本研究旨在模拟不同狭窄程度和脉搏率的颈动脉搏动血流。采用流-固耦合(FSI)和任意拉格朗日-欧拉(ALE)方法研究了不同狭窄程度、脉搏率和动脉壁性质对周围流体的影响。分别应用Carreau-Yasuda非牛顿超弹性模型和修正Mooney-Rivin超弹性...本研究旨在模拟不同狭窄程度和脉搏率的颈动脉搏动血流。采用流-固耦合(FSI)和任意拉格朗日-欧拉(ALE)方法研究了不同狭窄程度、脉搏率和动脉壁性质对周围流体的影响。分别应用Carreau-Yasuda非牛顿超弹性模型和修正Mooney-Rivin超弹性模型于具有非牛顿行为的血液和超弹性血管壁。结果得到血液的壁面径向位移、压力分布、轴向速度分布和壁面剪切应力。通过增加狭窄的严重程度,轴向速度、血压变化、最大壁面剪切应力和壁面径向位移均呈增长趋势。当脉率在狭窄程度为75%时,最大流量矩、壁面径向位移、压力、轴向速度和壁面剪应力的最大值均增大。此外,与弹性和刚性模型相比,将动脉壁视为超弹性模型,将其周围流体视为非牛顿和非定常,可以使模拟更加真实。在严重程度高达50%的狭窄中,红细胞受到轻微损害,而在严重程度为75%的狭窄中观察到溶血。通过改善动脉粥样硬化,弹性模量从500 k Pa提高到2 MPa,在60 bpm脉率和狭窄程度75%下,剪切应力最大值增长65%。与刚性和弹性动脉壁相比,动脉壁的超弹性模型导致较低的轴向速度、较低的血压、较低的剪切应力和较高的径向位移。展开更多
Membrane proteins are an important kind of proteins embedded in the membranes of cells and play crucial roles in living organisms, such as ion channels,transporters, receptors. Because it is difficult to determinate t...Membrane proteins are an important kind of proteins embedded in the membranes of cells and play crucial roles in living organisms, such as ion channels,transporters, receptors. Because it is difficult to determinate the membrane protein's structure by wet-lab experiments,accurate and fast amino acid sequence-based computational methods are highly desired. In this paper, we report an online prediction tool called Mem Brain, whose input is the amino acid sequence. Mem Brain consists of specialized modules for predicting transmembrane helices, residue–residue contacts and relative accessible surface area of a-helical membrane proteins. Mem Brain achieves aprediction accuracy of 97.9% of ATMH, 87.1% of AP,3.2 ± 3.0 of N-score, 3.1 ± 2.8 of C-score. Mem BrainContact obtains 62%/64.1% prediction accuracy on training and independent dataset on top L/5 contact prediction,respectively. And Mem Brain-Rasa achieves Pearson correlation coefficient of 0.733 and its mean absolute error of13.593. These prediction results provide valuable hints for revealing the structure and function of membrane proteins.Mem Brain web server is free for academic use and available at www.csbio.sjtu.edu.cn/bioinf/Mem Brain/.展开更多
Hydrocephalus is often treated with a cerebrospinal fluid shunt(CFS) for excessive amounts of cerebrospinal fluid in the brain.However,it is very difficult to distinguish whether the ventricular enlargement is due to ...Hydrocephalus is often treated with a cerebrospinal fluid shunt(CFS) for excessive amounts of cerebrospinal fluid in the brain.However,it is very difficult to distinguish whether the ventricular enlargement is due to hydrocephalus or other causes,such as brain atrophy after brain damage and surgery.The non-trivial evaluation of the consciousness level,along with a continuous drainage test of the lumbar cistern is thus clinically important before the decision for CFS is made.We studied 32 secondary mild hydrocephalus patients with different consciousness levels,who received T1 and diffusion tensor imaging magnetic resonance scans before and after lumbar cerebrospinal fluid drainage.We applied a novel machine-learning method to find the most discriminative features from the multi-modal neuroimages.Then,we built a regression model to regress the JFK Coma Recovery Scale-Revised(CRS-R) scores to quantify the level of consciousness.The experimental results showed that our method not only approximated the CRS-R scores but also tracked the temporal changes in individual patients.The regression model has high potential for the evaluation of consciousness in clinical practice.展开更多
The concept of Network Centric Therapy represents an amalgamation of wearable and wireless inertial sensor systems and machine learning with access to a Cloud computing environment. The advent of Network Centric Thera...The concept of Network Centric Therapy represents an amalgamation of wearable and wireless inertial sensor systems and machine learning with access to a Cloud computing environment. The advent of Network Centric Therapy is highly relevant to the treatment of Parkinson’s disease through deep brain stimulation. Originally wearable and wireless systems for quantifying Parkinson’s disease involved the use a smartphone to quantify hand tremor. Although originally novel, the smartphone has notable issues as a wearable application for quantifying movement disorder tremor. The smartphone has evolved in a pathway that has made the smartphone progressively more cumbersome to mount about the dorsum of the hand. Furthermore, the smartphone utilizes an inertial sensor package that is not certified for medical analysis, and the trial data access a provisional Cloud computing environment through an email account. These concerns are resolved with the recent development of a conformal wearable and wireless inertial sensor system. This conformal wearable and wireless system mounts to the hand with the profile of a bandage by adhesive and accesses a secure Cloud computing environment through a segmented wireless connectivity strategy involving a smartphone and tablet. Additionally, the conformal wearable and wireless system is certified by the FDA of the United States of America for ascertaining medical grade inertial sensor data. These characteristics make the conformal wearable and wireless system uniquely suited for the quantification of Parkinson’s disease treatment through deep brain stimulation. Preliminary evaluation of the conformal wearable and wireless system is demonstrated through the differentiation of deep brain stimulation set to “On” and “Off” status. Based on the robustness of the acceleration signal, this signal was selected to quantify hand tremor for the prescribed deep brain stimulation settings. Machine learning classification using the Waikato Environment for Knowledge Analysis (WEKA) was applied using the multilayer perceptron neural network. The multilayer perceptron neural network achieved considerable classification accuracy for distinguishing between the deep brain stimulation system set to “On” and “Off” status through the quantified acceleration signal data obtained by this recently developed conformal wearable and wireless system. The research achievement establishes a progressive pathway to the future objective of achieving deep brain stimulation capabilities that promote closed-loop acquisition of configuration parameters that are uniquely optimized to the individual through extrinsic means of a highly conformal wearable and wireless inertial sensor system and machine learning with access to Cloud computing resources.展开更多
