Shadow extraction and elimination is essential for intelligent transportation systems(ITS)in vehicle tracking application.The shadow is the source of error for vehicle detection,which causes misclassification of vehic...Shadow extraction and elimination is essential for intelligent transportation systems(ITS)in vehicle tracking application.The shadow is the source of error for vehicle detection,which causes misclassification of vehicles and a high false alarm rate in the research of vehicle counting,vehicle detection,vehicle tracking,and classification.Most of the existing research is on shadow extraction of moving vehicles in high intensity and on standard datasets,but the process of extracting shadows from moving vehicles in low light of real scenes is difficult.The real scenes of vehicles dataset are generated by self on the Vadodara–Mumbai highway during periods of poor illumination for shadow extraction of moving vehicles to address the above problem.This paper offers a robust shadow extraction of moving vehicles and its elimination for vehicle tracking.The method is distributed into two phases:In the first phase,we extract foreground regions using a mixture of Gaussian model,and then in the second phase,with the help of the Gamma correction,intensity ratio,negative transformation,and a combination of Gaussian filters,we locate and remove the shadow region from the foreground areas.Compared to the outcomes proposed method with outcomes of an existing method,the suggested method achieves an average true negative rate of above 90%,a shadow detection rate SDR(η%),and a shadow discrimination rate SDR(ξ%)of 80%.Hence,the suggested method is more appropriate for moving shadow detection in real scenes.展开更多
Image processing and image analysis are the main aspects for obtaining information from digital image owing to the fact that this techniques give the desired details in most of the applications generally and Non-Destr...Image processing and image analysis are the main aspects for obtaining information from digital image owing to the fact that this techniques give the desired details in most of the applications generally and Non-Destructive testing specifically. This paper presents a proposed method for the automatic detection of weld defects in radiographic images. Firstly, the radiographic images were enhanced using adaptive histogram equalization and are filtered using mean and wiener filters. Secondly, the welding area is selected from the radiography image. Thirdly, the Cepstral features are extracted from the Higher-Order Spectra (Bispectrum and Trispectrum). Finally, neural networks are used for feature matching. The proposed method is tested using 100 radiographic images in the presence of noise and image blurring. Results show that in spite of time consumption, the proposed method yields best results for the automatic detection of weld defects in radiography images when the features were extracted from the Trispectrum of the image.展开更多
Current LTE networks are experiencing significant growth in the number of users worldwide. The use of data services for online browsing, e-learning, online meetings and initiatives such as smart cities means that subs...Current LTE networks are experiencing significant growth in the number of users worldwide. The use of data services for online browsing, e-learning, online meetings and initiatives such as smart cities means that subscribers stay connected for long periods, thereby saturating a number of signalling resources. One of such resources is the Radio Resource Connected (RRC) parameter, which is allocated to eNodeBs with the aim of limiting the number of connected simultaneously in the network. The fixed allocation of this parameter means that, depending on the traffic at different times of the day and the geographical position, some eNodeBs are saturated with RRC resources (overused) while others have unused RRC resources. However, as these resources are limited, there is the problem of their underutilization (non-optimal utilization of resources at the eNodeB level) due to static allocation (manual configuration of resources). The objective of this paper is to design an efficient machine learning model that will take as input some key performance indices (KPIs) like traffic data, RRC, simultaneous users, etc., for each eNodeB per hour and per day and accurately predict the number of needed RRC resources that will be dynamically allocated to them in order to avoid traffic and financial losses to the mobile network operator. To reach this target, three machine learning algorithms have been studied namely: linear regression, convolutional neural networks and long short-term memory (LSTM) to train three models and evaluate them. The model trained with the LSTM algorithm gave the best performance with 97% accuracy and was therefore implemented in the proposed solution for RRC resource allocation. An interconnection architecture is also proposed to embed the proposed solution into the Operation and maintenance network of a mobile network operator. In this way, the proposed solution can contribute to developing and expanding the concept of Self Organizing Network (SON) used in 4G and 5G networks.展开更多
Introduction:The non-stationarity of electroencephalograms(EEG)has a substantial effect on the performance of classifiers in brain-computer interface(BCI)systems.To tackle this challenge,an adaptable version of the li...Introduction:The non-stationarity of electroencephalograms(EEG)has a substantial effect on the performance of classifiers in brain-computer interface(BCI)systems.To tackle this challenge,an adaptable version of the linear discriminant analysis(LDA)classifier was proposed.Accuracy is crucial when using BCIs for neurorestorative tasks or memory improvement.The accurate comprehension of brain responses facilitates more focused interventions,which may improve neurorestorative outcomes.BCIs equipped with adaptive classifers are useful for personalizing therapies to individual requirements and for improving neurorestorative processes.Notably,neurorestorative interventions that yield consistent,accurate,and reliable outcomes are more likely to inspire trust and elicit satisfaction in users.Methods:The proposed classifier continuously modified its parameters in accordance with EEG signals.The covariance matrix and mean values for each pair of classes were the updating parameters.The proposed classifier modifed the model parameters by prioritizing current signal data over older signal history.The proposed classifier was tested using a hybrid SSVEP+P300 BCI system.Results and conclusions:The proposed classifier had an estimated classification accuracy of 97.4%,and was more effective than pooled mean LDA and conventional multiclass LDA classifiers.Increased classification accuracy may increase the responsiveness of neurorestorative interventions and increase the usefulness of BCIs in neurorestoration.展开更多
