Hybrid intelligent framework for one-day ahead wind speed forecasting

Neural Computing and Applications - Nowadays wind power is considered as one of the fastest growing alternative energies, that is expected to continue to grow rapidly in the upcoming...     

Relevance feedback for CBIR: a new approach based on probabilistic feature weighting with positive and negative examples.

In content-based image retrieval, understanding the user's needs is a challenging task that requires integrating him in the process of retrieval. Relevance feedback (RF) has proven to be an effective tool for taking the user's judgement into account. In this paper, we present a new RF framework based on a feature selection algorithm that nicely combines the advantages of a probabilistic formulation with those of using both the positive example (PE) and the negative example (NE). Through interaction with the user, our algorithm learns the importance he assigns to image features, and then applies the results obtained to define similarity measures that correspond better to his judgement. The use of the NE allows images undesired by the user to be discarded, thereby improving retrieval accuracy. As for the probabilistic formulation of the problem, it presents a multitude of advantages and opens the door to more modeling possibilities that achieve a good feature selection. It makes it possible to cluster the query data into classes, choose the probability law that best models each class, model missing data, and support queries with multiple PE and/or NE classes. The basic principle of our algorithm is to assign more importance to features with a high likelihood and those which distinguish well between PE classes and NE classes. The proposed algorithm was validated separately and in image retrieval context, and the experiments show that it performs a good feature selection and contributes to improving retrieval effectiveness.     

Gripper Design for Radio Base Station Autonomous Maintenance System

For an autonomous system to perform maintenance tasks in a networking device or a radio base station (RBS), it has to deal with a series of technological challenges ranging from identifying hardware-related problems to manipulating connectors. This paper describes the development of a robot maintenance system dedicated to detect and resolve faulty links caused by unplugged or poorly connected cables. Although the maintenance system relies on four subsystems, we significantly focus on our low-cost and efficient custom gripper solution developed to handle RJ45 Ethernet connectors. To examine our gripper, we conducted three experiments. First, a qualitative questionnaire was submitted to 30 users in the case of the teleoperated scenario of the gripper attached to a robotic arm. Similarly, we also tested the automatic operation mode. The results showed that our system is reliable and delivers a highly efficient maintenance tool in both teleoperated and autonomous operation modes. The practical experiment containing the removal or unplugging of connectors demonstrated our gripper’s ability to adequately handle these, whereas the feedback from the questionnaire pointed to a positive user experience. The automatic test assessed the gripper’s robustness against the continuous operation.

     

Opening web applications for third-party development: a service-oriented solution

Web applications are nowadays prevalent software systems in our everyday’s life. A lot of these applications have been developed for end users only. Thus, they are not designed by considering future extensions that would be developed by third parties. One possible and interesting solution for opening these applications for such kind of extension development is to create and deploy Web services starting from these applications. In this paper, we present a method and a tool for semiautomatically creating Web service implementations from applications having Web interfaces. The proposed method generates operations that are published in Web services for each functionality provided by a Web application. In addition, it generates new operations starting from Web interfaces. Our approach goes further in the creation of services by generating executable orchestrations, as BPEL processes, starting from navigations in the Web interfaces of these applications and by providing BPMN choreography specifications starting from the collaborations between the generated Web services. We implemented and experimented our solution in the migration of three real-world Web applications toward Web service-oriented systems.     

SPIDER: An availability-aware framework for the service function chain placement in distributed scenarios

The network function virtualization (NFV) paradigm replaces hardware-dependent network functions by virtual network functions (VNFs) that can be deployed in commodity hardware, including legacy servers. Consequently, the use of NFV is expected to reduce operating and capital expenses, as well as improve service deployment operation and management flexibility. For many use cases, the VNFs must be visited and invoked following a specific order of execution in order to compose a complete network service, named service function chain (SFC). Nonetheless, despite the benefits from NFV and SFC virtualization technologies, their introduction must not harm network performance and service availability. On the one hand, redundancy is seen by network service planners as a mechanism well established to combat availability issues. At same time, there is a goal to optimize resource utilization in order to reduce operational expenditure. In this article, we share our experience in the design use of a framework, named SPIDER, focused on SFC placement that considers the network infrastructure condition and the required SFC availability to define the placement strategy. The SPIDER monitors the status of infrastructure nodes and links and defines which servers the VNFs should be placed on and the number of redundant replicas needed. We present a proof-of-concept of SPIDER using Kubernetes to launch the VNFs as containers. We also use Kubernetes to forward the traffic between the VNFs, composing the service chain. We perform experiments to evaluate the runtime of SPIDER and the SFC delay under different network conditions.     

