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

Deep learning predictions of survival based on MRI in amyotrophic lateral sclerosis

Parkinson disease (PD) is an age-related deterioration of certain nerve systems, which affects movement, balance, and muscle control of clients. PD is one of the common diseases which affect 1% of people older than 60 years. A new classification scheme based on support vector machine (SVM) selected features to train rotation forest (RF) ensemble classifiers is presented for improving diagnosis of PD. The dataset contains records of voice measurements from 31 people, 23 with PD and each record in the dataset is defined with 22 features. The diagnosis model first makes use of a linear SVM to select ten most relevant features from 22. As a second step of the classification model, six different classifiers are trained with the subset of features. Subsequently, at the third step, the accuracies of classifiers are improved by the utilization of RF ensemble classification strategy. The results of the experiments are evaluated using three metrics; classification accuracy (ACC), Kappa Error (KE) and Area under the Receiver Operating Characteristic (ROC) Curve (AUC). Performance measures of two base classifiers, i.e. KStar and IBk, demonstrated an apparent increase in PD diagnosis accuracy compared to similar studies in literature. After all, application of RF ensemble classification scheme improved PD diagnosis in 5 of 6 classifiers significantly. We, numerically, obtained about 97% accuracy in RF ensemble of IBk (a K-Nearest Neighbor variant) algorithm, which is a quite high performance for Parkinson disease diagnosis.

SVM feature selection based rotation forest ensemble classifiers to improve computer-aided diagnosis of Parkinson disease.

Providing real-time and accurate travel time information of transit vehicles can be very helpful as it assists passengers in planning their trips to minimize waiting times. The purpose of this research is to develop and compare dynamic travel time prediction models which can provide accurate prediction of bus travel time in order to give real-time information at a given downstream bus stop using only global positioning system (GPS) data. Historical Average (HA), Kalman Filtering (KF) and Artificial Neural Network (ANN) models are considered and developed in this paper. A case has been studied by making use of the three models. Promising results are obtained from the case study, indicating that the models can be used to implement an Advanced Public Transport System. The implementation of this system could assist transit operators in improving the reliability of bus services, thus attracting more travelers to transit vehicles and helping relieve congestion. The performances of the three models were assessed and compared with each other under two criteria: overall prediction accuracy and robustness. It was shown that the ANN outperformed the other two models in both aspects. In conclusion, it is shown that bus travel time information can be reasonably provided using only arrival and departure time information at stops even in the absence of traffic-stream data.

Dynamic Travel Time Prediction Models for Buses Using Only GPS Data

While advances in military relevant simulations provide potential for increasing assessment of Soldier readiness to Return-to-Duty (eg, following a blast injury), little has been done to develop these simulations into adaptive virtual environments (AVE) for improved neurocognitive and psychophysiological assessment Adaptive assessments offer the potential for dynamically adapting the difficulty level specific to the patient's knowledge or ability We present an iteration of the Virtual Reality for Cognitive Performance and Adaptive Treatment (VRCPAT) that proffers a framework for adapting scenarios in a game engine based upon the user's neurocognitive (task performance) and psychophysiological (eg, heart rate, skin response, heart rate, and pupil diameter) states

/pdf/adaptive-virtual-environments-for-neuropsychological-4o0aag0uwe.pdf

Adaptive virtual environments for neuropsychological assessment in serious games

Neural Networks are used to find a generalised solution from a sample set of a problem domain. When a small sample is all that is available, the correct division of data between the training, testing and validation sets is crucial to the performance of the resultant trained network. Data is often divided uniformly between the three data sets. We propose an alternative method for the optimal division of the data, based on empirical evidence from experiments with artificial data. The method is tested on real world data sets, with encouraging results.

A method for optimal division of data sets for use in neural networks

Predicting the outcome of a medical procedure or event with high level of accuracy can be a challenging task. To answer the challenge, data mining can play a significant role. The main objective of this study is to examine the performances of an Artificially Intelligent (AI)-based data mining technique namely Artificial Neural Network Ensemble (ANNE) in prediction of medical outcomes. It also describes a novel approach, namely "RIDC-ANNE". This approach tries to improve data quality by configuring an ensemble of bagged networks as a filter and identifying the regions in the data space that have high impact on the system performance. Furthermore, it can also be used to extract explanations and knowledge from several combined neural network classifiers. The methodology employed utilizes a series of clinical datasets. The datasets embody a number of important properties, which make them a good starting point for the purpose of this research. This study reveals that the RIDC-ANNE approach can be used to successfully extract the regions in the data space that have high impact on the system performance and enhance the overall utility of current neural network models.

Learning from Ensembles: Using Artificial Neural Network Ensemble for Medical Outcomes Prediction

The Second Life virtual world (SL) created by Linden Lab (LL) provides a rich three-dimensional environment, allowing the residents of this virtual community to create and trade unique content. Linden Scripting Language (LSL) is used to enhance the SL experience by providing a programming language capability for created objects. Primitives (prims) are the atomic objects from which complex objects are built; they can be scripted using LSL In this paper we specifically look at how LSL affects the SL experience, its strengths and weaknesses, and propose enhancements, also seeking to find where it has been innovative or unusual. One of the biggest problems in SL is lag – the way the experience slows under load. LSL scripts contribute considerably to lag and we look at how the design of the language attempts to assist in keeping the SL experience enjoyable.

A review of linden scripting language and its role in second life

Factors in Team Performance in a Virtual Squad Environment

It is well-known that the accuracy of a neural network classifier increases as the number of data points in the training set increases. A previous researcher has proposed a general mathematical model that explains the relationship between training sample size and predictive power. We examine this model using artificially generated data sets containing varying numbers of data points and some real world data sets. We find the model works well when large numbers of data points are available for training, but presents practical difficulties when the amount of available data is small and the data set is difficult to classify.

Robert Cox

Papers

A method for optimal division of data sets for use in neural networks

Learning from Ensembles: Using Artificial Neural Network Ensemble for Medical Outcomes Prediction

A review of linden scripting language and its role in second life

Factors in Team Performance in a Virtual Squad Environment

Accuracy of neural network classifiers as a property of the size of the data set