Technological advancements in the field of World Wide Web help the user to retrieve enormous number of documents as a response to a given query. Many of the research scholars proposed various techniques for retrieving the most relevant documents. All such techniques are applicable to normal web documents, where they are unsuitable for the Geo-spatial documents since it has complex information like direction, location, etc. To handle such information efficiently and to retrieve the spatial information a framework termed Semantic and Feature Aggregated Information Retrieval (SFAIR) has been proposed in this paper. This technique has four components namely (1) Clustering, (2) Indexing, (3) Retrieval, and (4) Ranking. Context-based Query Weighting (CQW) approach clusters the documents that are present in the corpus and indexed using multilevel hashing. On receiving the user query through the user interface, retrieval component uses Feature Probability and Density (FPD) technique retrieves the document that matches the user query. The FPD technique depends upon the features. The Semantic Density (SD) technique ranks the retrieved documents. Experimental result demonstrates the efficiency of the SFAIR technique over the existing technique.

Genetic algorithm (GA) based feature selection method is an evolving search heuristic, used to provide solutions to optimization problems. Feature selection is an important aspect that improves classification accuracy. The main objective of this work is to utilize GA for feature selection by integrating it with a bank of multi-class Support Vector Machine (SVM) for identification of the effective feature set. The proposed GA based approach finds its application in epileptic seizure detection. EEG dataset containing artefacts and noise were removed by employing constrained Independent Component Analysis (cICA) and Stationary Wavelet Transform (SWT). The features of the input data are constructed in the form of feature vector by FastICA technique. The fitness calculation for the selection of individuals in the GA is calculated by a Linear Discriminant Analysis (LDA) classifier. The multi-class Support Vector Machine (SVM) (one-against-all) classifier is used for the validation of the selected features. The samples are taken from 948 patients and the classes are divided as normal, seizure, and seizure-free using artificial neural networks. Experimental results demonstrate that the GA - multi-SVM feature selection technique can achieve higher accuracies as compared to the case without feature selection.

Wireless Sensor Network (WSN) consists of spatially distributed and dedicated sovereign sensor nodes with confined resources to politely monitor physical and environmental conditions. In recent years, there has been a rising interest in WSN. One of the major confrontations in WSN is developing an energy-efficient routing protocol to enhance the network longevity. With that concern, this work contributes in providing a novel approach called DAO-LEACH (Data Aggregation based Optimal- LEACH) by which the energy efficient routing in WSN is attained based on effective data ensemble and optimal clustering. Aggregating the data sent by cluster members comprehend in draining network load and amending the bandwidth. In order to minimize the energy dissipation of sensor nodes and optimize the resource utilization, cluster head is elected for each cluster. Moreover, the energy efficient route in WSN is obtained by combining the nodes having maximum residual energy. Experimental results have shown that the proposed approach furnishes efficient route for data transmission among the sensor nodes in an adept manner, thereby prolonging the network lifetime.

The prodigious growth of internet as an environment for learning has led to the development of enormous sites to offer knowledge to the novices in an efficient manner. However, evaluating the quality of those sites is a substantial task. With that concern, this paper attempts to evaluate the quality measures for enhancing the site design and contents of an e-learning framework, as it relates to information retrieval over the internet. Moreover, the proposal explores two main processes. Firstly, evaluating a website quality with the defined high-level quality metrics such as accuracy, feasibility, utility and propriety using Website Quality Assessment Model (WQAM) and secondly, developing an e-learning framework with improved quality. Specifically, the quality metrics are analyzed with the feedback compliance obtained through a Questionnaire Sample (QS). By which, the area of the website that requires improvement can be identified and then, a new e-learning framework has been developed with the incorporation of those enhancements.

Rapid improvement of electronic documents in World Wide Web has made overload to the users in accessing the information. Therefore, abstracting the primary content from numerous documents related to same topic is highly essential. Summarization of multiple documents helps in valuable decision-making in less time. This paper proposed a framework named Adept Multi-Document Summarization (AMDS) for efficient summarization of document, which achieves the aforementioned requirement. Here, the documents are preprocessed initially to remove the information that is less important. Summary of each preprocessed document is obtained through the sentence extraction process. Single document summarization is carried out based on graph model. A ranking method named Ingenious Ranking (IR) is proposed to rank and order the extracted single document summaries. It ranks the sentences in the generated summaries of each document and incorporates the individual summaries to generate a concise summary. Empirical results presented in this paper demonstrate the efficiency of the proposed AMDS framework.

Regression testing is a re-testing technique to test the changes, which is taken in the modified or enhanced application to ensure that the changes do not impairment the accessible behavior of the application. Modifications in the applications mainly focus on three types namely binding, process and interfaces. In order to accomplish the regression testing for a modified portion of an application, test cases are selected from a test suite. Selection, generation and prioritization of the test cases are more important and also it is a tough process in regression testing. In this article, we proposed a technique to automatically generate the test cases for testing the changes of various versions of BPEL (Business Process Execution Language) dataset. We construct a hierarchical test tree (HTT) for both the new and old versions composite services that are modified for an application and also for the unmodified. The changes are tracked by analyzing the control flow of both trees constructed above using the BPEL dataset. Test Case Prioritization Algorithm (TCPA), which uses multiple criteria are used to prioritize the tests cases. We analyzed the performance of the proposed technique and the experimental results showed that our method performs well than the earlier techniques.