关键词： Acoustic emission   planetary gearbox   artificial neural network   variable load and rotational speed   pattern recognition  

摘要： Diverse machines in the mining, energy, and other industrial sectors are subject to variable operating conditions (OCs) such as rotational speed and load. Therefore, the condition monitoring techniques must be adapted to face this scenario. Within these techniques, the acoustic emission (AE) technology has been successfully used as a technique for condition monitoring of components such as gears and bearings. An AE analysis involves the detection of transients within the signals, which are called AE bursts. Traditional methods for AE burst detection are based on the definition of threshold values. When the machine under study works under variable rotational speed and load, threshold-based methods could produce inadequate results due to the influence of these OCs on the AE. This paper presents a novel burst detection method based on pattern recognition using an artificial neural network (ANN) for classification. The results of the method were compared to an adaptive threshold method. Experimental data were measured in a planetary gearbox test rig under different OCs. The results showed that both methods perform similarly when signals measured under constant OCs are considered. However, when signals are measured under different OCs, the ANN method performs better. Thus, the comparative analysis showed the good potential of the approach to improve an AE analysis of variable speed and/or load machines.

关键词： Magnetic resonance imaging (MRI)   childhood trauma   post-traumatic stress disorder (PTSD)   dissociation  

摘要： Background A diagnosis of dissociative identity disorder (DID) is controversial and prone to under- and misdiagnosis. From the moment of seeking treatment for symptoms to the time of an accurate diagnosis of DID individuals received an average of four prior other diagnoses and spent 7 years, with reports of up to 12 years, in mental health services. Aim To investigate whether data-driven pattern recognition methodologies applied to structural brain images can provide biomarkers to aid DID diagnosis. Method Structural brain images of 75 participants were included: 32 female individuals with DID and 43 matched healthy controls. Individuals with DID were recruited from psychiatry and psychotherapy out-patient clinics. Probabilistic pattern classifiers were trained to discriminate cohorts based on measures of brain morphology. Results The pattern classifiers were able to accurately discriminate between individuals with DID and healthy controls with high sensitivity (72%) and specificity (74%) on the basis of brain structure. These findings provide evidence for a biological basis for distinguishing between DID-affected and healthy individuals. Conclusions We propose a pattern of neuroimaging biomarkers that could be used to inform the identification of individuals with DID from healthy controls at the individual level. This is important and clinically relevant because the DID diagnosis is controversial and individuals with DID are often misdiagnosed. Ultimately, the application of pattern recognition methodologies could prevent unnecessary suffering of individuals with DID because of an earlier accurate diagnosis, which will facilitate faster and targeted interventions. Declaration of interest The authors declare no competing financial interests.

关键词： high-frequency ventilation   phase angle delay   pneumothorax   preterm infant  

摘要： Pneumothoraxes are common in preterm infants and are a major cause of morbidity. Early detection and treatment of pneumothoraxes are vital to minimize further respiratory compromise. Electrical impedance tomography (EIT) has been suggested as a method of rapidly detecting pneumothoraxes at the bedside. Our objective was to define the EIT-derived regional phase angle differences in filling characteristics before and during spontaneous pneumothoraxes in preterm lambs. Preterm lambs (124-127 day gestation) were ventilated with high-frequency oscillatory ventilation for 120 min. EIT data and cardiorespiratory parameters were monitored continuously and recorded for 3 min every 15 min. Six animals spontaneously developed a pneumothorax within a gravity-nondependent quadrant of the lung and were included for this analysis. Changes in end-expiratory lung impedance (EELI), ventilation, and phase angle delay were calculated in the four lung quadrants at the onset of the pneumothorax and 15 and 30 min prior. At the onset of the pneumothorax, all animals showed a clear increase in EELI in the affected lung quadrant. Fifteen and thirty minutes before the pneumothorax there was a significant phase angle delay between the nondependent and dependent lung. At 1 min before pneumothorax this phase angle delay was isolated just to the affected quadrant (nondependent). These findings are the first description of the events within the lung at initiation of a pneumothorax, demonstrating distinct predictive changes in air-filling characteristics before the occurrence of pneumothorax. This suggests that EIT may be able to accurately identify the onset of a pneumothorax. NEW & NOTEWORTHY In this article we describe for the first time predictive changes in electrical impedance tomography-based regional filling characteristics of the lung before the onset of a one-sided pneumothorax in six preterm lambs ventilated with high-frequency oscillatory ventilation. This can give clinicians bedside in

关键词： Locomotion mode recognition   inter-day and inter-session   automatic training   robotic transtibial prosthesis  

摘要： Locomotion mode recognition across multiple sessions and days is an indispensable step towards the practical use of the robotic transtibial prosthesis. In this study, we proposed an adaptive recognition strategy to against the time-varying features of on-prosthesis mechanical signals in inter-session and inter-day recognition tasks. The strategy was designed with an automatic training algorithm which could update the classifiers with the data of the most recent completed gait cycles to seize the changes of the features brought by external disturbances. After implementation, we measured multiple experimental sessions on six transtibial amputees with intervals from a few hours (inter-session experiment) to several months (108 days at most in inter-day experiment). In each session, they performed five locomotion modes and eight locomotion transitions using the robotic prosthesis. Between each two experimental sessions, the subjects were required to doff the robotic prosthesis (including the socket). The proposed adaptive recognition algorithm significantly improved recognition accuracies in both experiments. In inter-session experiment, the proposed method increased the recognition accuracy from 89.3% to 92.8% than previous non-adaptive recognition method. In inter-day experiments, it increased the recognition accuracy from 60% to 88.8%. If taking three modes (level walking, stair ascending/descending) and four locomotion transitions into calculation, the recognizer produced an accuracy up to 96.6% (swing phase) for static mode and an accuracy of 96.9% for locomotion transitions on inter-day tasks without manual intervenes. Compared with state-of-the-art, our study extends the ability of the robotic transtibial prosthesis in locomotion mode recognition across multiple sessions and days. Future efforts are worth being paid in this direction to get more promising results.

