Hamdi Altaheri | King Saud University (original) (raw)
Papers by Hamdi Altaheri
Neural Computing and Applications, Aug 25, 2021
The brain–computer interface (BCI) is an emerging technology that has the potential to revolution... more The brain–computer interface (BCI) is an emerging technology that has the potential to revolutionize the world, with numerous applications ranging from healthcare to human augmentation. Electroencephalogram (EEG) motor imagery (MI) is among the most common BCI paradigms that have been used extensively in smart healthcare applications such as post-stroke rehabilitation and mobile assistive robots. In recent years, the contribution of deep learning (DL) has had a phenomenal impact on MI-EEG-based BCI. In this work, we systematically review the DL-based research for MI-EEG classification from the past ten years. This article first explains the procedure for selecting the studies and then gives an overview of BCI, EEG, and MI systems. The DL-based techniques applied in MI classification are then analyzed and discussed from four main perspectives: preprocessing, input formulation, deep learning architecture, and performance evaluation. In the discussion section, three major questions about DL-based MI classification are addressed: (1) Is preprocessing required for DL-based techniques? (2) What input formulations are best for DL-based techniques? (3) What are the current trends in DL-based techniques? Moreover, this work summarizes MI-EEG-based applications, extensively explores public MI-EEG datasets, and gives an overall visualization of the performance attained for each dataset based on the reviewed articles. Finally, current challenges and future directions are discussed.
Journal of King Saud University - Computer and Information Sciences
IEEE Internet of Things Journal
IEEE Transactions on Industrial Informatics
East Asian Science, Technology and Society: An International Journal, 2021
Citizen insecurity is a reality with which we must coexist, the cities of Latin America are among... more Citizen insecurity is a reality with which we must coexist, the cities of Latin America are among the most violent and insecure in the world. According to the statistics of the National Police of Peru, they report that by 2017 the crimes of theft or robbery were the most common because they had a monthly average of 15348 complaints, equivalent to 66.9% of the total crimes nationwide. The INEI (National Institute of Statistics and Informatics) revealed that in the same year the district of Carabayllo obtained 1.85% of the total complaints in Metropolitan Lima, occupying the 17th place in the ranking of districts with the highest number of complaints for this crime. That is why in the present research work a way to counteract these criminal acts was proposed, the first thing is to be located within the operating range of the RF module, so that the remote transmission control can activate it, the RF module will be connected to the power outlet and the siren. The siren will oversee persuading the criminal, in addition to alerting the neighbors about the events that are happening. It was obtained as a result that the system fulfills its purpose, it can be alerted in real time about some attempted theft or at the instant of a threat situation, only by pressing the button of the remote control we can persuade the criminals either by scaring them with the sound or with the help of the neighbors.
Sensors
Sign language is the main channel for hearing-impaired people to communicate with others. It is a... more Sign language is the main channel for hearing-impaired people to communicate with others. It is a visual language that conveys highly structured components of manual and non-manual parameters such that it needs a lot of effort to master by hearing people. Sign language recognition aims to facilitate this mastering difficulty and bridge the communication gap between hearing-impaired people and others. This study presents an efficient architecture for sign language recognition based on a convolutional graph neural network (GCN). The presented architecture consists of a few separable 3DGCN layers, which are enhanced by a spatial attention mechanism. The limited number of layers in the proposed architecture enables it to avoid the common over-smoothing problem in deep graph neural networks. Furthermore, the attention mechanism enhances the spatial context representation of the gestures. The proposed architecture is evaluated on different datasets and shows outstanding results.
Diagnostics
Electroencephalography-based motor imagery (EEG-MI) classification is a critical component of the... more Electroencephalography-based motor imagery (EEG-MI) classification is a critical component of the brain-computer interface (BCI), which enables people with physical limitations to communicate with the outside world via assistive technology. Regrettably, EEG decoding is challenging because of the complexity, dynamic nature, and low signal-to-noise ratio of the EEG signal. Developing an end-to-end architecture capable of correctly extracting EEG data’s high-level features remains a difficulty. This study introduces a new model for decoding MI known as a Multi-Branch EEGNet with squeeze-and-excitation blocks (MBEEGSE). By clearly specifying channel interdependencies, a multi-branch CNN model with attention blocks is employed to adaptively change channel-wise feature responses. When compared to existing state-of-the-art EEG motor imagery classification models, the suggested model achieves good accuracy (82.87%) with reduced parameters in the BCI-IV2a motor imagery dataset and (96.15%) i...
