MOHAMED Benouis

Nakroui ala , Nakouri ala

A deep learning alogrithm applied to Handover Management Within LTE

Sellami Mohammed , Sellami Mohammed

can we develop a Smart healthcare with behavioral & physiological change ?

To the best of current knowledge, the performance of federated learning predominantly depends on the efficiency of the aggregation server scheme utilized to consolidate model parameters received from distributed local devices. However, in practical scenarios, the global server often faces single-point failures due to four major issues: 1) variations in data distribution settings, such as independent identical distribution (IID) or non-independent identical distribution; 2) communication overhead; 3) limitations in hardware and resource storage availability; and 4) diverse participant participation behaviors. To address the latter concern, limited research has endeavored to establish a correlation between these heterogeneous settings and federated learning performance by analyzing different aspects of participant behavior. Inspired by the absence of a definitive verdict regarding the relationship between the global server and participant behavior, this paper investigates the aspect of participant selection methods and conducts a detailed comparative study among various participant selection methods

Citation

WAFA Bouras , Mohamed Benouis , Samir Akhrouf , brahim.bouderah@univ-msila.dz, ,(2024-05-13), Analysis Study of Participant Selection Methods in Federated Learning,ICEEAC’2024,Setif university

Smoking is a commonly observed habit worldwide, and is a major cause of disease leading to death. Many techniques have been established in medical and psychological science to help people quit smoking. However, the existing systems are complex, and usually expensive. Recently, wearable sensors and mobile application have become an alternative method of improving health. We propose a human behavioural classification based on the use of a one-dimensional local binary pattern (LBP), combined with a Probabilistic Neural Net (PNN) to differentiate the habits of activity as measured in data collected from a wearable device. Human activity signals were recorded from two sets of 6 and 11 participants, using a smart phones equipped with an accelerometer and gyroscope mounted on a wrist module. The data combined structured and naturalistic scenarios. The proposed architecture was compared to previously studied machine learning algorithms and found to out-perform them, exhibiting ceiling level performance.

Citation

Mohamed Benouis , ,(2019), Behavioural Smoking Identification via Hand-Movement Dynamics,The 5th IEEE International Conference on Internet of People (IoP 2019),leicester, Uk

Combination of multiple information extracted from different biometric modalities in multimodal biometric recognition system aims to solve the different drawbacks encountered in a unimodal biometric system. Fusion of many biometrics has proposed such as face, fingerprint, iris…etc. Recently, electrocardiograms (ECG) have been used as a new biometric technology in unimodal and multimodal biometric recognition system. ECG provides inherent the characteristic of liveness of a person, making it hard to spoof compared to other biometric techniques. Ear biometrics present a rich and stable source of information over an acceptable period of human life. Iris biometrics have been embedded with different biometric modalities such as fingerprint, face and palm print, because of their higher accuracy and reliability. In this paper, a new multimodal biometric system based ECG-ear-iris biometrics at feature level is proposed. Preprocessing techniques including normalization and segmentation are applied to ECG, ear and iris biometrics. Then, Local texture descriptors, namely 1D-LBP (One D-Local Binary Patterns), Shifted-1D-LBP and 1D-MR-LBP (Multi-Resolution) are used to extract the important features from the ECG signal and convert the ear and iris images to a 1D signals. KNN and RBF are used for matching to classify an unknown user into the genuine or impostor. The developed system is validated using the benchmark ID-ECG and USTB1, USTB2 and AMI ear and CASIA v1 iris databases. The experimental results demonstrate that the proposed approach outperforms unimodal biometric system. A Correct Recognition Rate (CRR) of 100% is achieved with an Equal Error Rate (EER) of 0.5%.

