Deepak Kumar Sharma

Anurag Singh, Deepak Kumar Sharma, Sudhir Kumar Sharma

Successful applications of deep learning (DL) requires large amount of annotated data. This often restricts the benefits of employing DL to businesses and individuals with large budgets for data-collection and computation. Summarization offers a possible solution by creating much smaller representative datasets that can allow real-time deep learning and analysis of big data and thus democratize use of DL. In the proposed work, our aim is to explore a novel approach to task-specific image corpus summarization using semantic information and self-supervision. Our method uses a classification-based Wasserstein generative adversarial network (CLSWGAN) as a feature generating network. The model also leverages rotational invariance as self-supervision and classification on another task. All these objectives are added on a features from resnet34 to make it discriminative and robust. The model then generates a summary at inference time by using K-means clustering in the semantic embedding space. Thus, another main advantage of this model is that it does not need to be retrained each time to obtain summaries of different lengths which is an issue with current end-to-end models. We also test our model efficacy by means of rigorous experiments both qualitatively and quantitatively.

Sachin Lakra, Deepak Kumar Sharma

Distributed Software Development today is in its childhood and not too widespread as a method of developing software in the global IT Industry. In this context, Petrinets are a mathematical model for describing distributed systems theoretically, whereas AttNets are one of their offshoots. But development of true distributed software is limited to network operating systems majorly. Software that runs on many machines with separate programs for each machine, are very few. This paper introduces and defines Distributed Object Oriented Software Engineering DOOSE as a new field in software engineering. The paper further gives a Distributed Object Oriented Software Process Model DOOSPM, called the DolNet, which describes how work may be done by a software development organization while working on Distributed Object Oriented DOO Projects.

Sachin Lakra, Deepak Kumar Sharma, Jugnesh Kumar et al.

In this paper, the authors propose a software metric called Class Activeness Metric which helps to determine the level of accessibility of the members of a class when it is instantiated as objects. Object interactions need to be straight forward as far as possible as complexity in these interactions can lead to time delays in accessing members not just confusing inheritance hierarchies. For object interactions to be non-complex, the classes must be designed well so that they are easily accessible. This necessitates the development of a metric for gauging the quality of design of a class. This metric is the Class Activeness Metric.

Sachin Lakra, T. V. Prasad, Deepak Kumar Sharma et al.

For the past few decades, man has been trying to create an intelligent computer which can talk and respond like he can. The task of creating a system that can talk like a human being is the primary objective of Automatic Speech Recognition. Various Speech Recognition techniques have been developed in theory and have been applied in practice. This paper discusses the problems that have been encountered in developing Speech Recognition, the techniques that have been applied to automate the task, and a representation of the core problems of present day Speech Recognition by using Fuzzy Mathematics.

Sachin Lakra, T. V. Prasad, Shree Harsh Atrey et al.

This paper makes an attempt to analyze the Activeness of a Distributed Object Oriented Component Library and develops a software metric called Distributed Component Activeness Quotient which is defined as the degree of readiness of a DOOCL. The advantages of the DCAQ include a possible comparison between various DOOCLs leading to selection of the best DOOCL for use during the development task, and providing a measure for gauging the usefulness of the DOOCL as indicated by the value of the DCAQ. The disadvantage of the DCAQ is that it may have some error because of its subjective and random nature. The Stability of a DOOCL is another characteristic which is indicated by the DCAQ. The greater the value of the DCAQ, greater will be the stability of the corresponding DOOCL.