UCSS is an integrated system (electronic device and computer-based software) designed as a univer... more UCSS is an integrated system (electronic device and computer-based software) designed as a universal and scalable system for control and security applications. The electronic device is an embedded system consisting of a microprocessor (Rabbit 2000 microprocessor) and a set of separate electronic cards that can be inserted according to the requirements of the application. The electronic unit has different communication capabilities allowing the building to be monitored and controlled from anywhere, anytime, using current wireless data technologies such as GSM, SMS, and GPRS. In addition to computer networks (Ethernet, Wi-Fi) and internet (HTTP, FTP). The 3D-Eye system is network-based computer software with a 3D graphical user interface used to control and monitor smart buildings. Using the 3D interface, the system can monitor and control the building devices such as elevators, escalators, laser detectors, air conditioning, etc. The system also provides various tools and options to d...
The date fruit dataset was created to address the requirements of many applications in the pre-ha... more The date fruit dataset was created to address the requirements of many applications in the pre-harvesting and harvesting stages. The two most important applications are automatic harvesting and visual yield estimation. The dataset is divided into two subsets and each of them is oriented into one of these two applications. The first dataset consists of 8079 images of more than 350 date bunches captured from 29 date palms. The date bunches belong to five date types: Naboot Saif, Khalas, Barhi, Meneifi, and Sullaj. The pictures of date bunches were captured using a color camera in six imaging sessions. The imaging sessions covered all date maturity stages: immature, Khalal, Rutab, and Tamar. The dataset is provided with a large degree of variations to reflect the challenges in natural environments and date fruit orchards. These variations in images include different angels and scales, different daylight conditions having poor illumination images, and date bunches covered by bags. The d...
In date cultivation, manual harvesting is the dominant method used, which is inefficient in terms... more In date cultivation, manual harvesting is the dominant method used, which is inefficient in terms of both time and the economy. Advanced agricultural automation such as robotic harvesting can significantly increase quality and yield as well as reduce production costs and delay. One of the most important aspects of harvesting robots is their ability to interpret and analyze visual data. Accurate vision system to detect, classify, and analyze fruits in real time is critical for the harvesting robot to be cost-effective and efficient. However, practical success in this area remains limited due to the difficulties caused by unstructured and unconstrained agricultural environments. Furthermore, research on machine vision for date fruits in the pre-harvesting and the harvesting stages is scarce. Hence, this research aims to develop intelligent systems for date fruit harvesting robotic in an orchard environment, including date fruit detection and segmentation, variety classification, matur...
IEEE Transactions on Industrial Informatics
The brain–computer interface (BCI) is an emerging technology that has the potential to revolution... more The brain–computer interface (BCI) is an emerging technology that has the potential to revolutionize the world, with numerous applications ranging from healthcare to human augmentation. Electroencephalogram (EEG) motor imagery (MI) is among the most common BCI paradigms that have been used extensively in smart healthcare applications such as post-stroke rehabilitation and mobile assistive robots. In recent years, the contribution of deep learning (DL) has had a phenomenal impact on MI-EEG-based BCI. In this work, we systematically review the DL-based research for MI-EEG classification from the past ten years. This article first explains the procedure for selecting the studies and then gives an overview of BCI, EEG, and MI systems. The DL-based techniques applied in MI classification are then analyzed and discussed from four main perspectives: preprocessing, input formulation, deep learning architecture, and performance evaluation. In the discussion section, three major questions abo...
