Adaptive neuro-fuzzy inference systems (ANFIS) for supervised classification of competence in MIS based on psychomotor skills

INTRODUCTION: Objective assessment of motor skills has become an important challenge in minimally invasive surgery (MIS) training.Currently, there is no gold standard defining and determining the residents' surgical competence.To aid in the decision process, we analyze the validity of a supervised classifier to determine the degree of MIS competence based on assessment of psychomotor skills METHODOLOGY: The ANFIS is trained to classify performance in a box trainer peg transfer task performed by two groups (expert/non expert). There were 42 participants included in the study: the non-expert group consisted of 16 medical students and 8 residents (< 10 MIS procedures performed), whereas the expert group consisted of 14 residents (> 10 MIS procedures performed) and 4 experienced surgeons. Instrument movements were captured by means of the Endoscopic Video Analysis (EVA) tracking system. Nine motion analysis parameters (MAPs) were analyzed, including time, path length, depth, average speed, average acceleration, economy of area, economy of volume, idle time and motion smoothness. Data reduction was performed by means of principal component analysis, and then used to train the ANFIS net. Performance was measured by leave one out cross validation. RESULTS: The ANFIS presented an accuracy of 80.95%, where 13 experts and 21 non-experts were correctly classified. Total root mean square error was 0.88, while the area under the classifiers' ROC curve (AUC) was measured at 0.81. DISCUSSION: We have shown the usefulness of ANFIS for classification of MIS competence in a simple box trainer exercise. The main advantage of using ANFIS resides in its continuous output, which allows fine discrimination of surgical competence. There are, however, challenges that must be taken into account when considering use of ANFIS (e.g. training time, architecture modeling). Despite this, we have shown discriminative power of ANFIS for a low-difficulty box trainer task, regardless of the individual significances between MAPs. Future studies are required to confirm the findings, inclusion of new tasks, conditions and sample population.

Automatic blood glucose classification for gestational diabetes with feature selection: decision trees vs neural networks

Automatic blood glucose classification may help specialists to provide a better interpretation of blood glucose data, downloaded directly from patients glucose meter and will contribute in the development of decision support systems for gestational diabetes. This paper presents an automatic blood glucose classifier for gestational diabetes that compares 6 different feature selection methods for two machine learning algorithms: neural networks and decision trees. Three searching algorithms, Greedy, Best First and Genetic, were combined with two different evaluators, CSF and Wrapper, for the feature selection. The study has been made with 6080 blood glucose measurements from 25 patients. Decision trees with a feature set selected with the Wrapper evaluator and the Best first search algorithm obtained the best accuracy: 95.92%.

Supervised classification of minimally invasive surgery psychomotor competence based on instruments motion analysis

Background Objective assessment of psychomotor skills has become an important challenge in the training of minimally invasive surgical (MIS) techniques. Currently, no gold standard defining surgical competence exists for classifying residents according to their surgical skills. Supervised classification has been proposed as a means for objectively establishing competence thresholds in psychomotor skills evaluation. This report presents a study comparing three classification methods for establishing their validity in a set of tasks for basic skills’ assessment. Methods Linear discriminant analysis (LDA), support vector machines (SVM), and adaptive neuro-fuzzy inference systems (ANFIS) were used. A total of 42 participants, divided into an experienced group (4 expert surgeons and 14 residents with >10 laparoscopic surgeries performed) and a nonexperienced group (16 students and 8 residents with <10 laparoscopic surgeries performed), performed three box trainer tasks validated for assessment of MIS psychomotor skills. Instrument movements were captured using the TrEndo tracking system, and nine motion analysis parameters (MAPs) were analyzed. The performance of the classifiers was measured by leave-one-out cross-validation using the scores obtained by the participants. Results The mean accuracy performances of the classifiers were 71 % (LDA), 78.2 % (SVM), and 71.7 % (ANFIS). No statistically significant differences in the performance were identified between the classifiers. Conclusions The three proposed classifiers showed good performance in the discrimination of skills, especially when information from all MAPs and tasks combined were considered. A correlation between the surgeons’ previous experience and their execution of the tasks could be ascertained from results. However, misclassifications across all the classifiers could imply the existence of other factors influencing psychomotor competence.

