Om Prakash Vyas

Fuzzy Rule-Based Approach for Software Fault Prediction

Knowing faulty modules prior to testing makes testing more effective and helps to obtain reliable software. Here, we develop a framework for automatic extraction of human understandable fuzzy rules for software fault detection/classification. This is an integrated framework to simultaneously identify useful determinants (attributes) of faults and fuzzy rules using those attributes. At the beginning of the training, the system assumes every attribute (feature) as a useless feature and then uses a concept of feature attenuating gate to select useful features. The learning process opens the gates or closes them more tightly based on utility of the features. Our system can discard derogatory and indifferent attributes and select the useful ones. It can also exploit subtle nonlinear interaction between attributes. In order to demonstrate the effectiveness of the framework, we have used several publicly available software fault data sets and compared the performance of our method with that of some existing methods. The results using tenfold cross-validation setup show that our system can find useful fuzzy rules for fault prediction.

Augmented intuitive dissimilarity metric for clustering of Web user sessions

Clustering is a very useful technique to categorise Web users with common browsing activities, access patterns and navigational behaviour. Web user clustering is used to build Web visitor profiles that make the core of a personalised information recommender system. These systems are used to comprehend Web users surfing activities by offering tailored content to Web users with similar interests. The principle objective of Web user sessions clustering is to maximise the intra-group while minimising the inter-group similarity. Efficient clustering of Web users’ sessions not only depend on the clustering algorithm’s nature but also depend on how well user concerns are captured and accommodated by the dissimilarity measure that are used. Determining the right dissimilarity measure to capture the access behaviour of the Web user is very significant for substantial clustering. In this paper, an intuitive dissimilarity measure is presented to estimate a Web user’s concern from augmented Web user sessions. The proposed usage dissimilarity measure between two Web user sessions is based on the accessing page relevance, the syntactic structure of page URL and hierarchical structure of the website. This proposed intuitive dissimilarity measure was used with K-Medoids Clustering algorithm for experimentation and results were compared with other independent dissimilarity measures. The worth of the generated clusters were evaluated by two unsupervised cluster validity indexes. The experimental results show that intuitive augmented session dissimilarity measure is more realistic and superior as compared to the other independent dissimilarity measures regarding cluster validity indexes.

Token Bus Based MAC protocol for Wireless Sensor Networks

this paper, we propose TBB-MAC, an enhancement for medium access control (MAC) protocol based on the token bus in wireless sensor networks (WSNs). In this type of networks, sensors are spatially correlated and they often sense and collect the information and send it to the sink. In this paper, we design an innovative contention-based MAC protocol to provide long network lifetime. Our ideas help wireless nodes at sleep mode as much as possible to avoid major energy waste causes, such as idle listening, collision and overhearing. We want to show that, TBB- MAC can be an efficient method to reduce redundant transmissions in sensor networks, thus diminishing energy consumption and transmission delay. Hence, the network lifetime can last longer and the sink receives events within shorter delays. We propose to apply our technique in S-MAC and T-MAC, the contention based protocols for WSN. By simulation and experimentation, we prove that TBB-MAC overpasses S-MAC and T-MAC in terms of energy consumption and transmission delay.

Semi-automatic terminology ontology learning based on topic modeling

Abstract Ontologies provide features like a common vocabulary, reusability, machine-readable content, and also allows for semantic search, facilitate agent interaction and ordering & structuring of knowledge for the Semantic Web (Web 3.0) application. However, the challenge in ontology engineering is automatic learning, i.e., the there is still a lack of fully automatic approach from a text corpus or dataset of various topics to form ontology using machine learning techniques. In this paper, two topic modeling algorithms are explored, namely LSI & SVD and Mr.LDA for learning topic ontology. The objective is to determine the statistical relationship between document and terms to build a topic ontology and ontology graph with minimum human intervention. Experimental analysis on building a topic ontology and semantic retrieving corresponding topic ontology for the users query demonstrating the effectiveness of the proposed approach.

Ontology-based classification and analysis of non-emergency smart-city events

Several challenges are faced by citizens of urban centers while dealing with day-to-day events, and the absence of a centralized reporting mechanism makes event-reporting and redressal a daunting task. With the push on information technology to adapt to the needs of smart-cities and integrate urban civic services, the use of Open311 architecture presents an interesting solution. In this paper, we present a novel approach that uses an existing Open311 ontology to classify and report non-emergency city-events, as well as to guide the citizen to the points of redressal. The use of linked open data and the semantic model serves to provide contextual meaning and make vast amounts of content hyper-connected and easily-searchable. Such a one-size-fits-all model also ensures reusability and effective visualization and analysis of data across several cities. By integrating urban services across various civic bodies, the proposed approach provides a single endpoint to the citizen, which is imperative for smooth functioning of smart cities.

