الصفحة 1
الصفحة 1
New trends in computational vision and bio-inspired computing : Selected works presented at the ICCVBIC 2018, Coimbatore, India
Gathers selected, peer-reviewed original contributions presented at the International Conference on Computational Vision and Bio-inspired Computing (ICCVBIC) conference which was held in Coimbatore, India, on November 29-30, 2018. The works included here offer a rich and diverse sampling of recent developments in the fields of Computational Vision, Fuzzy, Image Processing and Bio-inspired Computing. The topics covered include computer vision; cryptography and digital privacy; machine learning and artificial neural networks; genetic algorithms and computational intelligence; the Internet of Things; and biometric systems, to name but a few. The applications discussed range from security, healthcare and epidemic control to urban computing, agriculture and robotics.
New Algorithms for Macromolecular Simulation
Molecular simulation is a widely used tool in biology, chemistry, physics and engineering. This book contains a collection of articles by leading researchers who are developing new methods for molecular modelling and simulation. Topics addressed here include: multiscale formulations for biomolecular modelling, such as quantum-classical methods and advanced solvation techniques; protein folding methods and schemes for sampling complex landscapes; membrane simulations; free energy calculation; and techniques for improving ergodicity. The book is meant to be useful for practitioners in the simulation community and for those new to molecular simulation who require a broad introduction to the state of the art.
Introduction to Machine Learning with Applications in Information Security
Provides a classroom-tested introduction to a wide variety of machine learning and deep learning algorithms and techniques, reinforced via realistic applications. The book is accessible and doesn't prove theorems, or dwell on mathematical theory. The goal is to present topics at an intuitive level, with just enough detail to clarify the underlying concepts. The book covers core classic machine learning topics in depth, including Hidden Markov Models (HMM), Support Vector Machines (SVM), and clustering. Additional machine learning topics include k-Nearest Neighbor (k-NN), boosting, Random Forests, and Linear Discriminant Analysis (LDA). The fundamental deep learning topics of backpropagation, Convolutional Neural Networks (CNN), Multilayer Perceptrons (MLP), and Recurrent Neural Networks (RNN) are covered in depth. A broad range of advanced deep learning architectures are also presented, including Long Short-Term Memory (LSTM), Generative Adversarial Networks (GAN), Extreme Learning Machines (ELM), Residual Networks (ResNet), Deep Belief Networks (DBN), Bidirectional Encoder Representations from Transformers (BERT), and Word2Vec.
Instrumaster
Experiments with different neural network structures and algorithms in order to achieve musical note recognition as well as musical instrument recognition, all bundled in a mobile application. It also aims to create the most effective music-learning application that works completely offline, which is hard to find in modern music applications. The paper also explores why the instrument identifying AI is solely based on Multi-Layer Perceptron (MLP) and why the note-identifying AI system was chosen to be a ML system over CNN or other deep-learning trained AI. The paper presents feature extraction methods for audio signals and files and dives deep into the process, such as FFT, MFCCs, Wavelengths, sampling rates, etc. It also touches on Logistic Regression Algorithms, their limitations, and their performance with the different use cases in the application. All these techniques are then compared side by side for maximally added value, making this research paper a good reference for any future developers looking to find optimal neural networks techniques when it comes to audio processing and analysis.
Image-Based Rendering
Image-based rendering (IBR) refers to a collection of techniques and representations that allows 3D scenes and objects to be visualized in a realistic way without full 3D model reconstruction. The potential for photorealistic visualization has tremendous appeal, especially for applications such as video games, virtual travel, and E-commerce, which stand to greatly benefit from this technology.
How Data Quality Affects our Understanding of the Earnings Distribution
This book demonstrates how data quality issues affect all surveys and proposes methods that can be utilised to deal with the observable components of survey error in a statistically sound manner. This book begins by profiling the post-Apartheid period in South Africa's history when the sampling frame and survey methodology for household surveys was undergoing periodic changes due to the changing geopolitical landscape in the country. This book profiles how different components of error had disproportionate magnitudes in different survey years, including coverage error, sampling error, nonresponse error, measurement error, processing error and adjustment error.