Biomedical Signal Processing and Control
Abstract Motor imagery electroencephalography (MI-EEG) signals are generated when a person imagin... more Abstract Motor imagery electroencephalography (MI-EEG) signals are generated when a person imagines a task without actually performing it. In recent studies, MI-EEG has been used in the rehabilitation process of paralyzed patients, therefore, decoding MI-EEG signals accurately is an important task, and it is difficult task due to the low signal-to-noise ratio and the variation of brain waves between subjects. Deep learning techniques such as the convolution neural network (CNN) have shown an impact in extracting meaningful features to improve the accuracy of classification. In this paper, we propose TCNet-Fusion, a fixed hyperparameter-based CNN model that utilizes multiple techniques, such as temporal convolutional networks (TCNs), separable convolution, depth-wise convolution, and the fusion of layers. This model outperforms other fixed hyperparameter-based CNN models while remaining similar to those that utilize variable hyperparameter networks, which are networks that change their hyperparameters based on each subject, resulting in higher accuracy than fixed networks. It also uses less memory than variable networks. The EEG signal undergoes two successive 1D convolutions, first along with the time domain, then channel-wise. Then, we obtain an image-like representation, which is fed to the main TCN. During experimentation, the model achieved a classification accuracy of 83.73 % on the four-class MI of the BCI Competition IV-2a dataset, and an accuracy of 94.41 % on the High Gamma Dataset.
Advances in Mechanical Engineering, Nov 1, 2016
In this article, we introduce a localization system to reduce the accumulation of errors existing... more In this article, we introduce a localization system to reduce the accumulation of errors existing in the dead-reckoning method of mobile robot localization. Dead-reckoning depends on the information that comes from the encoders. Many factors, such as wheel slippage, surface roughness, and mechanical tolerances, affect the accuracy of dead-reckoning. Therefore, an accumulation of errors exists in the dead-reckoning method. In this article, we propose a new localization system to enhance the localization operation of the mobile robots. The proposed localization system uses the extended Kalman filter combined with infrared sensors in order to solve the problems of dead-reckoning. The proposed system executes the extended Kalman filter cycle, using the walls in the working environment as references (landmarks), to correct errors in the robot's position (positional uncertainty). The accuracy and robustness of the proposed method are evaluated in the experiment results' section.
European Symposium on Computer Modeling and Simulation, 2017
Arabic has four emphatic phonemes “dhaad” /d?/, “dhaa” /∂?/, “saad” /s?/, and “ttaa” /t?/. These ... more Arabic has four emphatic phonemes “dhaad” /d?/, “dhaa” /∂?/, “saad” /s?/, and “ttaa” /t?/. These phonemes are a special subset of Arabic language phoneme set and have unique characteristics. Emphatic phonemes are difficult to vocalize especially the /d?/ phoneme. Another emphatic phoneme that shows a high pronunciation and auditory similarity to /d?/ is /∂?/. The similarity between /d?/ and /∂?/ leads to massive confusions even for native Arabic speakers and listeners. In this work, an acoustic analysis for the two identical emphatic phonemes (/d?/ and /∂?/) is performed. Formants difference was calculated at certain interesting time's positions of each phoneme's time domain waveform. The formant's values and difference show obvious dissimilarities between the twophonemes. These dissimilarities are an indication of discrimination in the vocal tract while uttering and/or perceiving of the two phonemes within legal Arabic words.
2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
IEEE Access
The recording device along with the acoustic environment plays a major role in digital audio fore... more The recording device along with the acoustic environment plays a major role in digital audio forensics. We propose an acoustic source identification system in this paper, which includes identifying both the recording device and the environment in which it was recorded. A hybrid Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) is used in this study to automatically extract environments and microphone features from the speech sound. In the experiments, we investigated the effect of using the voiced and unvoiced segments of speech on the accuracy of the environment and microphone classification. We also studied the effect of background noise on microphone classification in 3 different environments, i.e., very quiet, quiet, and noisy. The proposed system utilizes a subset of the KSU-DB corpus containing 3 environments, 4 classes of recording devices, 136 speakers (68 males and 68 females), and 3600 recordings of words, sentences, and continuous speech. This research combines the advantages of both CNN and RNN (in particular bidirectional LSTM) models, called CRNN. The speech signals were represented as a spectrogram and were fed to the CRNN model as 2D images. The proposed method achieved accuracies of 98% and 98.57% for environment and microphone classification, respectively, using unvoiced speech segments.