The attributes of the ECG signal signifying the unique electrical properties of the heart offer the opportunity to expand the realm of biometrics, which pertains the identification of an individual based on physical c...The attributes of the ECG signal signifying the unique electrical properties of the heart offer the opportunity to expand the realm of biometrics, which pertains the identification of an individual based on physical characteristics. The temporal organization of the ECG signal offers a basis for composing a machine learning feature set. The four attributes of the feature set are derived through software automation enabled by Python. These four attributes are the temporal differential of the P wave maximum and T wave maximum relative to the R wave maximum and the Q wave minimum and S wave minimum relative to the R wave maximum. The multilayer perceptron neural network was applied and evaluated in terms of classification accuracy and time to develop the model. Superior performance was achieved with respect to a reduced feature set considering only the temporal differential of the P wave maximum and T wave maximum relative to the R wave maximum by comparison to all four attributes applied to the feature set and the temporal differential of the Q wave minimum and S wave minimum relative to the R wave maximum. With these preliminary findings and the advent of portable and wearable devices for the acquisition of the ECG signal, the temporal organization of the ECG signal offers robust potential for the field of biometrics.展开更多
Deep brain stimulation offers an advanced means of treating Parkinson’s disease in a patient specific context. However, a considerable challenge is the process of ascertaining an optimal parameter configuration. Impe...Deep brain stimulation offers an advanced means of treating Parkinson’s disease in a patient specific context. However, a considerable challenge is the process of ascertaining an optimal parameter configuration. Imperative for the deep brain stimulation parameter optimization process is the quantification of response feedback. As a significant improvement to traditional ordinal scale techniques is the advent of wearable and wireless systems. Recently conformal wearable and wireless systems with a profile on the order of a bandage have been developed. Previous research endeavors have successfully differentiated between deep brain stimulation “On” and “Off” status through quantification using wearable and wireless inertial sensor systems. However, the opportunity exists to further evolve to an objectively quantified response to an assortment of parameter configurations, such as the variation of amplitude, for the deep brain stimulation system. Multiple deep brain stimulation amplitude settings are considered inclusive of “Off” status as a baseline, 1.0 mA, 2.5 mA, and 4.0 mA. The quantified response of this assortment of amplitude settings is acquired through a conformal wearable and wireless inertial sensor system and consolidated using Python software automation to a feature set amenable for machine learning. Five machine learning algorithms are evaluated: J48 decision tree, K-nearest neighbors, support vector machine, logistic regression, and random forest. The performance of these machine learning algorithms is established based on the classification accuracy to distinguish between the deep brain stimulation amplitude settings and the time to develop the machine learning model. The support vector machine achieves the greatest classification accuracy, which is the primary performance parameter, and <span style="font-family:Verdana;">K-nearest neighbors achieves considerable classification accuracy with minimal time to develop the machine learning model.</span>展开更多
The inherently unique qualities of the heart infer the candidacy for the domain of biometrics, which applies physiological attributes to establish the recognition of a person’s identity. The heart’s characteristics ...The inherently unique qualities of the heart infer the candidacy for the domain of biometrics, which applies physiological attributes to establish the recognition of a person’s identity. The heart’s characteristics can be ascertained by recording the electrical signal activity of the heart through the acquisition of an electrocardiogram (ECG). With the application of machine learning the subject specific ECG signal can be differentiated. However, the process of distinguishing subjects through machine learning may be considered esoteric, especially for contributing subject matter experts external to the domain of machine learning. A resolution to this dilemma is the application of the J48 decision tree available through the Waikato Environment for Knowledge Analysis (WEKA). The J48 decision tree elucidates the machine learning process through a visualized decision tree that attains classification accuracy through the application of thresholds applied to the numeric attributes of the feature set. Additionally, the numeric attributes of the feature set for the application of the J48 decision tree are derived from the temporal organization of the ECG signal maxima and minima for the respective P, Q, R, S, and T waves. The J48 decision tree achieves considerable classification accuracy for the distinction of subjects based on their ECG signal, for which the machine learning model is briskly composed.展开更多
