clusterBMA: Bayesian model averaging for clustering.

Various methods have been developed to combine inference across multiple sets of results for unsupervised clustering, within the ensemble clustering literature. The approach of reporting results from one 'best' model out of several candidate clustering models generally ignores the uncertainty that arises from model selection, and results in inferences that are sensitive to the particular model and parameters chosen. Bayesian model averaging (BMA) is a popular approach for combining results across multiple models that offers some attractive benefits in this setting, including probabilistic interpretation of the combined cluster structure and quantification of model-based uncertainty. In this work we introduce clusterBMA, a method that enables weighted model averaging across results from multiple unsupervised clustering algorithms. We use clustering internal validation criteria to develop an approximation of the posterior model probability, used for weighting the results from each model. From a combined posterior similarity matrix representing a weighted average of the clustering solutions across models, we apply symmetric simplex matrix factorisation to calculate final probabilistic cluster allocations. In addition to outperforming other ensemble clustering methods on simulated data, clusterBMA offers unique features including probabilistic allocation to averaged clusters, combining allocation probabilities from 'hard' and 'soft' clustering algorithms, and measuring model-based uncertainty in averaged cluster allocation. This method is implemented in an accompanying R package of the same name. We use simulated datasets to explore the ability of the proposed technique to identify robust integrated clusters with varying levels of separation between subgroups, and with varying numbers of clusters between models. Benchmarking accuracy against four other ensemble methods previously demonstrated to be highly effective in the literature, clusterBMA matches or exceeds the performance of competing approaches under various conditions of dimensionality and cluster separation. clusterBMA substantially outperformed other ensemble methods for high dimensional simulated data with low cluster separation, with 1.16 to 7.12 times better performance as measured by the Adjusted Rand Index. We also explore the performance of this approach through a case study that aims to identify probabilistic clusters of individuals based on electroencephalography (EEG) data. In applied settings for clustering individuals based on health data, the features of probabilistic allocation and measurement of model-based uncertainty in averaged clusters are useful for clinical relevance and statistical communication.

EEG-based clusters differentiate psychological distress, sleep quality and cognitive function in adolescents.

INTRODUCTION: To better understand the relationships between neurophysiology, cognitive function and psychopathology risk in adolescence there is value in identifying data-driven subgroups based on measurements of brain activity and function, and then comparing cognition and mental health between such subgroups. METHODS: We developed a flexible and scaleable multi-stage analysis pipeline to identify data-driven clusters of 12-year-olds (M = 12.64, SD = 0.32) based on frequency characteristics calculated from resting state, eyes-closed electroencephalography (EEG) recordings. For this preliminary cross-sectional study, EEG data was collected from 59 individuals in the Longitudinal Adolescent Brain Study (LABS) being undertaken in Queensland, Australia. Applying multiple unsupervised clustering algorithms to these EEG features, we identified well-separated subgroups of individuals. To study patterns of difference in cognitive function and mental health symptoms between clusters, we applied Bayesian regression models to probabilistically identify differences in these measures between clusters. RESULTS: We identified 5 core clusters associated with distinct subtypes of resting state EEG frequency content. Bayesian models demonstrated substantial differences in psychological distress, sleep quality and cognitive function between clusters. By examining associations between neurophysiology and health measures across clusters, we have identified preliminary risk and protective profiles linked to EEG characteristics. CONCLUSION: This method provides the potential to identify neurophysiological subgroups of adolescents in the general population based on resting state EEG, and associated patterns of health and cognition that are not observed at the whole group level. This approach offers potential utility in clinical risk prediction for mental and cognitive health outcomes throughout adolescent development.

[Diagnosis of eco-environmental quality in the Keluke Lake basin, China]. / å¯é²å ‹æ¹–æµåŸŸç”Ÿæ€çŽ¯å¢ƒè´¨é‡è¯Šæ–­.

