Papers by Mourad Oussalah
Research Square (Research Square), Jul 27, 2021
Community detection is one of the basic problems in social network analysis. Community detection ... more Community detection is one of the basic problems in social network analysis. Community detection on an attributed social networks aims to discover communities that have not only adhesive structure but also homogeneous node properties. Although community detection has been extensively studied, attributed community detection of large social networks with a large number of attributes remains a vital challenge. To address this challenge, a novel attributed community detection method through an integration of feature weighting with node centrality techniques is developed in this paper. The developed method includes two main phases: (1) Weight Matrix Calculation, (2) Label Propagation Algorithm-based Attributed Community Detection. The aim of the first phase is to calculate the weight between two linked nodes using structural and attribute similarities, while, in the second phase, an improved label propagation algorithm-based community detection method in attributed social network is proposed. The purpose of the second phase is to detect different communities by employing the calculated weight matrix and node popularity. After implementing the proposed method, its performance is compared with several other state of the art methods using some benchmarked real-world datasets. The results indicate that the developed method outperforms several other state of the art methods and ascertain the effectiveness of the developed method for attributed community detection.
Research Square (Research Square), May 24, 2022
This study advocates a multi-criteria approach to improve the stream ow predictions in a data-sca... more This study advocates a multi-criteria approach to improve the stream ow predictions in a data-scarce catchment of Chennai metropolitan city of India using the Soil Water and Assessment Tool (SWAT). The remotely sensed evapotranspiration (ET) data, groundwater recharge estimation and parameter regionalization were used to improve model prediction. Dynamic change of Land Use and Land Cover (LULC) was accounted for along with multi-parameter calibration for reducing the uncertainty in model parameters. The results revealed an improved stream ow prediction accuracy by 10%, especially in the prediction of medium and high ows with the Nash-Sutcliffe e ciency of 0.60. The enhanced parameters were regionalized to ungauged sub-basins and validated using a measured ow event downstream of regionalization with 15% prediction uncertainty. This semi-arid catchment is dominated by ET (58%) and runoff (27%) in the region's hydrology. The nding of this study can be applied to improve the hydrological modeling and predictions in data-scarce regions.
The bag-of-words (BoW) model is one of the most popular representation methods for image classifi... more The bag-of-words (BoW) model is one of the most popular representation methods for image classification. However, the lack of spatial information, change of illumination, and inter-class similarity among scene categories impair its performance in the remote-sensing domain. To alleviate these issues, this paper proposes to explore the spatial dependencies between different image regions and introduce a neighborhoodbased collaborative learning (NBCL) for remote-sensing scene classification. Particularly, our proposed method employs multilevel features learning based on small, medium, and large neighborhood regions to enhance the discriminative power of image representation. To achieve this, image patches are selected through a fixed-size sliding window where each image is represented by four independent image region sequences. Apart from multilevel learning, we explicitly impose Gaussian pyramids to magnify the visual information of the scene images and optimize their position and scale parameters locally. Motivated by this, a local descriptor is exploited to extract multilevel and multiscale features that we represent in terms of codewords histogram by performing k-means clustering. Finally, a simple fusion strategy is proposed to balance the contribution of these features, and the fused features are incorporated into a Bidirectional Long Short-Term Memory (BiLSTM) network for constructing the final representation for classification. Experimental results on NWPU-RESISC45, AID, UC-Merced, and WHU-RS datasets demonstrate that the proposed approach not only surpasses the conventional bag-of-words approaches but also yields significantly higher classification performance than the existing stateof-the-art deep learning methods used nowadays. Index Terms-Scene classification, Bag-of-words (BoW) model, Gaussian pyramids, Neighborhood-based learning, Bidirectional Long Short-Term Memory (LSTM). I. INTRODUCTION R EMOTE sensing has received unprecedented attention due to its role in mapping land cover, geographic image retrieval, natural hazards detection, and monitoring changes in land cover. The currently available remote sensing satellites and instruments (e.g., IKONOS, unmanned aerial vehicles (UAVs), synthetic aperture radar, etc.,) for observing earth not only provide high-resolution scene images but also give us an opportunity to study the spatial information with a fine-grained
arXiv (Cornell University), Aug 28, 2022
Without deploying face anti-spoofing countermeasures, face recognition systems can be spoofed by ... more Without deploying face anti-spoofing countermeasures, face recognition systems can be spoofed by presenting a printed photo, a video, or a silicon mask of a genuine user. Thus, face presentation attack detection (PAD) plays a vital role in providing secure facial access to digital devices. Most existing video-based PAD countermeasures lack the ability to cope with long-range temporal variations in videos. Moreover, the key-frame sampling prior to the feature extraction step has not been widely studied in the face anti-spoofing domain. To mitigate these issues, this paper provides a data sampling approach by proposing a video processing scheme that models the long-range temporal variations based on Gaussian Weighting Function. Specifically, the proposed scheme encodes the consecutive t frames of video sequences into a single RGB image based on a Gaussian-weighted summation of the t frames. Using simply the data sampling scheme alone, we demonstrate that state-of-the-art performance can be achieved without any bells and whistles in both intra-database and inter-database testing scenarios for the three public benchmark datasets; namely, Replay-Attack, MSU-MFSD, and CASIA-FASD. In particular, the proposed scheme provides a much lower error (from 15.2% to 6.7% on CASIA-FASD and 5.9% to 4.9% on Replay-Attack) compared to baselines in cross-database scenarios.