Sea Bottom Classification by Means of Bathymetric LIDAR Data

Light Detection and Ranging (LIDAR) provides high horizontal and vertical resolution of spatial data located in point cloud images, and is increasingly being used in a number of applications and disciplines, which have concentrated on the exploit and manipulation of the data using mainly its three dimensional nature. Bathymetric LIDAR systems and data are mainly focused to map depths in shallow and clear waters with a high degree of accuracy. Additionally, the backscattering produced by the different materials distributed over the bottom surface causes that the returned intensity signal contains important information about the reflection properties of these materials. Processing conveniently these values using a Simplified Radiative Transfer Model, allows the identification of different sea bottom types. This paper presents an original method for the classification of sea bottom by means of information processing extracted from the images generated through LIDAR data. The results are validated using a vector database containing benthic information derived by marine surveys.

Autonomous classification models in ubiquitous environments

Stream-mining approach is defined as a set of cutting-edge techniques designed to process streams of data in real time, in order to extract knowledge. In the particular case of classification, stream-mining has to adapt its behaviour to the volatile underlying data distributions, what has been called concept drift. Moreover, it is important to note that concept drift may lead to situations where predictive models become invalid and have therefore to be updated to represent the actual concepts that data poses. In this context, there is a specific type of concept drift, known as recurrent concept drift, where the concepts represented by data have already appeared in the past. In those cases the learning process could be saved or at least minimized by applying a previously trained model. This could be extremely useful in ubiquitous environments that are characterized by the existence of resource constrained devices. To deal with the aforementioned scenario, meta-models can be used in the process of enhancing the drift detection mechanisms used by data stream algorithms, by representing and predicting when the change will occur. There are some real-world situations where a concept reappears, as in the case of intrusion detection systems (IDS), where the same incidents or an adaptation of them usually reappear over time. In these environments the early prediction of drift by means of a better knowledge of past models can help to anticipate to the change, thus improving efficiency of the model regarding the training instances needed. By means of using meta-models as a recurrent drift detection mechanism, the ability to share concepts representations among different data mining processes is open. That kind of exchanges could improve the accuracy of the resultant local model as such model may benefit from patterns similar to the local concept that were observed in other scenarios, but not yet locally. This would also improve the efficiency of training instances used during the classification process, as long as the exchange of models would aid in the application of already trained recurrent models, that have been previously seen by any of the collaborative devices. Which it is to say that the scope of recurrence detection and representation is broaden. In fact the detection, representation and exchange of concept drift patterns would be extremely useful for the law enforcement activities fighting against cyber crime. Being the information exchange one of the main pillars of cooperation, national units would benefit from the experience and knowledge gained by third parties. Moreover, in the specific scope of critical infrastructures protection it is crucial to count with information exchange mechanisms, both from a strategical and technical scope. The exchange of concept drift detection schemes in cyber security environments would aid in the process of preventing, detecting and effectively responding to threads in cyber space. Furthermore, as a complement of meta-models, a mechanism to assess the similarity between classification models is also needed when dealing with recurrent concepts. In this context, when reusing a previously trained model a rough comparison between concepts is usually made, applying boolean logic. The introduction of fuzzy logic comparisons between models could lead to a better efficient reuse of previously seen concepts, by applying not just equal models, but also similar ones. This work faces the aforementioned open issues by means of: the MMPRec system, that integrates a meta-model mechanism and a fuzzy similarity function; a collaborative environment to share meta-models between different devices; a recurrent drift generator that allows to test the usefulness of recurrent drift systems, as it is the case of MMPRec. Moreover, this thesis presents an experimental validation of the proposed contributions using synthetic and real datasets.

Improving classification using a Confidence Matrix based on weak classifiers applied to OCR

This paper proposes a new feature representation method based on the construction of a Confidence Matrix (CM). This representation consists of posterior probability values provided by several weak classifiers, each one trained and used in different sets of features from the original sample. The CM allows the final classifier to abstract itself from discovering underlying groups of features. In this work the CM is applied to isolated character image recognition, for which several set of features can be extracted from each sample. Experimentation has shown that the use of CM permits a significant improvement in accuracy in most cases, while the others remain the same. The results were obtained after experimenting with four well-known corpora, using evolved meta-classifiers with the k-Nearest Neighbor rule as a weak classifier and by applying statistical significance tests.