In order to clarify the eco-environmental quality and its evolution characteristics of Keluke Lake basin, we selected 15 factors of physical geography, meteorology, land use/cover and social economy using comprehensive investigation, remote sensing interpretation and inversion, statistical analysis and other technical means, based on the relevant theories of environmental ecology. We used factor analysis and entropy method to calculate the index weight, constructed watershed soil quality model and ecological environment quality diagnosis model, and analyzed the changes of soil and eco-environmental quality in the Keluke Lake basin in 2000, 2005, 2010 and 2015. The results showed that the average eco-environmental quality in four periods was 21, 47, 54, and 72, showing a stable upward trend. The eco-environmental quality level changed from poor to good, while soil quality was at the middle level. Spatially, the eco-environmental quality of the northern mountainous area, the downstream wetland and the surrounding area of the river improved significantly. The change of eco-environmental quality was a result of human activities and natural factors. Soil quality and lake area were key factors indicating the eco-environment of the Keluke Lake basin. The minimum ecological water demand of the Keluke Lake was the basic guarantee to maintain the benign development of the eco-environment of the lake basin.

Kernelized Sparse Bayesian Matrix Factorization.

Extracting low-rank and/or sparse structures using matrix factorization techniques has been extensively studied in the machine learning community. Kernelized matrix factorization (KMF) is a powerful tool to incorporate side information into the low-rank approximation model, which has been applied to solve the problems of data mining, recommender systems, image restoration, and machine vision. However, most existing KMF models rely on specifying the rows and columns of the data matrix through a Gaussian process prior and have to tune manually the rank. There are also computational issues of existing models based on regularization or the Markov chain Monte Carlo. In this article, we develop a hierarchical kernelized sparse Bayesian matrix factorization (KSBMF) model to integrate side information. The KSBMF automatically infers the parameters and latent variables including the reduced rank using the variational Bayesian inference. In addition, the model simultaneously achieves low-rankness through sparse Bayesian learning and columnwise sparsity through an enforced constraint on latent factor matrices. We further connect the KSBMF with the nonlocal image processing framework to develop two algorithms for image denoising and inpainting. Experimental results demonstrate that KSBMF outperforms the state-of-the-art approaches for these image-restoration tasks under various levels of corruption.

A pilot-scale three-dimensional electrochemical reactor combined with anaerobic-anoxic-oxic system for advanced treatment of coking wastewater.

Coking wastewater is highly concentrated and extremely toxic, greatly challenging the treatment technologies. Conventional biological technology such as anaerobic-anoxic-oxic (A2O) system is inefficient, since various biological reactions are inhibited by toxicants in coking wastewater. In this work, a pilot-scale three-dimensional electrochemical reactor (3DER) is integrated into the A2O system as a pretreatment unit to improve the treatment efficiency of coking wastewater. The results indicate that 3DER pretreatment increased the biodegradability of coking wastewater, promoting the degradation of coking wastewater in A2O system. The integrated 3DER-A2O system can remove 94.4% of COD and 76.2% of TN from coking wastewater, and the energy consumption was only 0.22 kWh/kg COD and 4.69 kWh/kg TN. The components of coking wastewater were significantly simplified and the acute toxicity was reduced from 99% to 12% after the treatment. The integrated 3DER-A2O system provides a new solution for coking wastewater treatment, showing a promising application potential.

High-speed robust polarization modulation for quantum key distribution.

Polarization modulation plays a key role in polarization-encoding quantum key distribution (QKD). Here, we report a new, to the best of our knowledge, polarization modulation scheme based on an inherently stable Sagnac interferometer. The presented scheme is free of polarization mode dispersion and calibration as well as insensitive to environmental influences. Successful experiments at a repetition frequency of 1.25 GHz have been conducted to demonstrate the feasibility and stability of the scheme. The measured average quantum bit-error rate of the four polarization states is as low as 0.27% for 80 consecutive minutes without any adjustment. This high-speed intrinsically stable polarization modulation can be widely applied to many polarization-encoding QKD systems, such as BB84, MDI, etc.

Optically injected intensity-stable pulse source for secure quantum key distribution.

