Sentiment classification for early detection of health alerts in the chemical textile domain

In the chemical textile domain experts have to analyse chemical components and substances that might be harmful for their usage in clothing and textiles. Part of this analysis is performed searching opinions and reports people have expressed concerning these products in the Social Web. However, this type of information on the Internet is not as frequent for this domain as for others, so its detection and classification is difficult and time-consuming. Consequently, problems associated to the use of chemical substances in textiles may not be detected early enough, and could lead to health problems, such as allergies or burns. In this paper, we propose a framework able to detect, retrieve, and classify subjective sentences related to the chemical textile domain, that could be integrated into a wider health surveillance system. We also describe the creation of several datasets with opinions from this domain, the experiments performed using machine learning techniques and different lexical resources such as WordNet, and the evaluation focusing on the sentiment classification, and complaint detection (i.e., negativity). Despite the challenges involved in this domain, our approach obtains promising results with an F-score of 65% for polarity classification and 82% for complaint detection.

Lightweight Internet Traffic Classification - A Subject Based Solution with Word Embeddings

Internet traffic classification is a relevant and mature research field, anyway of growing importance and with still open technical challenges, also due to the pervasive presence of Internet-connected devices into everyday life. We claim the need for innovative traffic classification solutions capable of being lightweight, of adopting a domain-based approach, of not only concentrating on application-level protocol categorization but also classifying Internet traffic by subject. To this purpose, this paper originally proposes a classification solution that leverages domain name information extracted from IPFIX summaries, DNS logs, and DHCP leases, with the possibility to be applied to any kind of traffic. Our proposed solution is based on an extension of Word2vec unsupervised learning techniques running on a specialized Apache Spark cluster. In particular, learning techniques are leveraged to generate word-embeddings from a mixed dataset composed by domain names and natural language corpuses in a lightweight way and with general applicability. The paper also reports lessons learnt from our implementation and deployment experience that demonstrates that our solution can process 5500 IPFIX summaries per second on an Apache Spark cluster with 1 slave instance in Amazon EC2 at a cost of $ 3860 year. Reported experimental results about Precision, Recall, F-Measure, Accuracy, and Cohen's Kappa show the feasibility and effectiveness of the proposal. The experiments prove that words contained in domain names do have a relation with the kind of traffic directed towards them, therefore using specifically trained word embeddings we are able to classify them in customizable categories. We also show that training word embeddings on larger natural language corpuses leads improvements in terms of precision up to 180%.

New Techniques in Deep Representation Learning

Thesis (Ph.D.)--University of Washington, 2016-06

Learning Models of Gene Expression from Synthetic DNA Sequences

Thesis (Ph.D.)--University of Washington, 2016-06

System for foreign exchange trading using genetic algorithms and reinforcement learning

Foreign exchange trading has emerged recently as a significant activity in many countries. As with most forms of trading, the activity is influenced by many random parameters so that the creation of a system that effectively emulates the trading process will be very helpful. A major issue for traders in the deregulated Foreign Exchange Market is when to sell and when to buy a particular currency in order to maximize profit. This paper presents novel trading strategies based on the machine learning methods of genetic algorithms and reinforcement learning.

An Incremental EM-based Learning Approach for On-Line Prediction of Hospital Resource Utilization

Objective: Inpatient length of stay (LOS) is an important measure of hospital activity, health care resource consumption, and patient acuity. This research work aims at developing an incremental expectation maximization (EM) based learning approach on mixture of experts (ME) system for on-line prediction of LOS. The use of a batchmode learning process in most existing artificial neural networks to predict LOS is unrealistic, as the data become available over time and their pattern change dynamically. In contrast, an on-line process is capable of providing an output whenever a new datum becomes available. This on-the-spot information is therefore more useful and practical for making decisions, especially when one deals with a tremendous amount of data. Methods and material: The proposed approach is illustrated using a real example of gastroenteritis LOS data. The data set was extracted from a retrospective cohort study on all infants born in 1995-1997 and their subsequent admissions for gastroenteritis. The total number of admissions in this data set was n = 692. Linked hospitalization records of the cohort were retrieved retrospectively to derive the outcome measure, patient demographics, and associated co-morbidities information. A comparative study of the incremental learning and the batch-mode learning algorithms is considered. The performances of the learning algorithms are compared based on the mean absolute difference (MAD) between the predictions and the actual LOS, and the proportion of predictions with MAD < 1 day (Prop(MAD < 1)). The significance of the comparison is assessed through a regression analysis. Results: The incremental learning algorithm provides better on-line prediction of LOS when the system has gained sufficient training from more examples (MAD = 1.77 days and Prop(MAD < 1) = 54.3%), compared to that using the batch-mode learning. The regression analysis indicates a significant decrease of MAD (p-value = 0.063) and a significant (p-value = 0.044) increase of Prop(MAD

Matching of catalogues by probabilistic pattern classification

We consider the statistical problem of catalogue matching from a machine learning perspective with the goal of producing probabilistic outputs, and using all available information. A framework is provided that unifies two existing approaches to producing probabilistic outputs in the literature, one based on combining distribution estimates and the other based on combining probabilistic classifiers. We apply both of these to the problem of matching the HI Parkes All Sky Survey radio catalogue with large positional uncertainties to the much denser SuperCOSMOS catalogue with much smaller positional uncertainties. We demonstrate the utility of probabilistic outputs by a controllable completeness and efficiency trade-off and by identifying objects that have high probability of being rare. Finally, possible biasing effects in the output of these classifiers are also highlighted and discussed.