Neural Computing and Applications, Aug 25, 2021
The brain–computer interface (BCI) is an emerging technology that has the potential to revolution... more The brain–computer interface (BCI) is an emerging technology that has the potential to revolutionize the world, with numerous applications ranging from healthcare to human augmentation. Electroencephalogram (EEG) motor imagery (MI) is among the most common BCI paradigms that have been used extensively in smart healthcare applications such as post-stroke rehabilitation and mobile assistive robots. In recent years, the contribution of deep learning (DL) has had a phenomenal impact on MI-EEG-based BCI. In this work, we systematically review the DL-based research for MI-EEG classification from the past ten years. This article first explains the procedure for selecting the studies and then gives an overview of BCI, EEG, and MI systems. The DL-based techniques applied in MI classification are then analyzed and discussed from four main perspectives: preprocessing, input formulation, deep learning architecture, and performance evaluation. In the discussion section, three major questions about DL-based MI classification are addressed: (1) Is preprocessing required for DL-based techniques? (2) What input formulations are best for DL-based techniques? (3) What are the current trends in DL-based techniques? Moreover, this work summarizes MI-EEG-based applications, extensively explores public MI-EEG datasets, and gives an overall visualization of the performance attained for each dataset based on the reviewed articles. Finally, current challenges and future directions are discussed.
Journal of King Saud University - Computer and Information Sciences
IEEE Internet of Things Journal
IEEE Transactions on Industrial Informatics
East Asian Science, Technology and Society: An International Journal, 2021
Citizen insecurity is a reality with which we must coexist, the cities of Latin America are among... more Citizen insecurity is a reality with which we must coexist, the cities of Latin America are among the most violent and insecure in the world. According to the statistics of the National Police of Peru, they report that by 2017 the crimes of theft or robbery were the most common because they had a monthly average of 15348 complaints, equivalent to 66.9% of the total crimes nationwide. The INEI (National Institute of Statistics and Informatics) revealed that in the same year the district of Carabayllo obtained 1.85% of the total complaints in Metropolitan Lima, occupying the 17th place in the ranking of districts with the highest number of complaints for this crime. That is why in the present research work a way to counteract these criminal acts was proposed, the first thing is to be located within the operating range of the RF module, so that the remote transmission control can activate it, the RF module will be connected to the power outlet and the siren. The siren will oversee persuading the criminal, in addition to alerting the neighbors about the events that are happening. It was obtained as a result that the system fulfills its purpose, it can be alerted in real time about some attempted theft or at the instant of a threat situation, only by pressing the button of the remote control we can persuade the criminals either by scaring them with the sound or with the help of the neighbors.
Sensors
Sign language is the main channel for hearing-impaired people to communicate with others. It is a... more Sign language is the main channel for hearing-impaired people to communicate with others. It is a visual language that conveys highly structured components of manual and non-manual parameters such that it needs a lot of effort to master by hearing people. Sign language recognition aims to facilitate this mastering difficulty and bridge the communication gap between hearing-impaired people and others. This study presents an efficient architecture for sign language recognition based on a convolutional graph neural network (GCN). The presented architecture consists of a few separable 3DGCN layers, which are enhanced by a spatial attention mechanism. The limited number of layers in the proposed architecture enables it to avoid the common over-smoothing problem in deep graph neural networks. Furthermore, the attention mechanism enhances the spatial context representation of the gestures. The proposed architecture is evaluated on different datasets and shows outstanding results.
Diagnostics
Electroencephalography-based motor imagery (EEG-MI) classification is a critical component of the... more Electroencephalography-based motor imagery (EEG-MI) classification is a critical component of the brain-computer interface (BCI), which enables people with physical limitations to communicate with the outside world via assistive technology. Regrettably, EEG decoding is challenging because of the complexity, dynamic nature, and low signal-to-noise ratio of the EEG signal. Developing an end-to-end architecture capable of correctly extracting EEG data’s high-level features remains a difficulty. This study introduces a new model for decoding MI known as a Multi-Branch EEGNet with squeeze-and-excitation blocks (MBEEGSE). By clearly specifying channel interdependencies, a multi-branch CNN model with attention blocks is employed to adaptively change channel-wise feature responses. When compared to existing state-of-the-art EEG motor imagery classification models, the suggested model achieves good accuracy (82.87%) with reduced parameters in the BCI-IV2a motor imagery dataset and (96.15%) i...
