A hybrid neural classifier for dimensionality reduction and data visualization and its application to fault detection and classification of induction motors

In this paper, a hybrid neural classifier combining the auto-encoder neural network and the Lattice Vector Quantization (LVQ) model is described. The auto-encoder network is used for dimensionality reduction by projecting high dimensional data into the 2D space. The LVQ model is used for data visualization by forming and adapting the granularity of a data map. The mapped data are employed to predict the target classes of new data samples. To improve classification accuracy, a majority voting scheme is adopted by the hybrid classifier. To demonstrate the applicability of the hybrid classifier, a series of experiments using simulated and real fault data from induction motors is conducted. The results show that the hybrid classifier is able to outperform the Multi-Layer Perceptron neural network, and to produce very good classification accuracy rates for various fault conditions of induction motors.

The role of the computer in learning ndjébbana

While Computer Assisted Language Learning (CALL) is being superseded by an integrated approach to language learning and technology, it still has great potential to assist indigenous peoples in becoming print-literate in their own languages. This can also help to combat the disempowerment experienced by indigenous people as their world is penetrated by others with radically different backgrounds. This paper reports on research on an application of CALL implemented among the Kunibídji, a remote, indigenous Australian community. It focuses on the use of talking books in Ndjébbana, a language with only 200 speakers; the books were displayed on touch-screens at various locations in the community. Investigations into the roles of the computer to support language learning and cultural understanding are also reported. The computer was found to be a useful tool in promoting Kunibídji collaboration and cultural transformation.

Computer simulation based parameter selection for resistance exercise

In contrast to most scientific disciplines, sports science research has been characterized by comparatively little effort investment in the development of relevant phenomenologi-cal models. Scarcer yet is the application of said models in practice. We present a framework which allows resistance training practitioners to employ a recently proposed neu-romuscular model in actual training program design. The first novelty concerns the monitoring aspect of coaching. A method for extracting training performance characteristics from loosely constrained video sequences, effortlessly and with minimal human input, using computer vision is described. The extracted data is subsequently used to fit the underlying neuromuscular model. This is achieved by solving an inverse dynamics problem corresponding to a particular exercise. Lastly, a computer simulation of hypothetical training bouts, using athlete-specific capability parameters, is used to predict the effected adaptation and changes in performance. The software described here allows the practitioner to manipulate hypothetical training parameters and immediately see their effect on predicted adaptation for a specific athlete. Thus, this work presents a holistic view of the monitoring-assessment-adjustment loop.

Common variants of the resistance mechanism in the Smith Machine: analysis of mechanical loading characteristics and application to strength-oriented and hypertrophy-oriented training

The Smith machine is a pervasive weight-training apparatus, used extensively by a wide population of weight trainers, from novices to high-level athletes. The advantages of using a Smith machine over free-weight resistance are disputed, with conflicting findings reported in the literature. In this study, we are interested in practical differences between 3 types of loading mechanisms found in modern Smith machines. In addition to the basic design comprising a constrained weighted barbell, alterations with a counterweight and a viscous resistance component are examined. The approach taken is that of employing a recently proposed representation of force characteristics that may be exhibited by a trainee and a predictive model of thus effected adaptation. A computer simulation is used to predict the effects of the 3 linear Smith machine designs in the framework of different exercise protocols. Our results demonstrate that each resistance component, vertically constrained load, counterweight, and viscous, can be matched with a particular training context, in which it should be preferred. Thus, a number of practical guidelines for weight-training practitioners are recommended. In summary, (a) at low intensities (55–75% of 1 repetition maximum [1RM]) used in strength-endurance training, a viscous resistance containing the Smith machine was found to offer advantages over both a constrained load only and counterweighted designs; (b) at medium intensities (75–85% of 1RM) typically employed in hypertrophy-specific training, the counterweighted Smith machine design was found to offer the best choice in terms of high-force development and total external work performed; finally, (c) at high training intensity (90–100% of 1RM), the optimal prescription was found to be more dependent on the specific athlete’s weaknesses, highlighting the need for continual monitoring of the athlete’s force production capabilities. To ensure that appropriate adjustments are made to the athlete’s training regimen, the practitioner should consider the full set of findings of this article and the accompanying discussion.

Gambling motives: application of the reasons for gambling questionnaire in an Australian population survey

The Reasons for Gambling Questionnaire (RGQ) consist of 15 items forming five factors: enhancement, social, money, recreation and coping. The RGQ was developed for use in the 2010 British Gambling Prevalence Survey (BGPS) and has now been employed in the second Social and Economic Impact Study (SEIS) of Gambling in Tasmania study conducted in 2011 in Australia. Given differences between Britain and Australia in terms of socio-demographic profiles, gambling cultures and attitudes, gambling access and availability, gambling regulation, and rates and patterns of gambling participation, the aims of this study were to analyse the RGQ data from the SEIS to: (1) determine the most commonly endorsed gambling motives in an Australian jurisdiction, (2) explore the factor structure of the RGQ in an Australian sample, and (3) explore how motives for gambling vary among different Australian population sub-groups. A representative sample of the Tasmanian population who had gambled in the previous 12 months (n = 2,796) were administered the RGQ via computer-assisted telephone interviewing. The five most commonly endorsed reasons for gambling were for fun (62 %), followed by the chance of winning big money (52 %), it being something to do with friends and family (48 %), to be sociable (40 %), and excitement (38 %). A principal component analysis revealed a five-factor structure that is slightly different from that derived in the BGPS: money, regulate internal state, positive feelings, social, and challenge reasons. Finally, gambling motives varied according to socio-demographic factors, number of gambling activities, problem gambling severity, and participation on different gambling activities. Although some of these findings are consistent with those from the BGPS, there are also some slight differences, suggesting that there may be regional-specific variations in gambling motives.

