Proceedings of the National Academy of Sciences, 1998
Familial multiple system tauopathy with presenile dementia (MSTD) is a neurodegenerative disease ... more Familial multiple system tauopathy with presenile dementia (MSTD) is a neurodegenerative disease with an abundant filamentous tau protein pathology. It belongs to the group of familial frontotemporal dementias with Parkinsonism linked to chromosome 17 (FTDP-17), a major class of inherited dementing disorders whose genetic basis is unknown. We now report a G to A transition in the intron following exon 10 of the gene for microtubule-associated protein tau in familial MSTD. The mutation is located at the 3′ neighboring nucleotide of the GT splice-donor site and disrupts a predicted stem-loop structure. We also report an abnormal preponderance of soluble tau protein isoforms with four microtubule-binding repeats over isoforms with three repeats in familial MSTD. This most likely accounts for our previous finding that sarkosyl-insoluble tau protein extracted from the filamentous deposits in familial MSTD consists only of tau isoforms with four repeats. These findings reveal that a depar...
Set intersection algorithms between sorted lists are important in triangles counting, community d... more Set intersection algorithms between sorted lists are important in triangles counting, community detection in graph analysis and in search engines where the intersection is computed between queries and inverted indexes. Many researches use GPU techniques for solving this intersection problem. The majority of these techniques focus on improving the level of parallelism by reducing redundant comparisons and distributing the workload among GPU threads. In this paper, we propose the GPU Test with Jumps (GTWJ) algorithm to compute the intersection between sorted lists using a new data structure. The idea of GTWJ is to group the data, of each sorted list, into a set of sequences. A sequence is identified by a key and is handled by a thread. Intersection is computed between sequences with the same key. This key allows skipping data packets in parallel if the keys do not match. A counter is used to avoid useless tests between cells of sequences with different lengths. Experiments on the data...
2016 17th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA), 2016
The electroencephalography (EEG) is the most essential tool for the diagnosis and the treatment o... more The electroencephalography (EEG) is the most essential tool for the diagnosis and the treatment of the epilepsy. It allows observing events strongly associated with epilepsy or epileptic spikes and locating the brain regions that cause the symptoms of epilepsy. This paper presents an automated classification of EEG signals for the detection of epileptic seizures with Single-Channel using the wavelet transform and the Extreme Learning Machine. The aim is to create a system with reduced computation time and resources with the minimum number of required electrodes. The decision making process is comprised of three steps: (a) Preprocessing, (b) feature extraction based on the wavelet transform, and (c) classification by the Extreme Learning Machine. The proposed algorithm has been tested on three different data sets from the CHB-MIT scalp EEG database using only the FT10-T8 channel. The proposed method achieves a classification accuracy of 94.85%.
2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2018
The automatic seizure detection system is designed to aid the physician's decision-making pro... more The automatic seizure detection system is designed to aid the physician's decision-making process with recognizing the sought EEG segments. Increasing the system sensitivity is the goal of several studies. In fact, ameliorating this criterion allows to find the same interpretations as found with a visual scanning. A patient-specific system is able to set its optimal parameters according to the patient which makes it more accurate than non-patient-specific system. This paper introduces a new patient-specific system with genetic and practical swarm optimisation algorithms. The results show that the proposed system is able to reach acceptable performances. Moreover, the use of the genetic algorithm improves the system sensitivity (95%) more than the practical swarm optimization (91%) which makes it a better method for the system parameter optimisation.
Data representation facilities offered by RDF (Resource Description Framework) have made it very ... more Data representation facilities offered by RDF (Resource Description Framework) have made it very popular. It is now considered as a standard in several fields (Web, Biology, ...). Indeed, by lightening the notion of schema, RDF allows a flexibility in the representation of data. This popularity has given rise to large datasets and has consequently led to the need for efficient processing of these data. In this paper, we propose a novel approach that we name QDAG (Querying Data as Graphs) allowing query processing on RDF data. We propose to combine RDF graph exploration with physical fragmentation of triples. Graph exploration makes possible to exploit the structure of the graph and its semantics while the fragmentation allows to group the nodes of the graph having the same properties. Compared to the state of the art (i.e., gStore, RDF3X, Virtuoso), our approach offers a compromise between efficient query processing and scalability. In this regard, we conducted an experimental study using real and synthetic datasets to validate our approach with respect to scalability and performance.
