Anupam Shukla

Bio: Anupam Shukla is an academic researcher from Indian Institute of Information Technology and Management, Gwalior. The author has contributed to research in topics: Artificial neural network & Motion planning. The author has an hindex of 22, co-authored 215 publications receiving 1896 citations. Previous affiliations of Anupam Shukla include Indian Institutes of Information Technology.

View variations effect in gait recognition and performance improvement using fusion

Abstract: This paper presents the view variations effect in gait recognition. Here different variation is created based on the walking in different angle of person with respect to particular line. Initially we are showing the result of what is the recognition rate when we are taking different view training and testing image. These results show that recognition through gait is affected by view variation. So we are using fusion strategy to improve the results. Here different view image are fuse using PCA algorithm. We are also showing the result of fusion based gait recognition in different view. All experiments are performed on CASIA gait data base. Our results show that fusion based gait recognition is more effective when we want recognition people in different view. Gait recognition is one kind of biometric technology that can be used to monitor people without their cooperation, it is also difficult to conceal.

Automatic Summary Generation from Single Document Using Information Gain

Abstract: With tons of information pouring in every day over Internet, it is not easy to read each and every document. The information retrieval from search engine is still far greater than that a user can handle and manage. So there is need of presenting the information in a summarized way. In this paper, an automatic abstractive summarization technique from single document is proposed. The sentences in the text are identified first. Then from those sentences segments, unique terms are identified. A Term-Sentence matrix is generated, where the column represents the sentences and the row represents the terms. The entries in the matrix are weight from information gain. Column with a maximum cosine similarity is selected as first sentence of the summary sentence and likewise. Results over documents indicate that the performance of the proposed approach compares very favorably with other approaches.

Discrete Invasive Weed Optimization Algorithm for Graph Based Combinatorial Road Network Management Problem

Abstract: Invasive Weed Optimization (IWO) Algorithm is a nature inspired swarm based continuous domain optimization meta-heuristics which mimicry the expansion-cum-survival strategy of the weeds in favorable, rich and unwanted regions which happens to be the best solution in terms of optimization with respect to competition, growth and nutrition These unwanted plants are in consistent competition and opposition from the other members of the nature either directly or indirectly and as a result their way of living, foraging and sustaining are the most robust and challenging This optimization technique has been proven to be successful in many continuous parameter domains due to their unique spreading characteristics and optimization search methods In this work we have extended the utility of the invasive weed optimization algorithm for graph based combinatorial optimization for path search and planning for vehicle routing from a source to destination The problem can be viewed as a multimodal optimization problem where selection of a certain sequence of multimodal solutions would be best solution For this we have modified the classical IWO to suit the graph based situation and made necessary change in implications to cope up with the graph parameters The convergence rate of the Discrete Invasive Weed Optimization (DIWO) Algorithm is being compared with Ant Colony Optimization (ACO) and Intelligent Water Drop (IWD) algorithm with an application on a road graph model for route optimization for vehicles with respect to multi-objective of travelling and waiting time

Modular Neural Networks

Abstract: Modular Neural Networks are use of a number of Neural Networks for problem solving. Here the various neural networks behave as modules to solve a part of the problem. The entire task of division of problem into the various modules as well as the integration of the responses of the modules to generate the final output of the system is done by an integrator. In this chapter we first look at the various Modular Neural Network models. Here we would mainly study two major models. The first model would cluster the entire input space with each module responsible for some part of it. The other model would make different neural networks work over the same problem. Here we would be using a response integration technique for figuring out the final output of the system. The other part of the chapter would present Evolutionary Modular Neural Networks. We would first present a simple genetic approach and then a co-evolutionary approach for this evolution of the entire Modular Neural Network.

Dealing QAP & KSP with Green Heron optimization algorithm — A new bio-inspired meta-heuristic

Abstract: In this paper a new biological phenomenon following meta-heuristics called Green Heron Optimization Algorithm (GHOA) is being discussed, for the first time, which acquired its inspiration from the Green Heron birds, their intelligence, perception analysis capability and technique for food acquisition. The natural phenomenon of the bird has been capped into some unique operations which favour the graph based and discrete combinatorial optimization problems but with slight modification can also be utilized for other wide variety of problems of the real world which have discrete representation of data and variables having several constraints. In this work we have mainly concentrated on the description, mathematical representations, presentations, features, limitations and performance analysis of the algorithm on the scattered dimensional datasets of the Quadratic Assignment Problem (QAP) & 0/1 Knapsack Problem (KSP) to clearly demarcate its performance with change in dimension that is scalability. The results of the simulation clearly reveal how the algorithm has worked optimally for the various datasets of the problem. GHOA is one of the few members in the discrete domain algorithms of the bio-inspired computation family which favours suitably the graph based problems like path planning, process scheduling etc and has the capability of recombination and local search for global optimization and refinement of the solutions.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Abstract: From the Publisher: The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Coverage control for mobile sensing networks

Abstract: This paper presents control and coordination algorithms for groups of vehicles. The focus is on autonomous vehicle networks performing distributed sensing tasks where each vehicle plays the role of a mobile tunable sensor. The paper proposes gradient descent algorithms for a class of utility functions which encode optimal coverage and sensing policies. The resulting closed-loop behavior is adaptive, distributed, asynchronous, and verifiably correct.

Artificial neural networks

Abstract: Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.