and Diagnosis (FDD) strategy designed to increase the performance and accuracy of fault diagnosis in grid-connected photovoltaic (GCPV) systems is developed. The evolved approach is threefold: first, a pre-processing of the training dataset is applied using a multiscale scheme that decomposes the data at multiple scales using high-pass/low-pass filters to separate the noise from the informative attributes and prevent the stochastic samples. Second, a principal component analysis (PCA) technique is applied to the newly obtained data to select, extract, and preserve only the more relevant, informative, and uncorrelated attributes; and finally, to distinguish between the diverse conditions, the extracted attributes are utilized to train the NNs classifiers. In this study, an effort is made to take into consideration all potential and frequent faults that might occur in PV systems. Thus, twenty-one faulty scenarios (line-to-line, line-to-ground, connectivity faults, and faults that can affect the normal operation of the bay-pass diodes) have been introduced and treated at different levels and locations; each scenario comprises various and diverse conditions, including the occurrence of simple faults in the PV1 array, simple faults in the PV2 array, multiple faults in PV1, multiple faults in PV2, and mixed faults in both PV arrays, in order to ensure a complete and global analysis, thereby reducing the loss of generated energy and maintaining the reliability and efficiency of such systems. The obtained outcomes demonstrate that the proposed approach not only achieves good accuracies but also reduces runtimes during the diagnosis process by avoiding noisy and stochastic data, thereby removing irrelevant and correlated samples from the original dataset.
{"title":"Enhanced Neural Network Method-Based Multiscale PCA for Fault Diagnosis: Application to Grid-Connected PV Systems","authors":"Khadija Attouri, Majdi Mansouri, Mansour Hajji, Abdelmalek Kouadri, Kais Bouzrara, Hazem Nounou","doi":"10.3390/signals4020020","DOIUrl":"https://doi.org/10.3390/signals4020020","url":null,"abstract":"In this work, an effective Fault Detection and Diagnosis (FDD) strategy designed to increase the performance and accuracy of fault diagnosis in grid-connected photovoltaic (GCPV) systems is developed. The evolved approach is threefold: first, a pre-processing of the training dataset is applied using a multiscale scheme that decomposes the data at multiple scales using high-pass/low-pass filters to separate the noise from the informative attributes and prevent the stochastic samples. Second, a principal component analysis (PCA) technique is applied to the newly obtained data to select, extract, and preserve only the more relevant, informative, and uncorrelated attributes; and finally, to distinguish between the diverse conditions, the extracted attributes are utilized to train the NNs classifiers. In this study, an effort is made to take into consideration all potential and frequent faults that might occur in PV systems. Thus, twenty-one faulty scenarios (line-to-line, line-to-ground, connectivity faults, and faults that can affect the normal operation of the bay-pass diodes) have been introduced and treated at different levels and locations; each scenario comprises various and diverse conditions, including the occurrence of simple faults in the PV1 array, simple faults in the PV2 array, multiple faults in PV1, multiple faults in PV2, and mixed faults in both PV arrays, in order to ensure a complete and global analysis, thereby reducing the loss of generated energy and maintaining the reliability and efficiency of such systems. The obtained outcomes demonstrate that the proposed approach not only achieves good accuracies but also reduces runtimes during the diagnosis process by avoiding noisy and stochastic data, thereby removing irrelevant and correlated samples from the original dataset.","PeriodicalId":93815,"journal":{"name":"Signals","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135692841","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}
E. Toki, Giorgos Tatsis, Vasileios A. Tatsis, Konstantinos Plachouras, J. Pange, I. Tsoulos
Early detection and evaluation of children at risk of neurodevelopmental disorders and/or communication deficits is critical. While the current literature indicates a high prevalence of neurodevelopmental disorders, many children remain undiagnosed, resulting in missed opportunities for effective interventions that could have had a greater impact if administered earlier. Clinicians face a variety of complications during neurodevelopmental disorders’ evaluation procedures and must elevate their use of digital tools to aid in early detection efficiently. Artificial intelligence enables novelty in taking decisions, classification, and diagnosis. The current research investigates the efficacy of various machine learning approaches on the biometric SmartSpeech datasets. These datasets come from a new innovative system that includes a serious game which gathers children’s responses to specifically designed speech and language activities and their manifestations, intending to assist during the clinical evaluation of neurodevelopmental disorders. The machine learning approaches were used by utilizing the algorithms Radial Basis Function, Neural Network, Deep Learning Neural Networks, and a variation of Grammatical Evolution (GenClass). The most significant results show improved accuracy (%) when using the eye tracking dataset; more specifically: (i) for the class Disorder with GenClass (92.83%), (ii) for the class Autism Spectrum Disorders with Deep Learning Neural Networks layer 4 (86.33%), (iii) for the class Attention Deficit Hyperactivity Disorder with Deep Learning Neural Networks layer 4 (87.44%), (iv) for the class Intellectual Disability with GenClass (86.93%), (v) for the class Specific Learning Disorder with GenClass (88.88%), and (vi) for the class Communication Disorders with GenClass (88.70%). Overall, the results indicated GenClass to be nearly the top competitor, opening up additional probes for future studies toward automatically classifying and assisting clinical assessments for children with neurodevelopmental disorders.