2018 IEEE International Conference on Industrial Technology (ICIT), 2018
This paper presents a fault detection method based on an unsupervised deep learning to monitor op... more This paper presents a fault detection method based on an unsupervised deep learning to monitor operating conditions of wastewater treatment plants (WWTPs). This method uses Deep Belief Networks (DBNs) model and one-class support vector machine (OCSVM). Here, DBN model is introduced to account for nonlinear aspects of WWTPs, while OCSVM is employes to reliably detect a fault in WWTP. The developed DBN-OCSVM approach has been tested through practical application on data from a decentralized wastewater treatment plant in Golden, CO, USA. Results show the effectiveness of the developed approach to monitor the WWTP.
Abstract: In this paper we investigated the building of a quranic reader controlled by speech. Th... more Abstract: In this paper we investigated the building of a quranic reader controlled by speech. This system is based on open source CMU Sphinx toolkit, which represents an HMM speech recognition toolkit built for English language, and tuned by us to support Arabic. For this purpose, we have collected a speech corpus called "Quranic Reader Command and Control Corpus" QRCCC from several speakers using web Java applet to train the HMM acoustic model. The performances of this model were tested by varying the training parameters "the number of Gaussians Mixtures and Senones" using Pocket Sphinx decoder. The model with the best parameters was chosen to be integrated in a demo application built using Sphinx-4 to perform recognition.
International Journal of Reasoning-based Intelligent Systems, 2011
In this paper, an Arabic character recognition system based on Artificial Neural Networks (ANN) i... more In this paper, an Arabic character recognition system based on Artificial Neural Networks (ANN) is presented. In this system, each drawn Arabic character is represented by binary values that are used as input to a simple feature extraction system, whose output is fed to a Kohonen neural network that consists of two layers (first layer 99 neurons, second layer 28 neurons). Simulation results are provided and show that the proposed system always produces a lower Mean Squared Error (MSE) and higher success rates than the most of the other classifier method solutions, especially when the contaminating noise level is low.
International Journal of Embedded and Real-Time Communication Systems, 2019
To provide correct data transmission and to handle the communication requirements, the routing al... more To provide correct data transmission and to handle the communication requirements, the routing algorithm should find a new path to steer packets from the source to the destination in a faulty network. Many solutions have been proposed to overcome faults in network-on-chips (NoCs). This article introduces a new fault-tolerant routing algorithm, to tolerate permanent and transient faults in NoCs. This solution called DINRA can satisfy simultaneously congestion avoidance and fault tolerance. In this work, a novel approach inspired by Catnap is proposed for NoCs using local and global congestion detection mechanisms with a hierarchical sub-network architecture. The evaluation (on reliability, latency and throughput) shows the effectiveness of this approach to improve the NoC performances compared to state of art. In addition, with the test module and fault register integrated in the basic architecture, the routers are able to detect faults dynamically and re-route packets to fault-free ...
International Journal of Technology Diffusion, 2016
The purpose of this article is to explore the teaching processes that use Quick Response (QR) cod... more The purpose of this article is to explore the teaching processes that use Quick Response (QR) codes and mobile devices to support blended learning at the National Institute of Telecommunications and ICT (INTTIC). The satisfactory results of our previous research show that the use of mobile technology could enhance accessibility and communication in a blended learning course. In Algeria, the mobile penetration rate stands at over 111% and 21% with 3G. Since most of our students have access to mobile technology, three in five were smartphones. Using this technology would encourage students to use their phones to send questions to their teachers, listen to a podcast and snip the quick response (QR) codes. This paper introduces the implementations of QR codes, vcard and QR voice as a new tool in the Moodle platform in our institute. The QR code contains the URL of the page of one particular Moodle course and quiz are added to the bottom of Moodle. The students' satisfaction had been...
