scispace - formally typeset
Search or ask a question
Author

Birahime Diouf

Bio: Birahime Diouf is an academic researcher from Cheikh Anta Diop University. The author has contributed to research in topics: Steganography & Polar code. The author has an hindex of 5, co-authored 16 publications receiving 43 citations.

Papers
More filters
Proceedings ArticleDOI
28 Jul 2015
TL;DR: Three methods to detect the spike in real EEG signal: Page Hinkley test, smoothed nonlinear energy operator (SNEO) and fractal dimension are proposed.
Abstract: Epilepsy is a common neurological condition which affects the central nervous system that causes people to have a seizure and can be assessed by electroencephalogram (EEG). Electroencephalography (EEG) signals reflect two types of paroxysmal activity: ictal activity and interictal paroxystic events (IPE). The relationship between IPE and ictal activity is an essential and recurrent question in epileptology. The spike detection in EEG is a difficult problem. Many methods have been developed to detect the IPE in the literature. In this paper we propose three methods to detect the spike in real EEG signal: Page Hinkley test, smoothed nonlinear energy operator (SNEO) and fractal dimension. Before using these methods, we filter the signal. The Singular Spectrum Analysis (SSA) filter is used to remove the noise in an EEG signal.

8 citations

Proceedings ArticleDOI
14 Apr 2014
TL;DR: The scheme proposed in this paper allows minimizing the embedding impact and gives similar results as those of PCS scheme with a reduced time complexity.
Abstract: This paper proposes two approaches that reduce the complexity of the Polar Coding Steganography (PCS). The first is based on lookup tables and the second exploits the form of the syndrome, calculated from cover vector and secret message, to evaluate la position of the cover vector changes. The scheme proposed in this paper allows minimizing the embedding impact and gives similar results as those of PCS scheme with a reduced time complexity.

8 citations

Proceedings ArticleDOI
01 Jul 2013
TL;DR: A new steganographic scheme based on the polar codes that works with the case of a constant profile as well with any profile and is applied to the cases of constant profile and of wet paper.
Abstract: In this paper, we propose a new steganographic scheme based on the polar codes. The scheme works according to two steps. The first offers a stego vector from given cover vector and message. The stego vector provided by the first method can be the optimal; in this case, the insertion is successful with a very low complexity. Otherwise, we formalize our problem in a linear program form with initial solution the stego vector given by the first method, to converge to the optimal solution. Our scheme works with the case of a constant profile as well with any profile; it is then adapted to the case of wet paper. Tests on multiple gray scale images showed its good performance in terms of minimizing the embedding impact. I. INTRODUCTION Steganography is a technique that allows hiding information in an unsuspected medium (image, sound or video) so that it was undetectable. To reach this objective it is indispensable to use a technique in order to reduce the distortion induced by the hiding of the secret message. The matrix embedding technique introduced by Crandall (1) has allowed the definition of steganographic schemes that minimize the embedding impact. The first implementation was created with the work of Westfeld (2) in which the Hamming codes were used. Afterwards, Bose-Chaudhuri- Hocquenghem (BCH) codes (3), (4), Reed-Solomon codes (RS) (5) and Syndrome-Trellis-Codes (STC) (6) are used in steganography. Combination of LSB, matrix embedding and wet paper techniques allowed building more effective and more reliable steganographic schemes. Our works is a contribution to schemes of minimizing embedding impact. We propose in this paper a new steganographic scheme based on the polar codes. The scheme is applied to the cases of constant profile and of wet paper. We will consider, thought all the paper, the cover vector v made up of the LSBs of the cover image, the stego vector y, the changes vector e (y=v+e), the secret message m and the parity check matrix H of the polar code used. This paper is organized as following. Section II describes matrix embedding and minimizing embedding impact. In Section III, we study the linear programming. The polar codes, used to implement our scheme, are presented in Section IV. In Section V, we propose the scheme. Section VI shows the results obtained when the scheme is applied on images. Section VII concludes the paper.

