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

This is the first part of a comprehensive and up-to-date survey of the techniques for tracking maneuvering targets without addressing the so-called measurement-origin uncertainty. It surveys various mathematical models of target motion/dynamics proposed for maneuvering target tracking, including 2D and 3D maneuver models as well as coordinate-uncoupled generic models for target motion. This survey emphasizes the underlying ideas and assumptions of the models. Interrelationships among models and insight to the pros and cons of models are provided. Some material presented here has not appeared elsewhere.

Survey of maneuvering target tracking. Part I. Dynamic models

Intelligent control may be viewed as the ability of a controller to operate in multiple environments by recognizing which environment is currently in existence and servicing it appropriately. An important prerequisite for an intelligent controller is the ability to adapt rapidly to any unknown but constant operating environment. This paper presents a general methodology for such adaptive control using multiple models, switching, and tuning. The approach was first introduced by Narendra et al. (1992) for improving the transient response of adaptive systems in a stable fashion. This paper proposes different switching and tuning schemes for adaptive control which combine fixed and adaptive models in novel ways. The principal mathematical results are the proofs of stability when these different schemes are used in the context of model reference control of an unknown linear time-invariant system. A variety of simulation results are presented to demonstrate the efficacy of the proposed methods.

Adaptive control using multiple models

The Interacting Multiple Model (IMM) estimator is a suboptimal hybrid filter that has been shown to be one of the most cost-effective hybrid state estimation schemes. The main feature of this algorithm is its ability to estimate the state of a dynamic system with several behavior modes which can "switch" from one to another. In particular, the IMM estimator can be a self-adjusting variable-bandwidth filter, which makes it natural for tracking maneuvering targets. The importance of this approach is that it is the best compromise available currently-between complexity and performance: its computational requirements are nearly linear in the size of the problem (number of models) while its performance is almost the same as that of an algorithm with quadratic complexity. The objective of this work is to survey and put in perspective the existing IMM methods for target tracking problems. Special attention is given to the assumptions underlying each algorithm and its applicability to various situations.

Interacting multiple model methods in target tracking: a survey

This is the fifth part of a series of papers that provide a comprehensive survey of techniques for tracking maneuvering targets without addressing the so-called measurement-origin uncertainty. Part I and Part II deal with target motion models. Part III covers measurement models and associated techniques. Part IV is concerned with tracking techniques that are based on decisions regarding target maneuvers. This part surveys the multiple-model methods $the use of multiple models (and filters) simultaneously - which is the prevailing approach to maneuvering target tracking in recent years. The survey is presented in a structured way, centered around three generations of algorithms: autonomous, cooperating, and variable structure. It emphasizes the underpinning of each algorithm and covers various issues in algorithm design, application, and performance.

Survey of maneuvering target tracking. Part V. Multiple-model methods

A new approach tothethree-dimensional airborne maneuveringtarget tracking problem ispresented. Themethod, which combines thecorrelated acceleration target modelofSinger [31 withtheadaptive semi-Markov maneuver modelof Gholson andMoose[8], leadstoa practical real-time trackingalgorithm that can beeasily implemented on a modern fire-control computer. Preliminary testing withactual radar measurementsindicates bothimproved tracking accuracy andincreased filter stability inresponsetorapid target accelerations inelevation, bearing, andrange.

Modeling andEstimation for Tracking Maneuvering Targets

A new approach to the three-dimensional airborne maneuvering target tracking problem is presented. The method, which combines the correlated acceleration target model of Singer [3] with the adaptive semi-Markov maneuver model of Gholson and Moose [8], leads to a practical real-time tracking algorithm that can be easily implemented on a modern fire-control computer. Preliminary testing with actual radar measurements indicates both improved tracking accuracy and increased filter stability in response to rapid target accelerations in elevation, bearing, and range.

Modeling and Estimation for Tracking Maneuvering Targets

Efficient handoff algorithms cost-effectively enhance the capacity and Quality of Service (QoS) of cellular systems. This research presents novel approaches for the design of high performance handoff algorithms that exploit attractive features of several existing algorithms, provide adaptation to dynamic cellular environment, and allow systematic tradeoffs among different system characteristics. A comprehensive foundation of handoff and related issues of cellular communications is given. The tools of artificial intelligence utilized in this research, neural networks and fuzzy logic, are introduced. The scope of existing simulation models for macrocellular and microcellular handoff algorithms is enhanced by incorporating several important features. New simulation models suitable for performance evaluation of soft handoff algorithms and overlay handoff algorithms are developed. Four basic approaches for the development of high performance algorithms are proposed and are based on fuzzy logic, neural networks, unified handoff candidate selection, and pattern classification. The fuzzy logic based approach allows an organized tuning of the handoff parameters to provide a balanced tradeoff among different system characteristics. The neural network based approach suggests neural encoding of the fuzzy logic systems to simultaneously achieve the goals of high performance and reduced complexity. The unified candidacy based approach recommends the use of a unified handoff candidate selection criterion to select the best handoff candidate under given constraints. The pattern classification based approach exploits the capability of fuzzy logic and neural networks to obtain an efficient architecture of an adaptive handoff algorithm. New algorithms suitable for microcellular systems, overlay systems, and systems employing soft handoff are described. A basic adaptive algorithm suitable for a microcellular environment is proposed. Adaptation to traffic, interference, and mobility has been superimposed on the basic generic algorithm to develop another microcellular algorithm. An adaptive overlay handoff algorithm that allows a systematic balance among the design parameters of an overlay system is proposed. Important considerations for soft handoff are discussed, and adaptation mechanisms for new soft handoff algorithms are developed.

Generic adaptive handoff algorithms using fuzzy logic and neural networks

An overlay system is a hierarchical architecture that uses large macrocells to overlay clusters of small microcells. Resource management in the overlay system is much more complex than in pure macrocell and microcell systems. A fixed parameter handoff algorithm cannot perform well in a complex and dynamic overlay environment. This paper proposes an adaptive overlay handoff algorithm that allows a systematic tradeoff among the system design parameters and improves the overall system performance.

Hugh F. Vanlandingham

Papers

Modeling andEstimation for Tracking Maneuvering Targets

Modeling and Estimation for Tracking Maneuvering Targets

Generic adaptive handoff algorithms using fuzzy logic and neural networks

Adaptive handoff algorithms for cellular overlay systems using fuzzy logic

Neural fuzzy techniques in vehicle acoustic signal classification