Proceedings of the National Academy of Sciences, 1998
Familial multiple system tauopathy with presenile dementia (MSTD) is a neurodegenerative disease ... more Familial multiple system tauopathy with presenile dementia (MSTD) is a neurodegenerative disease with an abundant filamentous tau protein pathology. It belongs to the group of familial frontotemporal dementias with Parkinsonism linked to chromosome 17 (FTDP-17), a major class of inherited dementing disorders whose genetic basis is unknown. We now report a G to A transition in the intron following exon 10 of the gene for microtubule-associated protein tau in familial MSTD. The mutation is located at the 3′ neighboring nucleotide of the GT splice-donor site and disrupts a predicted stem-loop structure. We also report an abnormal preponderance of soluble tau protein isoforms with four microtubule-binding repeats over isoforms with three repeats in familial MSTD. This most likely accounts for our previous finding that sarkosyl-insoluble tau protein extracted from the filamentous deposits in familial MSTD consists only of tau isoforms with four repeats. These findings reveal that a depar...
Set intersection algorithms between sorted lists are important in triangles counting, community d... more Set intersection algorithms between sorted lists are important in triangles counting, community detection in graph analysis and in search engines where the intersection is computed between queries and inverted indexes. Many researches use GPU techniques for solving this intersection problem. The majority of these techniques focus on improving the level of parallelism by reducing redundant comparisons and distributing the workload among GPU threads. In this paper, we propose the GPU Test with Jumps (GTWJ) algorithm to compute the intersection between sorted lists using a new data structure. The idea of GTWJ is to group the data, of each sorted list, into a set of sequences. A sequence is identified by a key and is handled by a thread. Intersection is computed between sequences with the same key. This key allows skipping data packets in parallel if the keys do not match. A counter is used to avoid useless tests between cells of sequences with different lengths. Experiments on the data...
2016 17th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA), 2016
The electroencephalography (EEG) is the most essential tool for the diagnosis and the treatment o... more The electroencephalography (EEG) is the most essential tool for the diagnosis and the treatment of the epilepsy. It allows observing events strongly associated with epilepsy or epileptic spikes and locating the brain regions that cause the symptoms of epilepsy. This paper presents an automated classification of EEG signals for the detection of epileptic seizures with Single-Channel using the wavelet transform and the Extreme Learning Machine. The aim is to create a system with reduced computation time and resources with the minimum number of required electrodes. The decision making process is comprised of three steps: (a) Preprocessing, (b) feature extraction based on the wavelet transform, and (c) classification by the Extreme Learning Machine. The proposed algorithm has been tested on three different data sets from the CHB-MIT scalp EEG database using only the FT10-T8 channel. The proposed method achieves a classification accuracy of 94.85%.
2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2018
The automatic seizure detection system is designed to aid the physician's decision-making pro... more The automatic seizure detection system is designed to aid the physician's decision-making process with recognizing the sought EEG segments. Increasing the system sensitivity is the goal of several studies. In fact, ameliorating this criterion allows to find the same interpretations as found with a visual scanning. A patient-specific system is able to set its optimal parameters according to the patient which makes it more accurate than non-patient-specific system. This paper introduces a new patient-specific system with genetic and practical swarm optimisation algorithms. The results show that the proposed system is able to reach acceptable performances. Moreover, the use of the genetic algorithm improves the system sensitivity (95%) more than the practical swarm optimization (91%) which makes it a better method for the system parameter optimisation.
Data representation facilities offered by RDF (Resource Description Framework) have made it very ... more Data representation facilities offered by RDF (Resource Description Framework) have made it very popular. It is now considered as a standard in several fields (Web, Biology, ...). Indeed, by lightening the notion of schema, RDF allows a flexibility in the representation of data. This popularity has given rise to large datasets and has consequently led to the need for efficient processing of these data. In this paper, we propose a novel approach that we name QDAG (Querying Data as Graphs) allowing query processing on RDF data. We propose to combine RDF graph exploration with physical fragmentation of triples. Graph exploration makes possible to exploit the structure of the graph and its semantics while the fragmentation allows to group the nodes of the graph having the same properties. Compared to the state of the art (i.e., gStore, RDF3X, Virtuoso), our approach offers a compromise between efficient query processing and scalability. In this regard, we conducted an experimental study using real and synthetic datasets to validate our approach with respect to scalability and performance.
