International Journal of Computational Intelligence and Applications

Techniques for automated classification need to be efficient when applied to large datasets. Machine learning techniques such as neural networks have been successfully applied to this class of problem, but training times can blow out as the size of the database increases. Some of the desirable features of classification algorithms for large databases are linear time complexity, training with only a single pass of the data, and accountability for class assignment decisions. A new training algorithm for classifiers based on the Cerebellar Model Articulation Controller (CMAC) possesses these features. An empirical investigation of this algorithm has found it to be superior to the traditional CMAC training algorithm, both in accuracy and time required to learn mappings between input vectors and class labels.

The optimal design of large-scale process plant is difficult due to the presence of Pareto sets or nondominated solutions. Many conventional and advanced mathematical techniques had been adopted which have their own limitations in solving the complex design problem. In this paper, nondominant-sorted genetic algorithms NSGA and NSGA-II have been adopted for the optimal design of complex Williams–Otto model process plant. The plant consists of a reactor, separation system consisting of heat exchanger, decanter and distillation column. Multiobjective optimization is used to maximize the profit, i.e. the return on investment, to maintain lesser use of costlier raw material and lesser disposal of the waste byproducts. So NSGA-II is employed in this study as an effective replacement for NSGA, classical genetic algorithm, conventional and traditional methods of optimization in solving multiobjective process design problems and to achieve fine-tuning of variables in determining Pareto optimal design parameters. NSGA-II method finding global optimal front has a significant effect on the design of control system for the real time and continuous robust control of complex process plant as each target vector provides proper direction and drives the process to multiobjective optimum conditions.

In the past few years, there has been a massive growth in the field of biologically inspired global search heuristics. Computational cost having been reduced almost dramatically, researchers from all corners are taking more interset in following the underlying principles of nature to solve nearly intractable search problems. In this paper, we attempt to solve one very important optimization problem arising in the field of two-dimensional IIR (infinite impulse response) filter design, with three naturally inspired global search algorithms. We have used a state-of-the-art real coded genetic algorithm (GA), one very recent and modified version of the particle swarm opimization (PSO) and finally an improved version of the differential evolution (DE) algorithm. The DE algorithm has been modified by us to prevent its premature convergence to some suboptimal region of the search space. The design task is formulated as a constrained minimization problem and solved by the three metaheuristics. Numerical results are presented over three difficult instances of the design problem. The study also compares the results with two recently published filter design methods. Our experiments reveal that the DE family of algorithms should receive primary attention in solving the constrained multidimensional filter design tasks.

This paper proposes an intelligent classification technique to identify two categories of MRI volume data as normal and abnormal. The manual interpretation of MRI slices based on visual examination by radiologist/physician may lead to incorrect diagnosis when a large number of MRIs are analyzed. In this work, the textural features are extracted from the MR data of patients and these features are used to classify a patient as belonging to normal (healthy brain) or abnormal (tumor brain). The categorization is obtained using various classifiers such as support vector machine (SVM), radial basis function, multilayer perceptron and k-nearest neighbor. The performance of these classifiers are analyzed and a quantitative indication of how better the SVM performance is when compared with other classifiers is presented. In intelligent computer aided health care system, the proposed classification system using SVM classifier can be used to assist the physician for accurate diagnosis.

In this paper, we describe a knowledge-based system for segmenting and labeling lung nodule on helical CT images. The system was developed under a blackboard environment that incorporates a lung knowledge model, image processing model, inference engine and a blackboard. Lung model, which contains both analogical and propositional knowledge about lung in the form of semantic networks, was used to guide the interpretation process. The system works in a hierarchical structure, from large structures to the final nodule candidates by focusing on the interested region step by step. The symbolic variables, introduced to accomplish high-level inference, were defined by fuzzy confidence functions in the lung model. Composite fuzzy functions were applied to evaluate the plausibility of the mapping between the image and lung model objects. Anatomical lung segments knowledge was embedded in the system to direct 3D validation of suspicious objects. Structures were identified and abnormal objects were reported. The experimental results obtained demonstrate the proof of concept and the potential of the automated knowledge-based lung nodule detection system.

A new direct adaptive type-2 fuzzy controller for a nonlinear dynamical system is developed in this paper. The parameters of the membership functions characterizing the linguistic terms in the type-2 fuzzy IF–THEN rules change according to some adaptive law for the purpose of controlling a plant to track a reference trajectory. A supervisory controller is appended to the type-2 fuzzy controller to force the state to be within the constraint set. Stability of this adaptive scheme is established using Lyapunov stability tools, where we guarantee the global stability of the resulting closed-loop system, in the sense that all signals involved are uniformly bounded. The simulation results for a Duffing forced-oscillation system show better performances, i.e. tracking error and control effort can be made smaller.

Reinforcement learning is one of the more attractive machine learning technologies, due to its unsupervised learning structure and ability to continually learn even as the operating environment changes. Additionally, by applying reinforcement learning to multiple cooperative software agents (a multi-agent system) not only allows each individual agent to learn from its own experience, but also opens up the opportunity for the individual agents to learn from the other agents in the system, thus accelerating the rate of learning. This research presents the novel use of fuzzy state aggregation, as the means of function approximation, combined with the fastest policy hill climbing methods of Win or Lose Fast (WoLF) and policy-dynamics based WoLF (PD-WoLF). The combination of fast policy hill climbing and fuzzy state aggregation function approximation is tested in two stochastic environments: Tileworld and the simulated robot soccer domain, RoboCup. The Tileworld results demonstrate that a single agent using the combination of FSA and PHC learns quicker and performs better than combined fuzzy state aggregation and Q-learning reinforcement learning alone. Results from the multi-agent RoboCup domain again illustrate that the policy hill climbing algorithms perform better than Q-learning alone in a multi-agent environment. The learning is further enhanced by allowing the agents to share their experience through a weighted strategy sharing.

In this paper, we propose the multi-learner based recursive supervised training (MLRT) algorithm, which uses the existing framework of recursive task decomposition, by training the entire dataset, picking out the best learnt patterns, and then repeating the process with the remaining patterns. Instead of having a single learner to classify all datasets during each recursion, an appropriate learner is chosen from a set of three learners, based on the subset of data being trained, thereby avoiding the time overhead associated with the genetic algorithm learner utilized in previous approaches. In this way MLRT seeks to identify the inherent characteristics of the dataset, and utilize it to train the data accurately and efficiently. We observed that empirically MLRT performs considerably well as compared with RPHP and other systems on benchmark data with 11% improvement in accuracy on the SPAM dataset and comparable performances on the VOWEL and the TWO-SPIRAL problems. In addition, for most datasets, the time taken by MLRT is considerably lower than that of the other systems with comparable accuracy. Two heuristic versions, MLRT-2 and MLRT-3, are also introduced to improve the efficiency in the system, and to make it more scalable for future updates. The performance in these versions is similar to the original MLRT system.