M. KHENNOUF Salah

MCA

Directory of teachers

Department

Departement of ELECTRONICS

Research Interests

Speaker Identification Author Identification Artificial Intelligence Author Attribution Renewable Energy

Contact Info

University of M'Sila, Algeria

Email : salah.khennouf@univ-msila.dz

On the Web:

  • Google Scholar N/A
  • ResearchGate
    ResearchGate N/A
  • ORCID N/A
  • SC
    Scopus N/A

Recent Publications

2024-10-29

AI Serving Homeland Security and Safety

AI Serving Homeland Security and Safety
Citation

M. KHENNOUF Salah, (2024-10-29), "AI Serving Homeland Security and Safety", [international] The International Conference for AI Serving Homeland Security and Safety , Doha - Qatar

Read Full Paper
2024-09-23

Improving Arabic Authorship Attribution on Imbalanced Dataset Using a Hybrid Approach

Abstract- Imbalanced Datasets are one of the major challenges in text mining. In order to tackle the issue of imbalanced datasets in the Authorship Attribution (AA) task, particularly when applied to Arabic text data, we proposed a new hybrid approach based on AraVec representation and Synthetic minority oversampling technique (SMOTE). That involves the use of layer of balancing after the embedding representation step in AraVec. This layer is trained to adjust the weight of each sample based on the class distribution, effectively balancing the training process for all classes. The results of the proposed approach have shown significant improvements over the model baseline and demonstrating its effectiveness in addressing the problem of imbalanced datasets in Arabic Authorship Attribution.
Citation

M. KHENNOUF Salah, (2024-09-23), "Improving Arabic Authorship Attribution on Imbalanced Dataset Using a Hybrid Approach", [national] The 4th Doctoral Days of Speech Communication And Signal Processing Laboratory , USTHB, Bab Ezzouar, Algiers - Algeria

Read Full Paper
2024-09-15

Pre-Project Work

Pre-Project Work
Citation

M. KHENNOUF Salah, (2024-09-15), "Pre-Project Work", [national] University Mohamed Boudiaf - Msila

Read Full Paper
2024-05-23

Système de pulvérisation Intelligent pour les Produits Chimiques Agricoles ; Cas d'Application Bio Anti-Gel

Système de pulvérisation Intelligent pour les Produits Chimiques Agricoles ; Cas d'Application Bio Anti-Gel,
Citation

M. KHENNOUF Salah, (2024-05-23), "Système de pulvérisation Intelligent pour les Produits Chimiques Agricoles ; Cas d'Application Bio Anti-Gel", [national] جامعة محمد بوضياف - المسيلة

Read Full Paper

Bio Anti-Gel pour la protection de Plants avec un Système de pulvérisation Intelligent

Bio Anti-Gel pour la protection de Plants avec un Système de pulvérisation Intelligent.
Citation

M. KHENNOUF Salah, (2024-05-23), "Bio Anti-Gel pour la protection de Plants avec un Système de pulvérisation Intelligent", [national] جامعة محمد بوضياف - المسيلة

Read Full Paper
2023-11-19

Dispositif d'amélioration de la force du signal Wifi

Dispositif d'amélioration de la force du signal Wifi
Citation

M. KHENNOUF Salah, (2023-11-19), "Dispositif d'amélioration de la force du signal Wifi", [national] Université de Msila

Read Full Paper

Un bracelet électronique de surveillance pour les patients atteints de la maladie d'Alzheimer

Un bracelet électronique de surveillance pour les patients atteints de la maladie d'Alzheimer
Citation

M. KHENNOUF Salah, (2023-11-19), "Un bracelet électronique de surveillance pour les patients atteints de la maladie d'Alzheimer", [national] Université de Msila

Read Full Paper
2023-06-26

Dispositif de systemes de sécurité domestique

Dispositif de systemes de sécurité domestique
Citation

M. KHENNOUF Salah, (2023-06-26), "Dispositif de systemes de sécurité domestique", [national] Université de Msila

Read Full Paper
2022-02-22

Réalisation d'un Système Automatique de Régulation de l'Ammoniac dans un aquarium

Réalisation d'un Système Automatique de Régulation de l'Ammoniac dans un aquarium.
Citation

M. KHENNOUF Salah, (2022-02-22), "Réalisation d'un Système Automatique de Régulation de l'Ammoniac dans un aquarium", [national] Université Mohamed BOUDIAF-Msila

