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 - Concepts and Techniques.

The PASCAL Visual Object Classes Challenge

IEEE Transactions on Pattern Analysis and Machine Intelligence

‡We describe the use of singular value decomposition in transforming genome-wide expression data from genes 3 arrays space to reduced diagonalized ‘‘eigengenes’’ 3 ‘‘eigenarrays’’ space, where the eigengenes (or eigenarrays) are unique orthonormal superpositions of the genes (or arrays). Normalizing the data by filtering out the eigengenes (and eigenarrays) that are inferred to represent noise or experimental artifacts enables meaningful comparison of the expression of different genes across different arrays in different experiments. Sorting the data according to the eigengenes and eigenarrays gives a global picture of the dynamics of gene expression, in which individual genes and arrays appear to be classified into groups of similar regulation and function, or similar cellular state and biological phenotype, respectively. After normalization and sorting, the significant eigengenes and eigenarrays can be associated with observed genome-wide effects of regulators, or with measured samples, in which these regulators are overactive or underactive, respectively.

Singular Value Decomposition for Genome-Wide Expression Data Processing and Modeling

Recent advancement in the area of medical imaging produces a huge amount of image data. Automatic extraction of meaningful information from these data has become necessary. In this regard, different image processing techniques provide efficient tools to extract and interpret meaningful information from the medical images, which, in turn, provide valuable directions for medical diagnosis. One of the major problems in real-life medical image data analysis is uncertainty. Among other soft computing techniques, rough sets provide a powerful tool to handle uncertainties, vagueness, and incompleteness associated with data, while fuzzy set and probabilistic paradigm serve as analytical tools for dealing with uncertainty that arises due to the overlapping characteristics and/or randomness in data. Hence, they can be integrated judiciously to develop efficient algorithms for automatic analysis of medical image data. In this regard, the paper presents a brief review on recent advances of rough set based hybrid intelligent approaches for medical image analysis.

Advances in Rough Set Based Hybrid Approaches for Medical Image Analysis

Selection of reliable genes from micro array gene expression data is essential to carry out a diagnostic test and successful treatment. In this regard, a rough set based gene selection algorithm is developed recently to select genes from micro array data. In this paper, a fuzzy discretization method is proposed for rough set based gene selection algorithm to compute relevance and significance of continuous valued genes directly. The performance of the proposed fuzzy discretization method, along with a comparison with crisp counterpart, is presented in terms of classification accuracy of K-nearest neighbor rule and support vector machine on seven micro array data sets. An important finding is that the proposed discretization method is shown to be effective in selecting relevant and significant genes from micro array data.

Fuzzy Discretization for Rough Set Based Gene Selection Algorithm

In order to apply the powerful kernel-based pattern recognition algorithms such as support vector machines to predict functional sites in proteins, amino acids need encoding prior to input. In this regard, a new string kernel function, termed as the modified bio-basis function, is proposed that maps a nonnumerical sequence space to a numerical feature space. The proposed string kernel function is developed based on the conventional bio-basis function and needs a bio-basis string as a support like conventional kernel function. The concept of zone of influence of a bio-basis string is introduced in the proposed kernel function to take into account the influence of each bio-basis string in nonnumerical sequence space. An efficient method is described to select a set of bio-basis strings for the proposed kernel function, integrating the Fisher ratio and a novel concept of degree of resemblance. The integration enables the method to select a reduced set of relevant and nonredundant bio-basis strings.

Efficient Design of Bio-Basis Function to Predict Protein Functional Sites Using Kernel-Based Classifiers

One of the main problems in real life omics data analysis is how to extract relevant and non-redundant features from high dimensional multimodal data sets. In general, supervised regularized canonical correlation analysis (SRCCA) plays an important role in extracting new features from multimodal omics data sets. However, the existing SRCCA optimizes regularization parameters based on the quality of first pair of canonical variables only using standard feature evaluation indices. In this regard, this paper introduces a new SRCCA algorithm, integrating judiciously the merits of SRCCA and rough hypercuboid approach, to extract relevant and nonredundant features in approximation spaces from multimodal omics data sets. The proposed method optimizes regularization parameters of the SRCCA based on the quality of a set of pairs of canonical variables using rough hypercuboid approach. While the rough hypercuboid approach provides an efficient way to calculate the degree of dependency of class labels on feature set in approximation spaces, the merit of SRCCA helps in extracting non-redundant features from multimodal data sets. The effectiveness of the proposed approach, along with a comparison with related existing approaches, is demonstrated on several real life data sets.

Pradipta Maji

Papers

Advances in Rough Set Based Hybrid Approaches for Medical Image Analysis

Fuzzy Discretization for Rough Set Based Gene Selection Algorithm

Efficient Design of Bio-Basis Function to Predict Protein Functional Sites Using Kernel-Based Classifiers

Rough Hypercuboid Based Supervised Regularized Canonical Correlation for Multimodal Data Analysis

Application of Fuzzy Cellular Automata (FCA) For Modeling Tree-Structured Pattern Classifier.