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

Cause, conseguenze e strategie di mitigazione Proponiamo il primo di una serie di articoli in cui affronteremo l’attuale problema dei mutamenti climatici. Presentiamo il documento redatto, votato e pubblicato dall’Ipcc - Comitato intergovernativo sui cambiamenti climatici - che illustra la sintesi delle ricerche svolte su questo tema rilevante.

/pdf/climate-change-2007-the-physical-science-basis-1x93ttz9jt.pdf

Climate Change 2007: The Physical Science Basis.

This review concentrates on advances in nitric oxide synthase (NOS) structure, function and inhibition made in the last seven years, during which time substantial advances have been made in our understanding of this enzyme family. There is now information on the enzyme structure at all levels from primary (amino acid sequence) to quaternary (dimerization, association with other proteins) structure. The crystal structures of the oxygenase domains of inducible NOS (iNOS) and vascular endothelial NOS (eNOS) allow us to interpret other information in the context of this important part of the enzyme, with its binding sites for iron protoporphyrin IX (haem), biopterin, L-arginine, and the many inhibitors which interact with them. The exact nature of the NOS reaction, its mechanism and its products continue to be sources of controversy. The role of the biopterin cofactor is now becoming clearer, with emerging data implicating one-electron redox cycling as well as the multiple allosteric effects on enzyme activity. Regulation of the NOSs has been described at all levels from gene transcription to covalent modification and allosteric regulation of the enzyme itself. A wide range of NOS inhibitors have been discussed, interacting with the enzyme in diverse ways in terms of site and mechanism of inhibition, time-dependence and selectivity for individual isoforms, although there are many pitfalls and misunderstandings of these aspects. Highly selective inhibitors of iNOS versus eNOS and neuronal NOS have been identified and some of these have potential in the treatment of a range of inflammatory and other conditions in which iNOS has been implicated.

/pdf/nitric-oxide-synthases-structure-function-and-inhibition-1t31plqilr.pdf

Nitric oxide synthases: structure, function and inhibition

I read this book the same weekend that the Packers took on the Rams, and the experience of the latter event, obviously, colored my judgment. Although I abhor anything that smacks of being a handbook (like, \"How to Earn a Merit Badge in Neurosurgery\") because too many volumes in biomedical science already evince a boyscout-like approach, I must confess that parts of this volume are fast, scholarly, and significant, with certain reservations. I like parts of this well-illustrated book because Dr. Sj6strand, without so stating, develops certain subjects on technique in relation to the acquisition of judgment and sophistication. And this is important! So, given that the author (like all of us) is somewhat deficient in some areas, and biased in others, the book is still valuable if the uninitiated reader swallows it in a general fashion, realizing full well that what will be required from the reader is a modulation to fit his vision, propreception, adaptation and response, and the kind of problem he is undertaking. A major deficiency of this book is revealed by comparison of its use of physics and of chemistry to provide understanding and background for the application of high resolution electron microscopy to problems in biology. Since the volume is keyed to high resolution electron microscopy, which is a sophisticated form of structural analysis, but really morphology in a modern guise, the physical and mechanical background of The instrument and its ancillary tools are simply and well presented. The potential use of chemical or cytochemical information as it relates to biological fine structure , however, is quite deficient. I wonder when even sophisticated morphol-ogists will consider fixation a reaction and not a technique; only then will the fundamentals become self-evident and predictable and this sine qua flon will become less mystical. Staining reactions (the most inadequate chapter) ought to be something more than a technique to selectively enhance contrast of morphological elements; it ought to give the structural addresses of some of the chemical residents of cell components. Is it pertinent that auto-radiography gets singled out for more complete coverage than other significant aspects of cytochemistry by a high resolution microscopist, when it has a built-in minimal error of 1,000 A in standard practice? I don't mean to blind-side (in strict football terminology) Dr. Sj6strand's efforts for what is \"routinely used in our laboratory\"; what is done is usually well done. It's just that …

Methods in Enzymology.

