Being sarcastic is to say something and to mean something else. Detecting sarcasm is key for social media analysis to differentiate between the two opposite polarities that an utterance may convey. Different techniques for detecting sarcasm are varying from rule-based models to Machine Learning and Deep Learning models. However, researchers tend to leverage Deep Learning in detecting sarcasm recently. On the other hand, the Arabic language has not witnessed much improvement in this research area. Bridging the gap in sarcasm detection of the Arabic language is the target behind this work. In

The radical change in technology and high customer expectations and demand are pushing the service desk to provide a competent service for the customers. And this service should be faster, more flexible and gives a more accurate response and high user experience. Replacing the human call agent’s activities with a cognitive agent could improve the user experience by providing a faster response to customer’s requests, removing the human errors and giving 24/7 support with less operational cost. The cognitive agent has the potential to scale personalized and tailored interactions. And this will

This paper deals with solving large instances of the Linear Sum Assignment Problems (LSAPs) under realtime constraints, using Graphical Processing Units (GPUs). The motivating scenario is an industrial application for P2P live streaming that is moderated by a central tracker that is periodically solving LSAP instances to optimize the connectivity of thousands of peers. However, our findings are generic enough to be applied in other contexts. Our main contribution is a parallel version of a heuristic algorithm called Deep Greedy Switching (DGS) on GPUs using the CUDA programming language. DGS

Federated learning (FL) has recently been proposed as an emerging paradigm to build machine learning models using distributed training datasets that are locally stored and maintained on different devices in 5G networks while providing privacy preservation for participants. In FL, the central aggregator accumulates local updates uploaded by participants to update a global model. However, there are two critical security threats: poisoning and membership inference attacks. These attacks may be carried out by malicious or unreliable participants, resulting in the construction failure of global

In order to solve combinatorial optimization problem are used mainly hybrid heuristics. Inspired from nature, both genetic and ant colony algorithms could be used in a hybrid model by using their benefits. The paper introduces a new model of Ant Colony Optimization using multiple colonies with different level of sensitivity to the ant’s pheromone. The colonies react different to the changing environment, based on their level of sensitivity and thus the exploration of the solution space is extended. Several discussion follows about the fuzziness degree of sensitivity and its influence on the

The automatic fitting of spiking neuron models to experimental data is a challenging problem. The integrate and fire model and Hodgkin–Huxley (HH) models represent the two complexity extremes of spiking neural models. Between these two extremes lies two and three differential-equation-based models. In this work, we investigate the problem of parameter estimation of two simple neuron models with a sharp reset in order to fit the spike timing of electro-physiological recordings based on two problem formulations. Five optimization algorithms are investigated; three of them have not been used to

The suffix array is an indexing data structure used in a wide range of applications in Bioinformatics. Biological DNA sequences are available to download from public servers in the form of compressed files, where the popular lossless compression program gzip [1] is employed. The straightforward method to construct the suffix array for this data involves decompressing the sequence file, storing it on disk, and then calling a suffix array construction program to build the suffix array. This scenario, albeit feasible, requires disk access and throws away valuable information in the compressed

Background: Due to recent progress in genome sequencing, more and more data for phylogenetic reconstruction based on rearrangement distances between genomes become available. However, this phylogenetic reconstruction is a very challenging task. For the most simple distance measures (the breakpoint distance and the reversal distance), the problem is NP-hard even if one considers only three genomes. Results: In this paper, we present a new heuristic algorithm that directly constructs a phylogenetic tree w.r.t. the weighted reversal and transposition distance. Experimental results on previously

Modeling and simulation are becoming extensively used in embedded and Real-Time Systems (RTSs) development throughout the development life-cycle, from the system-level design space exploration to the fine grained time analysis and evaluation of the system and even its components performance. At the core of these systems lies the processor which has been also the center of attention for most of the modeling and simulation efforts related to RTS simulation. Although the temporal accuracy of such models and simulators is of critical importance for Real-Time (RT) applications, it is not yet mature