The security of decoy-state quantum key distribution (QKD) highly depends on the accurate control of multiple intensity states. Although several theoretical studies on the QKD with loosely controlled source intensities have been proposed, there is still a large gap between the experimental realization and the theoretical analysis. In this paper, we adopt the gain-switching method to generate short optical pulses, and the corresponding intensity stabilities are quantitatively measured. The method via optical injection is proposed to make effective reductions of the intensity fluctuations from 6.47%∼1.59% to 1.95%∼1.15% at different optical powers. QKD performance adopting the experimental results is also analyzed and discussed. For a typical 40 dB high-attenuation QKD system, the relative increase on the secure key rates reaches 51.89% for the corresponding intensity fluctuations of 1.15% with optical injection and 1.59% without optical injection. The presented intensity-stable optical pulse source can find wide applications in different QKD protocols, such as BB84, DPS, COW, etc.

Image Denoising Based on Nonlocal Bayesian Singular Value Thresholding and Stein's Unbiased Risk Estimator.

Singular value thresholding (SVT)- or nuclear norm minimization (NNM)-based nonlocal image denoising methods often rely on the precise estimation of the noise variance. However, most existing methods either assume that the noise variance is known or require an extra step to estimate it. Under the iterative regularization framework, the error in the noise variance estimate propagates and accumulates with each iteration, ultimately degrading the overall denoising performance. In addition, the essence of these methods is still least squares estimation, which can cause a very high mean-squared error (MSE) and is inadequate for handling missing data or outliers. In order to address these deficiencies, we present a hybrid denoising model based on variational Bayesian inference and Stein's unbiased risk estimator (SURE), which consists of two complementary steps. In the first step, the variational Bayesian SVT performs a low-rank approximation of the nonlocal image patch matrix to simultaneously remove the noise and estimate the noise variance. In the second step, we modify the conventional SURE full-rank SVT and its divergence formulas for rank-reduced eigen-triplets to remove the residual artifacts. The proposed hybrid BSSVT method achieves better performance in recovering the true image compared with state-of-the-art methods.

The Chinese Mental Resilience Scale and its psychometric properties.

This study aimed to develop a Chinese Mental Resilience Scale. A total of 2500 healthy participants, in two representative samples of the Chinese population, were administered the scale. Exploratory factor analysis, confirmatory factor analysis, and correlation analysis were used to obtain the relevant coefficients and verify the reliability and validity of the scale. Five factors were extracted: willpower, family support, optimism and self-confidence, problem solving, and interpersonal interaction, plus a lying subscale, which together accounted for 54 percent of the total variance. The Chinese Mental Resilience Scale demonstrated good psychometric properties. It can be used to evaluate the mental resilience level of general Chinese population.

Symplectic geometry spectrum regression for prediction of noisy time series.

We present the symplectic geometry spectrum regression (SGSR) technique as well as a regularized method based on SGSR for prediction of nonlinear time series. The main tool of analysis is the symplectic geometry spectrum analysis, which decomposes a time series into the sum of a small number of independent and interpretable components. The key to successful regularization is to damp higher order symplectic geometry spectrum components. The effectiveness of SGSR and its superiority over local approximation using ordinary least squares are demonstrated through prediction of two noisy synthetic chaotic time series (Lorenz and Rössler series), and then tested for prediction of three real-world data sets (Mississippi River flow data and electromyographic and mechanomyographic signal recorded from human body).

Muscle networks: Connectivity analysis of EMG activity during postural control.

Understanding the mechanisms that reduce the many degrees of freedom in the musculoskeletal system remains an outstanding challenge. Muscle synergies reduce the dimensionality and hence simplify the control problem. How this is achieved is not yet known. Here we use network theory to assess the coordination between multiple muscles and to elucidate the neural implementation of muscle synergies. We performed connectivity analysis of surface EMG from ten leg muscles to extract the muscle networks while human participants were standing upright in four different conditions. We observed widespread connectivity between muscles at multiple distinct frequency bands. The network topology differed significantly between frequencies and between conditions. These findings demonstrate how muscle networks can be used to investigate the neural circuitry of motor coordination. The presence of disparate muscle networks across frequencies suggests that the neuromuscular system is organized into a multiplex network allowing for parallel and hierarchical control structures.