The quantification of gait is uniquely facilitated through the conformal wearable and wireless inertial sensor system, which consists of a profile comparable to a bandage. These attributes advance the ability to quant...The quantification of gait is uniquely facilitated through the conformal wearable and wireless inertial sensor system, which consists of a profile comparable to a bandage. These attributes advance the ability to quantify hemiplegic gait in consideration of the hemiplegic affected leg and unaffected leg. The recorded inertial sensor data, which is inclusive of the gyroscope signal, can be readily transmitted by wireless means to a secure Cloud. Incorporating Python to automate the post-processing of the gyroscope signal data can enable the development of a feature set suitable for a machine learning platform, such as the Waikato Environment for Knowledge Analysis (WEKA). An assortment of machine learning algorithms, such as the multilayer perceptron neural network, J48 decision tree, random forest, K-nearest neighbors, logistic regression, and naïve Bayes, were evaluated in terms of classification accuracy and time to develop the machine learning model. The K-nearest neighbors achieved optimal performance based on classification accuracy achieved for differentiating between the hemiplegic affected leg and unaffected leg for gait and the time to establish the machine learning model. The achievements of this research endeavor demonstrate the utility of amalgamating the conformal wearable and wireless inertial sensor with machine learning algorithms for distinguishing the hemiplegic affected leg and unaffected leg during gait.展开更多
Diadochokinesia pertains to a standard aspect of the conventional neurological examination, which involves the oscillation between muscle groups with an agonist and antagonist relationship. A representative example is...Diadochokinesia pertains to a standard aspect of the conventional neurological examination, which involves the oscillation between muscle groups with an agonist and antagonist relationship. A representative example is the pronation and supination of the forearm. Hemiparesis visibly demonstrates disparity of diadochokinesia, and clinical quantification is achieved through the use of an ordinal scale, which is inherently subjective. A conformal wearable and wireless inertial sensor equipped with a gyroscope mounted about the dorsum of the hand can objectively quantify diadochokinesia respective of forearm pronation and supination. The objective of the research endeavor was to apply an assortment of machine learning algorithms to distinguish between a hemiplegic affected and unaffected upper limb pair based on diadochokinesia with respect to pronation and supination of the forearm. Performance of the machine learning algorithms, such as the multilayer perceptron neural network, J48 decision tree, random forest, K-nearest neighbors, logistic regression, and naïve Bayes, were evaluated in consideration of classification accuracy and time to develop the machine learning model. The machine learning feature set was derived from the acquired gyroscope signal data. Using the gyroscope signal data from the conformal wearable and wireless inertial sensor the logistic regression and naïve Bayes machine learning algorithms achieved considerable performance capability with respect to both time to converge the machine learning model and classification accuracy for distinguishing between a hemiplegic upper limb pair for diadochokinesia in consideration of pronation and supination.展开更多
With the amalgamation of wearable systems equipped with inertial sensors, such as a gyroscope, and machine learning a therapy regimen can be objectively quantified, and then the initial phase and final phase of a one ...With the amalgamation of wearable systems equipped with inertial sensors, such as a gyroscope, and machine learning a therapy regimen can be objectively quantified, and then the initial phase and final phase of a one year therapy regimen can be distinguished through machine learning. In the context of rehabilitation of a hemiplegic ankle, a longitudinal therapy regimen incorporating stretching and then a series of repetitions for raising and lowering the foot of the hemiplegic ankle can be applied over the course of a year. Using a smartphone equipped with an application to function as a wearable and wireless gyroscope platform mounted to the dorsum of the foot by an armband, the initial phase and final phase of a one year longitudinally applied therapy regimen can be objectively quantified and recorded for subsequent machine learning. Considerable classification accuracy is attained to distinguish between the initial phase and final phase by a support vector machine for a one year longitudinally applied hemiplegic ankle therapy regimen based on the gyroscope signal data obtained by a smartphone functioning as a wearable and wireless inertial sensor system. .展开更多
The sense of telepresence is known to be essential in teleoperation environments, where the operator is physically separated from the vehicle. Usually only a visual feedback is provided, but it has been shown that by ...The sense of telepresence is known to be essential in teleoperation environments, where the operator is physically separated from the vehicle. Usually only a visual feedback is provided, but it has been shown that by extending the visual interface with haptic feedback, that is complementing the visual information through the sense of touch, the teleoperator has a better perception of information from the remote environment and its constraints. This paper focuses on a novel concept of haptic cueing for an airborne obstacle avoidance task; the novel cueing algorithm was designed to appear ＂natural＂ to the operator, and to improve the human-machine interface without directly acting on the actual aircraft commands. Two different haptic aiding concepts for obstacle avoidance support are presented： an existing and widely used system, belonging to what we called the Direct Haptic Aid （DItA） approach class, and a novel one based on the Indirect Haptic Aid （IHA） approach class. Tests with human operators show that a net improvement in terms of performance （i.e., the number of collisions） is provided by employing the 1HA haptic cue as compared to both the DHA haptic cue and/or the visual cues only. The results clearly show that the IHA philosophy is a valid alternative to the other commonly used approaches, which fall in the DHA category.展开更多