Condition monitoring of induction motors : A review and an application of an ensemble of hybrid intelligent models

In this paper, a review on condition monitoring of induction motors is first presented. Then, an ensemble of hybrid intelligent models that is useful for condition monitoring of induction motors is proposed. The review covers two parts, i.e.; (i) a total of nine commonly used condition monitoring methods of induction motors; and (ii) intelligent learning models for condition monitoring of induction motors subject to single and multiple input signals. Based on the review findings, the Motor Current Signature Analysis (MCSA) method is selected for this study owing to its online, non-invasive properties and its requirement of only single input source; therefore leading to a cost-effective condition monitoring method. A hybrid intelligent model that consists of the Fuzzy Min-Max (FMM) neural network and the Random Forest (RF) model comprising an ensemble of Classification and Regression Trees is developed. The majority voting scheme is used to combine the predictions produced by the resulting FMM-RF ensemble (or FMM-RFE) members. A benchmark problem is first deployed to evaluate the usefulness of the FMM-RFE model. Then, the model is applied to condition monitoring of induction motors using a set of real data samples. Specifically, the stator current signals of induction motors are obtained using the MCSA method. The signals are processed to produce a set of harmonic-based features for classification using the FMM-RFE model. The experimental results show good performances in both noise-free and noisy environments. More importantly, a set of explanatory rules in the form of a decision tree can be extracted from the FMM-RFE model to justify its predictions. The outcomes ascertain the effectiveness of the proposed FMM-RFE model in undertaking condition monitoring tasks, especially for induction motors, under different environments. © 2014 Elsevier Ltd. All rights reserved.

Detection and defense of application-layer DDoS attacks in backbone web traffic

Web servers are usually located in a well-organized data center where these servers connect with the outside Internet directly through backbones. Meanwhile, the application-layer distributed denials of service (AL-DDoS) attacks are critical threats to the Internet, particularly to those business web servers. Currently, there are some methods designed to handle the AL-DDoS attacks, but most of them cannot be used in heavy backbones. In this paper, we propose a new method to detect AL-DDoS attacks. Our work distinguishes itself from previous methods by considering AL-DDoS attack detection in heavy backbone traffic. Besides, the detection of AL-DDoS attacks is easily misled by flash crowd traffic. In order to overcome this problem, our proposed method constructs a Real-time Frequency Vector (RFV) and real-timely characterizes the traffic as a set of models. By examining the entropy of AL-DDoS attacks and flash crowds, these models can be used to recognize the real AL-DDoS attacks. We integrate the above detection principles into a modularized defense architecture, which consists of a head-end sensor, a detection module and a traffic filter. With a swift AL-DDoS detection speed, the filter is capable of letting the legitimate requests through but the attack traffic is stopped. In the experiment, we adopt certain episodes of real traffic from Sina and Taobao to evaluate our AL-DDoS detection method and architecture. Compared with previous methods, the results show that our approach is very effective in defending AL-DDoS attacks at backbones. © 2013 Elsevier B.V. All rights reserved.

Motor imagery data classification for BCI application using wavelet packet feature extraction

The noninvasive brain imaging modalities have provided us an extraordinary means for monitoring the working brain. Among these modalities, Electroencephalography (EEG) is the most widely used technique for measuring the brain signals under different tasks, due to its mobility, low cost, and high temporal resolution. In this paper we investigate the use of EEG signals in brain-computer interface (BCI) systems.

A modified fuzzy min-max neural network for data clustering and its application to power quality monitoring

When no prior knowledge is available, clustering is a useful technique for categorizing data into meaningful groups or clusters. In this paper, a modified fuzzy min-max (MFMM) clustering neural network is proposed. Its efficacy for tackling power quality monitoring tasks is demonstrated. A literature review on various clustering techniques is first presented. To evaluate the proposed MFMM model, a performance comparison study using benchmark data sets pertaining to clustering problems is conducted. The results obtained are comparable with those reported in the literature. Then, a real-world case study on power quality monitoring tasks is performed. The results are compared with those from the fuzzy c-means and k-means clustering methods. The experimental outcome positively indicates the potential of MFMM in undertaking data clustering tasks and its applicability to the power systems domain.

Application of extended multivariate modeling for information flow analysis of event related responses

Event related potential (ERP) analysis is one of the most widely used methods in cognitive neuroscience research to study the physiological correlates of sensory, perceptual and cognitive activity associated with processing information. To this end information flow or dynamic effective connectivity analysis is a vital technique to understand the higher cognitive processing under different events. In this paper we present a Granger causality (GC)-based connectivity estimation applied to ERP data analysis. In contrast to the generally used strictly causal multivariate autoregressive model, we use an extended multivariate autoregressive model (eMVAR) which also accounts for any instantaneous interaction among variables under consideration. The experimental data used in the paper is based on a single subject data set for erroneous button press response from a two-back with feedback continuous performance task (CPT). In order to demonstrate the feasibility of application of eMVAR models in source space connectivity studies, we use cortical source time series data estimated using blind source separation or independent component analysis (ICA) for this data set.

EEG signal analysis for BCI application using fuzzy system

An approach to EEG signal classification for brain-computer interface (BCI) application using fuzzy standard additive model is introduced in this paper. The Wilcoxon test is employed to rank wavelet coefficients. Top ranking wavelets are used to form a feature set that serves as inputs to the fuzzy classifiers. Experiments are carried out using two benchmark datasets, Ia and Ib, downloaded from the BCI competition II. Prevalent classifiers including feedforward neural network, support vector machine, k-nearest neighbours, ensemble learning Adaboost and adaptive neuro-fuzzy inference system are also implemented for comparisons. Experimental results show the dominance of the proposed method against competing approaches.