Data Mining - Concepts and Techniques.

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.

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

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.

Coverage control for mobile sensing networks

International Journal of Computer and Applications

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.

Artificial neural networks

In this paper, we present a deep learning based approach to assign POS tags to words in a piece of text given to it as input. We propose an unsupervised approach owing to the lack of a large Sanskrit annotated corpora and use the untagged Sanskrit Corpus prepared by JNU for our purpose. The only tagged corpora for Sanskrit is created by JNU which has 115,000 words which are not sufficient to apply supervised deep learning approaches. For the tag assignment purpose and determining model accuracy, we utilize this tagged corpus. We explore various methods through which each Sanskrit word can be represented as a point multi-dimensional vector space whose position accurately captures its meaning and semantic information associated with it. We also explore other data sources to improve performance and robustness of the vector representations. We use these rich vector representations and explore autoencoder based approaches for dimensionality reduction to compress these into encodings which are suitable for clustering in the vector space. We experiment with different dimensions of these compressed representations and present one which was found to offer the best clustering performance. For modelling the sequence in order to preserve the semantic information we feed these embeddings to a bidirectional LSTM autoencoder. We assign a POS tag to each of the obtained clusters and produce our result by testing the model on the tagged corpus.

Deep Learning Based Unsupervised POS Tagging for Sanskrit

Target searching with autonomous robots require an efficient target search method that considers their constraints and environmental characteristics. Particle swarm optimization (PSO) is a fantastic population-based optimization algorithm. It is often used in swarm robotics cooperative search jobs because of its inspiration resources and velocity updating function. Given the global optimization features of PSO, it is simple to converge on a particular location in a search environment and miss out on opportunities to learn more. This paper proposes an adaptive exploration robotic PSO (AERPSO) to solve multi-target search problems. The proposed method enhances the chances of exploring unexplored regions and helps with obstacle avoidance using evolutionary speed and aggregation degree. The adaptive inertia weight helps in enhanced exploration. The simulation results compiled from various simulation experiments show that AERPSO performs way ahead of the existing state-of-the-art techniques for target searching. The proposed algorithm improves the search time by approximately 40% and the detection rate by 25% in comparison with existing approaches. It balances exploration and exploitation to become an excellent approach for multi-target searching. • Propose an adaptive exploration robotic PSO to search multiple targets. • The method avoids local minima and keeps the diversity among the population. • It enhances the exploration by adapting the inertia weights. • The proposed algorithm deals with overshooting problem of PSO. 

AERPSO - An adaptive exploration robotic PSO based cooperative algorithm for multiple target searching

Communication in natural languages between computational systems and humans is an area that has attracted researchers for long. This type of communication can have wide ramification as such a system could find wide usage in several areas. WebBrowsing via input given as textual commands/sentences in natural languages is one such area. However, the enormous amount of input that could be given in natural languages present a huge challenge for machine learning of systems which are required to recognize sentences having similar meaning but different lexico-grammatical structures. In this paper, we describe how a binary recurring neural network can be used to sufficiently solve this problem for English. The system uses the Hopfield Neural Network to recognize the meaning of text using training files with limited dictionary. Detailed analysis and evaluation show that the system correctly recognizes/classifies approximately 92.2% of the input sentences according to their meaning.

/pdf/sentence-recognition-using-hopfield-neural-network-10zxk72o4u.pdf

Sentence Recognition Using Hopfield Neural Network

Due to information revolution, huge amount of data is available over internet but retrieving correct and relevant data is not an easy task. The information retrieval from search engines is still far greater than that a user can handle and manage. Thus there is need of presenting the information in an abstract way so that one can easily infer the meaning without reading the whole document. In this paper, Human aided text summarizer "SAAR" is being proposed for single document. From the document, a term-sentence matrix is generated. The entries in the matrix are weight from Reinforcement Learning. Thus generated summary is shown to the user and if the user approve it then it is the final summary, otherwise new summary is generated as per the user feedback in form of keywords. Results of experiments on DUC2006 documents indicate that the performance of the proposed approach compares very favorably with other approaches in terms of precision, recall, and F-score.

Human Aided Text Summarizer "SAAR" Using Reinforcement Learning

Financial time series forecast has been classified as standard problem in forecasting due to its high non-linearity and high volatility in data. Statistical methods such as GARCH, GJR, EGARCH and Artificial Neural Networks (ANNs) based on standard learning algorithms such as backpropagation have been widely used for forecasting time series volatility of various fields. In this paper, we propose hybrid model of statistical methods with ANNs. Statistical methods require assumptions about the market, they do not reflect all market variables and they may not capture the non-linearity. Shortcoming of ANNs is their process of identifying inputs insignificantly through which network produces output. The attempt for hybrid system is to outperform the forecast results and overcome the shortcomings by extracting input variables from statistical methods and include them in ANNs learning process. Further genetic algorithm is used for evolution of proposed hybrid models. Experimental results confirm the lesser root mean square error (RMSE) results obtained from proposed evolutionary hybrid ANN models EANN-GARCH, EANN-GJR, EANN-EGARCH than conventional ANNs and statistical methods.

Anupam Shukla

Papers

Deep Learning Based Unsupervised POS Tagging for Sanskrit

AERPSO - An adaptive exploration robotic PSO based cooperative algorithm for multiple target searching

Sentence Recognition Using Hopfield Neural Network

Human Aided Text Summarizer "SAAR" Using Reinforcement Learning

Financial Time Series Volatility Forecast Using Evolutionary Hybrid Artificial Neural Network