Automatic spiral analysis for objective assessment of motor symptoms in Parkinson's disease

Objective: To develop a method for objective quantification of PD motor symptoms related to Off episodes and peak dose dyskinesias, using spiral data gathered by using a touch screen telemetry device. The aim was to objectively characterize predominant motor phenotypes (bradykinesia and dyskinesia), to help in automating the process of visual interpretation of movement anomalies in spirals as rated by movement disorder specialists. Background: A retrospective analysis was conducted on recordings from 65 patients with advanced idiopathic PD from nine different clinics in Sweden, recruited from January 2006 until August 2010. In addition to the patient group, 10 healthy elderly subjects were recruited. Upper limb movement data were collected using a touch screen telemetry device from home environments of the subjects. Measurements with the device were performed four times per day during week-long test periods. On each test occasion, the subjects were asked to trace pre-drawn Archimedean spirals, using the dominant hand. The pre-drawn spiral was shown on the screen of the device. The spiral test was repeated three times per test occasion and they were instructed to complete it within 10 seconds. The device had a sampling rate of 10Hz and measured both position and time-stamps (in milliseconds) of the pen tip. Methods: Four independent raters (FB, DH, AJ and DN) used a web interface that animated the spiral drawings and allowed them to observe different kinematic features during the drawing process and to rate task performance. Initially, a number of kinematic features were assessed including ‘impairment’, ‘speed’, ‘irregularity’ and ‘hesitation’ followed by marking the predominant motor phenotype on a 3-category scale: tremor, bradykinesia and/or choreatic dyskinesia. There were only 2 test occasions for which all the four raters either classified them as tremor or could not identify the motor phenotype. Therefore, the two main motor phenotype categories were bradykinesia and dyskinesia. ‘Impairment’ was rated on a scale from 0 (no impairment) to 10 (extremely severe) whereas ‘speed’, ‘irregularity’ and ‘hesitation’ were rated on a scale from 0 (normal) to 4 (extremely severe). The proposed data-driven method consisted of the following steps. Initially, 28 spatiotemporal features were extracted from the time series signals before being presented to a Multilayer Perceptron (MLP) classifier. The features were based on different kinematic quantities of spirals including radius, angle, speed and velocity with the aim of measuring the severity of involuntary symptoms and discriminate between PD-specific (bradykinesia) and/or treatment-induced symptoms (dyskinesia). A Principal Component Analysis was applied on the features to reduce their dimensions where 4 relevant principal components (PCs) were retained and used as inputs to the MLP classifier. Finally, the MLP classifier mapped these components to the corresponding visually assessed motor phenotype scores for automating the process of scoring the bradykinesia and dyskinesia in PD patients whilst they draw spirals using the touch screen device. For motor phenotype (bradykinesia vs. dyskinesia) classification, the stratified 10-fold cross validation technique was employed. Results: There were good agreements between the four raters when rating the individual kinematic features with intra-class correlation coefficient (ICC) of 0.88 for ‘impairment’, 0.74 for ‘speed’, 0.70 for ‘irregularity’, and moderate agreements when rating ‘hesitation’ with an ICC of 0.49. When assessing the two main motor phenotype categories (bradykinesia or dyskinesia) in animated spirals the agreements between the four raters ranged from fair to moderate. There were good correlations between mean ratings of the four raters on individual kinematic features and computed scores. The MLP classifier classified the motor phenotype that is bradykinesia or dyskinesia with an accuracy of 85% in relation to visual classifications of the four movement disorder specialists. The test-retest reliability of the four PCs across the three spiral test trials was good with Cronbach’s Alpha coefficients of 0.80, 0.82, 0.54 and 0.49, respectively. These results indicate that the computed scores are stable and consistent over time. Significant differences were found between the two groups (patients and healthy elderly subjects) in all the PCs, except for the PC3. Conclusions: The proposed method automatically assessed the severity of unwanted symptoms and could reasonably well discriminate between PD-specific and/or treatment-induced motor symptoms, in relation to visual assessments of movement disorder specialists. The objective assessments could provide a time-effect summary score that could be useful for improving decision-making during symptom evaluation of individualized treatment when the goal is to maximize functional On time for patients while minimizing their Off episodes and troublesome dyskinesias.

