Rolling element bearing fault diagnosis using convolutional neural network and vibration image

Detecting in prior bearing faults is an essential task of machine health monitoring because bearings are the vital components of rotary machines. The performance of traditional intelligent fault diagnosis methods depend on feature extraction of fault signals, which requires signal processing techniques, expert knowledge, and human labor. Recently, deep learning algorithms have been applied widely in machine health monitoring. With the capacity of automatically learning complex features of input data, deep learning architectures have great potential to overcome drawbacks of traditional intelligent fault diagnosis. This paper proposes a method for diagnosing bearing faults based on a deep structure of convolutional neural network. Using vibration signals directly as input data, the proposed method is an automatic fault diagnosis system which does not require any feature extraction techniques and achieves very high accuracy and robustness under noisy environments.     

Becoming a high‐fidelity – super – imitator: what are the contributions of social and individual learning?

In contrast to other primates, human children's imitation performance goes from low to high fidelity soon after infancy. Are such changes associated with the development of other forms of learning? We addressed this question by testing 215 children (26–59 months) on two social conditions (imitation, emulation) – involving a demonstration – and two asocial conditions (trial‐and‐error, recall) – involving individual learning – using two touchscreen tasks. The tasks required responding to either three different pictures in a specific picture order (Cognitive: Airplane→Ball→Cow) or three identical pictures in a specific spatial order (Motor‐Spatial: Up→Down→Right). There were age‐related improvements across all conditions and imitation, emulation and recall performance were significantly better than trial‐and‐error learning. Generalized linear models demonstrated that motor‐spatial imitation fidelity was associated with age and motor‐spatial emulation performance, but cognitive imitation fidelity was only associated with age. While this study provides evidence for multiple imitation mechanisms, the development of one of those mechanisms – motor‐spatial imitation – may be bootstrapped by the development of another social learning skill – motor‐spatial emulation. Together, these findings provide important clues about the development of imitation, which is arguably a distinctive feature of the human species.     

Feature extraction via KPCA for classification of gait patterns

Automated recognition of gait pattern change is important in medical diagnostics as well as in the early identification of at-risk gait in the elderly. We evaluated the use of Kernel-based Principal Component Analysis (KPCA) to extract more gait features (i.e., to obtain more significant amounts of information about human movement) and thus to improve the classification of gait patterns. 3D gait data of 24 young and 24 elderly participants were acquired using an OPTOTRAK 3020 motion analysis system during normal walking, and a total of 36 gait spatio-temporal and kinematic variables were extracted from the recorded data. KPCA was used first for nonlinear feature extraction to then evaluate its effect on a subsequent classification in combination with learning algorithms such as support vector machines (SVMs). Cross-validation test results indicated that the proposed technique could allow spreading the information about the gait's kinematic structure into more nonlinear principal components, thus providing additional discriminatory information for the improvement of gait classification performance. The feature extraction ability of KPCA was affected slightly with different kernel functions as polynomial and radial basis function. The combination of KPCA and SVM could identify young-elderly gait patterns with 91% accuracy, resulting in a markedly improved performance compared to the combination of PCA and SVM. These results suggest that nonlinear feature extraction by KPCA improves the classification of young-elderly gait patterns, and holds considerable potential for future applications in direct dimensionality reduction and interpretation of multiple gait signals.     

Statistical learning of phonetic categories: insights from a computational approach

Recent evidence ( Maye, Werker & Gerken, 2002 ) suggests that statistical learning may be an important mechanism for the acquisition of phonetic categories in the infant's native language. We examined the sufficiency of this hypothesis and its implications for development by implementing a statistical learning mechanism in a computational model based on a mixture of Gaussians (MOG) architecture. Statistical learning alone was found to be insufficient for phonetic category learning – an additional competition mechanism was required in order for the categories in the input to be successfully learnt. When competition was added to the MOG architecture, this class of models successfully accounted for developmental enhancement and loss of sensitivity to phonetic contrasts. Moreover, the MOG with competition model was used to explore a potentially important distributional property of early speech categories – sparseness – in which portions of the space between phonetic categories are unmapped. Sparseness was found in all successful models and quickly emerged during development even when the initial parameters favoured continuous representations with no gaps. The implications of these models for phonetic category learning in infants are discussed.     