A PSO Based Approach for Producing Optimized Latent Factor in Special Reference to Big Data

Now a days application deal with Big Data has tremendously been used in the popular areas. To tackle with such kind of data various approaches have been developed by researchers in the last few decades. A recent investigated techniques to factored the data matrix through a known latent factor in a lower size space is the so called matrix factorization. In addition, one of the problems with the NMF approaches, its randomized valued could not provide absolute optimization in limited iteration, but having local optimization. Due to this, the authors have proposed a new approach that considers the initial values of the decomposition to tackle the issues of computationally expensive. They have devised an algorithm for initializing the values of the decomposed matrix based on the PSO. In this paper, the auhtors have intended a genetic algorithm based technique while incorporating the nonnegative matrix factorization. Through the experimental result, they will show the proposed method converse very fast in comparison to other low rank approximation like simple NMF multiplicative, and ACLS technique.

An ontological learning management system

The current learning systems typically lack the level of meta‐cognitive awareness, self‐directed learning, and time management skills. Most of the ontologically based learning management systems are in the proposed phase and those which are developed do not provide the necessary path guidance for proper learning. The systems available are not as adaptive from the viewpoint of the learner as required. Ontology engineering has become an important pillar for knowledge management and representation in recent years. The design, approach, and implementation of ontology in e‐ and m‐learning systems have made them more effective. In this paper, we have proposed a system for the betterment of knowledge management and representation of associated data as compared to the previously available learning management systems. Here, we have presented the application and implementation of ontological engineering methodology in the Computer Science domain. For knowledge management, we have created a domain associated ontology which represents knowledge of a single domain. Subsequently, ontology has been created to manage a learner profile so that a learner may be aligned to a proper path of learning. The learner ontology will use the VARK learning model which classifies what kind of learning does the learner requires so that necessary resources could be provided.

Energy Efficient Election protocol for wireless sensor networks

Wireless a sensor network, which typically consist of large number of sensor nodes, is deployed in environmental fields for sensing and actuating applications. The protocols in WSNs play an important role in energy savings and the performance of WSNs could be improved by designing suitable MAC protocols. Energy efficiency is one of the important research themes while designing wireless sensor network nodes as WSNs are battery powered. MAC protocols are also used to minimize latency and maximize throughput in wireless sensor networks. Observably there are many MAC protocols available nowadays for WSNs but the actual objective is minimizing the energy consumption so that the lifetime is maximized. This paper is aimed at to summarize the key requirements for MAC protocol design and we have proposed a new protocol: Energy Efficient Election protocol (EEE-MAC) for WSNs. Our protocol is based on cluster based election algorithm and it can be implemented with any existing protocols. We have compared our proposed protocol with the existing contention-based S-MAC and T-MAC protocols. The simulation results show that our protocol has achieved better energy saving than the other three protocols.

Blended e-Learning Training (BeLT): Enhancing Railway Station Controller Knowledge

With the growing economy, e-learning consequently gained increasing attention as it conveys knowledge globally with improved interactivity, assistance and reduced costs. For the past few years, accidental challenges have become the severe problem with railway units due to irresponsibility, lack of knowledge and improper guidance of station controllers (learners). While focusing on e-learning technologies railway units failed to admit learners need, cultural diversity and background skills by creating ethnically impartial e-learning environments, which resulted in inadequate training and degraded performance. The purpose of this study is to understand the vision of a global diverse group of station traffic controllers about e-learning courses developed by their individual railway units. The opinions of these officials have been verified by questionnaires on the basis of course organization, course accuracy, course effectiveness, course relevance, course productivity and course interactivity. The results obtained show that the developed e-learning course was highly helpful, interactive, creative, and user-friendly for learners. This leads to making e-learning conquered among independent learners.

Optimization of feature selection method for high dimensional data using fisher score and minimum spanning tree

For classification of High Dimensional data, feature selection is the most important step for obtaining optimal result with respect to processing power required and time taken. Feature selection is a method by which the most relevant feature is selected from a set of features containing redundant and irrelevant features thereby reducing the load on the classification algorithm. This paper proposes an implementation of this method in a two tier structure. In the first step, a high ranking feature is selected using the well-known filter based algorithm - Fisher Score. This algorithm selects the relevant feature from the feature set based on a preset threshold. The second step generates a cluster of redundant features utilizing MST (Minimum Spanning Tree) algorithm, which are then filtered out to preserve the most relevant features out of each cluster. This increases the classification accuracy as well as running time and hence the computation cost. The efficacy of the presented approach was validated by comparing the same with other well-known feature selection algorithms: Fisher Score, CFS and ConsSF with respect to three classifiers: IB1, C4.5, and Naïve Bayes. The presented approach achieved higher Classification accuracy and lower run time.