Recently, deep neural networks(DNNs) significantly outperform Gaussian mixture models in acoustic modeling for speech recognition. However, the substantial increase in computational load during the inference stage mak...Recently, deep neural networks(DNNs) significantly outperform Gaussian mixture models in acoustic modeling for speech recognition. However, the substantial increase in computational load during the inference stage makes deep models difficult to directly deploy on low-power embedded devices. To alleviate this issue,structure sparseness and low precision fixed-point quantization have been applied widely. In this work, binary neural networks for speech recognition are developed to reduce the computational cost during the inference stage.A fast implementation of binary matrix multiplication is introduced. On modern central processing unit(CPU)and graphics processing unit(GPU) architectures, a 5–7 times speedup compared with full precision floatingpoint matrix multiplication can be achieved in real applications. Several kinds of binary neural networks and related model optimization algorithms are developed for large vocabulary continuous speech recognition acoustic modeling. In addition, to improve the accuracy of binary models, knowledge distillation from the normal full precision floating-point model to the compressed binary model is explored. Experiments on the standard Switchboard speech recognition task show that the proposed binary neural networks can deliver 3–4 times speedup over the normal full precision deep models. With the knowledge distillation from the normal floating-point models, the binary DNNs or binary convolutional neural networks(CNNs) can restrict the word error rate(WER) degradation to within 15.0%,compared to the normal full precision floating-point DNNs or CNNs, respectively. Particularly for the binary CNN with binarization only on the convolutional layers, the WER degradation is very small and is almost negligible with the proposed approach.展开更多
Ensuring stable integration of diverse soft electronic components for reliable operation under dynamic conditions is crucial.However,integrating soft electronics,comprising various materials like polymers,metals,and h...Ensuring stable integration of diverse soft electronic components for reliable operation under dynamic conditions is crucial.However,integrating soft electronics,comprising various materials like polymers,metals,and hydrogels,poses challenges due to their different mechanical and chemical properties.This study introduces a dried-hydrogel adhesive made of poly(vinyl alcohol)and tannic acid multilayers(d-HAPT),which integrates soft electronic materials through moisture-derived chain entanglement.d-HAPT is a thin(~1μm)and highly transparent(over 85%transmittance in the visible light region)adhesive,showing robust bonding(up to 3.6 MPa)within a short time(<1 min).d-HAPT demonstrates practical application in wearable devices,including a hydrogel touch panel and strain sensors.Additionally,the potential of d-HAPT for use in implantable electronics is demonstrated through in vivo neuromodulation and electrocardiographic recording experiments while confirming its biocompatibility both in vitro and in vivo.It is expected that d-HAPT will provide a reliable platform for integrating soft electronic applications.展开更多
With increasing personalized healthcare,fiber-based wearable temperature sensors that can be incorporated into textiles have attracted more attention in the field of wearable electronics.Here,we present a flexible,wel...With increasing personalized healthcare,fiber-based wearable temperature sensors that can be incorporated into textiles have attracted more attention in the field of wearable electronics.Here,we present a flexible,well-passivated,polymer–nanocomposite–based fiber temperature sensor fabricated by a thermal drawing process of multiple materials.We engineered a preform to optimize material processability and sensor performance by considering the rheological and functional properties of the preform materials.The fiber temperature sensor consisted of a temperature-sensing core made from a conductive polymer composite of thermoplastic polylactic acid,a conductive carbon filler,reduced graphene oxide,and a highly flexible linear low-density polyethylene passivation layer.Our fiber temperature sensor exhibited adequate sensitivity(−0.285%/℃)within a temperature range of 25–45℃with rapid response and recovery times of 11.6 and 14.8 s,respectively.In addition,it demonstrated a consistent and reliable temperature response under repeated mechanical and chemical stresses,which satisfied the requirements for the long-term application of wearable fiber sensors.Furthermore,the fiber temperature sensor sewn onto a daily cloth and hand glove exhibited a highly stable performance in response to body temperature changes and temperature detection by touch.These results indicate the great potential of this sensor for applications in wearable,electronic skin,and other biomedical devices.展开更多
An integrated microball lens fiber catheter probe is demonstrated, which has better lateral resolution and longer working distance than a corresponding bare fiber probe with diverging beam for Fourier domain optical c...An integrated microball lens fiber catheter probe is demonstrated, which has better lateral resolution and longer working distance than a corresponding bare fiber probe with diverging beam for Fourier domain optical coherence tomography （FDOCT）. Simulation results are shown to gain the effect of the distance between the mieroball lens and the bare fiber to the focusing plane and beam width. The freedom of modifying the working distance and lateral resolution is shown. This is achieved by changing the gap distance between the single-mode fiber and the microball lens within the packaged surgical needle catheter without using an additional beam expander having a fixed length. The probe successfully acquired crosssectional images of ocular tissues from an animal sample with the proposed miniaturized imaging probe.展开更多