Automatic spiral analysis for objective assessment of motor symptoms in Parkinson's disease

A challenge for the clinical management of advanced Parkinson’s disease (PD) patients is the emergence of fluctuations in motor performance, which represents a significant source of disability during activities of daily living of the patients. There is a lack of objective measurement of treatment effects for in-clinic and at-home use that can provide an overview of the treatment response. The objective of this paper was to develop a method for objective quantification of advanced PD motor symptoms related to off episodes and peak dose dyskinesia, using spiral data gathered by a touch screen telemetry device. More specifically, the aim was to objectively characterize motor symptoms (bradykinesia and dyskinesia), to help in automating the process of visual interpretation of movement anomalies in spirals as rated by movement disorder specialists. Digitized upper limb movement data of 65 advanced PD patients and 10 healthy (HE) subjects were recorded as they performed spiral drawing tasks on a touch screen device in their home environment settings. Several spatiotemporal features were extracted from the time series and used as inputs to machine learning methods. The methods were validated against ratings on animated spirals scored by four movement disorder specialists who visually assessed a set of kinematic features and the motor symptom. The ability of the method to discriminate between PD patients and HE subjects and the test-retest reliability of the computed scores were also evaluated. Computed scores correlated well with mean visual ratings of individual kinematic features. The best performing classifier (Multilayer Perceptron) classified the motor symptom (bradykinesia or dyskinesia) with an accuracy of 84% and area under the receiver operating characteristics curve of 0.86 in relation to visual classifications of the raters. In addition, the method provided high discriminating power when distinguishing between PD patients and HE subjects as well as had good test-retest reliability. This study demonstrated the potential of using digital spiral analysis for objective quantification of PD-specific and/or treatment-induced motor symptoms.

Machine Learning Algorithms in Heavy Process Manufacturing

In a global economy, manufacturers mainly compete with cost efficiency of production, as the price of raw materials are similar worldwide. Heavy industry has two big issues to deal with. On the one hand there is lots of data which needs to be analyzed in an effective manner, and on the other hand making big improvements via investments in cooperate structure or new machinery is neither economically nor physically viable. Machine learning offers a promising way for manufacturers to address both these problems as they are in an excellent position to employ learning techniques with their massive resource of historical production data. However, choosing modelling a strategy in this setting is far from trivial and this is the objective of this article. The article investigates characteristics of the most popular classifiers used in industry today. Support Vector Machines, Multilayer Perceptron, Decision Trees, Random Forests, and the meta-algorithms Bagging and Boosting are mainly investigated in this work. Lessons from real-world implementations of these learners are also provided together with future directions when different learners are expected to perform well. The importance of feature selection and relevant selection methods in an industrial setting are further investigated. Performance metrics have also been discussed for the sake of completion.

Mill specific prediction of worsted yarn performance

Different spinning mills use different raw materials, processing methodologies, and equipment, all of which influence the quality of the yarns produced. Because of many variables, there is a difficulty in developing a universal empirical/theoretical model. This work presents a multilayer perceptron algorithm (MLP) model for the purpose of building a mill specific worsted spinning performance prediction tool. Sixteen inputs are used to predict key yarn properties and spinning performance, including number of fibers in cross-section, unevenness (U%), thin places, neps, yarn tenacity, elongation at break, thick places, and spinning ends-down. Validation of the model on mill specific commercial data set shows that the general fit to the target values is good. Importantly, the performance of the MLP shows a certain degree of stability to different, random selections of independent test data. Subsequent comparison against the predicted outputs of Sirolan Yarnspec™ confirms the overall performance of the artificial neural network (ANN) method to be more accuratefor mill specific predictions.

Predicting the rolling force in hot steel rolling mill using an ensemble model

Accurate prediction of the roll separating force is critical to assuring the quality of the final product in steel manufacturing. This paper presents an ensemble model that addresses these concerns. A stacked generalisation approach to ensemble modeling is used with two sets of the ensemble model members, the first set being learnt from the current input-output data of the hot rolling finishing mill, while another uses the available information on the previous coil in addition to the current information. Both sets of ensemble members include linear regression, multilayer perceptron, and k-nearest neighbor algorithms. A competitive selection model (multilayer perceptron) is then used to select the output from one of the ensemble members to be the final output of the ensemble model. The ensemble model created by such a stacked generalization is able to achieve extremely high accuracy in predicting the roll separation force with the average relative accuracy being within 1% of the actual measured roll force.

