International Journal on Artificial Intelligence Tools

Today's supply chains increasingly involve complex sets of processes, objectives and constraints, and therefore agent-based architectures for supply chain management (SCM) become much more difficult to implement and maintain. The paper presents a multi-agent architecture for specifying, analyzing and developing SCM systems, in which asynchronous teams (A-Team) of problem solving agents exchange results within populations that provide effective management of information flows in supply chains, and cooperate to produce sets of non-dominated solutions that show the tradeoffs between objectives. Our approach distinguishes itself by improving problem-solving efficiency based on a diverse set of algorithms without complicated synthesis efforts, removing the focus from agent communication and coordination details, and improving reusability, flexibility and extensibility by supporting object-oriented and component-based programming style. We examine the effectiveness of the architecture through a real-world case study and experimental results.

Information retrieval has been paid much attention and it is widely studied and applied in real world paradigms. For various aspects of information retrieval, various approaches have been proposed from various perspectives. It is necessary to provide a formally-unified and physically-interpretable model for classical problems in information retrieval (e.g., document classification, authority-page selection, and keyword extraction, etc.). In this paper we propose a theoretical model, called semantic field, inspired by the theories of lexical semantics and electrostatic field. Based on this physical model, information retrieval can be viewed from a theoretical perspective and interpreted by people's physical intuitions and natural heuristics. Centered on the concept of semantic field, we give some relevant properties, including semantic affinity, semantic coacervation degree and radiation of a semantic source. As the representative application of the proposed semantic field model, a novel method for automatic keyword extraction is discussed, and the feasibility is verified by corresponding experiments.

In the present contribution we propose an integral training procedure for the Locally Recurrent Probabilistic Neural Networks (LR PNNs). Specifically, the adjustment of the smoothing factor "sigma" in the pattern layer of the LR PNN and the training of the recurrent layer weights are integrated in an automatic process that iteratively estimates all adjustable parameters of the LR PNN from the available training data. Furthermore, in contrast to the original LR PNN, whose recurrent layer was trained to provide optimum separation among the classes on the training dataset, while striving to keep a balance between the learning rates for all classes, here the training strategy is oriented towards optimizing the overall classification accuracy, straightforwardly. More precisely, the new training strategy directly targets at maximizing the posterior probabilities for the target class and minimizing the posterior probabilities estimated for the non-target classes. The new fitness function requires fewer computations for each evaluation, and therefore the overall computational demands for training the recurrent layer weights are reduced. The performance of the integrated training procedure is illustrated on three different speech processing tasks: emotion recognition, speaker identification and speaker verification.

Principal components analysis (PCA) is a popular linear feature extractor, and widely used in signal processing, face recognition, etc. However, axes of the lower-dimensional space, i.e., principal components, are a set of new variables carrying no clear physical meanings. Thus we propose unsupervised feature selection algorithms based on eigenvectors analysis to identify critical original features for principal component. The presented algorithms are based on k-nearest neighbor rule to find the predominant row components and eight new measures are proposed to compute the correlation between row components in transformation matrix. Experiments are conducted on benchmark data sets and facial image data sets for gender classification to show their superiorities.

In this paper, we propose an automatic analyzing and transforming approach to L-system grammar extraction from real plants. Instead of using manually designed rules and cumbersome parameters, our method establishes the relationship between L-system grammars and the iterative trend of botanical entities, which reflect the endogenous factors that caused the plant branching process. To realize this goal, we use a digital camera to take multiple images of unfoliaged (leafless) plants and capture the topological and geometrical data of plant entities using image processing methods. The data then stored into specific data structures. A Hidden Markov based statistical model is then employed to reveal the hidden relations of plant entities which have been classified into categories based on their statistical properties extracted by a classic EM algorithm, the hidden relations have been integrated into the target L-system as grammars. Results show that our method is capable of automatically generating L-grammars for a given unfoliaged plant no matter what branching type it is belongs to.

Support vector machine (SVM) is a universal learning method. In this paper, an affine support vector machine (ASVM) for regression is presented for identification and control of input-affine nonlinear models. ASVM is a variant of SVM and so inherits its merits. The solution to ASVM is cast into a convex quadratic programming (QP). Hence ASVM has a unique global solution. In addition, the curse of dimensionality is avoided because ASVM is insensitive to the dimensionality of data. A commonly used model for a nonlinear system is a nonlinear autoregressive exogenous (NARX) model. ASVM could get good performance in both identification and control if a NARX model can be well represented by an input-affine nonlinear model. The experimental results validate the efficiency of ASVM in identification and control of discrete-time nonlinear systems.

In this work, it is proposed a new family of potentials for path planning algorithms, one kind to the goal and other to the obstacles. With these new potentials it is possible to parameterize the potential scale length and strength easily, providing better control over the moving object path characteristics. In this way, the path problem can be treated analytically. For example, the minimum distance between the moving object and the obstacles can be calculated as a function of the potential parameters. Simulations are made to test its ability to guide a vehicle through an obstacle-free path towards the goal. The success rate of the moving object on reaching the goal is compared with the potential parameters and with obstacle configuration and distribution parameters.