Background:The type Ⅲ secreted effectors(T3SEs)are one of the indispensable proteins in the growth and reproduction of Gram-negative bacteria.In particular,the pathogenesis of Gram-negative bacteria depends on the ty...Background:The type Ⅲ secreted effectors(T3SEs)are one of the indispensable proteins in the growth and reproduction of Gram-negative bacteria.In particular,the pathogenesis of Gram-negative bacteria depends on the type Ⅲ secreted effectors,and by injecting T3SEs into a host cell,the host cell's immunity can be destroyed.The high diversity of T3SE sequences and the lack of defined secretion signals make it difficult to identify and predict.Moreover,the related study of the pathological system associated with T3SE remains a hot topic in bioinformatics.Some computational tools have been developed to meet the growing demand for the recognition of T3SEs and the studies of type Ⅲ secretion systems(T3SS).Although these tools can help biological experiments in certain procedures,there is still room for improvement,even for the current best model,as the existing methods adopt handdesigned feature and traditional machine learning methods.Methods:In this study,we propose a powerful predictor based on deep learning methods,called WEDeepT3.Our work consists mainly of three key steps.First,we train word embedding vectors for protein sequences in a large-scale amino acid sequence database.Second,we combine the word vectors with traditional features extracted from protein sequences,like PSSM,to construct a more comprehensive feature representation.Finally,we construct a deep neural network model in the prediction of type Ⅲ secreted effectors.Results:The feature representation of WEDeepT3 consists of both word embedding and position-specific features.Working together with convolutional neural networks,the new model achieves superior performance to the state-ofthe-art methods,demonstrating the effectiveness of the new feature representation and the powerful learning ability of deep models.Conclusion:WEDeepT3 exploits both semantic information of Ar-mer fragments and evolutional information of protein sequences to accurately difYerentiate between T3SEs and non-T3SEs.WEDeepT3 is available at bcmi.sjtu.edu.cn/~yangyang/WEDeepT3.html.展开更多
It is attractive to formulate problems in computer vision and related fields in term of probabilis- tic estimation where the probability models are defined over graphs, such as grammars. The graphical struc- tures, an...It is attractive to formulate problems in computer vision and related fields in term of probabilis- tic estimation where the probability models are defined over graphs, such as grammars. The graphical struc- tures, and the state variables defined over them, give a rich knowledge representation which can describe the complex structures of objects and images. The proba- bility distributions defined over the graphs capture the statistical variability of these structures. These proba- bility models can be learnt from training data with lim- ited amounts of supervision. But learning these models suffers from the difficulty of evaluating the normaliza- tion constant, or partition function, of the probability distributions which can be extremely computationally demanding. This paper shows that by placing bounds on the normalization constant we can obtain compu- rationally tractable approximations. Surprisingly, for certain choices of loss functions, we obtain many of the standard max-margin criteria used in support vector machines （SVMs） and hence we reduce the learning to standard machine learning methods. We show that many machine learning methods can be obtained in this way as approximations to probabilistic methods including multi-class max-margin, ordinal regression, max-margin Markov networks and parsers, multiple- instance learning, and latent SVM. We illustrate this work by computer vision applications including image labeling, object detection and localization, and motion estimation. We speculate that rained by using better bounds better results can be ob- and approximations.展开更多
文摘本研究旨在模拟不同狭窄程度和脉搏率的颈动脉搏动血流。采用流-固耦合(FSI)和任意拉格朗日-欧拉(ALE)方法研究了不同狭窄程度、脉搏率和动脉壁性质对周围流体的影响。分别应用Carreau-Yasuda非牛顿超弹性模型和修正Mooney-Rivin超弹性模型于具有非牛顿行为的血液和超弹性血管壁。结果得到血液的壁面径向位移、压力分布、轴向速度分布和壁面剪切应力。通过增加狭窄的严重程度,轴向速度、血压变化、最大壁面剪切应力和壁面径向位移均呈增长趋势。当脉率在狭窄程度为75%时,最大流量矩、壁面径向位移、压力、轴向速度和壁面剪应力的最大值均增大。此外,与弹性和刚性模型相比,将动脉壁视为超弹性模型,将其周围流体视为非牛顿和非定常,可以使模拟更加真实。在严重程度高达50%的狭窄中,红细胞受到轻微损害,而在严重程度为75%的狭窄中观察到溶血。通过改善动脉粥样硬化,弹性模量从500 k Pa提高到2 MPa,在60 bpm脉率和狭窄程度75%下,剪切应力最大值增长65%。与刚性和弹性动脉壁相比,动脉壁的超弹性模型导致较低的轴向速度、较低的血压、较低的剪切应力和较高的径向位移。
基金supported by the National Natural Science Foundation of China(Nos.61671288,91530321,61603161)Science and Technology Commission of Shanghai Municipality(Nos.16JC1404300,17JC1403500,16ZR1448700)
文摘Membrane proteins are an important kind of proteins embedded in the membranes of cells and play crucial roles in living organisms, such as ion channels,transporters, receptors. Because it is difficult to determinate the membrane protein's structure by wet-lab experiments,accurate and fast amino acid sequence-based computational methods are highly desired. In this paper, we report an online prediction tool called Mem Brain, whose input is the amino acid sequence. Mem Brain consists of specialized modules for predicting transmembrane helices, residue–residue contacts and relative accessible surface area of a-helical membrane proteins. Mem Brain achieves aprediction accuracy of 97.9% of ATMH, 87.1% of AP,3.2 ± 3.0 of N-score, 3.1 ± 2.8 of C-score. Mem BrainContact obtains 62%/64.1% prediction accuracy on training and independent dataset on top L/5 contact prediction,respectively. And Mem Brain-Rasa achieves Pearson correlation coefficient of 0.733 and its mean absolute error of13.593. These prediction results provide valuable hints for revealing the structure and function of membrane proteins.Mem Brain web server is free for academic use and available at www.csbio.sjtu.edu.cn/bioinf/Mem Brain/.
