arXiv subjects

Mounir Ghogho

Publications and source records attributed to Mounir Ghogho.

54 records · Page 3Linked to original sources

arXiv2022

When Infodemic Meets Epidemic: a Systematic Literature Review

Epidemics and outbreaks present arduous challenges requiring both individual and communal efforts. Social media offer significant amounts of data that can be leveraged for bio-surveillance. They also provide a platform to quickly and efficiently reach a sizeable percentage of the population, hence their potential impact on various aspects of epidemic mitigation. The general objective of this systematic literature review is to provide a methodical overview of the integration of social media in different epidemic-related contexts. Three research questions were conceptualized for this review, resulting in over 10000 publications collected in the first PRISMA stage, 129 of which were selected for inclusion. A thematic method-oriented synthesis was undertaken and identified 5 main themes related to social media enabled epidemic surveillance, misinformation management, and mental health. Findings uncover a need for more robust applications of the lessons learned from epidemic post-mortem documentation. A vast gap exists between retrospective analysis of epidemic management and result integration in prospective studies. Harnessing the full potential of social media in epidemic related tasks requires streamlining the results of epidemic forecasting, public opinion understanding and misinformation propagation, all while keeping abreast of potential mental health implications. Pro-active prevention has thus become vital for epidemic curtailment and containment.

cs.SI↗

arXiv2022

Supervised Contrastive Learning as Multi-Objective Optimization for Fine-Tuning Large Pre-trained Language Models

Recently, Supervised Contrastive Learning (SCL) has been shown to achieve excellent performance in most classification tasks. In SCL, a neural network is trained to optimize two objectives: pull an anchor and positive samples together in the embedding space, and push the anchor apart from the negatives. However, these two different objectives may conflict, requiring trade-offs between them during optimization. In this work, we formulate the SCL problem as a Multi-Objective Optimization problem for the fine-tuning phase of RoBERTa language model. Two methods are utilized to solve the optimization problem: (i) the linear scalarization (LS) method, which minimizes a weighted linear combination of pertask losses; and (ii) the Exact Pareto Optimal (EPO) method which finds the intersection of the Pareto front with a given preference vector. We evaluate our approach on several GLUE benchmark tasks, without using data augmentations, memory banks, or generating adversarial examples. The empirical results show that the proposed learning strategy significantly outperforms a strong competitive contrastive learning baseline

cs.CL↗

arXiv2022

Experimental Investigation of Variational Mode Decomposition and Deep Learning for Short-Term Multi-horizon Residential Electric Load Forecasting

With the booming growth of advanced digital technologies, it has become possible for users as well as distributors of energy to obtain detailed and timely information about the electricity consumption of households. These technologies can also be used to forecast the household's electricity consumption (a.k.a. the load). In this paper, we investigate the use of Variational Mode Decomposition and deep learning techniques to improve the accuracy of the load forecasting problem. Although this problem has been studied in the literature, selecting an appropriate decomposition level and a deep learning technique providing better forecasting performance have garnered comparatively less attention. This study bridges this gap by studying the effect of six decomposition levels and five distinct deep learning networks. The raw load profiles are first decomposed into intrinsic mode functions using the Variational Mode Decomposition in order to mitigate their non-stationary aspect. Then, day, hour, and past electricity consumption data are fed as a three-dimensional input sequence to a four-level Wavelet Decomposition Network model. Finally, the forecast sequences related to the different intrinsic mode functions are combined to form the aggregate forecast sequence. The proposed method was assessed using load profiles of five Moroccan households from the Moroccan buildings' electricity consumption dataset (MORED) and was benchmarked against state-of-the-art time-series models and a baseline persistence model.

eess.SP↗

arXiv2022

Age-of-Updates Optimization for UAV-assisted Networks

Unmanned aerial vehicles (UAVs) have been proposed as a promising technology to collect data from IoT devices and relay it to the network. In this work, we are interested in scenarios where the data is updated periodically, and the collected updates are time-sensitive. In particular, the data updates may lose their value if they are not collected and analyzed timely. To maximize the data freshness, we optimize a new performance metric, namely the Age-of-Updates (AoU). Our objective is to carefully schedule the UAVs hovering positions and the users' association so that the AoU is minimized. Unlike existing works where the association parameters are considered as binary variables, we assume that devices send their updates according to a probability distribution. As a consequence, instead of optimizing a deterministic objective function, the objective function is replaced by an expectation over the probability distribution. The expected AoU is therefore optimized under quality of service and energy constraints. The original problem being non-convex, we propose an equivalent convex optimization that we solve using an interior-point method. Our simulation results show the performance of the proposed approach against a binary association.

