Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Data Mining Practical Machine Learning Tools and Techniques

Feature selection is an important task in data mining and machine learning to reduce the dimensionality of the data and increase the performance of an algorithm, such as a classification algorithm. However, feature selection is a challenging task due mainly to the large search space. A variety of methods have been applied to solve feature selection problems, where evolutionary computation (EC) techniques have recently gained much attention and shown some success. However, there are no comprehensive guidelines on the strengths and weaknesses of alternative approaches. This leads to a disjointed and fragmented field with ultimately lost opportunities for improving performance and successful applications. This paper presents a comprehensive survey of the state-of-the-art work on EC for feature selection, which identifies the contributions of these different algorithms. In addition, current issues and challenges are also discussed to identify promising areas for future research.

/pdf/a-survey-on-evolutionary-computation-approaches-to-feature-5c2qznm5vr.pdf

A Survey on Evolutionary Computation Approaches to Feature Selection

https://fada.birzeit.edu/bitstream/20.500.11889/5314/1/Hybrid%20Whale%20Optimization%20Algorithm%20with%20Simulated%20Annealing%20for%20FS.pdf

Hybrid Whale Optimization Algorithm with Simulated Annealing for Feature Selection

The fifth edition of "Numerical Methods for Engineers" continues its tradition of excellence. Instructors love this text because it is a comprehensive text that is easy to teach from. Students love it because it is written for them--with great pedagogy and clear explanations and examples throughout. The text features a broad array of applications, including all engineering disciplines. The revision retains the successful pedagogy of the prior editions. Chapra and Canale's unique approach opens each part of the text with sections called Motivation, Mathematical Background, and Orientation, preparing the student for what is to come in a motivating and engaging manner. Each part closes with an Epilogue containing sections called Trade-Offs, Important Relationships and Formulas, and Advanced Methods and Additional References. Much more than a summary, the Epilogue deepens understanding of what has been learned and provides a peek into more advanced methods. Approximately 80% of the end-of-chapter problems are revised or new to this edition. The expanded breadth of engineering disciplines covered is especially evident in the problems, which now cover such areas as biotechnology and biomedical engineering. Users will find use of software packages, specifically MATLAB and Excel with VBA. This includes material on developing MATLAB m-files and VBA macros.

Numerical methods for engineers

A new local search based hybrid genetic algorithm for feature selection

In this paper, we propose a new hybrid ant colony optimization (ACO) algorithm for feature selection (FS), called ACOFS, using a neural network. A key aspect of this algorithm is the selection of a subset of salient features of reduced size. ACOFS uses a hybrid search technique that combines the advantages of wrapper and filter approaches. In order to facilitate such a hybrid search, we designed new sets of rules for pheromone update and heuristic information measurement. On the other hand, the ants are guided in correct directions while constructing graph (subset) paths using a bounded scheme in each and every step in the algorithm. The above combinations ultimately not only provide an effective balance between exploration and exploitation of ants in the search, but also intensify the global search capability of ACO for a high-quality solution in FS. We evaluate the performance of ACOFS on eight benchmark classification datasets and one gene expression dataset, which have dimensions varying from 9 to 2000. Extensive experiments were conducted to ascertain how AOCFS works in FS tasks. We also compared the performance of ACOFS with the results obtained from seven existing well-known FS algorithms. The comparison details show that ACOFS has a remarkable ability to generate reduced-size subsets of salient features while yielding significant classification accuracy.

A new hybrid ant colony optimization algorithm for feature selection

This paper presents a currency recognition system using ensemble neural network (ENN) The individual neural networks (NNs) in an ENN are trained via negative correlation learning The objective of using negative correlation learning (NCL) is to expertise the individuals on different parts or portion of input patterns in an ensemble The available currencies in the market consist of new, old and noisy ones It is often difficult for machine to recognize these currencies; therefore we propose a system that uses ENN to identify them efficiently We performed our experiment for seven different types of TAKA (Bangladeshi currency) which are 2, 5, 10, 20, 50, 100 and 500 TAKA The image of different types note is converted in gray scale and compressed in the desired range Each pixel of the compressed image is given as an input to the network This system is able to recognize highly noisy or old image of TAKA Ensemble network is very useful for the classification of different types of currencies It reduces the chances of misclassification than a single network and ensemble network with independent training In experimental results we have shown this with artificially added noise in the test set We also find good result for similar pattern available in market

A Paper Currency Recognition System Using Negatively Correlated Neural Network Ensemble

Speaker Recognition is the process of identifying a speaker by analyzing spectral shape of the voice signal This is done by extracting & matching the feature of voice signal Mel-frequency Cepstrum Co-efficient (MFCC) is the feature extraction technique in which we will get some coefficients named Mel-Frequency Cepstrum coefficient This Cepstrum Co-efficient is extracted feature This extracted feature is taken as the input of Vector Quantization process Vector Quantization (VQ) is the typical feature matching technique in which VQ codebook is generated by providing pre-defined spectral vectors for each speaker to cluster the training vectors in a training session Finally test data are provided for searching the nearest neighbor to match that data with the trained data The result is to recognize correctly the speakers where music & speech data (Both in English & Bengali format) are taken for the recognition process The correct recognition is almost ninety percent It is comparatively better than Hidden Markov model (HMM) & Artificial Neural network (ANN)

An Automatic Speaker Recognition System

Multilayer feed-forward neural networks are widely used based on minimization of an error function. Back propagation (BP) is a famous training method used in the multilayer networks but it often suffers from the drawback of slow convergence. To make the learning faster, we propose 'Fusion of Activation Functions' (FAF) in which different conventional activation functions (AFs) are combined to compute final activation. This has not been studied extensively yet. One of the sub goals of the paper is to check the role of linear AFs in combination. We investigate whether FAF can enable the learning to be faster. Validity of the proposed method is examined by performing simulations on challenging nine real benchmark classification and time series prediction problems. The FAF has been applied to 2-bit, 3-bit and 4-bit parity, the breast cancer, Diabetes, Heart disease, Iris, wine, Glass and Soybean classification problems. The algorithm is also tested with Mackey-Glass chaotic time series prediction problem. The algorithm is shown to work better than other AFs used independently in BP such as sigmoid (SIG), arctangent (ATAN), logarithmic (LOG).

Md. Shahjahan

Papers

A new local search based hybrid genetic algorithm for feature selection

A new hybrid ant colony optimization algorithm for feature selection

A Paper Currency Recognition System Using Negatively Correlated Neural Network Ensemble

An Automatic Speaker Recognition System

Faster training using fusion of activation functions for feed forward neural networks.