基金supported by the National Natural Science Foundation of China (81571025 and 81702461)the National Key Research and Development Program of China (2018YFC0116400)+6 种基金the International Cooperation Project from Shanghai Science Foundation (18410711300)Shanghai Science and Technology Development Funds (16JC1420100)the Shanghai Sailing Program (17YF1426600)STCSM (19QC1400600, 17411953300)the Shanghai Pujiang Program (19PJ1406800)the Shanghai Municipal Science and Technology Major Project (No.2018SHZDZX01) and ZJlabthe Interdisciplinary Program of Shanghai Jiao Tong University。
文摘Hydrocephalus is often treated with a cerebrospinal fluid shunt(CFS) for excessive amounts of cerebrospinal fluid in the brain.However,it is very difficult to distinguish whether the ventricular enlargement is due to hydrocephalus or other causes,such as brain atrophy after brain damage and surgery.The non-trivial evaluation of the consciousness level,along with a continuous drainage test of the lumbar cistern is thus clinically important before the decision for CFS is made.We studied 32 secondary mild hydrocephalus patients with different consciousness levels,who received T1 and diffusion tensor imaging magnetic resonance scans before and after lumbar cerebrospinal fluid drainage.We applied a novel machine-learning method to find the most discriminative features from the multi-modal neuroimages.Then,we built a regression model to regress the JFK Coma Recovery Scale-Revised(CRS-R) scores to quantify the level of consciousness.The experimental results showed that our method not only approximated the CRS-R scores but also tracked the temporal changes in individual patients.The regression model has high potential for the evaluation of consciousness in clinical practice.
文摘The concept of Network Centric Therapy represents an amalgamation of wearable and wireless inertial sensor systems and machine learning with access to a Cloud computing environment. The advent of Network Centric Therapy is highly relevant to the treatment of Parkinson’s disease through deep brain stimulation. Originally wearable and wireless systems for quantifying Parkinson’s disease involved the use a smartphone to quantify hand tremor. Although originally novel, the smartphone has notable issues as a wearable application for quantifying movement disorder tremor. The smartphone has evolved in a pathway that has made the smartphone progressively more cumbersome to mount about the dorsum of the hand. Furthermore, the smartphone utilizes an inertial sensor package that is not certified for medical analysis, and the trial data access a provisional Cloud computing environment through an email account. These concerns are resolved with the recent development of a conformal wearable and wireless inertial sensor system. This conformal wearable and wireless system mounts to the hand with the profile of a bandage by adhesive and accesses a secure Cloud computing environment through a segmented wireless connectivity strategy involving a smartphone and tablet. Additionally, the conformal wearable and wireless system is certified by the FDA of the United States of America for ascertaining medical grade inertial sensor data. These characteristics make the conformal wearable and wireless system uniquely suited for the quantification of Parkinson’s disease treatment through deep brain stimulation. Preliminary evaluation of the conformal wearable and wireless system is demonstrated through the differentiation of deep brain stimulation set to “On” and “Off” status. Based on the robustness of the acceleration signal, this signal was selected to quantify hand tremor for the prescribed deep brain stimulation settings. Machine learning classification using the Waikato Environment for Knowledge Analysis (WEKA) was applied using the multilayer perceptron neural network. The multilayer perceptron neural network achieved considerable classification accuracy for distinguishing between the deep brain stimulation system set to “On” and “Off” status through the quantified acceleration signal data obtained by this recently developed conformal wearable and wireless system. The research achievement establishes a progressive pathway to the future objective of achieving deep brain stimulation capabilities that promote closed-loop acquisition of configuration parameters that are uniquely optimized to the individual through extrinsic means of a highly conformal wearable and wireless inertial sensor system and machine learning with access to Cloud computing resources.
文摘The attributes of the ECG signal signifying the unique electrical properties of the heart offer the opportunity to expand the realm of biometrics, which pertains the identification of an individual based on physical characteristics. The temporal organization of the ECG signal offers a basis for composing a machine learning feature set. The four attributes of the feature set are derived through software automation enabled by Python. These four attributes are the temporal differential of the P wave maximum and T wave maximum relative to the R wave maximum and the Q wave minimum and S wave minimum relative to the R wave maximum. The multilayer perceptron neural network was applied and evaluated in terms of classification accuracy and time to develop the model. Superior performance was achieved with respect to a reduced feature set considering only the temporal differential of the P wave maximum and T wave maximum relative to the R wave maximum by comparison to all four attributes applied to the feature set and the temporal differential of the Q wave minimum and S wave minimum relative to the R wave maximum. With these preliminary findings and the advent of portable and wearable devices for the acquisition of the ECG signal, the temporal organization of the ECG signal offers robust potential for the field of biometrics.