ArXiv, 2018
This paper describes work carried out on a model for the evolution of graph classes in complex ob... more This paper describes work carried out on a model for the evolution of graph classes in complex objects. By defining evolution rules and propagation strategies on graph classes, we aim to define a user-definable means to manage data evolution model which tackles the complex nature of the classes managed, using the concepts defined in object systems. So, depending on their needs and on those of the targeted application, designers can choose the evolution mechanism they consider to suit them best. They can either create new evolutions or reuse predefined ones to respond to a given need.
Proceedings of the 7th International Conference on Evaluation of Novel Approaches to Software Engineering, 2012
This paper presents a part of an approach for software processes reuse based on software architec... more This paper presents a part of an approach for software processes reuse based on software architectures. This solution is proposed after the study of existing work on software process reuse field. Our study focuses on approaches for reusing based on software architectures and domain ontology. AoSP (Architecture oriented Software Process) approach exploits the progress of two research fields that promote reusing for the Software process reusing: Ontology and software architectures. This article details how the software process architectures are described and discusses the software process ontology conceptualization and instantiation.
Intelligent Automation and Soft Computing, 2002
Abstract Linear regression has been used for a long time in various applications, with linear lea... more Abstract Linear regression has been used for a long time in various applications, with linear least squares as the best known tool. It is also known in probability / statistics theory that this method is particularly sensitive to outliers. Hence, statisticians introduced robust statistical tools that allow robustness and efficiency to overcome the effects of outlier. On the other hand, Tanaka and Hayashi provide basic ideas for fuzzy linear regression when data are rather ill-known and given in terms of fuzzy sets, even if the robustness of the method in the presence of outliers still is poor and over-estimated. This paper attempts to provide a hybrid approach by combining both robust statistical tools and the fuzzy approach. Particularly, the least median of squares estimator and the least trimmed squares estimator have been considered. The method is then tested in a robotics application where aforce-controlled contact situation is assessed.
Social Science Research Network, 2023
This paper presents experimental data concerning combustion characteristics of full-scale biomass... more This paper presents experimental data concerning combustion characteristics of full-scale biomass-fired bubbling fluidized bed (BFB) steam boiler with a thermal output of 31 MW. The purpose of the experimental measurements is to show how the values of selected combustion parameters vary in reality depending on measurement position. Experimentation involves specifically a determination of combustion gas temperature and concentration of gas species i.e. O 2 , CO 2 , CO and NO X at different positions in the furnace and the flue gas trains. Character of results from the furnace indicates the intermediate stage of thermochemical reactions. Increased levels of CO close to the wall have been found, this may be indicating reducing atmosphere and thereby increased corrosion risk. Results from flue gas trains demonstrate that behavior there is related to the fluid dynamics and heat transfer, the temperature is too low for further combustion reactions. Results show great variations among measured values of all measurands depending on a distance along the line from the wall to the center of the boiler. The measurements from permanently installed fixed sensors are not giving value representing average conditions, but overall profiles can be correlated to online measurements from fixed sensors.
The Panama Papers is a collection of 11.5 million leaked records that contain information for mor... more The Panama Papers is a collection of 11.5 million leaked records that contain information for more than 214,488 offshore entities. This collection is growing rapidly as more leaked records become available online. In this paper, we present a work in progress on a web browser plugin that detects company names from the Panama Papers and alerts the user by means of unobtrusive visual cues. We matched a random sample of company names from the Public Works and Government Services Canada registry against the Panama Papers using three different string matching techniques. Monge-Elkan is found to provide the best matching results but at increased computational cost. Levenshtein-based approach is found to provide the best tradeoff between matching and computational cost, while Jacquard index like approach is found to be less sensitive to slight textual change.
World Automation Congress, Jun 1, 2000
arXiv (Cornell University), Jul 6, 2023
Face presentation attacks (PA), also known as spoofing attacks, pose a substantial threat to biom... more Face presentation attacks (PA), also known as spoofing attacks, pose a substantial threat to biometric systems that rely on facial recognition systems, such as access control systems, mobile payments, and identity verification systems. To mitigate the spoofing risk, several video-based methods have been presented in the literature that analyze facial motion in successive video frames. However, estimating the motion between adjacent frames is a challenging task and requires high computational cost. In this paper, we rephrase the face anti-spoofing task as a motion prediction problem and introduce a deep ensemble learning model with a frame skipping mechanism. In particular, the proposed frame skipping adopts a uniform sampling approach by dividing the original video into video clips of fixed size. By doing so, every nth frame of the clip is selected to ensure that the temporal patterns can easily be perceived during the training of three different recurrent neural networks (RNNs). Motivated by the performance of individual RNNs, a meta-model is developed to improve the overall detection performance by combining the prediction of individual RNNs. Extensive experiments were performed on four datasets, and state-of-the-art performance is reported on MSU-MFSD (3.12%), Replay-Attack (11.19%), and OULU-NPU (12.23%) databases by using half total error rates (HTERs) in the most challenging cross-dataset testing scenario.
Scandinavian Journal of Medicine & Science in Sports, Feb 8, 2023
Introduction: Data evaluating mortality benefit from replacing sedentary time with physical activ... more Introduction: Data evaluating mortality benefit from replacing sedentary time with physical activity are sparse. We explored reallocating time spent in sedentary behavior to physical activity of different intensities in relation to mortality risk.
Uploads
Papers by Mourad Oussalah