An artificial neural network-based hairiness prediction model for worsted wool yarns

This study evaluated the performance of multilayer perceptron (MLP) and multivariate linear regression (MLR) models for predicting the hairiness of worsted-spun wool yarns from various top, yarn and processing parameters. The results indicated that the MLP model predicted yarn hairiness more accurately than the MLR model, and should have wide mill specific applications. On the basis of sensitivity analysis, the factors that affected yarn hairiness significantly included yarn twist, ring size, average fiber length (hauteur), fiber diameter and yarn count, with twist having the greatest impact on yarn hairiness.

Improving the prediction of the roll separating force in a hot steel finishing mill

This paper focuses on the development of a hybrid phenomenological/inductive model to improve the current physical setup force model on a five stand industrial hot strip finishing mill. We approached the problem from two directions. In the first approach, the starting point was the output of the current setup force model. A feedforward multilayer perceptron (MLP) model was then used to estimate the true roll separating force using some other available variables as additional inputs to the model.

It was found that it is possible to significantly improve the estimation of a roll separating force from 5.3% error on average with the current setup model to 2.5% error on average with the hybrid model. The corresponding improvements for the first coils are from 7.5% with the current model to 3.8% with the hybrid model. This was achieved by inclusion, in addition to each stand's force from the current model, the contributions from setup forces from the other stands, as well as the contributions from a limited set of additional variables such as: a) aim width; b) setup thickness; c) setup temperature; and d) measured force from the previous coil.

In the second approach, we investigated the correlation between the large errors in the current model and input parameters of the model. The data set was split into two subsets, one representing the "normal" level of error between the current model and the measured force value, while the other set contained the coils with a "large" level of error. Additional set of data with changes in each coil's inputs from the previous coil's inputs was created to investigate the dependency on the previous coil.

The data sets were then analyzed using a C4.5 decision tree. The main findings were that the level of the speed vernier variable is highly correlated with the large errors in the current setup model. Specifically, a high positive speed vernier value often correlated to a large error. Secondly, it has been found that large changes to the model flow stress values between coils are correlated frequently with larger errors in the current setup force model.

Mixed transfer function neural networks for knowledge acquistition

Modeling helps to understand and predict the outcome of complex systems. Inductive modeling methodologies are beneficial for modeling the systems where the uncertainties involved in the system do not permit to obtain an accurate physical model. However inductive models, like artificial neural networks (ANNs), may suffer from a few drawbacks involving over-fitting and the difficulty to easily understand the model itself. This can result in user reluctance to accept the model or even complete rejection of the modeling results. Thus, it becomes highly desirable to make such inductive models more comprehensible and to automatically determine the model complexity to avoid over-fitting. In this paper, we propose a novel type of ANN, a mixed transfer function artificial neural network (MTFANN), which aims to improve the complexity fitting and comprehensibility of the most popular type of ANN (MLP - a Multilayer Perceptron).

Prediction of Drug Dissolution Profiles Using Artificial Neural Networks

This paper investigates the efficacy and reliability of Artificial Neural Networks (ANNs) as an intelligent decision support tool for pharmaceutical product formulation. Two case studies have been employed to evaluate capabilities of the Multilayer Perceptron network in predicting drug dissolution/release profiles. Performances of the network were evaluated using similarity factor (&fnof[sub 2]) — an index recommended by the United States Food and Drug Administration for profile comparison in pharmaceutical research. In addition, the bootstrap method was applied to assess the network prediction reliability by estimating confidence intervals associated with the results. The Multilayer Perceptron network also demonstrated a superior performance in comparison with multiple regression models. The results reveal that the ANN system has potentials to be a decision support tool for profile prediction in pharmaceutical experimentation, and the bootstrap method could be used as a means to assess reliability of the network prediction. [ABSTRACT FROM AUTHOR].

Use of circle-segments as a data visualization technique for feature selection in pattern classification

One of the issues associated with pattern classification using data based machine learning systems is the “curse of dimensionality”. In this paper, the circle-segments method is proposed as a feature selection method to identify important input features before the entire data set is provided for learning with machine learning systems. Specifically, four machine learning systems are deployed for classification, viz. Multilayer Perceptron (MLP), Support Vector Machine (SVM), Fuzzy ARTMAP (FAM), and k-Nearest Neighbour (kNN). The integration between the circle-segments method and the machine learning systems has been applied to two case studies comprising one benchmark and one real data sets. Overall, the results after feature selection using the circle segments method demonstrate improvements in performance even with more than 50% of the input features eliminated from the original data sets.