文摘Deep brain stimulation offers an advanced means of treating Parkinson’s disease in a patient specific context. However, a considerable challenge is the process of ascertaining an optimal parameter configuration. Imperative for the deep brain stimulation parameter optimization process is the quantification of response feedback. As a significant improvement to traditional ordinal scale techniques is the advent of wearable and wireless systems. Recently conformal wearable and wireless systems with a profile on the order of a bandage have been developed. Previous research endeavors have successfully differentiated between deep brain stimulation “On” and “Off” status through quantification using wearable and wireless inertial sensor systems. However, the opportunity exists to further evolve to an objectively quantified response to an assortment of parameter configurations, such as the variation of amplitude, for the deep brain stimulation system. Multiple deep brain stimulation amplitude settings are considered inclusive of “Off” status as a baseline, 1.0 mA, 2.5 mA, and 4.0 mA. The quantified response of this assortment of amplitude settings is acquired through a conformal wearable and wireless inertial sensor system and consolidated using Python software automation to a feature set amenable for machine learning. Five machine learning algorithms are evaluated: J48 decision tree, K-nearest neighbors, support vector machine, logistic regression, and random forest. The performance of these machine learning algorithms is established based on the classification accuracy to distinguish between the deep brain stimulation amplitude settings and the time to develop the machine learning model. The support vector machine achieves the greatest classification accuracy, which is the primary performance parameter, and <span style="font-family:Verdana;">K-nearest neighbors achieves considerable classification accuracy with minimal time to develop the machine learning model.</span>
文摘The inherently unique qualities of the heart infer the candidacy for the domain of biometrics, which applies physiological attributes to establish the recognition of a person’s identity. The heart’s characteristics can be ascertained by recording the electrical signal activity of the heart through the acquisition of an electrocardiogram (ECG). With the application of machine learning the subject specific ECG signal can be differentiated. However, the process of distinguishing subjects through machine learning may be considered esoteric, especially for contributing subject matter experts external to the domain of machine learning. A resolution to this dilemma is the application of the J48 decision tree available through the Waikato Environment for Knowledge Analysis (WEKA). The J48 decision tree elucidates the machine learning process through a visualized decision tree that attains classification accuracy through the application of thresholds applied to the numeric attributes of the feature set. Additionally, the numeric attributes of the feature set for the application of the J48 decision tree are derived from the temporal organization of the ECG signal maxima and minima for the respective P, Q, R, S, and T waves. The J48 decision tree achieves considerable classification accuracy for the distinction of subjects based on their ECG signal, for which the machine learning model is briskly composed.
文摘The quantification of gait is uniquely facilitated through the conformal wearable and wireless inertial sensor system, which consists of a profile comparable to a bandage. These attributes advance the ability to quantify hemiplegic gait in consideration of the hemiplegic affected leg and unaffected leg. The recorded inertial sensor data, which is inclusive of the gyroscope signal, can be readily transmitted by wireless means to a secure Cloud. Incorporating Python to automate the post-processing of the gyroscope signal data can enable the development of a feature set suitable for a machine learning platform, such as the Waikato Environment for Knowledge Analysis (WEKA). An assortment of machine learning algorithms, such as the multilayer perceptron neural network, J48 decision tree, random forest, K-nearest neighbors, logistic regression, and naïve Bayes, were evaluated in terms of classification accuracy and time to develop the machine learning model. The K-nearest neighbors achieved optimal performance based on classification accuracy achieved for differentiating between the hemiplegic affected leg and unaffected leg for gait and the time to establish the machine learning model. The achievements of this research endeavor demonstrate the utility of amalgamating the conformal wearable and wireless inertial sensor with machine learning algorithms for distinguishing the hemiplegic affected leg and unaffected leg during gait.
文摘Diadochokinesia pertains to a standard aspect of the conventional neurological examination, which involves the oscillation between muscle groups with an agonist and antagonist relationship. A representative example is the pronation and supination of the forearm. Hemiparesis visibly demonstrates disparity of diadochokinesia, and clinical quantification is achieved through the use of an ordinal scale, which is inherently subjective. A conformal wearable and wireless inertial sensor equipped with a gyroscope mounted about the dorsum of the hand can objectively quantify diadochokinesia respective of forearm pronation and supination. The objective of the research endeavor was to apply an assortment of machine learning algorithms to distinguish between a hemiplegic affected and unaffected upper limb pair based on diadochokinesia with respect to pronation and supination of the forearm. Performance of the machine learning algorithms, such as the multilayer perceptron neural network, J48 decision tree, random forest, K-nearest neighbors, logistic regression, and naïve Bayes, were evaluated in consideration of classification accuracy and time to develop the machine learning model. The machine learning feature set was derived from the acquired gyroscope signal data. Using the gyroscope signal data from the conformal wearable and wireless inertial sensor the logistic regression and naïve Bayes machine learning algorithms achieved considerable performance capability with respect to both time to converge the machine learning model and classification accuracy for distinguishing between a hemiplegic upper limb pair for diadochokinesia in consideration of pronation and supination.