A comparative study of surface EMG classification by fuzzy relevance vector machine and fuzzy support vector machine.

We present a multiclass fuzzy relevance vector machine (FRVM) learning mechanism and evaluate its performance to classify multiple hand motions using surface electromyographic (sEMG) signals. The relevance vector machine (RVM) is a sparse Bayesian kernel method which avoids some limitations of the support vector machine (SVM). However, RVM still suffers the difficulty of possible unclassifiable regions in multiclass problems. We propose two fuzzy membership function-based FRVM algorithms to solve such problems, based on experiments conducted on seven healthy subjects and two amputees with six hand motions. Two feature sets, namely, AR model coefficients and room mean square value (AR-RMS), and wavelet transform (WT) features, are extracted from the recorded sEMG signals. Fuzzy support vector machine (FSVM) analysis was also conducted for wide comparison in terms of accuracy, sparsity, training and testing time, as well as the effect of training sample sizes. FRVM yielded comparable classification accuracy with dramatically fewer support vectors in comparison with FSVM. Furthermore, the processing delay of FRVM was much less than that of FSVM, whilst training time of FSVM much faster than FRVM. The results indicate that FRVM classifier trained using sufficient samples can achieve comparable generalization capability as FSVM with significant sparsity in multi-channel sEMG classification, which is more suitable for sEMG-based real-time control applications.

Hybrid soft computing systems for electromyographic signals analysis: a review.

Electromyographic (EMG) is a bio-signal collected on human skeletal muscle. Analysis of EMG signals has been widely used to detect human movement intent, control various human-machine interfaces, diagnose neuromuscular diseases, and model neuromusculoskeletal system. With the advances of artificial intelligence and soft computing, many sophisticated techniques have been proposed for such purpose. Hybrid soft computing system (HSCS), the integration of these different techniques, aims to further improve the effectiveness, efficiency, and accuracy of EMG analysis. This paper reviews and compares key combinations of neural network, support vector machine, fuzzy logic, evolutionary computing, and swarm intelligence for EMG analysis. Our suggestions on the possible future development of HSCS in EMG analysis are also given in terms of basic soft computing techniques, further combination of these techniques, and their other applications in EMG analysis.

Some insights into the binding mechanism of the GABAA receptor: a combined docking and MM-GBSA study.

Gamma-aminobutyric type A receptor (GABAAR) is a member of the Cys-loop family of pentameric ligand gated ion channels (pLGICs). It has been identified as a key target for many clinical drugs. In the present study, we construct the structure of human 2α12ß2γ2 GABA(A)R using a homology modeling method. The structures of ten benzodiazepine type drugs and two non-benzodiazepine type drugs were then docked into the potential benzodiazepine binding site on the GABA(A)R. By analyzing the docking results, the critical residues His102 (α1), Phe77 (γ2) and Phe100 (α1) were identified in the binding site. To gain insight into the binding affinity, molecular dynamics (MD) simulations were performed for all the receptor-ligand complexes. We also examined single mutant GABA(A)R (His102A) in complexes with the three drugs (flurazepam, eszopiclone and zolpidem) to elucidate receptor-ligand interactions. For each receptor-ligand complex (with flurazepam, eszopiclone and zolpidem), we calculated the average distance between the C(α) of the mutant residue His102A (α1) to the center of mass of the ligands. The results reveal that the distance between the C(α) of the mutant residue His102A (α1) to the center of flurazepam is larger than that between His102 (α1) to flurazepam in the WT type complex. Molecular mechanic-generalized Born surface area (MM-GBSA)-based binding free energy calculations were performed. The binding free energy was decomposed into ligand-residue pairs to create a ligand-residue interaction spectrum. The predicted binding free energies correlated well (R(2) = 0.87) with the experimental binding free energies. Overall, the major interaction comes from a few groups around His102 (α1), Phe77 (γ2) and Phe100 (α1). These groups of interaction consist of at least of 12 residues in total with a binding energy of more than 1 kcal mol(-1). The simulation study disclosed herein provides a meaningful insight into GABA(A)R-ligand interactions and helps to arrive at a binding mode hypothesis with implications for drug design.