math.OC↗

arXiv2022

KG-NSF: Knowledge Graph Completion with a Negative-Sample-Free Approach

Knowledge Graph (KG) completion is an important task that greatly benefits knowledge discovery in many fields (e.g. biomedical research). In recent years, learning KG embeddings to perform this task has received considerable attention. Despite the success of KG embedding methods, they predominantly use negative sampling, resulting in increased computational complexity as well as biased predictions due to the closed world assumption. To overcome these limitations, we propose \textbf{KG-NSF}, a negative sampling-free framework for learning KG embeddings based on the cross-correlation matrices of embedding vectors. It is shown that the proposed method achieves comparable link prediction performance to negative sampling-based methods while converging much faster.

cs.LG↗

arXiv2021

Leveraging Open Threat Exchange (OTX) to Understand Spatio-Temporal Trends of Cyber Threats: Covid-19 Case Study

Understanding the properties exhibited by Spatial-temporal evolution of cyber attacks improve cyber threat intelligence. In addition, better understanding on threats patterns is a key feature for cyber threats prevention, detection, and management and for enhancing defenses. In this work, we study different aspects of emerging threats in the wild shared by 160,000 global participants form all industries. First, we perform an exploratory data analysis of the collected cyber threats. We investigate the most targeted countries, most common malwares and the distribution of attacks frequency by localisation. Second, we extract attacks' spreading patterns at country level. We model these behaviors using transition graphs decorated with probabilities of switching from a country to another. Finally, we analyse the extent to which cyber threats have been affected by the COVID-19 outbreak and sanitary measures imposed by governments to prevent the virus from spreading.

cs.CR↗

arXiv2020

GraphCL: Contrastive Self-Supervised Learning of Graph Representations

We propose Graph Contrastive Learning (GraphCL), a general framework for learning node representations in a self supervised manner. GraphCL learns node embeddings by maximizing the similarity between the representations of two randomly perturbed versions of the intrinsic features and link structure of the same node's local subgraph. We use graph neural networks to produce two representations of the same node and leverage a contrastive learning loss to maximize agreement between them. In both transductive and inductive learning setups, we demonstrate that our approach significantly outperforms the state-of-the-art in unsupervised learning on a number of node classification benchmarks.

cs.LG↗

arXiv2020

NoSQL Databases: Yearning for Disambiguation

The demanding requirements of the new Big Data intensive era raised the need for flexible storage systems capable of handling huge volumes of unstructured data and of tackling the challenges that traditional databases were facing. NoSQL Databases, in their heterogeneity, are a powerful and diverse set of databases tailored to specific industrial and business needs. However, the lack of theoretical background creates a lack of consensus even among experts about many NoSQL concepts, leading to ambiguity and confusion. In this paper, we present a survey of NoSQL databases and their classification by data model type. We also conduct a benchmark in order to compare different NoSQL databases and distinguish their characteristics. Additionally, we present the major areas of ambiguity and confusion around NoSQL databases and their related concepts, and attempt to disambiguate them.

cs.DB↗

arXiv2019

Exploratory Data Analysis of a Network Telescope Traffic and Prediction of Port Probing Rates

Understanding the properties exhibited by large scale network probing traffic would improve cyber threat intelligence. In addition, the prediction of probing rates is a key feature for security practitioners in their endeavors for making better operational decisions and for enhancing their defense strategy skills. In this work, we study different aspects of the traffic captured by a /20 network telescope. First, we perform an exploratory data analysis of the collected probing activities. The investigation includes probing rates at the port level, services interesting top network probers and the distribution of probing rates by geolocation. Second, we extract the network probers exploration patterns. We model these behaviors using transition graphs decorated with probabilities of switching from a port to another. Finally, we assess the capacity of Non-stationary Autoregressive and Vector Autoregressive models in predicting port probing rates as a first step towards using more robust models for better forecasting performance.

cs.CR↗

arXiv2019

Fusion Rules for Distributed Detection in Clustered Wireless Sensor Networks with Imperfect Channels