UCSS is an integrated system (electronic device and computer-based software) designed as a univer... more UCSS is an integrated system (electronic device and computer-based software) designed as a universal and scalable system for control and security applications. The electronic device is an embedded system consisting of a microprocessor (Rabbit 2000 microprocessor) and a set of separate electronic cards that can be inserted according to the requirements of the application. The electronic unit has different communication capabilities allowing the building to be monitored and controlled from anywhere, anytime, using current wireless data technologies such as GSM, SMS, and GPRS. In addition to computer networks (Ethernet, Wi-Fi) and internet (HTTP, FTP). The 3D-Eye system is network-based computer software with a 3D graphical user interface used to control and monitor smart buildings. Using the 3D interface, the system can monitor and control the building devices such as elevators, escalators, laser detectors, air conditioning, etc. The system also provides various tools and options to d...
The date fruit dataset was created to address the requirements of many applications in the pre-ha... more The date fruit dataset was created to address the requirements of many applications in the pre-harvesting and harvesting stages. The two most important applications are automatic harvesting and visual yield estimation. The dataset is divided into two subsets and each of them is oriented into one of these two applications. The first dataset consists of 8079 images of more than 350 date bunches captured from 29 date palms. The date bunches belong to five date types: Naboot Saif, Khalas, Barhi, Meneifi, and Sullaj. The pictures of date bunches were captured using a color camera in six imaging sessions. The imaging sessions covered all date maturity stages: immature, Khalal, Rutab, and Tamar. The dataset is provided with a large degree of variations to reflect the challenges in natural environments and date fruit orchards. These variations in images include different angels and scales, different daylight conditions having poor illumination images, and date bunches covered by bags. The d...
In date cultivation, manual harvesting is the dominant method used, which is inefficient in terms... more In date cultivation, manual harvesting is the dominant method used, which is inefficient in terms of both time and the economy. Advanced agricultural automation such as robotic harvesting can significantly increase quality and yield as well as reduce production costs and delay. One of the most important aspects of harvesting robots is their ability to interpret and analyze visual data. Accurate vision system to detect, classify, and analyze fruits in real time is critical for the harvesting robot to be cost-effective and efficient. However, practical success in this area remains limited due to the difficulties caused by unstructured and unconstrained agricultural environments. Furthermore, research on machine vision for date fruits in the pre-harvesting and the harvesting stages is scarce. Hence, this research aims to develop intelligent systems for date fruit harvesting robotic in an orchard environment, including date fruit detection and segmentation, variety classification, matur...
IEEE Transactions on Industrial Informatics
The brain–computer interface (BCI) is an emerging technology that has the potential to revolution... more The brain–computer interface (BCI) is an emerging technology that has the potential to revolutionize the world, with numerous applications ranging from healthcare to human augmentation. Electroencephalogram (EEG) motor imagery (MI) is among the most common BCI paradigms that have been used extensively in smart healthcare applications such as post-stroke rehabilitation and mobile assistive robots. In recent years, the contribution of deep learning (DL) has had a phenomenal impact on MI-EEG-based BCI. In this work, we systematically review the DL-based research for MI-EEG classification from the past ten years. This article first explains the procedure for selecting the studies and then gives an overview of BCI, EEG, and MI systems. The DL-based techniques applied in MI classification are then analyzed and discussed from four main perspectives: preprocessing, input formulation, deep learning architecture, and performance evaluation. In the discussion section, three major questions abo...
