http://www.eecs.ucf.edu/~dcm/Teaching/COT4810-Spring2011/Literature/SensorNetworksSurvey.pdf

Wireless sensor networks: a survey

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

Publisher Summary This chapter provides an account of different neural network architectures for pattern recognition. A neural network consists of several simple processing elements called neurons. Each neuron is connected to some other neurons and possibly to the input nodes. Neural networks provide a simple computing paradigm to perform complex recognition tasks in real time. The chapter categorizes neural networks into three types: single-layer networks, multilayer feedforward networks, and feedback networks. It discusses the gradient descent and the relaxation method as the two underlying mathematical themes for deriving learning algorithms. A lot of research activity is centered on learning algorithms because of their fundamental importance in neural networks. The chapter discusses two important directions of research to improve learning algorithms: the dynamic node generation, which is used by the cascade correlation algorithm; and designing learning algorithms where the choice of parameters is not an issue. It closes with the discussion of performance and implementation issues.

Neural Networks for Pattern Recognition

Data Mining - Concepts and Techniques.

We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

The use of GIS technology in engineering, in general, and in hydrology, in particular, has become feasible due primarily to the possibility of handling and integrating enormous amounts of geographic data efficiently. As shown in Figure 4.1, a GIS can be thought of as a powerful tool capable of creating and manipulating maps, with the necessary links to retrieve, manipulate, and update data from a database. Both maps and attribute data constitute abstractions or simplifications of the real world.

Spatial Data Characteristics

Devices related to a conductive fabric sensor are provided. A device can comprise an insulting and flexible fabric substrate, a central transmitting electrode on a top surface of the insulting and flexible fabric substrate, a plurality of receiving electrodes surrounding the central transmitting electrode and connected to the central transmitting electrode, and a power supply configured to generate a respective electric field between the central transmitting electrode and each receiving electrode of the plurality receiving electrodes.

Three dimensional touch conductive fabric

The purpose of this paper is on the study of data fusion applications in traditional, spatial and aerial video stream applications which addresses the processing of data from multiple sources using co-occurrence information and uses a common semantic metric. Use of co-occurrence information to infer semantic relations between measurements avoids the need to make use of such external information, such as labels. Many of the current Vector Space Models (VSM) do not preserve the co-occurrence information leading to a not so useful similarity metric. We propose a proximity matrix embedding part of the learning metric embedding which has entries showing the relations between co-occurrence frequency observed in input sets. First, we show an implicit spatial sensor proximity matrix calculation using Jaccard similarity for an array of sensor measurements and compare with the state-of-the-art kernel PCA learning from feature space proximity representation; it relates to a k-radius ball of nearest neighbors. Finally, we extend the class co-occurrence boosting of our unsupervised model using pre-trained multi-modal reuse.

Fast multi-modal reuse: co-occurrence pre-trained deep learning models

Most mainstream intellectuals, particularly economists, have almost dismissed Gandhiji.. Economists are important here because they influence the socio-political thinking the most. In traditional societies, economic system was subservient to the social system. In the modern societies the reverse appears to be true. Gandhian thought does not figure prominently in the development debate in the world in general and in the West in particular, because the Western thought has been polarised mainly into two ideologies. At one end, is conservatism, which ideologically places a strong emphasis on ‘the individual’. The facilitating agency is free. At the other end are the communism and socialism. Recent changes and developments have caused turbulence at both the ends. Neither systems is able to fully comprehend the changes and so, not able to cope with the problems of sustainability. In this contemporary context, the Gandhian Way holds a reasonable promise to ensure sustainability of the societies.[Text of the Gandhi Memorial Lecture delivered at the Mahatma Gandhi Institute, Moka, Mauritius on October 2, 2006.]

http://www.esocialsciences.org/Download/repecDownload.aspx?fname=Liberty_an1512200656.pdf&fcategory=Articles&AId=735&fref=repec

Liberty and Individualism in Gandhian Perspective Implications for Sustainability of Societies

This paper addresses the NP-complete, deterministic scheduling problem for a single server system. Given a set of n tasks along with the precedence-constraints among them, their timing requirements, setup costs and their completion deadlines, a neuromorphic model is used to construct a non-preemptive optimal processing schedule such that the total completion time, total tarediness and the number of tardy jobs is minimized. This model exhibits faster convergence than techniques based on gradient projection methods.

S. Sitharama Iyengar

Papers

Spatial Data Characteristics

Three dimensional touch conductive fabric

Fast multi-modal reuse: co-occurrence pre-trained deep learning models

Liberty and Individualism in Gandhian Perspective Implications for Sustainability of Societies

Nonlinear neural network for deterministic scheduling