Read Full Paper
2022

A New Design for Enhancing Highly Sensitive Interferometer Biosensor Using a Silicon Rib Waveguide

In this paper, we have proposed a new design, to enhance and simulate a Highly Sensitive Mach-Zehnder Interferometer (MZI) Biochemical sensing platform using a Silicon Rib Waveguide. We considered two different MZI configurations: the first one with an S-bend & Y-junction and the second with an angular Y-junction. We determined the critical cutoff radius and the critical cut-off angle for the S-bend & Y-junction and the angular Yjunction configurations respectively. Based on the analyses of the evanescent field intensity, the mode polarization and cross section dimensions of the Silicon Rib waveguide are optimized using beam propagation method. The critical parameters of the design are calculated to ensure minimal optical losses and a new sensitivity value of 308 dB/RIU with a detection limit of 10-7, which shows the ability of the structure to produce biosensor.
Citation

M. KHENNOUF Salah, (2022), "A New Design for Enhancing Highly Sensitive Interferometer Biosensor Using a Silicon Rib Waveguide", [national] Instrumentation Mesure Métrologie , International Information and Engineering Technology Association

Read Full Paper

Performances Evaluation of Automatic Authorship Attribution on Ancient Arabic Documents

Authorship Attribution is a research area concerned with the automatic classification of text documents based on their authors. The main objective of this investigation area is to find out who is the author of a given text. This task becomes very tough as far as old text documents are concerned. In this paper, we attempted to broach the Authorship Attribution problem as it applies to old text documents. For this purpose, several experiments are conducted and their results are commented. In order to validate the performances of our system, we constructed a special dataset that we called ''A10P '' (10 Ancient Arabic Philosophers), by quoting texts from the works of 10 ancient Arabic philosophers, where the topic of the different texts is the same. Moreover, the genre of the authors is also the same.
Citation

M. KHENNOUF Salah, Halim Sayoud, , (2022), "Performances Evaluation of Automatic Authorship Attribution on Ancient Arabic Documents", [international] International Conference of advanced Technology in Electronic and Electrical Engineering , University of Msila

Read Full Paper
2020

Fiabilité et Maintenance des Systèmes Electroniques

Ce cours de Fiabilité et Maintenance des Systèmes Electroniques a été rédigé, conformément au programme officiel de formation, à l’intention des étudiants qui
préparent, un master dans le domaine des Sciences et Technologies, Filière : Electronique, Option : Instrumentation. Il est enseigné en 3ème semestre, à raison d’une heure et demi de cours par semaine est complété par une heure de travaux pratiques. Le contenu du programme proposé par la tutelle est relativement long, l’enseignant doit alors se limiter aux concepts importants et c’est à l’étudiant de fournir un effort supplémentaire pour prendre en charge tous ces concepts. Ce cours, indispensable pour l’étudiant en master électronique, se divise en six chapitres.
Citation

M. KHENNOUF Salah, (2020), "Fiabilité et Maintenance des Systèmes Electroniques", [national] University of M'sila

Read Full Paper

Kernel Function and Dimensionality Reduction Effects on Speaker Discrimination System

In this research work, we are dealing with an Automatic Speaker Verification problem, which consists on the determination if a person really is the person he/she claims to be, using his/her speech signal characteristics. Therefore, we conducted three series of experiments applied to a subset of Hub4 Broadcast-News database using a Support Vector Machine (SVM) as classifier and the Mel Frequency Spectral Coefficients (MFSC) as speakers’ features. In the first series of experiments, we investigated the effect of the number of features in order to obtain the minimum number that gives a Good Verification Score (GVScore). In the second series of experiments, as there are many
types of kernel functions, the appropriate one for speaker verification is investigated. In the last series of experiments, we investigated the GVScore with regard to speaker gender (Male vs. Male, Female vs. Female and Male vs. Female). In our approach, we have used the MFSC as features extraction, which are calculated in both training and testing sessions. The obtained results of the proposed techniques are quite interesting.
Citation

M. KHENNOUF Salah, SAYOUD Halim, , (2020), "Kernel Function and Dimensionality Reduction Effects on Speaker Discrimination System", [international] The 6th International Conference on Electrical Engineering- ICEE’2020 , Istanbul, Turkey