基金funded by Researchers Supporting Project Number(RSP2023R503),King Saud University,Riyadh,Saudi Arabia。
文摘Shadow extraction and elimination is essential for intelligent transportation systems(ITS)in vehicle tracking application.The shadow is the source of error for vehicle detection,which causes misclassification of vehicles and a high false alarm rate in the research of vehicle counting,vehicle detection,vehicle tracking,and classification.Most of the existing research is on shadow extraction of moving vehicles in high intensity and on standard datasets,but the process of extracting shadows from moving vehicles in low light of real scenes is difficult.The real scenes of vehicles dataset are generated by self on the Vadodara–Mumbai highway during periods of poor illumination for shadow extraction of moving vehicles to address the above problem.This paper offers a robust shadow extraction of moving vehicles and its elimination for vehicle tracking.The method is distributed into two phases:In the first phase,we extract foreground regions using a mixture of Gaussian model,and then in the second phase,with the help of the Gamma correction,intensity ratio,negative transformation,and a combination of Gaussian filters,we locate and remove the shadow region from the foreground areas.Compared to the outcomes proposed method with outcomes of an existing method,the suggested method achieves an average true negative rate of above 90%,a shadow detection rate SDR(η%),and a shadow discrimination rate SDR(ξ%)of 80%.Hence,the suggested method is more appropriate for moving shadow detection in real scenes.
文摘Image processing and image analysis are the main aspects for obtaining information from digital image owing to the fact that this techniques give the desired details in most of the applications generally and Non-Destructive testing specifically. This paper presents a proposed method for the automatic detection of weld defects in radiographic images. Firstly, the radiographic images were enhanced using adaptive histogram equalization and are filtered using mean and wiener filters. Secondly, the welding area is selected from the radiography image. Thirdly, the Cepstral features are extracted from the Higher-Order Spectra (Bispectrum and Trispectrum). Finally, neural networks are used for feature matching. The proposed method is tested using 100 radiographic images in the presence of noise and image blurring. Results show that in spite of time consumption, the proposed method yields best results for the automatic detection of weld defects in radiography images when the features were extracted from the Trispectrum of the image.
文摘Current LTE networks are experiencing significant growth in the number of users worldwide. The use of data services for online browsing, e-learning, online meetings and initiatives such as smart cities means that subscribers stay connected for long periods, thereby saturating a number of signalling resources. One of such resources is the Radio Resource Connected (RRC) parameter, which is allocated to eNodeBs with the aim of limiting the number of connected simultaneously in the network. The fixed allocation of this parameter means that, depending on the traffic at different times of the day and the geographical position, some eNodeBs are saturated with RRC resources (overused) while others have unused RRC resources. However, as these resources are limited, there is the problem of their underutilization (non-optimal utilization of resources at the eNodeB level) due to static allocation (manual configuration of resources). The objective of this paper is to design an efficient machine learning model that will take as input some key performance indices (KPIs) like traffic data, RRC, simultaneous users, etc., for each eNodeB per hour and per day and accurately predict the number of needed RRC resources that will be dynamically allocated to them in order to avoid traffic and financial losses to the mobile network operator. To reach this target, three machine learning algorithms have been studied namely: linear regression, convolutional neural networks and long short-term memory (LSTM) to train three models and evaluate them. The model trained with the LSTM algorithm gave the best performance with 97% accuracy and was therefore implemented in the proposed solution for RRC resource allocation. An interconnection architecture is also proposed to embed the proposed solution into the Operation and maintenance network of a mobile network operator. In this way, the proposed solution can contribute to developing and expanding the concept of Self Organizing Network (SON) used in 4G and 5G networks.
文摘Introduction:The non-stationarity of electroencephalograms(EEG)has a substantial effect on the performance of classifiers in brain-computer interface(BCI)systems.To tackle this challenge,an adaptable version of the linear discriminant analysis(LDA)classifier was proposed.Accuracy is crucial when using BCIs for neurorestorative tasks or memory improvement.The accurate comprehension of brain responses facilitates more focused interventions,which may improve neurorestorative outcomes.BCIs equipped with adaptive classifers are useful for personalizing therapies to individual requirements and for improving neurorestorative processes.Notably,neurorestorative interventions that yield consistent,accurate,and reliable outcomes are more likely to inspire trust and elicit satisfaction in users.Methods:The proposed classifier continuously modified its parameters in accordance with EEG signals.The covariance matrix and mean values for each pair of classes were the updating parameters.The proposed classifier modifed the model parameters by prioritizing current signal data over older signal history.The proposed classifier was tested using a hybrid SSVEP+P300 BCI system.Results and conclusions:The proposed classifier had an estimated classification accuracy of 97.4%,and was more effective than pooled mean LDA and conventional multiclass LDA classifiers.Increased classification accuracy may increase the responsiveness of neurorestorative interventions and increase the usefulness of BCIs in neurorestoration.