Hierarchical Bayesian Optimization Algorithm : Toward a New Generation of Evolutionary Algorithms
This book provides a framework for the design of competent optimization techniques by combining advanced evolutionary algorithms with state-of-the-art machine learning techniques. The book focuses on two algorithms that replace traditional variation operators of evolutionary algorithms by learning and sampling Bayesian networks: the Bayesian optimization algorithm (BOA) and the hierarchical BOA (hBOA). BOA and hBOA are theoretically and empirically shown to provide robust and scalable solution for broad classes of nearly decomposable and hierarchical problems. A theoretical model is developed that estimates the scalability and adequate parameter settings for BOA and hBOA. The performance of BOA and hBOA is analyzed on a number of artificial problems of bounded difficulty designed to test BOA and hBOA on the boundary of their design envelope.
Hexagonal image processing : A practical approach
Hexagonal Image Processing provides an introduction to the processing of hexagonally sampled images, includes a survey of the work done in the field, and presents a novel framework for hexagonal image processing (HIP) based on hierarchical aggregates. Digital image processing is currently dominated by the use of square sampling lattices, however, hexagonal sampling lattices can also be used to define digital images. The strengths offered by hexagonal lattices over square lattices are considerable: • higher packing density, • uniform connectivity of points (pixels) in the lattice, • better angular resolution by virtue of having more nearest neighbours, and • superlative representation of curves. The utility of the HIP framework is demonstrated by implementing several basic image processing techniques (for the spatial and frequency domain) and some applications. The HIP framework serves as a tool for comparing processing of images defined on a square vs hexagonal grid, to determine their relative merits and demerits. The theory and algorithms covered are supplemented by attention to practical details such as accommodating hardware that support only images sampled on a square lattice. Including a Foreword written by Professor Narendra Ahuja, an eminent researcher in the field of Image Processing and Computer Vision, the book’s fresh approach to the subject offers insight and workable know-how to both researchers and postgraduates.
Design and analysis of randomized algorithms : Introduction to design paradigms
Randomness is a powerful phenomenon that can be harnessed to solve various problems in all areas of computer science. Randomized algorithms are often more efficient, simpler and, surprisingly, also more reliable than their deterministic counterparts. Computing tasks exist that require billions of years of computer work when solved using the fastest known deterministic algorithms, but they can be solved using randomized algorithms in a few minutes with negligible error probabilities. Introducing the fascinating world of randomness, this book systematically teaches the main algorithm design paradigms – foiling an adversary, abundance of witnesses, fingerprinting, amplification, and random sampling, etc. – while also providing a deep insight into the nature of success in randomization. Taking sufficient time to present motivations and to develop the reader's intuition, while being rigorous throughout, this text is a very effective and efficient introduction to this exciting field.
Deep learning and computer vision in remote sensing-I
In the last few years, huge amounts of progress have been made regarding remote sensing in the field of computer vision. This success and progress is mostly due to the effectiveness of deep learning (DL) algorithms. In addition, the remote sensing community has shifted its attention to DL, and DL algorithms have been used to achieve significant success in many image analysis tasks. However, with regard to remote sensing, a number of challenges caused by difficulties in data acquisition and annotation have not been fully solved yet. This reprint is a collection of novel developments in the field of remote sensing using computer vision, deep learning, and artificial intelligence. The articles published involve fundamental theoretical analyses as well as those demonstrating their application to real-world problems.
Cooperative Bug Isolation : Winning Thesis of the 2005 ACM Doctoral Dissertation Competition
Efforts to understand and predict the behavior of software date back to the earliest days of computer programming,over half a century ago. In the intervening decades, the need for effective methods of understanding software has only increased; so- ware has spread to become the underpinning of much of modern society, and the potentially disastrous consequences of broken or poorly understood software have become all too apparent.
Cognitive Vision Systems : Sampling the Spectrum of Approaches
This volume is a post-event proceedings volume and contains selected papers based on the presentations given, and the lively discussions that ensued, during a seminar held in Dagstuhl Castle, Germany, in October 2003. Co-sponsored by ECVision, the cognitive vision network of excellence, it was organized to further strengthen cooperation between research groups from different countries, and scientists active in related areas were invited from around the world.
Beginning Java™ SE 6 Platform : From novice to professional
Beginning Java™ SE 6 Platform: From Novice to Professional steers you through the maze of Java Standard Edition (SE) 6 features. The first chapter sets the stage by introducing Java SE 6 in terms of its name change, themes, an overview, and a sampling of new features. It also briefly discusses the first two Java SE 6 updates.