2018 IEEE International Conference on Industrial Technology (ICIT), 2018
This paper presents a fault detection method based on an unsupervised deep learning to monitor op... more This paper presents a fault detection method based on an unsupervised deep learning to monitor operating conditions of wastewater treatment plants (WWTPs). This method uses Deep Belief Networks (DBNs) model and one-class support vector machine (OCSVM). Here, DBN model is introduced to account for nonlinear aspects of WWTPs, while OCSVM is employes to reliably detect a fault in WWTP. The developed DBN-OCSVM approach has been tested through practical application on data from a decentralized wastewater treatment plant in Golden, CO, USA. Results show the effectiveness of the developed approach to monitor the WWTP.
Abstract: In this paper we investigated the building of a quranic reader controlled by speech. Th... more Abstract: In this paper we investigated the building of a quranic reader controlled by speech. This system is based on open source CMU Sphinx toolkit, which represents an HMM speech recognition toolkit built for English language, and tuned by us to support Arabic. For this purpose, we have collected a speech corpus called "Quranic Reader Command and Control Corpus" QRCCC from several speakers using web Java applet to train the HMM acoustic model. The performances of this model were tested by varying the training parameters "the number of Gaussians Mixtures and Senones" using Pocket Sphinx decoder. The model with the best parameters was chosen to be integrated in a demo application built using Sphinx-4 to perform recognition.
International Journal of Reasoning-based Intelligent Systems, 2011
In this paper, an Arabic character recognition system based on Artificial Neural Networks (ANN) i... more In this paper, an Arabic character recognition system based on Artificial Neural Networks (ANN) is presented. In this system, each drawn Arabic character is represented by binary values that are used as input to a simple feature extraction system, whose output is fed to a Kohonen neural network that consists of two layers (first layer 99 neurons, second layer 28 neurons). Simulation results are provided and show that the proposed system always produces a lower Mean Squared Error (MSE) and higher success rates than the most of the other classifier method solutions, especially when the contaminating noise level is low.
International Journal of Embedded and Real-Time Communication Systems, 2019
To provide correct data transmission and to handle the communication requirements, the routing al... more To provide correct data transmission and to handle the communication requirements, the routing algorithm should find a new path to steer packets from the source to the destination in a faulty network. Many solutions have been proposed to overcome faults in network-on-chips (NoCs). This article introduces a new fault-tolerant routing algorithm, to tolerate permanent and transient faults in NoCs. This solution called DINRA can satisfy simultaneously congestion avoidance and fault tolerance. In this work, a novel approach inspired by Catnap is proposed for NoCs using local and global congestion detection mechanisms with a hierarchical sub-network architecture. The evaluation (on reliability, latency and throughput) shows the effectiveness of this approach to improve the NoC performances compared to state of art. In addition, with the test module and fault register integrated in the basic architecture, the routers are able to detect faults dynamically and re-route packets to fault-free ...
International Journal of Technology Diffusion, 2016
The purpose of this article is to explore the teaching processes that use Quick Response (QR) cod... more The purpose of this article is to explore the teaching processes that use Quick Response (QR) codes and mobile devices to support blended learning at the National Institute of Telecommunications and ICT (INTTIC). The satisfactory results of our previous research show that the use of mobile technology could enhance accessibility and communication in a blended learning course. In Algeria, the mobile penetration rate stands at over 111% and 21% with 3G. Since most of our students have access to mobile technology, three in five were smartphones. Using this technology would encourage students to use their phones to send questions to their teachers, listen to a podcast and snip the quick response (QR) codes. This paper introduces the implementations of QR codes, vcard and QR voice as a new tool in the Moodle platform in our institute. The QR code contains the URL of the page of one particular Moodle course and quiz are added to the bottom of Moodle. The students' satisfaction had been...
Uploads
Papers by Mohamed Senouci