Measuring concept semantic relatedness through common spatial pattern feature extraction on EEG signals

We study the semantic relationship between pairs of nouns of concrete objects such as “HORSE - SHEEP” and “SWING - MELON” and how this relationship activity is reflected in EEG signals. We collected 18 sets of EEG records; each set containing 150 events of stimulation. In this work we focus on feature extraction algorithms. Particularly, we highlight Common Spatial Pattern (CSP) as a method of feature extraction. Based on these latter, different classifiers were trained in order to associate a set of signals to a previously learned human answer, pertaining to two classes: semantically related, or not semantically related. The results of classification accuracy were evaluated comparing with other four methods of feature extraction, and using classification algorithms from five different families. In all cases, classification accuracy was benefited from using CSP instead of FDTW, LPC, PCA or ICA for feature extraction. Particularly with the combination CSP-Naïve Bayes we obtained the best average precision of 84.63%.     

问题解决测验中过程数据的特征抽取与能力评估

基于计算机的问题解决测验可以实时记录被试探索环境和解决问题时的详细行动痕迹,并保存为过程数据。首先介绍了过程数据的分析流程,然后从问题解决测验入手,分别对过程数据的特征抽取和能力估计建模两方面的研究进行了梳理和评价。未来研究应注意：提高分析结果的可解释性;特征提取时纳入更多信息;实现更复杂问题情景下的能力评估;注重方法的实用性;以及融合与借鉴不同领域的分析方法。     

Beyond Four‐Walled Campuses: Models of Ecumenical Theological Education in Interfaith Issues in India

This article examines the relevancy of three education system models – professional or university, banking or teacher‐centred, and campus or residential – from an inter‐religious perspective. These models are no longer adequate in a multi‐religious context and a shift is imperative. We need to evolve a model of education “together with people”, which includes all sections of the society – rich and poor, young and old, Christians and non‐Christians. An inclusive curriculum that affirms plurality/diversity and the common good is urgently needed. This must take place within the larger academic world. A theological education in interaction with the secular learning process will contribute to reinforcing moral and ethical values in society for the common good.     

Taken with Surprise: Critical Incidents in Teaching

Abstract. This collection of essays tackles thorny questions related to critical incidents in teaching. By using different pedagogical methods and techniques, each author provokes creative thinking about how to address specific concerns common to teaching. The authors demonstrate that the teaching and learning process must make room for – if not celebrate – the surprises that happen not only to the students, but to the teachers as well. The discussion of critical incidents helps to promote reflection on teaching practice and prompt insights into the intricate dynamics shaping the increasingly diverse learning community. Each individual essay is accompanied by reflection questions that can be used to spark conversation among colleagues and/or prompt further personal reflection on teaching and learning.     

Group work in general practice

In this article, consideration is given to a problem often experienced in relation to courses offering psychodynamic understanding to front-line workers with troubled clients – the complexity for the student in taking the learning ‘home’ in a productive manner and the potential isolation of the student in, or alienation from, their workplace. A model of course delivery is described in which an active three-way partnership between student, course and workplace is fostered which enhances the students' learning, enables the workplace to benefit more fully from the course and enhances the effectiveness of the course in improving service to the ultimate client – the service user.     