Improving kNN multi-label classification in Prototype Selection scenarios using class proposals

Prototype Selection (PS) algorithms allow a faster Nearest Neighbor classification by keeping only the most profitable prototypes of the training set. In turn, these schemes typically lower the performance accuracy. In this work a new strategy for multi-label classifications tasks is proposed to solve this accuracy drop without the need of using all the training set. For that, given a new instance, the PS algorithm is used as a fast recommender system which retrieves the most likely classes. Then, the actual classification is performed only considering the prototypes from the initial training set belonging to the suggested classes. Results show that this strategy provides a large set of trade-off solutions which fills the gap between PS-based classification efficiency and conventional kNN accuracy. Furthermore, this scheme is not only able to, at best, reach the performance of conventional kNN with barely a third of distances computed, but it does also outperform the latter in noisy scenarios, proving to be a much more robust approach.

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%.

Classification and analysis of integrating frameworks in multiscale modelling

Chemical engineers are turning to multiscale modelling to extend traditional modelling approaches into new application areas and to achieve higher levels of detail and accuracy. There is, however, little advice available on the best strategy to use in constructing a multiscale model. This paper presents a starting point for the systematic analysis of multiscale models by defining several integrating frameworks for linking models at different scales. It briefly explores how the nature of the information flow between the models at the different scales is influenced by the choice of framework, and presents some restrictions on model-framework compatibility. The concepts are illustrated with reference to the modelling of a catalytic packed bed reactor. (C) 2004 Elsevier Ltd. All rights reserved.

Classification of oximetry signals using Bayesian neural networks to assist in the detection of obstructive sleep apnoea syndrome

In the present study, multilayer perceptron (MLP) neural networks were applied to help in the diagnosis of obstructive sleep apnoea syndrome (OSAS). Oxygen saturation (SaO2) recordings from nocturnal pulse oximetry were used for this purpose. We performed time and spectral analysis of these signals to extract 14 features related to OSAS. The performance of two different MLP classifiers was compared: maximum likelihood (ML) and Bayesian (BY) MLP networks. A total of 187 subjects suspected of suffering from OSAS took part in the study. Their SaO2 signals were divided into a training set with 74 recordings and a test set with 113 recordings. BY-MLP networks achieved the best performance on the test set with 85.58% accuracy (87.76% sensitivity and 82.39% specificity). These results were substantially better than those provided by ML-MLP networks, which were affected by overfitting and achieved an accuracy of 76.81% (86.42% sensitivity and 62.83% specificity). Our results suggest that the Bayesian framework is preferred to implement our MLP classifiers. The proposed BY-MLP networks could be used for early OSAS detection. They could contribute to overcome the difficulties of nocturnal polysomnography (PSG) and thus reduce the demand for these studies.

Task classification and decision processes in monitoring behaviour

Task classification is introduced as a method for the evaluation of monitoring behaviour in different task situations. On the basis of an analysis of different monitoring tasks, a task classification system comprising four task 'dimensions' is proposed. The perceptual speed and flexibility of closure categories, which are identified with signal discrimination type, comprise the principal dimension in this taxonomy, the others being sense modality, the time course of events, and source complexity. It is also proposed that decision theory provides the most complete method for the analysis of performance in monitoring tasks. Several different aspects of decision theory in relation to monitoring behaviour are described. A method is also outlined whereby both accuracy and latency measures of performance may be analysed within the same decision theory framework. Eight experiments and an organizational study are reported. The results show that a distinction can be made between the perceptual efficiency (sensitivity) of a monitor and his criterial level of response, and that in most monitoring situations, there is no decrement in efficiency over the work period, but an increase in the strictness of the response criterion. The range of tasks exhibiting either or both of these performance trends can be specified within the task classification system. In particular, it is shown that a sensitivity decrement is only obtained for 'speed' tasks with a high stimulation rate. A distinctive feature of 'speed' tasks is that target detection requires the discrimination of a change in a stimulus relative to preceding stimuli, whereas in 'closure' tasks, the information required for the discrimination of targets is presented at the same point In time. In the final study, the specification of tasks yielding sensitivity decrements is shown to be consistent with a task classification analysis of the monitoring literature. It is also demonstrated that the signal type dimension has a major influence on the consistency of individual differences in performance in different tasks. The results provide an empirical validation for the 'speed' and 'closure' categories, and suggest that individual differences are not completely task specific but are dependent on the demands common to different tasks. Task classification is therefore shovn to enable improved generalizations to be made of the factors affecting 1) performance trends over time, and 2) the consistencv of performance in different tasks. A decision theory analysis of response latencies is shown to support the view that criterion shifts are obtained in some tasks, while sensitivity shifts are obtained in others. The results of a psychophysiological study also suggest that evoked potential latency measures may provide temporal correlates of criterion shifts in monitoring tasks. Among other results, the finding that the latencies of negative responses do not increase over time is taken to invalidate arousal-based theories of performance trends over a work period. An interpretation in terms of expectancy, however, provides a more reliable explanation of criterion shifts. Although the mechanisms underlying the sensitivity decrement are not completely clear, the results rule out 'unitary' theories such as observing response and coupling theory. It is suggested that an interpretation in terms of the memory data limitations on information processing provides the most parsimonious explanation of all the results in the literature relating to sensitivity decrement. Task classification therefore enables the refinement and selection of theories of monitoring behaviour in terms of their reliability in generalizing predictions to a wide range of tasks. It is thus concluded that task classification and decision theory provide a reliable basis for the assessment and analysis of monitoring behaviour in different task situations.