关键词： Multiresolution analysis   topology pattern recognition   text classification   high-dimensional space  

摘要： Traditional pattern recognition is based on "optimal partition" and the goal is to find an optimal classification interface based on the distribution of each category in high-dimensional space, thus has its inherent shortcomings and deficiencies. While topology pattern recognition can effectively compensate for the shortcomings of traditional pattern recognition, topological pattern recognition is based on "cognition" and the goal is to find the appropriate cover according to the "complex set cover" in high-dimensional space to achieve cognitive effect. Topological pattern recognition can effectively consummate the characteristics of high error rate, low recognition rate and repetitive training in the existing recognition system with low training sample number. At present, topology pattern recognition has been applied in many areas of social life. However, one problem that can't be ignored is that topological pattern recognition requires a long training time and low fault tolerance rate. Therefore, this paper proposes an improved multidimensional-multiresolution topological pattern recognition, and applies it to text classification and recognition. The results show that the improved multidimensional-multiresolution topological pattern recognition method can effectively reduce the training time of text classification and improve the classification efficiency.

关键词： Valve stiction   Fault detection   Artificial neural network   Classification   Pattern recognition  

摘要： A non-invasive method for detecting valves suffering from stiction using multi-layer feed-forward neural networks (NN) is proposed, via a simple class-based diagnosis. The proposed Stiction Detection Network (SDN) uses a transformation of PV (process variable) and OP (controller output) operational data. Verification of the proposed SDN model's detection accuracy is done through cross-validation with generated samples and benclunarking with various industrial loops. The industrial loop benchmark predictions of the proposed SDN method has a combined accuracy of 78% (75% in predicting stiction, and 81% for non-stiction) in predicting loop condition, matching capabilities of other established methods in accurately predicting realistic industrial loops suffering from stiction, while also being applicable to all types of oscillatory control signals.

关键词： STS transitions   Knee exoskeleton   Mode recognition   Real-time   Assistive torque control  

摘要： Assistive torque control is important for people who cannot fully accomplish sit-to-stand and stand-to-sit (STS) transitions. In this paper, we proposed a three-level control strategy for a bionic knee exoskeleton based on real-time STS transition recognition. Motion features were obtained from one potentiometer and two inertial measurement units integrated in the exoskeleton. A multi-class support vector classifier was utilized to infer the subject's real-time motion intent. Twelve able-bodied subjects were recruited in experiments. Mean accuracy across subjects was 97.63%+/- 0.01%. Once STS transition was detected, the proposed control system could add assistive torque in time to assist the subject to accomplish the transition. (C) 2019 Published by Elsevier B.V.

关键词： Aero-engine   fault diagnosis   grey relational analysis   synergetic pattern recognition   gas-path system  

摘要： The gas-path system is an important sub-system in aero-engines. There are various indistinguishable faults in aero-engine gas-path systems. These faults are easily misjudged because the characteristic parameters are similar. Due to the many kinds of faults, current studies have poor accuracy in distinguishing similar faults. To improve fault diagnosis accuracy for gas-path systems, a fault diagnosis method based on grey relational analysis and synergetic pattern recognition is proposed. In the proposed method, grey relational analysis is used to initially distinguish the faults into different types and obtain similar fault types. Synergetic pattern recognition contributes to accurately diagnose faults which are difficult to recognize. A case study is used to verify the effectiveness and accuracy of the proposed model. The results show that faults in common types of gas-path systems can be diagnosed accurately by the proposed method.

摘要： There is currently a huge interest in the use of artificial intelligence (AI) technologies for various data analysis applications. Among these applications are radiation detection and spectra analysis tasks aiming at qualitative and quantitative information extraction on the assaying radioisotopes. AI tools are foreseen as promising techniques to deal with complex spectra analysis cases, where the traditional statistical tools are subject to deficiencies, due to high degree of noise, peak overlapping and statistical uncertainties because of the room temperature operation of detectors such as CdZnTe and LaBr3(Ce). However, over the years there has been no comprehensive assessment of possible conceptual designs of such AI-based algorithms for spectra analysis purposes applied to uranium enrichment determination tasks. This paper analyzes different AI-based methodologies for the qualitative and quantitative analyses of uranium spectra and presents the AI-based Cluster Analysis via Machine Intelligence and Learning Algorithms (CAMILA) code for uranium enrichment determination. The performance assessment of multivariate and pattern recognition methodologies limits and possibilities is conducted in view of different physical conditions of the measurement system, such as the degree of attenuation and sample-to-detector distance, as well as impact of the neural network (NN) design on the algorithm performance. Tests are conducted on uranium spectra of CBNM certified standards with enrichment degrees from 0.31% up to 4.46% of (235) U atomic abundance measured with different statistical quality, as well as on simulated uranium spectra with a broad range of enrichment degrees. Implemented unfolding and analysis routines of the algorithms are described in detail and results are presented.

关键词： Corrosion   Response to Comment