Algorithms and Models for the Web-Graph ; 5th International Workshop, WAW 2007, San Diego, CA, USA, December 11-12, 2007, Proceedings
The book address a wide variety of topics related to the study of the Web-graph such as random graph models for the Web-graph, PageRank analysis and computation, decentralized search, local partitioning algorithms,and traceroute sampling. The Web-graph has been the focal point of a tremendous amount of research for more than a decade. The view of the Web as a graph has great practical importance and has also generated much interesting theoretical work.
Algorithms and data structures for massive datasets
Learn: Probabilistic sketching data structures for practical problems Choosing the right database engine for your application Evaluating and designing efficient on-disk data structures and algorithms Understanding the algorithmic trade-offs involved in massive-scale systems Deriving basic statistics from streaming data Correctly sampling streaming data Computing percentiles with limited space resources Algorithms and Data Structures for Massive Datasets reveals a toolbox of new methods that are perfect for handling modern big data applications. You'll explore the novel data structures and algorithms that underpin Google, Facebook, and other enterprise applications that work with truly massive amounts of data. These effective techniques can be applied to any discipline, from finance to text analysis. Graphics, illustrations, and hands-on industry examples make complex ideas practical to implement in your projects--and there's no mathematical proofs to puzzle over. Work through this one-of-a-kind guide, and you'll find the sweet spot of saving space without sacrificing your data's accuracy. About the Technology Standard algorithms and data structures may become slow--or fail altogether--when applied to large distributed datasets. Choosing algorithms designed for big data saves time, increases accuracy, and reduces processing cost.
Algorithmic Aspects of Wireless Sensor Networks ; 4th International Workshop, ALGOSENSORS 2008, Reykjavik, Iceland, July 2008. Revised Selected Papers
This book constitutes the reviewed proceedings of the Fourth International Workshop on Algorithmic Aspects of Wireless Sensor Networks, ALGOSENSORS 2008, held in Reykjavik, Iceland, Wroclaw, Poland, July 12, 2008.
Advances in image enhancement
In the era of the internet of things, images have played important roles in human–computer interactions, and with the arrival of big data technology, people have higher requirements regarding image quality, especially for images collected in dark light. This can be addressed through the development of camera hardware quality, i.e., the resolution and exposure time of cameras, which may require high computational costs. As an alternative, image enhancement techniques can exact salient features to improve the quality of captured images according to the differences in diverse features, although they suffer from some challenges, i.e., a low contrast, artifacts, and overexposure, thus making it decidedly necessary to determine how to use advanced image enhancement techniques.
Advances and applications of DSmT for information fusion: Collected works ; Vol.3
One of the most comprehensive and flexible fusion theory based on belief functions. It can work in all fusion spaces: power set, hyper-power set, and super-power set, and has various fusion and conditioning rules that can be applied depending on each application. Some new generalized rules are introduced in this volume with codes for implementing some of them. For the qualitative fusion, the DSm Field and Linear Algebra of Refined Labels (FLARL) is proposed which can convert any numerical fusion rule to a qualitative fusion rule. When one needs to work on a refined frame of discernment, the refinement is done using Smarandache s algebraic codification. New interpretations and implementations of the fusion rules based on sampling techniques and referee functions are proposed, including the probabilistic proportional conflict redistribution rule.
Advances and applications of DSmT for information fusion ; Vol. 4
One of the most comprehensive and flexible fusion theory based on belief functions. It can work in all fusion spaces: power set, hyper-power set, and super-power set, and has various fusion and conditioning rules that can be applied depending on each application. Some new generalized rules are introduced in this volume with codes for implementing some of them. For the qualitative fusion, the DSm Field and Linear Algebra of Refined Labels (FLARL) is proposed which can convert any numerical fusion rule to a qualitative fusion rule. When one needs to work on a refined frame of discernment, the refinement is done using Smarandache s algebraic codification. New interpretations and implementations of the fusion rules based on sampling techniques and referee functions are proposed, including the probabilistic proportional conflict redistribution rule.
A First Course in Statistical Inference
Offers a modern and accessible introduction to Statistical Inference, the science of inferring key information from data. Aimed at beginning undergraduate students in mathematics, it presents the concepts underpinning frequentist statistical theory. Written in a conversational and informal style, this concise text concentrates on ideas and concepts, with key theorems stated and proved. Detailed worked examples are included and each chapter ends with a set of exercises, with full solutions given at the back of the book. Examples using R are provided throughout the book, with a brief guide to the software included. Topics covered in the book include: sampling distributions, properties of estimators, confidence intervals, hypothesis testing, ANOVA, and fitting a straight line to paired data.
