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

On robust estimation of the location parameter

It is shown that, particularly for terrestrial cellular telephony, the interference-suppression feature of CDMA (code division multiple access) can result in a many-fold increase in capacity over analog and even over competing digital techniques. A single-cell system, such as a hubbed satellite network, is addressed, and the basic expression for capacity is developed. The corresponding expressions for a multiple-cell system are derived. and the distribution on the number of users supportable per cell is determined. It is concluded that properly augmented and power-controlled multiple-cell CDMA promises a quantum increase in current cellular capacity. >

On the capacity of a cellular CDMA system

Imaging spectrometers measure electromagnetic energy scattered in their instantaneous field view in hundreds or thousands of spectral channels with higher spectral resolution than multispectral cameras. Imaging spectrometers are therefore often referred to as hyperspectral cameras (HSCs). Higher spectral resolution enables material identification via spectroscopic analysis, which facilitates countless applications that require identifying materials in scenarios unsuitable for classical spectroscopic analysis. Due to low spatial resolution of HSCs, microscopic material mixing, and multiple scattering, spectra measured by HSCs are mixtures of spectra of materials in a scene. Thus, accurate estimation requires unmixing. Pixels are assumed to be mixtures of a few materials, called endmembers. Unmixing involves estimating all or some of: the number of endmembers, their spectral signatures, and their abundances at each pixel. Unmixing is a challenging, ill-posed inverse problem because of model inaccuracies, observation noise, environmental conditions, endmember variability, and data set size. Researchers have devised and investigated many models searching for robust, stable, tractable, and accurate unmixing algorithms. This paper presents an overview of unmixing methods from the time of Keshava and Mustard's unmixing tutorial to the present. Mixing models are first discussed. Signal-subspace, geometrical, statistical, sparsity-based, and spatial-contextual unmixing algorithms are described. Mathematical problems and potential solutions are described. Algorithm characteristics are illustrated experimentally.

/pdf/hyperspectral-unmixing-overview-geometrical-statistical-and-2lb11fr9l4.pdf

Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches

Stable non-Gaussian random processes , by G. Samorodnitsky and M. S. Taqqu. Pp. 632. £49.50. 1994. ISBN 0-412-05171-0 (Chapman and Hall).

In this paper we treat rate-compatible punctured low-density parity-check (RCP-LDPC) codes. We show how a mother code can be efficiently punctured to achieve good performance over a wide range of rates and discuss the design of a mother code. While this approach can be applied to virtually any time-varying channel, we apply it to the ultra wide band (UWB) channel, e.g. 802.15.3a, and we show that RCP-LDPC codes perform well as compared to a selection of fixed rate unpunctured codes. They reduce the implementation complexity and enable the use of retransmission protocols based on incremental redundancy to increase the throughput

Rate-compatible punctured low-density parity-check codes for ultra wide band systems

The Universal Mobile Telecommunications System (UMTS) is composed of an FDD and TDD mode. The spectrum allocation is in such a way that both modes have an adjacent carrier at 1920 MHz. The implications thereof with respect to system capacity are investigated. In this context the separation distance of the TDD and FDD base station (BS) and frame synchronisation are varied. It is shown that the most detrimental effects for the FDD interface are for small BS separations. In contrast, the optimum with respect to TDD capacity is found for the co-location of both base stations. This yields a trade-off for the optimal BS locations. Moreover, an adjacent channel protection factor of 30 dB in an interference limited system such as CDMA is shown to be too low unless a significant capacity loss is acceptable.

The effects of interference between the TDD and FDD mode in UMTS at the boundary of 1920 MHz

An important task in underwater passive sonar signal processing is the determination of target signatures based on the narrow-band signal content in the received signal. To achieve good classification performance it is important to be able to separate the different sources (e.g. engine, hull and drive) present in the signature, and to determine the distinct frequency coupling pattern of each of these sources. In this work we demonstrate how this can be done using bispectral techniques applied to data recorded at a sea trial in the Baltic Sea. As a target we used a 23 ft fiberglass motor boat powered by a 4-cylinder, 4-stroke, turbo-charged diesel engine connected to a stern drive with two counter rotating propellers. Data was recorded with a bottom mounted hydrophone array as well as with accelerometers mounted on the engine and the hull. It was found that the harmonics that propagated through water are engine related at low speeds and drive related at high speeds. The hull vibrations are only present at very low speeds. Moreover, we found that normalized bispectrum measures (skewness) could provide additional coupling information not visible in the standard bispectrum.

Passive sonar signature estimation using bispectral techniques

A hybrid cellular and ad hoc network for high data rate wireless access is considered. An air-interface which uses TDD in combination with time division multiple access (TDMA) is assumed. Interference and resource reuse are important issues in hybrid networks. For this purpose analytical models for the reuse efficiency and a capacity bound of such a network are developed. These models are based on an exclusion range concept which is introduced to keep interference at an acceptable level. It is found that with this interference limiting measure, multi hop networks can benefit from a multi hop reuse gain compared to single hop networks. However, it is further found that this gain does not significantly increase for more than 5 hops. Furthermore, the pre-requisite for being able to exploit the multi hop reuse gain is a certain TS granularity. It was observed that with an increasing number of TS per frame, the mean and the variance of the number of supported hops increased almost linearly

Performance analysis for hybrid wireless networks

This paper studies a sparse signal recovery task in time-varying (time-adaptive) environments. The contribution of the paper to sparsity-aware online learning is threefold; first, a Generalized Thresholding (GT) operator, which relates to both convex and non-convex penalty functions, is introduced. This operator embodies, in a unified way, the majority of well-known thresholding rules which promote sparsity. Second, a non-convexly constrained, sparsity-promoting, online learning scheme, namely the Adaptive Projection-based Generalized Thresholding (APGT), is developed that incorporates the GT operator with a computational complexity that scales linearly to the number of unknowns. Third, the novel family of partially quasi-nonexpansive mappings is introduced as a functional analytic tool for treating the GT operator. By building upon the rich fixed point theory, the previous class of mappings helps us, also, to establish a link between the GT operator and a union of linear subspaces; a non-convex object which lies at the heart of any sparsity promoting technique, batch or online. Based on such a functional analytic framework, a convergence analysis of the APGT is provided. Furthermore, extensive experiments suggest that the APGT exhibits competitive performance when compared to computationally more demanding alternatives, such as the sparsity-promoting Affine Projection Algorithm (APA)- and Recursive Least Squares (RLS)-based techniques.

Stephen McLaughlin

Papers

Rate-compatible punctured low-density parity-check codes for ultra wide band systems

The effects of interference between the TDD and FDD mode in UMTS at the boundary of 1920 MHz

Passive sonar signature estimation using bispectral techniques

Performance analysis for hybrid wireless networks

Generalized Thresholding and Online Sparsity-Aware Learning in a Union of Subspaces