Fuzzy central tendency measure for time series variability analysis with application to fatigue electromyography signals.

A new method, namely fuzzy central tendency measure (fCTM) analysis, that could enable measurement of the variability of a time series, is presented in this study. Tests on simulated data sets show that fCTM is superior to the conventional central tendency measure (CTM) in several respects, including improved relative consistency and robustness to noise. The proposed fCTM method was applied to electromyograph (EMG) signals recorded during sustained isometric contraction for tracking local muscle fatigue. The results showed that the fCTM increased significantly during the development of muscle fatigue, and it was more sensitive to the fatigue phenomenon than mean frequency (MNF), the most commonly-used muscle fatigue indicator.

A hybrid symplectic principal component analysis and central tendency measure method for detection of determinism in noisy time series with application to mechanomyography.

We present a hybrid symplectic geometry and central tendency measure (CTM) method for detection of determinism in noisy time series. CTM is effective for detecting determinism in short time series and has been applied in many areas of nonlinear analysis. However, its performance significantly degrades in the presence of strong noise. In order to circumvent this difficulty, we propose to use symplectic principal component analysis (SPCA), a new chaotic signal de-noising method, as the first step to recover the system dynamics. CTM is then applied to determine whether the time series arises from a stochastic process or has a deterministic component. Results from numerical experiments, ranging from six benchmark deterministic models to 1/f noise, suggest that the hybrid method can significantly improve detection of determinism in noisy time series by about 20 dB when the data are contaminated by Gaussian noise. Furthermore, we apply our algorithm to study the mechanomyographic (MMG) signals arising from contraction of human skeletal muscle. Results obtained from the hybrid symplectic principal component analysis and central tendency measure demonstrate that the skeletal muscle motor unit dynamics can indeed be deterministic, in agreement with previous studies. However, the conventional CTM method was not able to definitely detect the underlying deterministic dynamics. This result on MMG signal analysis is helpful in understanding neuromuscular control mechanisms and developing MMG-based engineering control applications.

Molecular dynamics investigation of Cl(-) transport through the closed and open states of the 2α12ß2γ2 GABA(A) receptor.

The α1ß2γ2 gamma-aminobutyric type A receptor (GABA(A)R) is one of the most widely expressed GABA(A)R subtypes in the mammalian brain. GABA(A)Rsbelonging to the Cys-loop superfamily of ligand-gated ion channels have been identified as key targets for many clinical drugs, and the motions that govern the gating mechanism are still not well understood. In this study, an open-state GABA(A)R was constructed using the structure of the glutamate-gated chloride channel (GluCl), which has a high sequence identity to GABA(A)R. A closed-state model was constructed using the structure of the nicotinic acetylcholine receptor (nAChR). Molecular dynamics simulations of the open-state and closed-state GABA(A)R were performed. We calculated the electrostatic potential of the two conformations, the pore radius of the two ion channels and the root-mean-square fluctuation. We observed the presence of two positively charged girdles around the ion channel and found flexible regions in the GABA(A)R. Then, the free-energy of chloride ion permeations through the closed-state and open-state G GABA(A)R has been estimated using adaptive biasing force (ABF) simulation. For the closed-state G GABA(A)R, we observed two major energy barriers for chloride ion translocation in the transmembrane domain (TMD). For the open-state GABA(A)R, there was only one energy barrier formed by two Thr261 (α1), two Thr255 (ß2) and one Thr271 (γ2). By using ABF simulation, the overall free-energy profile is obtained for Cl(-) transporting through GABA(A)R, which gives a complete map of the ion channel of Cl(-) permeation.

Towards the application of one-dimensional sonomyography for powered upper-limb prosthetic control using machine learning models.

