Mohammed Sadgal

An Agent Based Traffic Regulation System for the Roadside Air Quality Control

This paper describes an on-road air quality monitoring and control approach by proposing an agent-based system for modeling the urban road network infrastructure, establishing the real-time and predicted air pollution indexes in different road segments and generating recommendations and regulation proposals for road users. This can help by reducing vehicle emissions in the most polluted road sections, optimizing the pollution levels while maximizing the vehicle flow. For this, we use data sets gathered from a set of air quality monitoring stations, embedded low-cost e-participatory pollution sensors, contextual data, and the road network available data. These data are used in the air quality indexes calculation and then the generation of a dynamic traffic network. This network is represented by a weighted graph in which the edges weights evolve according to the pollution indexes. In this paper, we propose to combine the benefits of agent technology with both machine learning and big data tools. An artificial neural networks model and the Dijkstra algorithm are used for air quality prediction and the least polluted path finding in the road network. All data processing tasks are performed over a Hadoop-based framework: HBase and MapReduce.

Integration of non-functional requirements in a service-oriented and model-driven approach

To face the problems of scalability and complexity of information systems (IS), conceptual models must be able to understand the requirements needed for its development. Beyond the consideration of functional requirements, other more critical requirements have emerged: Non-functional requirements to reflect complex situations that occur in the real world. In this work, we introduce an approach for the integration of non-functional requirements in the conception of information systems. The proposed approach is an approach based on service-oriented architectures (SOA), model driven architecture (MDA), and automatic transformations of models.

Object detection based on HOG features: Faces and dual-eyes augmented reality

Histogram of oriented gradients have been widely used for classification, face detection and recognition. In this paper we present a virtual eye glasses try-on system based on augmented reality and HOG features for face and eyes detection. Machine learning algorithms are used for real time eyes tracking, the resulting face and eyes positions are continuously utilized to overlay the glasses image over the face. The system helps evaluating glasses before trying them in the store and makes possible the design of its own style.

Modeling Multi-agent System of Management Road Transport: Tasks Planning and Negotiation

The Management Systems of Road Transport (MSRT) must include responsibility for planning the routes and schedules of vehicles fleet involved in the road haulage, distribution and logistics. It must ensure that all operations are carried out in maximum safety, environmental controls and traffic congestion, driver hours, customs requirements, and minimum cost. The complexity of the real-time scheduling of transport orders which comes in an asynchronous and dynamic way makes the MSRT especially suitable for using techniques from Distributed AI. To manage this complex field addressed under a high degree of dynamism and uncertainty which is characterized by an inherent distribution of knowledge and control, we propose in this work, a modeling of an MSRT by a multi-agents system, the modeling of the agents and their interaction by AUML language and we deal with the cooperation during tasks planning in the MSRT.

Aerial image processing and object recognition

The processing of images representing natural scenes requires substantial elaboration at all levels: preprocessing, segmentation, recognition, and interpretation. These steps unmistakably influence the result quality of a vision system, so it must be endowed with some capabilities. We present here the vision problem in terms of internal organization and information management. The object is represented on a scale of categories and the task of the recognition algorithms is to find the most detailed category according to information extracted from the image. All tasks operate on one level. On this principle, we propose a model for the internal representation of a vision system, which tries to generalize the recognition of objects using categorization and cooperation.

Towards a pervasive information system for patient triage and referral in emergency departments

Every day, many people come to emergency departments; the orientation and placement of these patients in a waiting list according to the seriousness of their health conditions is an important task that requires a lot of skilled human resources and time. In addition, some people abuse the system by seeking care for minor problems, which significantly increases the emergency department overcrowding. To facilitate and accelerate the process of triage and referral in emergency departments, we propose to create a pervasive environment with a set of sensors. The information system (IS) of this space must exactly determine the patients state of health and whether he or she must be presented urgently to a specialist, or may be queued according to a given order of priorities; in some cases, he or she must be referred to specialised emergency (maternity, psychiatry, cardiology, etc.). In this document, we present the architecture, implementation and simulation of our system for triage and referral in emergency departments.

A Credibility and Classification-Based Approach for Opinion Analysis in Social Networks

There is an ongoing interest in examining users’ experiences made available through social media. Unfortunately these experiences like reviews on products and/or services are sometimes conflicting and thus, do not help develop a concise opinion on these products and/or services. This paper presents a multi-stage approach that extracts and consolidates reviews after addressing specific issues such as user multi-identity and user limited credibility. A system along with a set of experiments demonstrate the feasibility of the approach.

Multi-agent framework for social CRM: Extracting and analyzing opinions

Numerous studies have discussed the benefits of using social networks, even companies started to exploit the usefulness of this valuable information sources. Collecting social data then integrating them into a CRM (Customer Relationship Management) has led companies to understand the customer needs and therefore to improve the development process of their products or their services quality. In this work, we propose a multi-agent framework for analyzing extracted opinions from social media. In the development process, we were brought to consider the huge volumes of data (Big Data) and the response time. To do so, an architecture based on Map/Reduce analysis using Hadoop was made in order to perform the data refinement (classify or remove special words or delete the unvaluable reviews) and sentiment analysis (Sentigem). Finally, a study case using Twitter (Twitter4J API) as a data source, was made to verify the effectiveness of the proposed framework.

How can crowdsourcing help in crisis situations? Missing kids case study

Crowdsourcing consists of tools and methods that harness the potential of the crowd (intelligence and sense of creativity). It is increasingly used in different fields especially in some extreme emergency cases that require broad collaboration of all citizens. This collaboration will be unsuccessful or at least a heavy work without the ubiquity of new information technologies and the emergence of smartphones and mobile devices. They become more and more powerful mainly with the ‘anytime and anywhere’ Internet access. The contribution of this paper is twofold: we introduce a framework that can be widely used by government organizations to stimulate the crowd participation in a missing child case and we also reveal the importance of crowdsourcing in an e-government context to cope with societys changes.

Face Detection for Augmented Reality Application Using Boosting-based Techniques

Augmented reality has gained an increasing research interest over the few last years. Customers requirements have become more intense and more demanding, the need of the different industries to re-adapt their products and enhance them by recent advances in the computer vision and more intelligence has become a necessary. In this work we present a marker-less augmented reality application that can be used and expanded in the e-commerce industry. We take benefit of the well known boosting techniques to train and evaluate different face detectors using the multi-block local binary features. The work purpose is to select the more relevant training parameters in order to maximize the classification accuracy. Using the resulted face detector, the position of the face will serve as a marker in the proposed augmented reality.