Serotonin neurons and aversive conditioning in the rat

The acute and long-term effects of p -chloroamphetamine (PCA) on one-way and two-way active avoidance (AA), passive avoidance (PA) learning, fear retention (FR) and on central monoamine concentrations were examined in the male rat. Acute PCA administration (0.63–5 mg/kg i.p.), which releases presynaptic 5-HT, produced a dose-related impairment of both one-and two-way AA acquisition, AA retention, PA and fear retention. The selective serotonin (5-HT) uptake inhibitor zimelidine, but not the noradrenaline (NA) uptake inhibitor desipramine, blocked the avoidance deficit induced by acute PCA. Degeneration of brain 5-HT neurons by a high neurotoxic dose of PCA (2 × 10 mg/kg i.p.) failed to change AA and PA learning but blocked the avoidance deficit induced by acute PCA. Degeneration of locus coeruleus NA neurones with DSP4 (1 × 50 mg/kg), a selective NA neurotoxin, failed to block the acute PCA action. Thus, the acute avoidance learning impairment appears to be specifically related to the acute release of endogenous 5-HT. Both acute and long-term PCA treatment affected 5-HT neurones preferentially in the forebrain while marginal effects were observed in the midbrain and spinal cord. A marked impairment in the retention and retrieval of fear conditioning in the rat was also observed following acute PCA administration. The serotoninergic mechanisms underlying the retrieval deficit were found to be similar but not identical to those involved in AA acquisition. These results suggest an important role for central 5-HT neurones in aversive learning processes. The possible involvement of 5-HT neurones in learning, memorial and/or retrieval processes is discussed.     

Serotonin neurons and aversive conditioning in the rat

The acute and long-term effects of p-chloroamphetamine (PCA) on one-way and two-way active avoidance (AA), passive avoidance (PA) learning, fear retention (FR) and on central monoamine concentrations were examined in the male rat. Acute PCA administration (0.63–5 mg/kg i.p.), which releases presynaptic 5-HT, produced a dose-related impairment of both one-and two-way AA acquisition, AA retention, PA and fear retention. The selective serotonin (5-HT) uptake inhibitor zimelidine, but not the noradrenaline (NA) uptake inhibitor desipramine, blocked the avoidance deficit induced by acute PCA. Degeneration of brain 5-HT neurons by a high neurotoxic dose of PCA (2 × 10 mg/kg i.p.) failed to change AA and PA learning but blocked the avoidance deficit induced by acute PCA. Degeneration of locus coeruleus NA neurones with DSP4 (1 × 50 mg/kg), a selective NA neurotoxin, failed to block the acute PCA action. Thus, the acute avoidance learning impairment appears to be specifically related to the acute release of endogenous 5-HT. Both acute and long-term PCA treatment affected 5-HT neurones preferentially in the forebrain while marginal effects were observed in the midbrain and spinal cord. A marked impairment in the retention and retrieval of fear conditioning in the rat was also observed following acute PCA administration. The serotoninergic mechanisms underlying the retrieval deficit were found to be similar but not identical to those involved in AA acquisition. These results suggest an important role for central 5-HT neurones in aversive learning processes. The possible involvement of 5-HT neurones in learning, memorial and/or retrieval processes is discussed.     

The multifaceted nature of unsupervised category learning

A substantial portion of category-learning research has focused on one learning mode--namely, classification learning (a supervised learning mode). Subsequently, theories of category learning have focused on how the abstract structure of categories (i.e., the co-occurrence patterns of feature values) affects acquisition. Recent work in supervised learning has shown that a learner's interactions with the stimulus set also plays an important role in acquisition. The present study extends this work to unsupervised learning situations involving simple one-dimensional stimuli. The results suggest that categorization performance is a function of both learning mode (i.e., study conditions) and learning problem (i.e., category structure). Unsupervised learning, like supervised learning, appears to be multifaceted, with different learning modes best paired with certain learning problems.     