The use of context in the classification of urban aerial imagery

Urban regions present some of the most challenging areas for the remote sensing community. Many different types of land cover have similar spectral responses, making them difficult to distinguish from one another. Traditional per-pixel classification techniques suffer particularly badly because they only use these spectral properties to determine a class, and no other properties of the image, such as context. This project presents the results of the classification of a deeply urban area of Dudley, West Midlands, using 4 methods: Supervised Maximum Likelihood, SMAP, ECHO and Unsupervised Maximum Likelihood. An accuracy assessment method is then developed to allow a fair representation of each procedure and a direct comparison between them. Subsequently, a classification procedure is developed that makes use of the context in the image, though a per-polygon classification. The imagery is broken up into a series of polygons extracted from the Marr-Hildreth zero-crossing edge detector. These polygons are then refined using a region-growing algorithm, and then classified according to the mean class of the fine polygons. The imagery produced by this technique is shown to be of better quality and of a higher accuracy than that of other conventional methods. Further refinements are suggested and examined to improve the aesthetic appearance of the imagery. Finally a comparison with the results produced from a previous study of the James Bridge catchment, in Darleston, West Midlands, is made, showing that the Polygon classified ATM imagery performs significantly better than the Maximum Likelihood classified videography used in the initial study, despite the presence of geometric correction errors.

Hierarchical classification of G-protein-coupled receptors with data-driven selection of attributes and classifiers

We address the important bioinformatics problem of predicting protein function from a protein's primary sequence. We consider the functional classification of G-Protein-Coupled Receptors (GPCRs), whose functions are specified in a class hierarchy. We tackle this task using a novel top-down hierarchical classification system where, for each node in the class hierarchy, the predictor attributes to be used in that node and the classifier to be applied to the selected attributes are chosen in a data-driven manner. Compared with a previous hierarchical classification system selecting classifiers only, our new system significantly reduced processing time without significantly sacrificing predictive accuracy.

Examination of the predictive value of structural magnetic resonance scans in bipolar disorder:a pattern classification approach

Background - Bipolar disorder (BD) is one of the leading causes of disability worldwide. Patients are further disadvantaged by delays in accurate diagnosis ranging between 5 and 10 years. We applied Gaussian process classifiers (GPCs) to structural magnetic resonance imaging (sMRI) data to evaluate the feasibility of using pattern recognition techniques for the diagnostic classification of patients with BD. Method - GPCs were applied to gray (GM) and white matter (WM) sMRI data derived from two independent samples of patients with BD (cohort 1: n = 26; cohort 2: n = 14). Within each cohort patients were matched on age, sex and IQ to an equal number of healthy controls. Results - The diagnostic accuracy of the GPC for GM was 73% in cohort 1 and 72% in cohort 2; the sensitivity and specificity of the GM classification were respectively 69% and 77% in cohort 1 and 64% and 99% in cohort 2. The diagnostic accuracy of the GPC for WM was 69% in cohort 1 and 78% in cohort 2; the sensitivity and specificity of the WM classification were both 69% in cohort 1 and 71% and 86% respectively in cohort 2. In both samples, GM and WM clusters discriminating between patients and controls were localized within cortical and subcortical structures implicated in BD. Conclusions - Our results demonstrate the predictive value of neuroanatomical data in discriminating patients with BD from healthy individuals. The overlap between discriminative networks and regions implicated in the pathophysiology of BD supports the biological plausibility of the classifiers.