Interactive email filtering: Learning from misclassified examples

Learning from mistakes has proven to be an effective way of learning in the interactive document classifications. In this paper we propose an approach to effectively learning from mistakes in the email filtering process. Our system has employed both SVM and Winnow machine learning algorithms to learn from misclassified email documents and refine the email filtering process accordingly. Our experiments have shown that the training of an email filter becomes much effective and faster

Precision-recall operating characteristic (P-ROC) curves in imprecise environments

Traditionally, machine learning algorithms have been evaluated in applications where assumptions can be reliably made about class priors and/or misclassification costs. In this paper, we consider the case of imprecise environments, where little may be known about these factors and they may well vary significantly when the system is applied. Specifically, the use of precision-recall analysis is investigated and compared to the more well known performance measures such as error-rate and the receiver operating characteristic (ROC). We argue that while ROC analysis is invariant to variations in class priors, this invariance in fact hides an important factor of the evaluation in imprecise environments. Therefore, we develop a generalised precision-recall analysis methodology in which variation due to prior class probabilities is incorporated into a multi-way analysis of variance (ANOVA). The increased sensitivity and reliability of this approach is demonstrated in a remote sensing application.

Classifying an opponent's behaviour in robot soccer

This paper illustrates the prediction of opponent behaviour in a competitive, highly dynamic, multi-agent and partially observableenvironment, namely RoboCup small size league robot soccer. The performance is illustrated in the context of the highly successful robot soccer team, the RoboRoos. The project is broken into three tasks; classification of behaviours, modelling and prediction of behaviours and integration of the predictions into the existing planning system. A probabilistic approach is taken to dealing with the uncertainty in the observations and with representing the uncertainty in the prediction of the behaviours. Results are shown for a classification system using a Naïve Bayesian Network that determines the opponent’s current behaviour. These results are compared to an expert designed fuzzy behaviour classification system. The paper illustrates how the modelling system will use the information from behaviour classification to produce probability distributions that model the manner with which the opponents perform their behaviours. These probability distributions are show to match well with the existing multi-agent planning system (MAPS) that forms the core of the RoboRoos system.

User-centred ontology learning for knowledge management

Automatic ontology building is a vital issue in many fields where they are currently built manually. This paper presents a user-centred methodology for ontology construction based on the use of Machine Learning and Natural Language Processing. In our approach, the user selects a corpus of texts and sketches a preliminary ontology (or selects an existing one) for a domain with a preliminary vocabulary associated to the elements in the ontology (lexicalisations). Examples of sentences involving such lexicalisation (e.g. ISA relation) in the corpus are automatically retrieved by the system. Retrieved examples are validated by the user and used by an adaptive Information Extraction system to generate patterns that discover other lexicalisations of the same objects in the ontology, possibly identifying new concepts or relations. New instances are added to the existing ontology or used to tune it. This process is repeated until a satisfactory ontology is obtained. The methodology largely automates the ontology construction process and the output is an ontology with an associated trained leaner to be used for further ontology modifications.

The exact sample complexity of PAC-learning problems with unit VC dimension

The Vapnik-Chervonenkis (VC) dimension is a combinatorial measure of a certain class of machine learning problems, which may be used to obtain upper and lower bounds on the number of training examples needed to learn to prescribed levels of accuracy. Most of the known bounds apply to the Probably Approximately Correct (PAC) framework, which is the framework within which we work in this paper. For a learning problem with some known VC dimension, much is known about the order of growth of the sample-size requirement of the problem, as a function of the PAC parameters. The exact value of sample-size requirement is however less well-known, and depends heavily on the particular learning algorithm being used. This is a major obstacle to the practical application of the VC dimension. Hence it is important to know exactly how the sample-size requirement depends on VC dimension, and with that in mind, we describe a general algorithm for learning problems having VC dimension 1. Its sample-size requirement is minimal (as a function of the PAC parameters), and turns out to be the same for all non-trivial learning problems having VC dimension 1. While the method used cannot be naively generalised to higher VC dimension, it suggests that optimal algorithm-dependent bounds may improve substantially on current upper bounds.

Noisy fitness evaluation in genetic algorithms and the dynamics of learning

A theoretical model is presented which describes selection in a genetic algorithm (GA) under a stochastic fitness measure and correctly accounts for finite population effects. Although this model describes a number of selection schemes, we only consider Boltzmann selection in detail here as results for this form of selection are particularly transparent when fitness is corrupted by additive Gaussian noise. Finite population effects are shown to be of fundamental importance in this case, as the noise has no effect in the infinite population limit. In the limit of weak selection we show how the effects of any Gaussian noise can be removed by increasing the population size appropriately. The theory is tested on two closely related problems: the one-max problem corrupted by Gaussian noise and generalization in a perceptron with binary weights. The averaged dynamics can be accurately modelled for both problems using a formalism which describes the dynamics of the GA using methods from statistical mechanics. The second problem is a simple example of a learning problem and by considering this problem we show how the accurate characterization of noise in the fitness evaluation may be relevant in machine learning. The training error (negative fitness) is the number of misclassified training examples in a batch and can be considered as a noisy version of the generalization error if an independent batch is used for each evaluation. The noise is due to the finite batch size and in the limit of large problem size and weak selection we show how the effect of this noise can be removed by increasing the population size. This allows the optimal batch size to be determined, which minimizes computation time as well as the total number of training examples required.