BACKGROUND: The inherent properties of surface electromyography limit its potential for multi-degrees of freedom control. Our previous studies demonstrated that wrist angle could be predicted by muscle thickness measured from B-mode ultrasound, and hence, it could be an alternative signal for prosthetic control. However, an ultrasound imaging machine is too bulky and expensive. OBJECTIVE: We aim to utilize a portable A-mode ultrasound system to examine the feasibility of using one-dimensional sonomyography (i.e. muscle thickness signals detected by A-mode ultrasound) to predict wrist angle with three different machine learning models - (1) support vector machine (SVM), (2) radial basis function artificial neural network (RBF ANN), and (3) back-propagation artificial neural network (BP ANN). STUDY DESIGN: Feasibility study using nine healthy subjects. METHODS: Each subject performed wrist extension guided at 15, 22.5, and 30 cycles/minute, respectively. Data obtained from 22.5 cycles/minute trials was used to train the models and the remaining trials were used for cross-validation. Prediction accuracy was quantified by relative root mean square error (RMSE) and correlation coefficients (CC). RESULTS: Excellent prediction was noted using SVM (RMSE = 13%, CC = 0.975), which outperformed the other methods. CONCLUSION: It appears that one-dimensional sonomyography could be an alternative signal for prosthetic control. Clinical relevance Surface electromyography has inherent limitations that prohibit its full functional use for prosthetic control. Research that explores alternative signals to improve prosthetic control (such as the one-dimensional sonomyography signals evaluated in this study) may revolutionize powered prosthesis design and ultimately benefit amputee patients.

[Early diagnosis and treatment of compartment syndrome caused by landslides:a report of 20 cases].

OBJECTIVE: To summarize early diagnosis and treatment methods of 20 patients with compartment syndrome caused by landslides during coal mine accidents in order to improve the level of diagnosis and treatment of compartment syndrome and reduce disability. METHODS: From September 2006 to April 2010,20 patients with compartment syndrome were treated with the methods of early decompression, systemic support. All the patients were male with an average age of 42 years (ranged, 23 to 54). All the patients with high tension limb swelling, pain, referred pain passive positive; 5 extremities feeling diminish or disappear and the distal blood vessel beat were normal or weakened or disappeared; myoglobinuria, hyperkalemia, serum urea nitrogen and creatinine increased in 5 cases and oliguria in occurred 1 case. The function of affected limbs was observed according to disability ratings. RESULTS: Three cases complicated with infection of affected limb and 6 cases occurred with renal function insufficiency. Total recovery was in 16 cases, basically recovery in 3, amputation in 1 case. All patients were followed up for 6-15 months with an average of 12 months. The ability to work according to national standard identification--Employee work-related injuries and occupational disability rating classification (GB/T16180-2006) to assess, grade 5 was in 1 case, grade 8 in 2 cases, grade 10 in 1 case, no grade in 16 cases. CONCLUSION: Arteriopalmus of dorsalis pedis weaken and vanished can not be regard as an evidence in early diagnosis of compartment syndrome. Early diagnosis and decompression, systemic support and treatment is the key in reducing disability.

Ant colony optimization-based feature selection method for surface electromyography signals classification.

This paper presented a new ant colony optimization (ACO) feature selection method to classify hand motion surface electromyography (sEMG) signals. The multiple channels of sEMG recordings make the dimensionality of sEMG feature grow dramatically. It is known that the informative feature subset with small size is a precondition for the accurate and computationally efficient classification strategy. Therefore, this study proposed an ACO based feature selection scheme using the heuristic information measured by the minimum redundancy maximum relevance criterion (ACO-mRMR). The experiments were conducted on ten subjects with eight upper limb motions. Two feature sets, i.e., time domain features combined with autoregressive model coefficients (TDAR) and wavelet transform (WT) features, were extracted from the recorded sEMG signals. The average classification accuracies of using ACO reduced TDAR and WT features were 95.45±2.2% and 96.08±3.3%, respectively. The principal component analysis (PCA) was also conducted on the same data sets for comparison. The average classification accuracies of using PCA reduced TDAR and WT features were 91.51±4.9% and 89.87±4.4%, respectively. The results demonstrated that the proposed ACO-mRMR based feature selection method can achieve considerably high classification rates in sEMG motion classification task and be applicable to other biomedical signals pattern analysis.