两种学习模式下类别学习的结果：原型和样例

利用“学习－迁移”的任务范式和单一特征类别判断技术,探讨了分类和推理两种类别学习模式的结果,比较了两种学习模式的效果和策略。研究表明：两种学习模式产生了不同的结果,分类学习的结果是样例,推理学习的结果是原型;在学习效果方面,分类学习比推理学习在达标比例上更高,但在进度上差异不显著;在策略运用方面,分类学习比推理学习更快地使用单维度策略,而在高水平策略的运用上,两者差异不显著     

Representative co-design: Utilising a source of experiential knowledge for athlete development and performance preparation

Contemporary models for athlete development and performance preparation in sport have advocated a role re-conceptualisation for coaches grounded as learning environment designers. Within this re-conceptualisation, expert practitioners are encouraged to draw upon their experiential knowledge to design representative and meaningful learning activities that place the performer-environment interaction at its core. However, we propose that, currently, a critical source of experiential knowledge is often overlooked within the process of learning design – that of performers. Specifically, practitioner-performer interactions could enrich the design of learning environments by promoting the utilisation of soliciting affordances and encouraging the psychological engagement of performers. This paper introduces the concept of representative co-design – a notion which builds on existing research by framing how the insights and experiences of performers can be negotiated within the design of practice tasks that seek to faithfully simulate interacting constraints of competition to enrich learning environments. We frame the notion of representative co-design, and contend its importance within more contemporary athlete development and performance preparation models, at two levels: (i) that of enriching physical education curricula to develop thought provoking, ‘intelligent’ child/adolescent learners, and (ii) that of enriching contemporary athlete preparation models in high-performance sport to enhance learning and engagement, and to develop ‘next generation’ coaches within current athletes. To bring this conceptualisation to life, we present two exemplars demonstrating the notion of representative co-design, while concurrently highlighting areas for future research.     

Generalization and similarity in exemplar models of categorization: Insights from machine learning

Exemplar theories of categorization depend on similarity for explaining subjects’ ability to generalize to new stimuli. A major criticism of exemplar theories concerns their lack of abstraction mechanisms and thus, seemingly, of generalization ability. Here, we use insights from machine learning to demonstrate that exemplar models can actually generalize very well. Kernel methods in machine learning are akin to exemplar models and are very successful in real-world applications. Their generalization performance depends crucially on the chosen similarity measure. Although similarity plays an important role in describing generalization behavior, it is not the only factor that controls generalization performance. In machine learning, kernel methods are often combined with regularization techniques in order to ensure good generalization. These same techniques are easily incorporated in exemplar models. We show that the generalized context model (Nosofsky, 1986) and ALCOVE (Kruschke, 1992) are closely related to a statistical model called kernel logistic regression. We argue that generalization is central to the enterprise of understanding categorization behavior, and we suggest some ways in which insights from machine learning can offer guidance.     

Competitive Learning: From Interactive Activation to Adaptive Resonance

Functional and mechanistic comparisons are made between several network models of cognitive processing: competitive learning, interactive activation, adaptive resonance, and back propagation. The starting point of this comparison is the article of Rumelhart and Zipser (1985) on feature discovery through competitive learning. All the models which Rumelhart and Zipser (1985) have described were shown in Grossberg (1976b) to exhibit a type of learning which is temporally unstable. Competitive learning mechanisms can be stabilized in response to an arbitrary input environment by being supplemented with mechanisms for learning top-down expectancies, or templates; for matching bottom-up input patterns with the top-down expectancies; and for releasing orienting reactions in a mismatch situation, thereby updating short-term memory and searching for another internal representation. Network architectures which embody all of these mechanisms were called adaptive resonance models by Grossberg (1976c). Self-stabilizing learning models are candidates for use in real-world applications where unpredictable changes can occur in complex input environments. Competitive learning postulates are inconsistent with the postulates of the interactive activation model of McClelland and Rumelhart (1981), and suggest different levels of processing and interaction rules for the analysis of word recognition. Adaptive resonance models use these alternative levels and interaction rules. The self-organizing learning of an adaptive resonance model is compared and contrasted with the teacher-directed learning of a back propagation model. A number of criteria for evaluating real-time network models of cognitive processing are described and applied.