Adaptive Multi-Updating Strategy Based Particle Swarm Optimization

Particle swarm optimization(PSO)is a stochastic computation tech-nique that has become an increasingly important branch of swarm intelligence optimization.However,like other evolutionary algorithms,PSO also suffers from premature convergence and entrapment into local optima in dealing with complex multimodal problems.Thus this paper puts forward an adaptive multi-updating strategy based particle swarm optimization(abbreviated as AMS-PSO).To start with,the chaotic sequence is employed to generate high-quality initial particles to accelerate the convergence rate of the AMS-PSO.Subsequently,according to the current iteration,different update schemes are used to regulate the particle search process at different evolution stages.To be specific,two different sets of velocity update strategies are utilized to enhance the exploration ability in the early evolution stage while the other two sets of velocity update schemes are applied to improve the exploitation capability in the later evolution stage.Followed by the unequal weightage of acceleration coefficients is used to guide the search for the global worst particle to enhance the swarm diversity.In addition,an auxiliary update strategy is exclusively leveraged to the global best particle for the purpose of ensuring the convergence of the PSO method.Finally,extensive experiments on two sets of well-known benchmark functions bear out that AMS-PSO outperforms several state-of-the-art PSOs in terms of solution accuracy and convergence rate.

Exploiting structural similarity of log files in fault diagnosis for Web service composition

With increasing deployment of Web services, the research on the dependability and availability of Web service composition becomes more and more active. Since unexpected faults of Web service composition may occur in different levels at runtime, log analysis as a typical data- driven approach for fault diagnosis is more applicable and scalable in various architectures. Considering the trend that more and more service logs are represented using XML or JSON format which has good flexibility and interoperability, fault classification problem of semi-structured logs is considered as a challenging issue in this area. However, most existing approaches focus on the log content analysis but ignore the structural information and lead to poor performance. To improve the accuracy of fault classification, we exploit structural similarity of log files and propose a similarity based Bayesian learning approach for semi-structured logs in this paper. Our solution estimates degrees of similarity among structural elements from heterogeneous log data, constructs combined Bayesian network （CBN）, uses similarity based learning algorithm to compute probabilities in CBN, and classifies test log data into most probable fault categories based on the generated CBN. Experimental results show that our approach outperforms other learning approaches on structural log datasets.

Cognitive Machine Learning

Cognitive machine learning refers to the combination of machine learning and brain cognitive mechanism, specifically, combining machine learning with mind model CAM. Three research directions are proposed in this paper, that is, emergency of learning, complementary learning system and evolution of learning.

Hybrid Designing of a Neural System by Combining Fuzzy Logical Framework and PSVM for Visual Haze-Free Task

Brain-like computer research and development have been growing rapidly in recent years. It is necessary to design large scale dynamical neural networks (more than 106 neurons) to simulate complex process of our brain. But such kind of task is not easy to achieve only based on the analysis of partial differential equations, especially for those complex neural models, e.g. Rose-Hindmarsh (RH) model. So in this paper, we develop a novel approach by combining fuzzy logical designing with Proximal Support Vector Machine Classifiers (PSVM) learning in the designing of large scale neural networks. Particularly, our approach can effectively simplify the designing process, which is crucial for both cognition science and neural science. At last, we conduct our approach on an artificial neural system with more than 108 neurons for haze-free task, and the experimental results show that texture features extracted by fuzzy logic can effectively increase the texture information entropy and improve the effect of haze-removing in some degree.

Motivation Learning in Mind Model CAM

Motivation learning aims to create abstract motivations and related goals. It is one of the high-level cognitive functions in Consciousness And Memory model (CAM). This paper proposes a new motivation learning algorithm which allows an agent to create motivations or goals based on introspective process. The simulation of cyborg rat maze search shows that the motivation learning algorithm can adapt agents’ behavior in response to dynamic environment.

A Cognitive Model for Multi-Agent Collaboration

In multi-agent system, agents work together for solving complex tasks and reaching common goals. In this paper, we propose a cognitive model for multi-agent collaboration. Based on the cognitive model, an agent architecture will also be presented. This agent has BDI, awareness and policy driven mechanism concurrently. These approaches are integrated in one agent that will make multi-agent collaboration more practical in the real world.

Cognitive Cycle in Mind Model CAM

Cognitive cycle is a basic procedure of mental activities in cognitive level. Human cognition consists of cascading cycles of recurring brain events. This paper presents a cognitive cycle for the mind model CAM (Consciousness And Memory). Each cognitive cycle perceives the current situation, through motivation phase with reference to ongoing goals, and then composes internal or external action streams to reach the goals in response. We use dynamic description logic which is an extended description logic with action to formalize descriptions and algorithms of cognitive cycle. Two important algorithms, including hierarchical goal and action composition, is proposed in the paper.

Foundations of Intelligence Science

In order to make significant progress toward achievement of human level machine intelligence a paradigm shift is needed. More specifically, the natural intelligence and artificial intelligence should be closely interacted in Intelligence Science study, instead of separate from each other. In order to reach the paradigm, brain science, cognitive science, artificial intelligence and others should cross-research together. Brain science explores the essence of brain, research on the principle and model of natural intelligence in molecular, cell and behavior level. Cognitive science studies human mental activity, such as perception, learning, memory, thinking, consciousness etc. Artificial intelligence attempts simulation, extension and expansion of human intelligence using artificial methodology and technology. All together pursue to explore the mechanism and principle of intelligence which is the engine of advanced science and technology. The paper will give the definition of intelligence and discuss ten big issues of Intelligence Science. The conclusion and perspective will be given in last section.

A dynamic description logic based system for video event detection

Video event detection is an important research area nowadays.Modeling the video event is a key problem in video event detection.In this paper,we combine dynamic description logic with linear time temporal logic to build a logic system for video event detection.The proposed logic system is named as LTD_(ALCO)which can represent and inference the static,dynamic and temporal knowledge in one uniform logic system.Based on the LTD_(ALCO),a framework for video event detection is proposed.The video event detection framework can automatically obtain the logic description of video content with the help of ontology-based computer vision techniques and detect the specified video event based on satisfiability checking on LTD_(ALCO)formulas.