Data Mining Using Neural Networks

Finding information hidden in data is as theoretically difficult as it is practically important. With the objective of discovering unknown patterns from data, the methodologies of data mining were derived from statistics, machine learning, and artificial intelligence, and are being used successfully in application areas such as bioinformatics, banking, retail, and many others. Wang and Fu present in detail the state of the art on how to utilize fuzzy neural networks, multilayer perceptron neural networks, radial basis function neural networks, genetic algorithms, and support vector machines in such applications. They focus on three main data mining tasks: data dimensionality reduction, classification, and rule extraction. The book is targeted at researchers in both academia and industry, while graduate students and developers of data mining systems will also profit from the detailed algorithmic descriptions.

readers will find concrete implementation strategies, reinforced with real-world business examples and a minimum of formulas, and case studies drawn from a broad range of industries. The book illustrates the popular data mining functions of classification, clustering, modeling, and time-series forecasting--through examples developed using the IBM Neural Network Utility.

Statistical Learning using Neural Networks: A Guide for Statisticians and Data Scientists with Python introduces artificial neural networks starting from the basics and increasingly demanding more effort from readers, who can learn the theory and its applications in statistical methods with concrete Python code examples. It presents a wide range of widely used statistical methodologies, applied in several research areas with Python code examples, which are available online. It is suitable for scientists and developers as well as graduate students. Key Features: Discusses applications in several research areas Covers a wide range of widely used statistical methodologies Includes Python code examples Gives numerous neural network models This book covers fundamental concepts on Neural Networks including Multivariate Statistics Neural Networks, Regression Neural Network Models, Survival Analysis Networks, Time Series Forecasting Networks, Control Chart Networks, and Statistical Inference Results. This book is suitable for both teaching and research. It introduces neural networks and is a guide for outsiders of academia working in data mining and artificial intelligence (AI). This book brings together data analysis from statistics to computer science using neural networks.

Neural networks are a hot topic in the business community today. Also marketed as intelligent techniques, business intelligence and data mining, many businesses are now realising the potential of neural networks to give them a competitive edge. Nevertheless most neural network books are written by electrical engineers for electrical engineers, with a high level of mathematics. Those few books aimed at the business community invariably focus exclusively on financial prediction. Consequently, Introduction to Neural Networks and Data Mining for Business Applications is a ground breaking text. With a minimum of mathematics, it shows the potential of neural networks to unlock hidden information in data of various industries including retail, marketing, insurance, telecommunications, banking and finance, and operations management. The book covers the development of neural network research and its impact on business; the early neural Perceptron model and its limitations; backpropagation, the most commonly used learning paradigm in business applications; self-organisation; and adaptive resonance theory. Data mining is then covered including the purpose, methodology, and concepts of directed and undirected knowledge discovery. Other intelligent techniques often used in conjunction with neural networks are also covered, including genetic algorithms, fuzzy logic, and expert systems. The text concludes with a discussion of the future of neural networks research and applications. Extensive business case studies are used throughout the text to demonstrate techniques.

This book provides a thorough summary of the means currently available to the investigators of Artificial Intelligence for making criminal behavior (both individual and collective) foreseeable, and for assisting their investigative capacities. The volume provides chapters on the introduction of artificial intelligence and machine learning suitable for an upper level undergraduate with exposure to mathematics and some programming skill or a graduate course. It also brings the latest research in Artificial Intelligence to life with its chapters on fascinating applications in the area of law enforcement, though much is also being accomplished in the fields of medicine and bioengineering. Individuals with a background in Artificial Intelligence will find the opening chapters to be an excellent refresher but the greatest excitement will likely be the law enforcement examples, for little has been done in that area. The editors have chosen to shine a bright light on law enforcement analytics utilizing artificial neural network technology to encourage other researchers to become involved in this very important and timely field of study.

These are the proceedings of the tenth event of the Industrial Conference on Data Mining ICDM held in Berlin (www.data-mining-forum.de). For this edition the Program Committee received 175 submissions. After the pe- review process, we accepted 49 high-quality papers for oral presentation that are included in this book. The topics range from theoretical aspects of data mining to app- cations of data mining such as on multimedia data, in marketing, finance and telec- munication, in medicine and agriculture, and in process control, industry and society. Extended versions of selected papers will appear in the international journal Trans- tions on Machine Learning and Data Mining (www.ibai-publishing.org/journal/mldm). Ten papers were selected for poster presentations and are published in the ICDM Poster Proceeding Volume by ibai-publishing (www.ibai-publishing.org). In conjunction with ICDM four workshops were held on special hot applicati- oriented topics in data mining: Data Mining in Marketing DMM, Data Mining in LifeScience DMLS, the Workshop on Case-Based Reasoning for Multimedia Data CBR-MD, and the Workshop on Data Mining in Agriculture DMA. The Workshop on Data Mining in Agriculture ran for the first time this year. All workshop papers will be published in the workshop proceedings by ibai-publishing (www.ibai-publishing.org). Selected papers of CBR-MD will be published in a special issue of the international journal Transactions on Case-Based Reasoning (www.ibai-publishing.org/journal/cbr).

DATA MINING AND MACHINE LEARNING APPLICATIONS The book elaborates in detail on the current needs of data mining and machine learning and promotes mutual understanding among research in different disciplines, thus facilitating research development and collaboration. Data, the latest currency of today’s world, is the new gold. In this new form of gold, the most beautiful jewels are data analytics and machine learning. Data mining and machine learning are considered interdisciplinary fields. Data mining is a subset of data analytics and machine learning involves the use of algorithms that automatically improve through experience based on data. Massive datasets can be classified and clustered to obtain accurate results. The most common technologies used include classification and clustering methods. Accuracy and error rates are calculated for regression and classification and clustering to find actual results through algorithms like support vector machines and neural networks with forward and backward propagation. Applications include fraud detection, image processing, medical diagnosis, weather prediction, e-commerce and so forth. The book features: A review of the state-of-the-art in data mining and machine learning, A review and description of the learning methods in human-computer interaction, Implementation strategies and future research directions used to meet the design and application requirements of several modern and real-time applications for a long time, The scope and implementation of a majority of data mining and machine learning strategies. A discussion of real-time problems. Audience Industry and academic researchers, scientists, and engineers in information technology, data science and machine and deep learning, as well as artificial intelligence more broadly.

New to the second edition of this advanced text are several chapters on regression, including neural networks and deep learning.