7 citations

Journal ArticleDOI
TL;DR: A new classification method of spikes morphology based on the Support Vector Machines (SVM) is proposed, which is a supervised classification method using kernel functions to identify the different spikes morphologies in EEG signals.

7 citations

Proceedings ArticleDOI
01 Sep 2016
TL;DR: A small length polar, encoded for a MIMO (Multiple-Input Multiple-Output) systems with soft output MMSE-SIC (Minimum Mean Square Error-Successive Cancellation) detection, is applied to improve the coded performance while reducing the complexity.
Abstract: Polar codes are proven capacity-achieving and are shown to have equivalent or even better finite length performance than turbo/LDPC codes under some improved decoding algorithm over the Additive White Gaussian Noise (AWGN) channels. Polar coding is based on the so-called channel polarization phenomenon induced by a transform over the underlying binary-input channel. The channel polarization is found to be universal in many signal processing problems and is applied to the coded modulation schemes. In this paper, a small length polar, encoded for a MIMO (Multiple-Input Multiple-Output) systems with soft output MMSE-SIC (Minimum Mean Square Error-Successive Cancellation) detection, is applied to improve the coded performance while reducing the complexity. In order to prove this theory, we compare the proposed MMSE-SIC BER to Zero Forcing (ZF) and Maximum Likelihood (ML) by using 2*2 MIMO systems into Rayleigh channel with BPSK (Binary Phase-Shift Keying) modulation. Simulation results show that MMSE-SIC complexity is lower than the two others detections. We show that the performance of the proposed approach using polar code (128, 64) at 10−2 BER (Bit Error Rate) is around 3dB i.e. 0,66% compared to the optimal ML, while ZF performance is the worst.

5 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: This paper reviews the art of steganography with GANs according to the different strategies in data hiding, which are cover modification, cover selection, and cover synthesis.
Abstract: In the past few years, the Generative Adversarial Network (GAN), which proposed in 2014, has achieved great success. There have been increasing research achievements based on GAN in the field of computer vision and natural language processing. Image steganography is an information security technique aiming at hiding secret messages in common digital images for covert communication. Recently, research on image steganography has demonstrated great potential by introducing GAN and other neural network techniques. In this paper, we review the art of steganography with GANs according to the different strategies in data hiding, which are cover modification, cover selection, and cover synthesis. We discuss the characteristics of the three strategies of GAN-based steganography and analyze their evaluation metrics. Finally, some existing problems of image steganography with GAN are summarized and discussed. Potential future research topics are also forecasted.

47 citations

Proceedings ArticleDOI
01 Jul 2018
TL;DR: An epileptic EEG classification system based on IED detection that employs a Convolutional Neural Network for waveform-level classification and a Support Vector Machine for EEG-level Classification is proposed.
Abstract: Diagnosis of epilepsy based on visual inspection of electroencephalogram (EEG) abnormalities is an inefficient, time-consuming, and expert-centered process. Moreover, the diagnosis based on ictal epileptiform events is challenging as the ictal patterns are infrequent. Consequently, the development of an automated, fast, and reliable epileptic EEG diagnostic system is essential. The interictal epileptiform discharges (IEDs) are recurring patterns that are highly suggestive of epilepsy. In this paper, we propose an epileptic EEG classification system based on IED detection. The proposed system comprises of three modules: pre-processing, waveform-level classification, and EEG-level classification. We employ a Convolutional Neural Network (CNN) for waveform-level classification and a Support Vector Machine (SVM) for EEG-level classification. We evaluated the proposed system on a dataset of 156 EEGs recorded at Massachusetts General Hospital (MGH), Boston. The system achieved a mean 4-fold classification accuracy of 83.86% for classifying EEGs with and without IEDs.