Read Full Paper
2018

Speaker discrimination based on fuzzy fusion and feature reduction techniques

In this paper, we propose a research work on speaker discrimination using a multi-classifier fusion with focus on feature reduction effects. Speaker discrimination consists in the automatic distinction between two speakers using the vocal characteristics of their speeches. A number of features are extracted using Mel Frequency Spectral Coefficients and then reduced using Relative Speaker Characteristic (RSC) along with the Principal Components Analysis (PCA). Several classification methods are implemented to ensure the discrimination task. Since different classifiers are employed, two fusion algorithms at the decision level, referred to as Weighted Fusion and Fuzzy Fusion, are proposed to boost the classification performances. These algorithms are based on the weighting of the different classifiers outputs. Furthermore, the effects of speaker gender and feature reduction on the speaker discrimination task have been examined too. The evaluation of our approaches was conducted on a subset of Hub-4 Broadcast-News. The experimental results have shown that the speaker discrimination accuracy is improved by 5–15% using the (RSC–PCA) feature reduction. In addition, the proposed fusion methods recorded an improvement of about 10% compared to the individual scores of the classifiers. Finally, we noticed that the gender has an important impact on the discrimination performances.
Citation

M. KHENNOUF Salah, SAYOUD Halim, , (2018), "Speaker discrimination based on fuzzy fusion and feature reduction techniques", [national] International Journal of Speech Technology , Springer

Read Full Paper
2017

Automatic Authorship Attribution of Transcribed Texts –Application on Oral Religious Discourses

Authorship attribution is the application of the linguistic study of an anonymous text to identify its actual author. In this paper, we are interested in identifying the author of texts obtained through the transcription of oral discourses. For this purpose, we constructed a special corpus that we called ''SC2T'' (Speech Converted to Text), containing text documents with an average size of 275 words, which are obtained by transcribing oral religious discourses of 14 Arabic contemporary preachers speaking in the same topic. These texts were transcribed manually retaining all the repeated as well as the mispronounced words. Several features and classifiers were employed and evaluated with respect to the Score of Good Authorship Attribution (SGAA) performances. Results are quite interesting and show that the most robust feature in authorship Attribution is the character-Tetragram, which provides a SGAA of 80%.
Citation

M. KHENNOUF Salah, Hassina HADJADJ, Halim SAYOUD, , (2017), "Automatic Authorship Attribution of Transcribed Texts –Application on Oral Religious Discourses", [international] NTERNATIONAL CONFERENCE ON ELECTRONICS AND NEW TECHNOLOGIES , Univ-M'sila

Read Full Paper
2015

Energy conversion optimization of Si-solar cell using different wavelength filters

Photovoltaic (PV) solar energy conversion systems (or solar cells) are the most widely used power systems. However, these devices suffer of very low conversion efficiency. This is due to the wavelength mismatch between the narrow wavelength band associated with the semiconductor energy gap and the broad band of the (blackbody) Emission curve of the Sun [1]. Thus, the photovoltaic conversion is highly wavelength dependant and is most efficient when converting photons of energies close to PV cell band gap energy [2].
In the present research work, we tried to treat this problem, which is related to the optimization of the energy conversion of a Si-solar cell, using different colored filters having different wavelength. For this purpose, we have conducted an experimental work aiming to find out the P-Y characteristics of the solar cell. This experimental work consists of applying an illuminating light source on a Si-solar cell (type 307-137) across 4 colored filters (Red, Blue, Yellow and Green) one by one, each one having a specific wavelength, and measuring each time the resulting voltage and current (power). The obtained results are quite interesting.
Citation

M. KHENNOUF Salah, (2015), "Energy conversion optimization of Si-solar cell using different wavelength filters", [international] THE FIRST INTERNATIONAL CONFERENCE ON SOLAR ENERGY (INCOSOLE 2015) , University of Bordj Bou Arréridj

Read Full Paper
2013

Virtual speaker tracking by camera using a sound source localisation with two microphones

Our research work deals with the problem of automatic speaker tracking by camera. Such tracking systems do exist nowadays, but they suffer from a number of mechanical problems. To overcome these problems, we thought of employing a virtual tracking system using a fixed camera that does not require any mechanical part. But, is it possible to track a moving speaker with a fixed camera? If the task is already difficult enough with a mobile camera, how difficult would it be with a fixed camera? Trying to find a solution to the problem, we have proposed and conceived a virtual tracking system, which is able to ensure the required task by using only two cardioid microphones and a classic video camera. In this virtual tracking system, the task of speaker tracking is ensured by the orientation of the region of interest ROI of the camera towards the active speaker; we have called this method the virtual region of interest VROI based technique. Experiments show the good performance of the new virtual technique.
Citation