An accelerated particle swarm optimization based levenberg marquardt back propagation algorithm

The Levenberg Marquardt (LM) algorithm is one of the most effective algorithms in speeding up the convergence rate of the Artificial Neural Networks (ANN) with Multilayer Perceptron (MLP) architectures. However, the LM algorithm suffers the problem of local minimum entrapment. Therefore, we introduce several improvements to the Levenberg Marquardt algorithm by training the ANNs with meta-heuristic nature inspired algorithm. This paper proposes a hybrid technique Accelerated Particle Swarm Optimization using Levenberg Marquardt (APSO_LM) to achieve faster convergence rate and to avoid local minima problem. These techniques are chosen since they provide faster training for solving pattern recognition problems using the numerical optimization technique.The performances of the proposed algorithm is evaluated using some bench mark of classification’s datasets. The results are compared with Artificial Bee Colony (ABC) Algorithm using Back Propagation Neural Network (BPNN) algorithm and other hybrid variants. Based on the experimental result, the proposed algorithms APSO_LM successfully demonstrated better performance as compared to other existing algorithms in terms of convergence speed and Mean Squared Error (MSE) by introducing the error and accuracy in network convergence.

An improved Gbest guided artificial bee colony (IGGABC) algorithm for classification and prediction tasks

Artificial Neural Networks (ANN) performance depends on network topology, activation function, behaviors of data, suitable synapse's values and learning algorithms. Many existing works used different learning algorithms to train ANN for getting high performance. Artificial Bee Colony (ABC) algorithm is one of the latest successfully Swarm Intelligence based technique for training Multilayer Perceptron (MLP). Normally Gbest Guided Artificial Bee Colony (GGABC) algorithm has strong exploitation process for solving mathematical problems, however the poor exploration creates problems like slow convergence and trapping in local minima. In this paper, the Improved Gbest Guided Artificial Bee Colony (IGGABC) algorithm is proposed for finding global optima. The proposed IGGABC algorithm has strong exploitation and exploration processes. The experimental results show that IGGABC algorithm performs better than that standard GGABC, BP and ABC algorithms for Boolean data classification and time-series prediction tasks.

A novel aggregate gene selection method for microarray data classification

This paper introduces a novel method for gene selection based on a modification of analytic hierarchy process (AHP). The modified AHP (MAHP) is able to deal with quantitative factors that are statistics of five individual gene ranking methods: two-sample t-test, entropy test, receiver operating characteristic curve, Wilcoxon test, and signal to noise ratio. The most prominent discriminant genes serve as inputs to a range of classifiers including linear discriminant analysis, k-nearest neighbors, probabilistic neural network, support vector machine, and multilayer perceptron. Gene subsets selected by MAHP are compared with those of four competing approaches: information gain, symmetrical uncertainty, Bhattacharyya distance and ReliefF. Four benchmark microarray datasets: diffuse large B-cell lymphoma, leukemia cancer, prostate and colon are utilized for experiments. As the number of samples in microarray data datasets are limited, the leave one out cross validation strategy is applied rather than the traditional cross validation. Experimental results demonstrate the significant dominance of the proposed MAHP against the competing methods in terms of both accuracy and stability. With a benefit of inexpensive computational cost, MAHP is useful for cancer diagnosis using DNA gene expression profiles in the real clinical practice.

Sistema inteligente para estimar a porosidade em sedimentos a partir da análise de sinais GPR

This Thesis presents the elaboration of a methodological propose for the development of an intelligent system, able to automatically achieve the effective porosity, in sedimentary layers, from a data bank built with information from the Ground Penetrating Radar GPR. The intelligent system was built to model the relation between the porosity (response variable) and the electromagnetic attribute from the GPR (explicative variables). Using it, the porosity was estimated using the artificial neural network (Multilayer Perceptron MLP) and the multiple linear regression. The data from the response variable and from the explicative variables were achieved in laboratory and in GPR surveys outlined in controlled sites, on site and in laboratory. The proposed intelligent system has the capacity of estimating the porosity from any available data bank, which has the same variables used in this Thesis. The architecture of the neural network used can be modified according to the existing necessity, adapting to the available data bank. The use of the multiple linear regression model allowed the identification and quantification of the influence (level of effect) from each explicative variable in the estimation of the porosity. The proposed methodology can revolutionize the use of the GPR, not only for the imaging of the sedimentary geometry and faces, but mainly for the automatically achievement of the porosity one of the most important parameters for the characterization of reservoir rocks (from petroleum or water)

Comparison of logistic and neural network models to fit to the egg production curve of White Leghorn hens

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)