45 citations

Journal ArticleDOI
TL;DR: This work verifies the availability of polar codes for the practical construction of steganography codes and provides a methodology for designing better steganographic codes based on any advance of polar coding/decoding.
Abstract: Steganography is an information hiding technique for covert communication. So far Syndrome-Trellis Codes (STC), a convolutional codes-based method, is the only near-optimal coding method, i.e., it can approach the rate-distortion bound of content-adaptive steganography in practice. However, as a secure communication application, steganography needs the diversity of coding methods. This paper proposes another and a better near-optimal steganographic coding method based on polar codes, using Successive Cancellation List (SCL) decoding algorithm to minimize additive distortion in steganography. Considering a steganographic channel as a binary symmetric channel, the proposed Steganographic Polar Codes (SPC) chooses parity-check matrix by setting embedding payload as the initial value of Arikan’s heuristic and computes decoding channel metric from the optimal modification probability of minimal distortion model. To overcome the inherent defect of polar codes only suiting for code length of a power of 2, we introduce three strategies to generalize SPC for arbitrary length. Experimental results validate the versatility of SPC to minimize arbitrary distortion. When compared with STC, the overall coding performance of SPC is more superior with low embedding complexity. This work verifies the availability of polar codes for the practical construction of steganographic codes and provides a methodology for designing better steganographic codes based on any advance of polar coding/decoding.

34 citations

Journal ArticleDOI
TL;DR: Zhang et al. as discussed by the authors developed a new deep learning approach, which employs a long short-term memory (LSTM) network architecture and an auxiliary classifier generative adversarial network (AC-GAN), to train on both expert-annotated and augmented spike events from intracranial electroencephalography (iEEG) recordings of epilepsy patients.
Abstract: Objective Automatic detection of interictal epileptiform discharges (IEDs, short as ``spikes'') from an epileptic brain can help predict seizure recurrence and support the diagnosis of epilepsy. Developing fast, reliable and robust detection methods for IEDs based on scalp or intracortical EEG may facilitate online seizure monitoring and closed-loop neurostimulation. Approach We developed a new deep learning approach, which employs a long short-term memory (LSTM) network architecture (``IEDnet'') and an auxiliary classifier generative adversarial network (AC-GAN), to train on both expert-annotated and augmented spike events from intracranial electroencephalography (iEEG) recordings of epilepsy patients. We validated our IEDnet with two real-world iEEG datasets, and compared IEDnet with the support vector machine (SVM) and random forest (RF) classifiers on their detection performances. Main results IEDnet achieved excellent cross-validated detection performances in terms of both sensitivity and specificity, and outperformed SVM and RF. Synthetic spike samples augmented by AC-GAN further improved the detection performance. In addition, the performance of IEDnet was robust with respect to the sampling frequency and noise. Furthermore, we also demonstrated the cross-institutional generalization ability of IEDnet while testing between two datasets. Significance IEDnet achieves excellent detection performances in identifying interictal spikes. AC-GAN can produce augmented iEEG samples to improve supervised deep learning.

20 citations

Journal ArticleDOI
01 Feb 2022-Sensors
TL;DR: A hypothesis to this end is posed that assumes the applicability of machine-learning solutions for IoT system static analysis, and a proposal of an intelligent framework concept for the static analysis of IoT systems is proposed.
Abstract: Ensuring security for modern IoT systems requires the use of complex methods to analyze their software. One of the most in-demand methods that has repeatedly been proven to be effective is static analysis. However, the progressive complication of the connections in IoT systems, the increase in their scale, and the heterogeneity of elements requires the automation and intellectualization of manual experts’ work. A hypothesis to this end is posed that assumes the applicability of machine-learning solutions for IoT system static analysis. A scheme of this research, which is aimed at confirming the hypothesis and reflecting the ontology of the study, is given. The main contributions to the work are as follows: systematization of static analysis stages for IoT systems and decisions of machine-learning problems in the form of formalized models; review of the entire subject area publications with analysis of the results; confirmation of the machine-learning instrumentaries applicability for each static analysis stage; and the proposal of an intelligent framework concept for the static analysis of IoT systems. The novelty of the results obtained is a consideration of the entire process of static analysis (from the beginning of IoT system research to the final delivery of the results), consideration of each stage from the entirely given set of machine-learning solutions perspective, as well as formalization of the stages and solutions in the form of “Form and Content” data transformations.

15 citations