IJISA Vol. 8, No. 9, Sep. 2016
Cover page and Table of Contents: PDF (size: 120KB)
Neo-fuzzy elements are used as nodes for an evolving cascade system. The proposed system can tune both its parameters and architecture in an online mode. It can be used for solving a wide range of Data Mining tasks (namely time series forecasting). The evolving cascade system with neo-fuzzy nodes can process rather large data sets with high speed and effectiveness.[...] Read more.
Forecasting CPU availability in volunteer computing systems using a single prediction algorithm is insufficient due to the diversity of the world-wide distributed resources. In this paper, we draw-up the main guidelines to develop an appropriate CPU availability prediction system for such computing infrastructures. To reduce solution time and to enhance precision, we use simple prediction techniques, precisely vector autoregressive models and a tendency-based technique. We propose a predictor construction process which automatically checks assumptions of vector autoregressive models in time series. Three different past analyses are performed. For a given volunteer resource, the proposed prediction system selects the appropriate predictor using the multi-state based prediction technique. Then, it uses the selected predictor to forecast CPU availability indicators. We evaluated our prediction system using real traces of more than 226000 hosts of Seti@home. We found that the proposed prediction system improves the prediction accuracy by around 24%.[...] Read more.
Very large scale integration (VLSI) circuit comprises of integrated circuit (IC) with transistors in a single chip, widely used in many sophisticated electronic devices. In our paper, we proposed VLSI circuit design by implementing satisfiability problem in Hopfield neural network as circuit verification technique. We restrict our logic construction to 2-Satisfiability (2-SAT) and 3-Satisfiability (3-SAT) clauses in order to suit with the transistor configuration in VLSI circuit. In addition, we developed VLSI circuit based on Hopfield neural network in order to detect any possible error earlier than the manual circuit design. Microsoft Visual C++ 2013 is used as a platform for training, testing and validating of our proposed design. Hence, the performance of our proposed technique evaluated based on global VLSI configuration, circuit accuracy and the runtime. It has been observed that the VLSI circuits (HNN-2SAT and HNN-3SAT circuit) developed by proposed design are better than the conventional circuit due to the early error detection in our circuit.[...] Read more.
With the advent of Industrial Revolution, not only the choices in various fields increased but also the era of computer came into existence thereby revolutionizing the global market. People had numerous choices in front of them that often led to the confusion about what product might actually fulfill their requirements. So the need for having a system which could facilitate the selection criteria and eradicate the dilemma of masses, was realized and ultimately recommender systems of present day world were introduced. So we can refer recommender systems as software tools that narrow down our choices and provide us with the most suitable suggestions as per our requirements. In this paper, we propose a novel recommender system i.e. RWARS (Research Work Area Recommender System) that will recommend research work area to a user based on his/her characteristics similar to those of other users. The characteristics considered here are hobbies, subjects of interests, programming skills and future objectives. The proposed system will use Cosine Similarity approach of Collaborative Filtering.[...] Read more.
Mating preferentialism among animals is the natural form of elitism that has a higher genetic variance and a shorter number of interactions. This concept refers to fact that most animals cannot breed indefinitely – this is the case of elitism - and suffer DNA degradation. In this paper, two types of preferentialism were analyzed (mutation and second best); in both cases we found evidence of improvements over no-preferentialism or elitism. The best number of generations for preferentialism was determined to be 5, from a group of 3 to 20, with the smallest average of iterations and the most consistent average fitness. A sequencing of 0 to 7 was selected and used in association with mutation preferentialism in order to determine the best number of generations. In the case of BinaryF6, mutation preferentialism has a higher average best fitness (ABF) (0.9986) and a lower number of interactions (2259). Second best preferentialism has a better average last fitness (ALF) (0.6070) and a little higher number of interactions (3956). These results reveal that the two suggested form of preferentialism exhibit significant improvements in terms of time and result quality when they are compared with elitism (ABF of 0.9981, ALF of 0.6005 and an average number of interactions of 18197) or with no-preferentialism (ABF of 0.9982, ALF of 0.5177 and average number of interactions of 181088.[...] Read more.
In the field of optimization, Genetic Algorithm that incorporates the process of evolution plays an important role in finding the best solution to a problem. One of the main issues that arise in the medical field is to search a finite number of factors or features that actually affect or predict the survival of the patients especially with poor prognosis disease, thus helping them in early diagnosis. This paper discusses the various steps that are performed in genetic algorithm and how it is going to help in extracting knowledge out of high dimensional medical dataset. The more the attributes or features, the more difficult it is to correctly predict the class of that sample or instance. This is because of inefficient, useless, noisy attributes in the dataset. So, here the main aim is to search the strong features or genes that can strongly predict the class of subject (patient) i.e. healthy or cancerous and thus help in early detection and treatment.[...] Read more.
Biological systems, including agriculture and allied sectors are very complex and nonlinear in nature. The pace of current climate change, which is unique about it, makes the biological system more and more complicated and unpredictable. The novelty or ambiguity that the variable environment presents, demands for the development of self-adaptive intelligent systems in agriculture and allied sectors. Agriculture is emerging as knowledge-based enterprise that demands efficient need-based information retrieval systems and smart actions. Intelligence is that resource that guides actions and provide options under variable, uncertain and unseen conditions. The objective of the current paper is to analyze the attributes that are considered to be characteristics of intelligence having wide potential for the development of intelligent system and technologies for agricultural applications. The intelligent techniques like forecasting, database management, knowledge discovery, deception, simulation, contingency planning etc. revolutionize the whole agricultural sector opening new and competent options and dimensions. Sustainable agricultural development demands multidisciplinary holistic approach and intelligence should be the guiding principle that demands study of human cognitive psychology.[...] Read more.
The main general purpose of this research is the automatic construction of rule-based expert system in diagnosis domain based on an expert system tool and a multi-intelligent agent system. The first goal is used an expert system tool (shell) which is called Diagnosis Domain Tool for Rule-based Expert System (DDTRES) . The second goal is used a multi-intelligent agent architecture for knowledge extraction to elicit knowledge from its resources (domain experts, text documents, databases) for automatic construction of a knowledge base. That means, instead of using traditional methods for knowledge base construction, we used automatic way for that job. In order to achieve second objective, the following agents have been used: The Expert Mining Intelligent Agent (EMIA), The Text Mining Intelligent Agent (TMIA) , and The Multi-Intelligent Agent for Knowledge Discovery in Database (MIAKDD) . We are aim to produce an effective final knowledge base by cooperation between EMIA, TMIA, and MIAKDD approaches and integrated with the diagnosis domain tool (DDTRES) to produce a complete rule-based expert system in diagnosis domain. We applied the captured rule-based expert system on heart diseases diagnosis, we found system performance is between a good and a very good range.[...] Read more.