Citation

Mohamed Benouis , , (2019), Multimodal biometric system for ECG, ear and iris recognition based on local descriptors, Multimed Tools Appl, Vol:78, Issue:78, pages:22509–22535, springer

This paper presents multi-modal biometric authentication approach using gait and electrocardiogram (ECG) signals, which can diminish the drawback of unimodal biometric approach as well as to improve authentication system performance. In acquisition phase, data sets are collected from three different databases, ECG-ID, MIT-BIH Arrhythmia database and UCI Machine Learning Repository (Gait). In Feature extraction phase of both signals (ECG and Gait) is performed by using 1D-local binary pattern. Features are obtained by merging two modalities as one feature. In classification approach, three classifiers are developed to classify subjects. K-nearest neighbour (KNN), relying on Euclidean distance, PNN (Probabilistic Neural Network), RBF (Radial Basis Function) and Support Vector Machine (SVM), relying on One-against-all (OAA). The proposed multimodal system has been tested over 18 subjects, and its identification accuracy was about 100%. Our result demonstrate that our approach outperforms rather than unimodal biometric system in terms of Correct Recognition Rate, Equal Error Rate, False Acceptance Rate and False Reject Rate.

Citation

Mohamed Benouis , , (2019), An Improved Behavioral Biometric System based on Gait and ECG signals, International Journal of Intelligent Engineering and Systems, Vol:12, Issue:6, pages:147-156, INASS

ECG analysis has been investigated as promising biometric in many fields especially in medical science and cardiovascular disease for last decades in order to exploit the discriminative capability provided by these liveness measures developing a robust ECG based recognition system. In this paper, an ECG biometric recognition system was proposed based on shifted 1D-LBP. Shifted 1D-LBP was applied to extract the representative non-fiducial features from preprocessed and segmented ECG heartbeats. For matching step, K Nearest Neighbors (KNN) was adopted. Two benchmark databases namely MIT-BIH/Normal Sinus Rhythm and ECG-ID database were used to validate the proposed approach. A Correct Recognition Rate (CRR) of 100% and 97% was achieved with MIT-BIH/Normal Sinus Rhythm and ECG-ID databases, respectively.

Citation

Mohamed Benouis , ,(2018), Shifted 1D-LBP Based ECG Recognition System,https://link.springer.com/book/10.1007/978-3-030-05481-6,Laghouat, algeria

he sensitivity to illumination variations, pose, gender, age, clothing and any another source of changes, can be one of the most important challenges, in gait recognition system. In this paper, we adopt many approaches to extract signatures of human body (static model) using a model-based method, such as static body parameters, ellipse-fitting and robust shape coding. To reduce the dimension of this features set, a principal component analysis (PCA) technique is employed. Then, a deep belief networks classifier is used to classify the gait signatures. The performance of the deep belief network (DBN) is superior to other classifiers such as k-nearest neighbour (KNN) and dynamic times warping (DTW). The comparison is performed for viewpoint changes, clothing and carrying conditions. The proposed approach has been validated on the gait database B.

Citation

Mohamed Benouis , , (2017), Gait Recognition Based on Model- Based Methods and Deep Belief Networks, International Journal of Biometrics, Vol:8, Issue:3, pages:237 - 253, Inderscience

Face recognition is considered as one of the best biometric methods used for human identification and verification; this is because of its unique features that differ from one person to another, and its importance in the security field. This paper proposes an algorithm for face recognition and classification using a system based on WPD, fractal codes and two-dimensional subspace for feature extraction, and Combined Learning Vector Quantization and PNN Classifier as Neural Network approach for classification. This paper presents a new approach for extracted features and face recognition .Fractal codes which are determined by a fractal encoding method are used as feature in this system. Fractal image compression is a relatively recent technique based on the representation of an image by a contractive transform for which the fixed point is close to the original image. Each fractal code consists of five parameters such as corresponding domain coordinates for each range block. Brightness offset and an affine transformation. The proposed approach is tested on ORL and FEI face databases. Experimental results on this database demonstrated the effectiveness of the proposed approach for face recognition with high accuracy compared with previous methods.

Citation

Mohamed Benouis , ,(2015), A Novel Technique For Human Face Recognition Using Fractal Code and Bi-dimensional Subspace,CIIA 2015: Computer Science and Its Applications,Saida, Algeria

In this paper, we present an new approach to face recognition based on the combination of feature extraction methods, such as two-dimensional DWT-2DPCA and DWT-2DLDA, with a probabilistic neural networks. The technique 2D-DWT is used to eliminate the illumination, noise and redundancy of a face in order to reduce calculations of the probabilistic neural network operations.

Citation

Mohamed Benouis , ,(2013), Face recognition approach based on two-dimensional subspace analysis and PNN,International Symposium on Programming and Systems (ISPS’2013),Algeria