In this paper we investigate fusion rules for distributed detection in large random clustered-wireless sensor networks (WSNs) with a three-tier hierarchy; the sensor nodes (SNs), the cluster heads (CHs) and the fusion center (FC). The CHs collect the SNs' local decisions and relay them to the FC that then fuses them to reach the ultimate decision. The SN-CH and the CH-FC channels suffer from additive white Gaussian noise (AWGN). In this context, we derive the optimal log-likelihood ratio (LLR) fusion rule, which turns out to be intractable. So, we develop a sub-optimal linear fusion rule (LFR) that weighs the cluster's data according to both its local detection performance and the quality of the communication channels. In order to implement it, we propose an approximate maximum likelihood based LFR (LFR-aML), which estimates the required parameters for the LFR. We also derive Gaussian-tail upper bounds for the detection and false alarms probabilities for the LFR. Furthermore, an optimal CH transmission power allocation strategy is developed by solving the Karush-Kuhn-Tucker (KKT) conditions for the related optimization problem. Extensive simulations show that the LFR attains a detection performance near to that of the optimal LLR and confirms the validity of the proposed upper bounds. Moreover, when compared to equal power allocation, simulations show that our proposed power allocation strategy achieves a significant power saving at the expense of a small reduction in the detection performance.

eess.SP↗

arXiv2018

Deep Learning for Inferring the Surface Solar Irradiance from Sky Imagery

We present a novel approach to perform ground-based estimation and prediction of the surface solar irradiance with the view to predicting photovoltaic energy production. We propose the use of mini-batch k-means clustering to extract features, referred to as per cluster number of pixels (PCNP), from sky images taken by a low-cost fish eye camera. These features are first used to classify the sky as clear or cloudy using a single hidden layer neural network; the classification accuracy achieves 99.7%. If the sky is classified as cloudy, we propose to use a deep neural network having as input features the PCNP to predict intra-hour variability of the solar irradiance. Toward this objective, in this paper, we focus on estimating the deep neural network model relating the PCNP features and the solar irradiance, which is an important step before performing the prediction task. The proposed deep learning-based estimation approach is shown to have an accuracy of 95%.

cs.CV↗

arXiv2018

Energy balancing for robotic aided clustered wireless sensor networks using mobility diversity algorithms

We consider the problem of energy balancing in a clustered wireless sensor network (WSN) deployed randomly in a large field and aided by a mobile robot (MR). The sensor nodes (SNs) are tasked to monitor a region of interest (ROI) and report their test statistics to the cluster heads (CHs), which subsequently report to the fusion center (FC) over a wireless fading channel. To maximize the lifetime of the WSN, the MR is deployed to act as an adaptive relay between a subset of the CHs and the FC. To achieve this we develop a multiple-link mobility diversity algorithm (MDA) executed by the MR that will allow to compensate simultaneously for the small-scale fading at the established wireless links (i.e., the MR-to-FC as well as various CH-to-MR communication links). Simulation results show that the proposed MR aided technique is able to significantly reduce the transmission power required and thus extend the operational lifetime of the WSN. We also show how the effect of small-scale fading at various wireless links is mitigated by using the proposed multiple-link MDA executed by a MR equipped with a single antenna.

cs.DC↗

arXiv2018

Robotic Mobility Diversity Algorithm with Continuous Search Space

Small scale fading makes the wireless channel gain vary significantly over small distances and in the context of classical communication systems it can be detrimental to performance. But in the context of mobile robot (MR) wireless communications, we can take advantage of the fading using a mobility diversity algorithm (MDA) to deliberately locate the MR at a point where the channel gain is high. There are two classes of MDAs. In the first class, the MR explores various points, stops at each one to collect channel measurements and then locates the best position to establish communications. In the second class the MR moves, without stopping, along a continuous path while collecting channel measurements and then stops at the end of the path. It determines the best point to establish communications. Until now, the shape of the continuous path for such MDAs has been arbitrarily selected and currently there is no method to optimize it. In this paper, we propose a method to optimize such a path. Simulation results show that such optimized paths provide the MDAs with an increased performance, enabling them to experience higher channel gains while using less mechanical energy for the MR motion.

cs.RO↗

arXiv2017

Information-Centric Offloading in Cellular Networks with Coordinated Device-to-Device Communication

In this paper, we develop a comprehensive analytical framework for cache enabled cellular networks overlaid with coordinated device-to-device (D2D) communication. We follow an approach similar to LTE Direct, where the base station (BS) is responsible for establishing D2D links. We consider that an arbitrary requesting user is offloaded to D2D mode to communicate with one of its 'k' closest D2D helpers within the macrocell subject to content availability and helper selection scheme. We consider two different D2D helper selection schemes: 1) uniform selection (US), where the D2D helper is selected uniformly and 2) nearest selection (NS), where the nearest helper possessing the content is selected. Employing tools from stochastic geometry, we model the locations of BSs and D2D helpers using independent homogeneous Poisson point processes (HPPPs). We characterize the D2D mode probability of an arbitrary user for both the NS and US schemes. The distribution of the distance between an arbitrary user and its ith neighboring D2D helper within the macrocell is derived using disk approximation for the Voronoi cell, which is shown to be reasonably accurate. We fully characterize the overall coverage probability and the average ergodic rate of an arbitrary user requesting a particular content. We show that significant performance gains can be achieved compared to conventional cellular communication under both the NS and US schemes when popular contents are requested and NS scheme always outperforms the US scheme. Our analysis reveals an interesting trade off between the performance metrics and the number of candidate D2D helpers 'k'. We conclude that enhancing D2D opportunities for the users does not always result in better performance and the network parameters have to be carefully tuned to harness maximum gains.

