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 Practical Machine Learning Tools and Techniques

A review on machinery diagnostics and prognostics implementing condition-based maintenance

An Introduction to MultiAgent Systems.

Some patients, especially patients with chronic diseases such as heart disease, require continuous monitoring of their condition. Wearable devices for patient monitoring were introduced many years ago – for instance, wearable ambulatory ECG (electrocardiogram) recorders commonly known as Holter monitors (Figure 1) are used for monitoring cardiac patients. However, these monitors are quite bulky and can only record the signal for a limited time. Patients are often asked to wear a Holter monitor for a few days and then return to the clinic for diagnosis. This often overlooks transient but life-threatening events. In addition, we don’t know under what condition the signals are acquired, and this often leads to false alarms. For example, a sudden rise in heart rate may be caused by emotion, such as watching a horror movie, or by exercise, rather than by a heart condition. Body sensing To address these issues, the concept of Body Sensor Networks (BSN) was first proposed in 2002 by Prof. Guang-Zhong Yang from Imperial College London. The aim of the BSN is to provide a truly personalised monitoring platform that is pervasive, intelligent, and Figure 1 A patient wearing a Holter monitor

Body sensor networks

This paper reviews the potential benefits that can be obtained by the implementation of data fusion in a multi-sensor environment. A thorough review of the commonly used data fusion frameworks is presented together with important factors that need to be considered during the development of an effective data fusion problem-solving strategy. A system-based approach is defined for the application of data fusion systems within engineering. Structured guidelines for users are proposed.

/pdf/a-review-of-data-fusion-models-and-architectures-towards-irnrlvvifw.pdf

A Review of data fusion models and architectures: towards engineering guidelines

http://uhra.herts.ac.uk/bitstream/handle/2299/2247/902342.pdf;sequence=1

An intelligent maintenance system for continuous cost-based prioritisation of maintenance activities

With increasing demands for wireless sensing nodes for assets control and condition monitoring; needs for alternatives to expensive conventional accelerometers in vibration measurements have been arisen. Micro-Electro Mechanical Systems (MEMS) accelerometer is one of the available options. The performances of three of the MEMS accelerometers from different manufacturers are investigated in this paper and compared to a well calibrated commercial accelerometer used as a reference for MEMS sensors performance evaluation. Tests were performed on a real CNC machine in a typical industrial environmental workshop and the achieved results are presented.

/pdf/suitability-of-mems-accelerometers-for-condition-monitoring-4jnn9sanmx.pdf

Suitability of MEMS Accelerometers for Condition Monitoring: An experimental study

https://uhra.herts.ac.uk/bitstream/handle/2299/3359/903246.pdf;sequence=1

Performance Evaluation of MEMS Accelerometers

http://uhra.herts.ac.uk/bitstream/handle/2299/4973/904255.pdf?sequence=1

Andrew Starr

Papers

A Review of data fusion models and architectures: towards engineering guidelines

An intelligent maintenance system for continuous cost-based prioritisation of maintenance activities

Suitability of MEMS Accelerometers for Condition Monitoring: An experimental study

Performance Evaluation of MEMS Accelerometers

Acoustic monitoring of engine fuel injection based on adaptive filtering techniques