Biomedical Signal Processing and Control
Abstract Motor imagery electroencephalography (MI-EEG) signals are generated when a person imagin... more Abstract Motor imagery electroencephalography (MI-EEG) signals are generated when a person imagines a task without actually performing it. In recent studies, MI-EEG has been used in the rehabilitation process of paralyzed patients, therefore, decoding MI-EEG signals accurately is an important task, and it is difficult task due to the low signal-to-noise ratio and the variation of brain waves between subjects. Deep learning techniques such as the convolution neural network (CNN) have shown an impact in extracting meaningful features to improve the accuracy of classification. In this paper, we propose TCNet-Fusion, a fixed hyperparameter-based CNN model that utilizes multiple techniques, such as temporal convolutional networks (TCNs), separable convolution, depth-wise convolution, and the fusion of layers. This model outperforms other fixed hyperparameter-based CNN models while remaining similar to those that utilize variable hyperparameter networks, which are networks that change their hyperparameters based on each subject, resulting in higher accuracy than fixed networks. It also uses less memory than variable networks. The EEG signal undergoes two successive 1D convolutions, first along with the time domain, then channel-wise. Then, we obtain an image-like representation, which is fed to the main TCN. During experimentation, the model achieved a classification accuracy of 83.73 % on the four-class MI of the BCI Competition IV-2a dataset, and an accuracy of 94.41 % on the High Gamma Dataset.
Advances in Mechanical Engineering, Nov 1, 2016
In this article, we introduce a localization system to reduce the accumulation of errors existing... more In this article, we introduce a localization system to reduce the accumulation of errors existing in the dead-reckoning method of mobile robot localization. Dead-reckoning depends on the information that comes from the encoders. Many factors, such as wheel slippage, surface roughness, and mechanical tolerances, affect the accuracy of dead-reckoning. Therefore, an accumulation of errors exists in the dead-reckoning method. In this article, we propose a new localization system to enhance the localization operation of the mobile robots. The proposed localization system uses the extended Kalman filter combined with infrared sensors in order to solve the problems of dead-reckoning. The proposed system executes the extended Kalman filter cycle, using the walls in the working environment as references (landmarks), to correct errors in the robot's position (positional uncertainty). The accuracy and robustness of the proposed method are evaluated in the experiment results' section.
European Symposium on Computer Modeling and Simulation, 2017
Arabic has four emphatic phonemes “dhaad” /d?/, “dhaa” /∂?/, “saad” /s?/, and “ttaa” /t?/. These ... more Arabic has four emphatic phonemes “dhaad” /d?/, “dhaa” /∂?/, “saad” /s?/, and “ttaa” /t?/. These phonemes are a special subset of Arabic language phoneme set and have unique characteristics. Emphatic phonemes are difficult to vocalize especially the /d?/ phoneme. Another emphatic phoneme that shows a high pronunciation and auditory similarity to /d?/ is /∂?/. The similarity between /d?/ and /∂?/ leads to massive confusions even for native Arabic speakers and listeners. In this work, an acoustic analysis for the two identical emphatic phonemes (/d?/ and /∂?/) is performed. Formants difference was calculated at certain interesting time's positions of each phoneme's time domain waveform. The formant's values and difference show obvious dissimilarities between the twophonemes. These dissimilarities are an indication of discrimination in the vocal tract while uttering and/or perceiving of the two phonemes within legal Arabic words.
2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
IEEE Access
The recording device along with the acoustic environment plays a major role in digital audio fore... more The recording device along with the acoustic environment plays a major role in digital audio forensics. We propose an acoustic source identification system in this paper, which includes identifying both the recording device and the environment in which it was recorded. A hybrid Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) is used in this study to automatically extract environments and microphone features from the speech sound. In the experiments, we investigated the effect of using the voiced and unvoiced segments of speech on the accuracy of the environment and microphone classification. We also studied the effect of background noise on microphone classification in 3 different environments, i.e., very quiet, quiet, and noisy. The proposed system utilizes a subset of the KSU-DB corpus containing 3 environments, 4 classes of recording devices, 136 speakers (68 males and 68 females), and 3600 recordings of words, sentences, and continuous speech. This research combines the advantages of both CNN and RNN (in particular bidirectional LSTM) models, called CRNN. The speech signals were represented as a spectrogram and were fed to the CRNN model as 2D images. The proposed method achieved accuracies of 98% and 98.57% for environment and microphone classification, respectively, using unvoiced speech segments.