Bhanu Prasad

A knowledge-based product recommendation system for e-commerce

This paper presents a knowledge-based product recommendation system for Business-to-Customer (B2C) e-commerce purposes. The system is based on the observation that the purchase patterns of previous users play a vital role in recommending the products to new users if the new users already followed parts of the existing patterns. The system is based on Case-Based Reasoning Plan Recognition (CBRPR) approaches and Automated Collaborative Filtering (ACF) approaches. The system also addresses the issue of organising and utilising the information related to the products that are purchased repetitively by a user. The system is named RecommendEx and is tested in a simulated environment to test its operational performance. The evaluation results are included.

Agent based Resource Brokering and Allocation in Wireless Grids

This paper presents an agent based model for discovery, brokering and allocation of cost effective resources to computational jobs. A wireless grid environment of virtual organizations is considered. Agents are employed to perform resource brokering and allocation tasks. The model is simulated for different wireless grid scenarios, to test its operational effectiveness

Classification of Text Documents Using Adaptive Fuzzy C-Means Clustering

In this paper, we propose a new method of representing text documents based on clustering of term frequency vectors. Term frequency vectors of each cluster are used to form a symbolic representation (interval valued representation) by the use of mean and standard deviation. In order to cluster the term frequency vectors, we make use of fuzzy C-Means clustering method for interval type data based on adaptive squared Euclidean distance between vectors of intervals. Further, to corroborate the efficacy of the proposed model we conducted extensive experimentation on standard datasets like 20 Newsgroup Large, 20 Mini Newsgroup, Vehicles Wikipedia and our own created datasets like Google Newsgroup and Research Article Abstracts. We have compared our classification accuracy achieved by the Symbolic classifier with the other existing Naive Bayes classifier, KNN classifier, Centroid based classifier and SVM classifiers. The experimental results reveal that the achieved classification accuracy is better than that of the existing methods. In addition, our method is based on a simple matching scheme; it requires negligible time for classification.

A Decision Making System for the Treatment of Dental Caries

This paper presents a diagnosis system that helps the dentists to decide the course of treatment for dental caries. The inference mechanism of the system is based on the Bayesian Network (BN) and is designed to decide among various possible treatment plans. The system has been evaluated with the help of 13 different dentists to test its operational effectiveness. The system improves the confidence level of a dentist while deciding the treatment plan. As a result, it improves the effectiveness of the dentist and his/her business. Using this system, patients can also get information regarding the nature of treatment and the associated cost as well.

Soft Query-Answering Computing in P2P Systems with Epistemically Independent Peers

Knowledge-based systems typically deals with incomplete and uncertain knowledge. Numerous extensions have been made to the logic programming and deductive databases in order to handle this incompleteness/uncertainty. These extensions can broadly be characterized into non-probabilistic and probabilistic formalisms. Approximate (uncertain) information can be considered as a kind of relativization of truth values for sentences. This is the standard approach used in several many-valued logics. For example, these many-valued logics include the smallest 4-valued logic programming based on Belnap’s bilattice [1] with two additional logic values (’unknown’ and ’possible’ values for incomplete and locally-inconsistent information respectively), and infinitary fuzzy logics and their extensions [2] and combinations [3] also. In query-answering from distributed databases, especially in the web framework, we often have to deal with partial information and query-algorithms which are defined for real-time applications. Hence the obtained results are generally incomplete. That is, the soft computing query-answering in web database applications is naturally correlated with effective non-omniscient query-agents. There does not exist a centralized control mechanism to handle the entire information in web database applications. The complete answers to such queries are practically undecidable because an enormous amount of time is required to compute the answers. As a result, such answering systems cannot be used in practice. Some approximative algorithms are needed to obtain reasonable but incomplete answers. In addition, these algorithms need to be parametrically incremental.

Mining fuzzy temporal patterns from process instances with weighted temporal graphs

This paper presents an algorithm for mining fuzzy temporal patterns from a given process instance. The fuzzy representation of time intervals embedded between the activities is used for this purpose. Initially, the activities are portrayed with their temporal relationships through temporal graphs and then, the defined data structures are used to retrieve the data suitable for the proposed algorithm. Similar to the familiar k-itemsets and k-dim sequences, their counterparts are introduced in this work. The proposed process-instance level data structure generates an optimum number of temporal itemsets. The proposed algorithm differs from the other existing algorithms on this topic in the representation of the mined data and patterns. An example is provided to demonstrate the algorithm.

Software Test Effort Estimation Using Particle Swarm Optimization

Software testing is a key component in the software development life cycle. This paper presents a modification to the Constructive Cost Model (COCOMO) technique by using particle swarm optimization. The resultant technique significantly increases the accuracy of the COCOMO approach and also incorporates the much needed flexibility related to the software and the development team.

An algorithm for discovering the frequent closed itemsets in a large database

Previous research revealed that the problem of discovering a complete set of frequent itemsets from a large database can be reduced to the problem of discovering the frequent closed itemsets, and this process results in a much smaller set of itemsets without information loss. This article is based on the observation that the set of all itemsets can be grouped into non-overlapping clusters such that each cluster is identified by a unique closed tidset. It is also found that there is only one closed itemset in each cluster and it is the superset of all itemsets with the same support. Therefore, the problem of discovering closed itemsets can be further considered as the problem of clustering the set of itemsets and then identifying each cluster by a unique closed tidset. This article presents CloseMiner, a new algorithm for discovering all frequent closed itemsets by grouping the set of itemsets into non-overlapping clusters. Experimental evaluation based on a number of real and synthetic databases has proved that CloseMiner outperforms the existing systems APRIORI and CHARM.

AN AGENT BASED POWER AND BANDWIDTH AWARE ROUTING FOR MOBILE AD-HOC NETWORKS

Ad-hoc wireless networks are power constrained as the nodes operate with limited battery energy. To maximize the lifetime of these networks, transactions through each mobile node must be controlled...

An Influence Diagram Based Approach for Estimating Staff Training in Software Industry

The successful completion of a software development process depends on the analytical capability and foresightedness of the project manager. For the project manager, the main intriguing task is to manage the risk factors as they adversely influence the completion deadline. One such key risk factor is staff training. The risk of this factor can be avoided by pre-judging the amount of training required by the staff. So, a procedure is required to help the project manager make this decision. This paper presents a system that uses influence diagrams to implement the risk model to aid decision making. The system also considers the cost of conducting the training, based on various risk factors such as, (i) Lack of experience with project software; (ii) Newly appointed staff; (iii) Staff not well versed with the required quality standards; and (iv) Lack of experience with project environment. The system provides estimated requirement details for staff training at the beginning of a software development project.