Image classification is a complex process that may be affected by many factors. This paper examines current practices, problems, and prospects of image classification. The emphasis is placed on the summarization of major advanced classification approaches and the techniques used for improving classification accuracy. In addition, some important issues affecting classification performance are discussed. This literature review suggests that designing a suitable image-processing procedure is a prerequisite for a successful classification of remotely sensed data into a thematic map. Effective use of multiple features of remotely sensed data and the selection of a suitable classification method are especially significant for improving classification accuracy. Non-parametric classifiers such as neural network, decision tree classifier, and knowledge-based classification have increasingly become important approaches for multisource data classification. Integration of remote sensing, geographical information systems (GIS), and expert system emerges as a new research frontier. More research, however, is needed to identify and reduce uncertainties in the image-processing chain to improve classification accuracy.

/pdf/a-survey-of-image-classification-methods-and-techniques-for-5bc5ltr9dq.pdf

A survey of image classification methods and techniques for improving classification performance

The existence of mixed pixels led to the development of several approaches for soft (or fuzzy) classification in which each pixel is allocated to all classes in varying proportions. However, while the proportions of each land cover within each pixel may be predicted, the spatial location of each land cover within each pixel is not. There exist many different potential techniques for sub-pixel mapping from remotely sensed imagery to identify specific class. The fuzzy-based possibilistic c-means (PCM), noise cluster (NC) and noise cluster with entropy (NCE) classifiers were applied to identify the Bhuj, India (2001), earthquake induced soil liquefaction and compared as soft computing approaches via supervised classification. The soil liquefaction identification was empirically investigated and compared with class-based sensor-independent (CBSI) spectral band ratio using Landsat-7 temporal images. It has been found that CBSI-based temporal indices yield the better results for identification of liquefied soil...

Study of soft classification approaches for identification of earthquake-induced liquefied soil

In the area of remote sensing, the decision making are not generally deterministic due to the involvement of fuzziness in the classification of remotely sensed imagery. A considerable number of identification errors are due to pixels that show an affinity with several information classes. The fuzzy concept is a valuable tool for dealing with classification problems. In remote sensing classification, fuzzy based classifiers are becoming increasingly popular. Due to the wide acceptance of fuzzy c-mean (FCM) and possibilistic c-means (PCM) classifiers, this has been used as a benchmark to evaluate the performance of other classifiers with optimized value of weighting exponent 'm' in this research. Evaluation of soft classification through FERM, SCM and Fuzzy kappa coefficient, using Euclidean norm based measures led to an improvement wherein FCM-Overall accuracy (MIN-LEAST) operator reflects higher classification accuracy, i.e., 97% and the value of Fuzzy Kappa coefficient is 0.97 with minimum uncertainty in it, for the optimized value of weighting exponent 'm' i.e. 4.0. In this experimentation two supervised classifiers namely FCM and PCM have been selected to demonstrate the improvement in the classification accuracy by FERM, SCM, MIN-MIN, MIN-LEAST, Fuzzy Kappa coefficient and uncertainty in SCM and Fuzzy Kappa coefficients. Index Terms—Fuzzy c-Mean (FCM), Fuzzy Error Matrix (FERM), Possiblistic c-Mean (PCM), Sub-pixel confusion-uncertainty matrix(SCM),

