Abderrahim El Qadi

Scheduling meeting solved by neural network and Min-conflict heuristic

The Meeting scheduling problem (MSP) is an important vehicle of communication in business, factories and team works. MSP requires a careful balance between the individual personal preferences and the organization. In this paper we propose a new approach to solve meeting scheduling problem. The proposed network combines the characteristics of neural networks and conflicts minimization approach. This approach is divided into three steps: The first concerns formulating a meeting scheduling problem as a CSP problem, then we reformulate this CSP as a quadratic problem under linear constraint(QP). The second step applies the continuous Hopfield network to solve the QP. The later step involves the Min-conflict heuristic to improve the solution given by the second step. The performance of the proposed approach with direct approach which uses CHN alone are compared over some generated meeting instances.

Bag-of-features for image memorability evaluation

Image memorability represents the degree to which images are remembered or forgotten after a period of time. Studying image memorability in computer vision is the task of finding special characteristics in memorable images, in order to develop a representative model of this type of images. Several approaches have been realised to examine features that can affect image memorability. In this study, the authors use bag-of-features as another kind of visual feature descriptor to assess image memorability. The authors’ method based on bag-of-visual-words (BoVWs) technique involves four main steps. First, the authors extract local image features from regions/points of interest which are automatically detected. Then, they encode these local features by mapping them to a created visual vocabulary. Later, the authors apply features pooling and normalisation techniques to obtain image BoVW representation. Finally, the authors use this representation to examine image memorability as a problem of classification. They present different implementation choices for each step and compare reached results. The authors’ method performs best significant results in comparison with other approaches found in literature.

A new approach to build a geographical taxonomy of adjacency automatically using the latent semantic indexing method

In this paper, we introduce an approach for constructing a geographical taxonomy of adjacency for a country, to be used in reformulating spatial queries. The proposed approach uses the best-ranked documents retrieved by the search engine while submitting the spatial entity composed of a spatial relationship and a noun of a city A. Then, apply to it the Latent Semantic Indexing method to found the nearest cities Bi to A, and proceed to a step of validation of each link by verifying if A is also found in the results of the cities Bi. In our experiments, we constructed a geographical taxonomy of adjacency for Morocco. We varied the spatial relationship used in the step of documents retrieving to compare the results of the different spatial relationships, and we used google web services as a search engine to compare the results returned in every case. Then we used the constructed taxonomy in geographical query reformulation. We have used the Un-interpolated Average Precision (UAP) to compare the returned documents before and after reformulation. According to our results, we note that reformulating geographical queries based on our built taxonomy improves widely the precision of the queries.

Context-Based Query Expansion Method for Short Queries Using Latent Semantic Analyses

Short queries are the key difficulty in information retrieval (IR). A plenty of query expansion techniques has been proposed to solve this problem. In this paper, we propose three different models for query suggestion using the cosine similarity (CS), the Language Models (LM) or their fusion. The expansion terms are selected using the Latent Semantic Analyses method based on the result of the three query suggestion methods. The approaches proposed improve the precision of the user query by adding additional context to it. Experimental results show that expanding short queries by our approaches improves the effectiveness of the IR system by 48,1 % using the CS based model, 19,2 % using the LM model, and 13,5 % using the fusion model.

CHN and Min-Conflict Heuristic to Solve Scheduling Meeting Problems

Meetings are important for teem works, However, scheduling a meeting that involves persons with different preferences and engagements remains a difficult task. This paper proposes a new hybrid approach to solve meeting scheduling problem (MSP). The proposed network combines the characteristics of neural networks and minimizing conflicts approach. Her the MSP is considerate as Constraint Satisfaction Problem, then we apply Continuous Hopfield Neural Netwok (CHN) and Conflicts Minimization Heuristics to solve a quadratic reformulation of the CSP-MSP model in other words the Min-Conflict heuristic will improve the given CHN solution. So, the performance of the network is compared with the existing scheduling algorithms under various experimental conditions.

Neural Network and Local Search to Solve Binary CSP

With the rapid growth of communications via the Internet, the need for an effective firewall system which has not badly affect the overall network performances has been increased. In this paper, a Field Programmable Gate Array (FPGA) -based firewall system with high performance has been implemented using Network FPGA (NetFPGA) with Xilinx Kintex-7 XC7K325T FPGA. Based on NetFPGA reference router project, a NetFPGA-based firewall system was implemented. The hardware module performs rule matching operation using content addressable memory (CAM) for higher speed data processing. To evaluate system performance, throughput, latency, and memory utilization were measured for different cases using different tools, also the number of rules that an incoming packet is subjected to was varied to get more readings using both software and hardware features. The results showed that the designed firewall system provides better performance than traditional firewalls. System throughput was doubled times of the one with Linux-Iptables firewalls.

Rules of photography for image memorability analysis

Photos are becoming more spread with digital age. Cameras, smart phones and Internet provide large dataset of images available to a wide audience. Assessing memorability of these photos is becoming a challenging task. Besides, finding the best representative model for memorable images will enable memorability prediction. The authors develop a new approach-based rule of photography to evaluate image memorability. In fact, they use three groups of features: image basic features, layout features and image composition features. In addition, they introduce a diversified panel of classifiers based on some data mining techniques used for memorability analysis. They experiment their proposed approach and they compare its results to the state-of-the-art approaches dealing with image memorability. Their approach experiments results prove that models used in their approach are encouraging predictors for image memorability.

A Comparative Study of Software Defined Networks Controllers

SDN revolutionized networks by decoupling the control plane from the data plane and by introducing programmability and flexibility into the network. With this new paradigm, a new network entity appeared to be the most important in the SDN architecture since it allows setting the policies of the network this entity is the Network Operating System also called controller. In this paper we compare and evaluate new and different controllers to select the most fitting in term of performance.

Visual content learning for visualizations memorability classification

Images on the Internet and in multimedia systems are rising successively. There are different research works on visual information and automatic analysis of images. Image memorability is a new task in computer vision. Actually, the human brain processes simultaneously millions of images and other information from multiple sources. Among these various images and information some of them are more memorable than others. Studying images memorability is an image processing task, which tends to define and establish the characteristics of memorable images. These characteristics are used to create a representative model for predicting images memorability. In this paper, we present an approach for visualizations memorability analysis and evaluation. We use a set of features that are automatically extracted from visualizations. Then, we employ different classification methods to explore these features and visualizations scores.

Evaluation de l'analyse sémantique latente et du modèle vectoriel standard appliqués à la langue arabe

In the objective of a possible performance improvement of the Arabic information retrieval systems, we propose to introduce the latent semantic analysis method to cure the problems arising from the vector- space model. The present contribution describes how linguistic processing and weighting schemes could improve the LSA method, and the comparison between the vector-space model and LSA approach, which aim to reduce the index term number of an Arabic corpus specialized in the environment field. The results of our experiments show clearly a positive influence of the linguistic processing and weighting schemes, and LSA improvement compared to the vector-space model.