M. KHENNOUF Salah, SAYOUD Halim, , (2013), "Virtual speaker tracking by camera using a sound source localisation with two microphones", [national] International Journal of Networking and Virtual Organisations , Inderscience

Read Full Paper
2012

Automatic Speaker Localization and Tracking: Using a Fusion of the Filtered Correlation with the Energy Differential

This paper presents a system of speaker localization for a purpose of speaker tracking by camera. The authors use the information given by the two microphones, placed in opposition, to determine the position of the active speaker in trying to supervise the audio-visual recording. To achieve the speaker localization task, the authors have proposed and employed two methods, which are called respectively: the filtered correlation method and the energy differential method. The principle of the first method is based on the calculation of the correlation between the two signals collected by the two microphones and a special filtering. The second is based on the computation of the logarithmic energy differential between these two signals. However, when different methods are used simultaneously to make a decision, it is often interesting to use a fusion technique combining those estimations or decisions in order to enhance the system performances. For that purpose, this paper proposes two fusion techniques operating at the decision level which are used to fuse the two estimations into one that should be more precise.
Citation

M. KHENNOUF Salah, (2012), "Automatic Speaker Localization and Tracking: Using a Fusion of the Filtered Correlation with the Energy Differential", [national] Advancing the Next-Generation of Mobile Computing: Emerging Technologies , Information Science Reference (an imprint of IGI Global)

Read Full Paper
2011

Automatic speaker tracking by camera using two-channel-based sound source localization

Purpose
The purpose of this paper is two‐fold. First, to deal with the problem of audio speaker localization and second, to deal with the problem of mobile camera control. The task of speaker localization consists of determining the position of the active speaker and the task of camera control consists of orienting a mobile camera towards that active speaker. These steps represent the main task of speaker tracking, which is the global purpose of the research work.

Design/methodology/approach
In this approach, two‐channel‐based estimation of the speaker position is achieved by comparing the signals received by two cardioids microphones, which are placed the one against the other and separated by a fixed distance. The localization technique presented in this paper is inspired from the human ears, which act as two different sound observation points, enabling humans to estimate the direction of the speaking person with a good precision. Concerning the camera control part, the authors have conceived an automatic system for generating the command signals and controlling the rotation of the mobile camera by a stepper motor.

Findings
The off‐line experiments of speaker tracking by camera have been done in a small meeting room without echo cancelation. Results show the good performances of the proposed localization methods and a correct tracking by camera.

Practical implications
This new technique can be used for the automatic supervision of smart rooms.

Originality/value
The work described in this paper is original, since it uses only two microphones for the speaker localization.
Citation

M. KHENNOUF Salah, SAYOUD Halim, OUAMOUR Siham, , (2011), "Automatic speaker tracking by camera using two-channel-based sound source localization", [national] International Journal of Intelligent Computing and Cybernetics , Emeral Group Publishing Ltd

Read Full Paper
2010

Automatic Speaker Localization and Tracking Using a Fusion of the Filtered Correlation with the Energy Differential

This paper presents a system of speaker localization for a purpose of speaker tracking by camera. The authors use the information given by the two microphones, placed in opposition, to determine the position of the active speaker in trying to supervise the audio-visual recording. To achieve the speaker localization task, the authors have proposed and employed two methods, which are called respectively: the filtered correlation method and the energy differential method. The principle of the first method is based on the calculation of the correlation between the two signals collected by the two microphones and a special filtering. The second is based on the computation of the logarithmic energy differential between these two signals. However, when different methods are used simultaneously to make a decision, it is often interesting to use a fusion technique combining those estimations or decisions in order to enhance the system performances. For that purpose, this paper proposes two fusion techniques operating at the decision level which are used to fuse the two estimations into one that should be more precise.
Citation

M. KHENNOUF Salah, OUAMOUR Siham, SAYOUD Halim, , (2010), "Automatic Speaker Localization and Tracking Using a Fusion of the Filtered Correlation with the Energy Differential", [national] International Journal of Mobile Computing and Multimedia Communications , IGI Global publishing

Read Full Paper
← Back to Researchers List