{"title":"Employing Classification Techniques on SmartSpeech Biometric Data towards Identification of Neurodevelopmental Disorders","authors":"E. Toki, Giorgos Tatsis, Vasileios A. Tatsis, Konstantinos Plachouras, J. Pange, I. Tsoulos","doi":"10.3390/signals4020021","DOIUrl":"https://doi.org/10.3390/signals4020021","url":null,"abstract":"Early detection and evaluation of children at risk of neurodevelopmental disorders and/or communication deficits is critical. While the current literature indicates a high prevalence of neurodevelopmental disorders, many children remain undiagnosed, resulting in missed opportunities for effective interventions that could have had a greater impact if administered earlier. Clinicians face a variety of complications during neurodevelopmental disorders’ evaluation procedures and must elevate their use of digital tools to aid in early detection efficiently. Artificial intelligence enables novelty in taking decisions, classification, and diagnosis. The current research investigates the efficacy of various machine learning approaches on the biometric SmartSpeech datasets. These datasets come from a new innovative system that includes a serious game which gathers children’s responses to specifically designed speech and language activities and their manifestations, intending to assist during the clinical evaluation of neurodevelopmental disorders. The machine learning approaches were used by utilizing the algorithms Radial Basis Function, Neural Network, Deep Learning Neural Networks, and a variation of Grammatical Evolution (GenClass). The most significant results show improved accuracy (%) when using the eye tracking dataset; more specifically: (i) for the class Disorder with GenClass (92.83%), (ii) for the class Autism Spectrum Disorders with Deep Learning Neural Networks layer 4 (86.33%), (iii) for the class Attention Deficit Hyperactivity Disorder with Deep Learning Neural Networks layer 4 (87.44%), (iv) for the class Intellectual Disability with GenClass (86.93%), (v) for the class Specific Learning Disorder with GenClass (88.88%), and (vi) for the class Communication Disorders with GenClass (88.70%). Overall, the results indicated GenClass to be nearly the top competitor, opening up additional probes for future studies toward automatically classifying and assisting clinical assessments for children with neurodevelopmental disorders.","PeriodicalId":93815,"journal":{"name":"Signals","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47234649","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}
Deeksha Adiani, Kelley Colopietro, Joshua W. Wade, Miroslava Migovich, Timothy J. Vogus, N. Sarkar
Computer-based job interview training, including virtual reality (VR) simulations, have gained popularity in recent years to support and aid autistic individuals, who face significant challenges and barriers in finding and maintaining employment. Although popular, these training systems often fail to resemble the complexity and dynamism of the employment interview, as the dialogue management for the virtual conversation agent either relies on choosing from a menu of prespecified answers, or dialogue processing is based on keyword extraction from the transcribed speech of the interviewee, which depends on the interview script. We address this limitation through automated dialogue act classification via transfer learning. This allows for recognizing intent from user speech, independent of the domain of the interview. We also redress the lack of training data for a domain general job interview dialogue act classifier by providing an original dataset with responses to interview questions within a virtual job interview platform from 22 autistic participants. Participants’ responses to a customized interview script were transcribed to text and annotated according to a custom 13-class dialogue act scheme. The best classifier was a fine-tuned bidirectional encoder representations from transformers (BERT) model, with an f1-score of 87%.
{"title":"Dialogue Act Classification via Transfer Learning for Automated Labeling of Interviewee Responses in Virtual Reality Job Interview Training Platforms for Autistic Individuals","authors":"Deeksha Adiani, Kelley Colopietro, Joshua W. Wade, Miroslava Migovich, Timothy J. Vogus, N. Sarkar","doi":"10.3390/signals4020019","DOIUrl":"https://doi.org/10.3390/signals4020019","url":null,"abstract":"Computer-based job interview training, including virtual reality (VR) simulations, have gained popularity in recent years to support and aid autistic individuals, who face significant challenges and barriers in finding and maintaining employment. Although popular, these training systems often fail to resemble the complexity and dynamism of the employment interview, as the dialogue management for the virtual conversation agent either relies on choosing from a menu of prespecified answers, or dialogue processing is based on keyword extraction from the transcribed speech of the interviewee, which depends on the interview script. We address this limitation through automated dialogue act classification via transfer learning. This allows for recognizing intent from user speech, independent of the domain of the interview. We also redress the lack of training data for a domain general job interview dialogue act classifier by providing an original dataset with responses to interview questions within a virtual job interview platform from 22 autistic participants. Participants’ responses to a customized interview script were transcribed to text and annotated according to a custom 13-class dialogue act scheme. The best classifier was a fine-tuned bidirectional encoder representations from transformers (BERT) model, with an f1-score of 87%.","PeriodicalId":93815,"journal":{"name":"Signals","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48652191","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：