Integrating customer's preferences in the QFD planning process using a combined benchmarking and imprecise goal programming model

Quality function deployment (QFD) is a customer-oriented design tool for developing new or improved products to achieve higher customer satisfaction by integrating various functions of an organization. The engineering characteristics (ECs) affecting the product performances are designed to match the customer attributes (CAs). However, from the viewpoint of the QFD team, product design processes are performed in imprecise environments, and more than one factor must be taken into account in determining the target levels of ECs, especially the limited resources and increased market competition. This paper presents an imprecise goal programming (GP) approach to determine the optimum target levels of ECs in QFD for maximizing customer satisfaction under resource limitation and considerations of market competition. Based on benchmarking data of CAs, the concept of satisfaction functions is utilized to formulate explicitly the customer's preferences and to integrate the competitive analysis of target market into the modelling and solution process. In addition, the relationships linking CAs and ECs and the ECs to each other are integrated by functional relationships. The proposed approach will be illustrated through a car door design example.     

Traffic analysis and synthetic models of second life

Virtual Worlds (VW), such as Massive Multiplayer Online Social Games, have been gaining increasing attention in the last few years, mainly due to the new way users interact with them. However, little effort has been devoted to understand their traffic profile and the implications to the traffic management area. With the current growing rate of VWs’ usage, their traffic demand could eventually impose a significant burden on the operation of a typical Internet Service Provider (ISP) network. In this paper, we seek to understand the traffic behavior of an increasingly popular VW application, namely Second Life (SL), from both the connection and network level perspectives. We also show results of a traffic analysis of a SL client, when an avatar performs different actions in the VW, at different places and under different network conditions. Our results show that SL makes intensive use of network resources (mostly bandwidth), since the capacity needed for having a full SL experience (listening to live music) may reach 500 kbps. We then extend the traffic analysis work on SL by providing analytical models for its traffic profile. We aim at helping the network management and planning area to estimate the impact of an intense use of such VW on access links or core networks. Such synthetic models are also useful to the networking research community for the use in network simulations.     

Supervisory control based on minimal cuts and Petri net sub-controllers coordination

This paper addresses the synthesis of Petri net (PN) controller for the forbidden state transition problem with a new utilisation of the theory of regions. Moreover, as any method of control synthesis based on a reachability graph, the theory of regions suffers from the combinatorial explosion problem. The proposed work minimises the number of equations in the linear system of theory of regions and therefore one can reduce the computation time. In this paper, two different approaches are proposed to select minimal cuts in the reachability graph in order to synthesise a PN controller. Thanks to a switch from one cut to another, one can activate and deactivate the corresponding?PNcontroller. An application is implemented in a flexible manufacturing system to illustrate the present method. Finally, comparison with previous works with experimental results in obtaining a maximally permissive controller is presented.     

Evidential data mining: precise support and confidence

Associative classification has been shown to provide interesting results whenever of use to classify data. With the increasing complexity of new databases, retrieving valuable information and classifying incoming data is becoming a thriving and compelling issue. The evidential database is a new type of database that represents imprecision and uncertainty. In this respect, extracting pertinent information such as frequent patterns and association rules is of paramount importance task. In this work, we tackle the problem of pertinent information extraction from an evidential database. A new data mining approach, denoted EDMA, is introduced that extracts frequent patterns overcoming the limits of pioneering works of the literature. A new classifier based on evidential association rules is thus introduced. The obtained association rules, as well as their respective confidence values, are studied and weighted with respect to their relevance. The proposed methods are thoroughly experimented on several synthetic evidential databases and showed performance improvement.