Study of Fuzzy Based Classifier Parameter Using Fuzzy Matrix

Image classification is a tedious process and that is affected by various parameters. This paper examines current practices of image classification. In remotely sensed data the easiest and usual assumption is that each pixel represents a homogeneous area on the ground. However in real world, it is found to be heterogeneous in nature. For this reason it has been proposed that fuzziness should be accommodated in the classification procedure and preserves the extracted information. The prime focus in this research work is to select suitable parameters for classification of remotely sensed data which improves the accuracy of classification output and to study the behaviour of associated learning parameters for optimization estimation, with different fuzzy based functions.The estimation of uncertainty is done by entropy for FCM, PCM and noise clustering without entropy based classifier, and hence is sensitive to uncertain variations. The geographic latitude/longitude, of study area extends from 28°52'29”N to 28°54'20”N and 79°34'25”E to 79°36'34”E. The images for this research work have been taken from two different sensors namely LISS-III and LISSIV belonging to satellite IRS-P6. Soft classified outputs from FCM, PCM and noise clustering without entropy classifiers for LISS-III with LISS-IV have been evaluated using sub-pixel confusion uncertainty matrix (SCM), for overall accuracy, fuzzy kappa coefficient and entropy. In this research work it has been tried to generate fraction outputs from FCM, PCM, and noise clustering without entropy. These outputs have been generated from LISS-III and LISS-IV images of IRS-P6 data. The SCM and fuzzy kappa coefficients are used to major relative accuracies, while entropy is an absolute uncertainty indicator. From resultant aspect, while monitoring entropy of fraction images for different regularizing parameter values, optimum regularizing parameter has been obtained for 'm'=1.9 and ' which gives highest accuracy from sub-pixel confusion uncertainty matrix (SCM) i.e. 94.65% and LISS-III entropy is 0.04 using noise clustering without entropy based classifier. Where in optimum regularizing parameters value('m') for FCM and PCM is 3.2 , which gives an SCM accuracy 72.98% and 42.55% respectively. The LISS-III entropy for FCM and PCM classifier is 0.011 and 1.98. From this work it can be concluded that output from noise clustering without entropy classifier has higher classification accuracy with lowest uncertainty with respect to FCM and PCM based classifiers. This research work has been done using indigenously developed Sub-pixel Multi-spectral Image Classification (SMIC) tool. Fuzzy c-Mean (FCM), Possiblistic c-Mean (PCM), Noise clustering (NC), Sub pixel confusion uncertainty matrix (SCM) ! '=1,

Investigation of Image Classification Techniques for Performance Enhancement

In plug-and-play image restoration, the regularization is performed using powerful denoisers such as nonlocal means (NLM) or BM3D. This is done within the framework of alternating direction method of multipliers (ADMM), where the regularization step is formally replaced by an off-the-shelf denoiser. Each plug-and-play iteration involves the inversion of the forward model followed by a denoising step. In this paper, we present a couple of ideas for improving the efficiency of the inversion and denoising steps. First, we propose to use linearized ADMM, which generally allows us to perform the inversion at a lower cost than standard ADMM. Moreover, we can easily incorporate hard constraints into the optimization framework as a result. Second, we develop a fast algorithm for doubly stochastic NLM, originally proposed by Sreehari et al. (IEEE TCI, 2016), which is about 80x faster than brute-force computation. This particular denoiser can be expressed as the proximal map of a convex regularizer and, as a consequence, we can guarantee convergence for linearized plug-and-play ADMM. We demonstrate the effectiveness of our proposals for super-resolution and single-photon imaging.

Linearized ADMM and Fast Nonlocal Denoising for Efficient Plug-and-Play Restoration

This paper proposes a technique to detect the change in some dominantly available classes in an urban area such as vegetation, built-up, and water bodies. Landsat Thematic Mapper (TM) and Landsat 8 imageries have been selected for a particular area of NCR (National Capital Region), New Delhi, India. In this study, three spectral indices have been used to characterize three foremost urban land-use classes, i.e., normalized difference built-up index (NDBI) to characterize built-up area, modified normalized difference water index (MNDWI) to signify open water and modified soil-adjusted vegetation index (MSAVI2) to symbolize green vegetation. Subsequently, for reducing the dimensionality of Landsat data, a new FCC has been generated using above mentioned indices, which consist of three thematic-oriented bands in place of the seven Landsat bands. Hence, a substantial reduction is accomplished in correlation and redundancy among raw satellite data, and consequently reduces the spectral misperception of the three land-use classes. Thus, uniqueness has been gained in the spectral signature values of the three dominant land-use classes existing in an urban area. Further, the benefits of using MSAVI2 as compared with NDVI and MNDWI as compared to NDWI for the highly urbanized area have been emphasized in this research work. Through a supervised classification, the three classes have been identified on the imageries and the change between the image pairs has been found. The overall accuracy (OA) of change detection is 92.6 %. Therefore, the study shows that this technique is effective and reliable for detection of change.

Sanjay Ghosh

Papers

Study of soft classification approaches for identification of earthquake-induced liquefied soil

Study of Fuzzy Based Classifier Parameter Using Fuzzy Matrix

Investigation of Image Classification Techniques for Performance Enhancement

Linearized ADMM and Fast Nonlocal Denoising for Efficient Plug-and-Play Restoration

Spectral Indices Based Change Detection in an Urban Area Using Landsat Data