cs.NI↗

arXiv2016

Entropy and Channel Capacity under Optimum Power and Rate Adaptation over Generalized Fading Conditions

Accurate fading characterization and channel capacity determination are of paramount importance in both conventional and emerging communication systems. The present work addresses the nonlinearity of the propagation medium and its effects on the channel capacity. Such fading conditions are first characterized using information theoretic measures, namely, Shannon entropy, cross entropy and relative entropy. The corresponding effects on the channel capacity with and without power adaptation are then analyzed. Closed-form expressions are derived and validated through comparisons with respective results from computer simulations. It is shown that the effects of fading nonlinearities are significantly larger than those of fading parameters such as the scattered-wave power ratio, and the correlation coefficient between the in-phase and quadrature components in each cluster of multipath components.

cs.IT↗

arXiv2016

A Distributed Satisfactory Content Delivery Scheme for QoS Provisioning in Delay Tolerant Networks

We deal in this paper with the content forwarding problem in Delay Tolerant Networks (DTNs). We first formulate the content delivery interaction as a non-cooperative satisfaction game. On one hand, the source node seeks to ensure a delivery probability above some given threshold. On the other hand, the relay nodes seek to maximize their own payoffs. The source node offers a reward (virtual coins) to the relay which caches and forwards the file to the final destination. Each relay faces the dilemma of accepting/rejecting to cache the source's file. Cooperation incurs energy cost due to caching, carrying and forwarding the source's file. Yet, when a relay accepts to cooperate, it may receive some reward if it succeeds to be the first relay to forward the content to the destination. Otherwise, the relay may receive some penalty in the form of a constant regret; the latter parameter is introduced to make incentive for cooperation. Next, we introduce the concept of Satisfaction Equilibrium (SE) as a solution concept to the induced game. Now, the source node is solely interested in reaching a file delivery probability greater than some given threshold, while the relays behave rationally to maximize their respective payoffs. Full characterizations of the SEs for both pure and mixed strategies are derived. Furthermore, we propose two learning algorithms allowing the players (source/relays) to reach the SE strategies. Finally, extensive numerical investigations and some learning simulations are carried out to illustrate the behaviour of the interacting nodes.

cs.GT↗

arXiv2015

Distributed Optimal Quantization and Power Allocation for Sensor Detection Via Consensus

We address the optimal transmit power allocation problem (from the sensor nodes (SNs) to the fusion center (FC)) for the decentralized detection of an unknown deterministic spatially uncorrelated signal which is being observed by a distributed wireless sensor network. We propose a novel fully distributed algorithm, in order to calculate the optimal transmit power allocation for each sensor node (SN) and the optimal number of quantization bits for the test statistic in order to match the channel capacity. The SNs send their quantized information over orthogonal uncorrelated channels to the FC which linearly combines them and makes a final decision. What makes this scheme attractive is that the SNs share with their neighbours just their individual transmit powers at the current states. As a result, the SN processing complexity is further reduced.

eess.SY↗

arXiv2015

Quantized Fusion Rules for Energy-Based Distributed Detection in Wireless Sensor Networks

We consider the problem of soft decision fusion in a bandwidth-constrained wireless sensor network (WSN). The WSN is tasked with the detection of an intruder transmitting an unknown signal over a fading channel. A binary hypothesis testing is performed using the soft decision of the sensor nodes (SNs). Using the likelihood ratio test, the optimal soft fusion rule at the fusion center (FC) has been shown to be the weighted distance from the soft decision mean under the null hypothesis. But as the optimal rule requires a-priori knowledge that is difficult to attain in practice, suboptimal fusion rules are proposed that are realizable in practice. We show how the effect of quantizing the test statistic can be mitigated by increasing the number of SN samples, i.e., bandwidth can be traded off against increased latency. The optimal power and bit allocation for the WSN is also derived. Simulation results show that SNs with good channels are allocated more bits, while SNs with poor channels are censored.

cs.IT↗