Tiago Sousa

Particle swarm based Data Mining Algorithms for classification tasks

Particle Swarm Optimisers are inherently distributed algorithms where the solution for a problem emerges from the interactions between many simple individual agents called particles. This article proposes the use of the Particle Swarm Optimiser as a new tool for Data Mining. In the first phase of our research, three different Particle Swarm Data Mining Algorithms were implemented and tested against a Genetic Algorithm and a Tree Induction Algorithm (J48). From the obtained results, Particle Swarm Optimisers proved to be a suitable candidate for classification tasks. The second phase was dedicated to improving one of the Particle Swarm optimiser variants in terms of attribute type support and temporal complexity. The data sources here used for experimental testing are commonly used and considered as a de facto standard for rule discovery algorithms reliability ranking. The results obtained in these domains seem to indicate that Particle Swarm Data Mining Algorithms are competitive, not only with other evolutionary techniques, but also with industry standard algorithms such as the J48 algorithm, and can be successfully applied to more demanding problem domains.

A Particle Swarm Data Miner

This paper describes the implementation of Data Mining tasks using Particle Swarm Optimisers. The object of our research has been to apply such algorithms to classification rule discovery. Results, concerning accuracy and speed performance, were empirically compared with another evolutionary algorithm, namely a Genetic Algorithm and with J48 – a Java implementation of C4.5. The data sets used for experimental testing have already been widely used and proven reliable for testing other Data Mining algorithms. The obtained results seem to indicate that Particle Swarm Optimisers are competitive with other evolutionary techniques, and could come to be successfully applied to more demanding problem domains.

Swarm optimisation as a new tool for data mining

This paper proposes the use of particle swarm optimisers as a tool for data mining. To evaluate its usefulness, we empirically compare the performance of three variants of the particle optimiser with another evolutionary algorithm, namely a genetic algorithm, in rule discovery for classification tasks. Such tasks are considered core tools for decision support systems in a widespread area, ranging from the industry, commerce, military and scientific fields. The data sources used here for experimental testing are commonly used and considered as a de facto standard for rule discovery algorithms reliability ranking. The results obtained in these domains seem to indicate that particle swarm optimisers are competitive with other evolutionary techniques, and can be successfully applied to more demanding problem domains.

Organizational strategic adaptation in the presence of inertia

This paper extends the particle swarm metaphor into the domain of organization science. A simulator (OrgSwarm) which can be used to model the adaptation of a population of organizations on a strategic landscape is introduced. The simulator embeds a number of features of the process of organizational adaptation, including the resistance of organizations to change (strategic inertia), errorful assessments of the payoffs to proposed strategies, and market competition. These features allow the examination of a wide range of real-life scenarios in organizational adaptation. The paper reports the results of a number of simulation experiments and these suggest that agent (management) uncertainty as to the payoffs to potential strategies has the effect of lowering the average payoffs obtained by a population of organizations. The results also suggest that a degree of strategic inertia can assist rather than hamper adaptive efforts at a populational level.

Investigating Strategic Inertia Using OrgSwarm

The previous adversary models of public key cryptography usually have a nature assumption that permanent/temporary secret (private) keys must be kept safely and internal secret states are not leaked to an adversary. However, in practice, it is difficult to keep away from all possible kinds of leakage on these secret data due to a new kind of threat, called “side-channel attacks”. By sidechannel attacks, an adversary could obtain partial information of these secret data so that some existing adversary models could be insufficient. Indeed, the study of leakage-resilient cryptography resistant to side-channel attacks has received significant attention recently. Up to date, no work has been done on the design of leakage-resilient certificateless key encapsulation (LR-CL-KE) or public key encryption (LR-CL-PKE) schemes under the continual leakage model. In this article, we propose the first LR-CL-KE scheme under the continual leakage model. Moreover, in the generic bilinear group (GBG) model, we formally prove that the proposed LR-CL-KE scheme is semantically secure against chosen ciphertext attacks for both Type I and Type II adversaries.

A Particle Swarm Model of Organizational Adaptation

This study introduces the particle swarm metaphor to the domain of organizational adaptation. A simulation model (OrgSwarm) is constructed to examine the impact of strategic inertia, in the presence of errorful assessments of future payoffs to potential strategies, on the adaptation of the strategic fitness of a population of organizations. The results indicate that agent (organization) uncertainty as to the payoffs of potential strategies has the affect of lowering average payoffs obtained by a population of organizations. The results also indicate that a degree of strategic inertia, in the presence of an election mechanism, assists rather than hampers adaptive efforts in static and slowly changing strategic environments.

Agent-based modelling of product invention

This study describes a novel simulation model of the process of product invention. Invention is conceptualized as a process of directed evolutionary adaptation, on a landscape of product design possibilities, by a population of profit-seeking agents (inventors). The simulation experiments examine the sensitivity of the rate of advance in product fitness to the choice of search heuristics employed by inventors. The key finding of the experiments is that if search heuristics are confined to those which are rooted in past experience, or to heuristics which merely generate variety, limited product advance occurs. Notable product fitness advance only occurs when inventors expectations as to the relative fitness of potential product inventions are incorporated into the model of invention. The results demonstrate the importance of human direction and expectations in invention. They also support the importance of formal product / project evaluation procedures in organizations, and the importance of market information when inventing new products.

Modified Particle Swarm Optimization applied to integrated demand response and DG resources scheduling

The elastic behavior of the demand consumption jointly used with other available resources such as distributed generation (DG) can play a crucial role for the success of smart grids. The intensive use of Distributed Energy Resources (DER) and the technical and contractual constraints result in large-scale non linear optimization problems that require computational intelligence methods to be solved. This paper proposes a Particle Swarm Optimization (PSO) based methodology to support the minimization of the operation costs of a virtual power player that manages the resources in a distribution network and the network itself. Resources include the DER available in the considered time period and the energy that can be bought from external energy suppliers. Network constraints are considered. The proposed approach uses Gaussian mutation of the strategic parameters and contextual self-parameterization of the maximum and minimum particle velocities. The case study considers a real 937 bus distribution network, with 20310 consumers and 548 distributed generators. The obtained solutions are compared with a deterministic approach and with PSO without mutation and Evolutionary PSO, both using self-parameterization.

Reactive power management strategies in future smart grids

The reactive power management in distribution network with large penetration of distributed energy resources is an important task in future power systems. The control of reactive power allows the inclusion of more distributed recourses and a more efficient operation of distributed network. Currently, the reactive power is only controlled in large power plants and in high and very high voltage substations. In this paper, several reactive power control strategies considering a smart grids paradigm are proposed. In this context, the management of distributed energy resources and of the distribution network by an aggregator, namely Virtual Power Player (VPP), is proposed and implemented in a MAS simulation tool. The proposed methods have been computationally implemented and tested using a 32-bus distribution network with intensive use of distributed resources, mainly the distributed generation based on renewable resources. Results concerning the evaluation of the reactive power management algorithms are also presented and compared.

Development of a Hybrid Application for Psychotic Disorders Self-Management.

This paper describes iCOPE, a hybrid web/mobile application prototype with the purpose of improving the self-management of psychotic disorders. The development of iCOPE was driven by a multidisciplinary collaboration between mental health occupational therapists and medical computing engineers. A usability test was performed to assess the satisfaction with the technological proposal. Several modules were identified as crucial and were employed in iCOPE: stress management, problem solving, medication adherence, symptoms monitoring and social interaction. Results of a usability survey to therapists and patients revealed general approval of the user interfaces.