文摘With the amalgamation of wearable systems equipped with inertial sensors, such as a gyroscope, and machine learning a therapy regimen can be objectively quantified, and then the initial phase and final phase of a one year therapy regimen can be distinguished through machine learning. In the context of rehabilitation of a hemiplegic ankle, a longitudinal therapy regimen incorporating stretching and then a series of repetitions for raising and lowering the foot of the hemiplegic ankle can be applied over the course of a year. Using a smartphone equipped with an application to function as a wearable and wireless gyroscope platform mounted to the dorsum of the foot by an armband, the initial phase and final phase of a one year longitudinally applied therapy regimen can be objectively quantified and recorded for subsequent machine learning. Considerable classification accuracy is attained to distinguish between the initial phase and final phase by a support vector machine for a one year longitudinally applied hemiplegic ankle therapy regimen based on the gyroscope signal data obtained by a smartphone functioning as a wearable and wireless inertial sensor system. .
文摘The sense of telepresence is known to be essential in teleoperation environments, where the operator is physically separated from the vehicle. Usually only a visual feedback is provided, but it has been shown that by extending the visual interface with haptic feedback, that is complementing the visual information through the sense of touch, the teleoperator has a better perception of information from the remote environment and its constraints. This paper focuses on a novel concept of haptic cueing for an airborne obstacle avoidance task; the novel cueing algorithm was designed to appear ＂natural＂ to the operator, and to improve the human-machine interface without directly acting on the actual aircraft commands. Two different haptic aiding concepts for obstacle avoidance support are presented： an existing and widely used system, belonging to what we called the Direct Haptic Aid （DItA） approach class, and a novel one based on the Indirect Haptic Aid （IHA） approach class. Tests with human operators show that a net improvement in terms of performance （i.e., the number of collisions） is provided by employing the 1HA haptic cue as compared to both the DHA haptic cue and/or the visual cues only. The results clearly show that the IHA philosophy is a valid alternative to the other commonly used approaches, which fall in the DHA category.
基金the National Natural Science Foundation of China (Nos. 61603252 and U1736202)experiments have been carried out on the Pi supercomputer at Shanghai Jiao Tong University.
文摘Recently, deep neural networks(DNNs) significantly outperform Gaussian mixture models in acoustic modeling for speech recognition. However, the substantial increase in computational load during the inference stage makes deep models difficult to directly deploy on low-power embedded devices. To alleviate this issue,structure sparseness and low precision fixed-point quantization have been applied widely. In this work, binary neural networks for speech recognition are developed to reduce the computational cost during the inference stage.A fast implementation of binary matrix multiplication is introduced. On modern central processing unit(CPU)and graphics processing unit(GPU) architectures, a 5–7 times speedup compared with full precision floatingpoint matrix multiplication can be achieved in real applications. Several kinds of binary neural networks and related model optimization algorithms are developed for large vocabulary continuous speech recognition acoustic modeling. In addition, to improve the accuracy of binary models, knowledge distillation from the normal full precision floating-point model to the compressed binary model is explored. Experiments on the standard Switchboard speech recognition task show that the proposed binary neural networks can deliver 3–4 times speedup over the normal full precision deep models. With the knowledge distillation from the normal floating-point models, the binary DNNs or binary convolutional neural networks(CNNs) can restrict the word error rate(WER) degradation to within 15.0%,compared to the normal full precision floating-point DNNs or CNNs, respectively. Particularly for the binary CNN with binarization only on the convolutional layers, the WER degradation is very small and is almost negligible with the proposed approach.
基金supported by Nano·Material Technology Development Program through the National Research Foundation of Korea(NRF)funded by Ministry of Science and ICT(NRF-2021M3H4A1A04092883)supported by the Korea Medical Device Development Fund grant funded by theKorea government(the Ministry of Science and ICT,theMinistry of Trade,Industry and Energy,the Ministry of Health&Welfare,the Ministry of Food and Drug Safety)(Project Number:1711196794,RS-2023-00243310)。
文摘Ensuring stable integration of diverse soft electronic components for reliable operation under dynamic conditions is crucial.However,integrating soft electronics,comprising various materials like polymers,metals,and hydrogels,poses challenges due to their different mechanical and chemical properties.This study introduces a dried-hydrogel adhesive made of poly(vinyl alcohol)and tannic acid multilayers(d-HAPT),which integrates soft electronic materials through moisture-derived chain entanglement.d-HAPT is a thin(~1μm)and highly transparent(over 85%transmittance in the visible light region)adhesive,showing robust bonding(up to 3.6 MPa)within a short time(<1 min).d-HAPT demonstrates practical application in wearable devices,including a hydrogel touch panel and strain sensors.Additionally,the potential of d-HAPT for use in implantable electronics is demonstrated through in vivo neuromodulation and electrocardiographic recording experiments while confirming its biocompatibility both in vitro and in vivo.It is expected that d-HAPT will provide a reliable platform for integrating soft electronic applications.
基金supported by National Research Foundation of Korea(NRF)funded by the Ministry of Science and ICT(2021M3F3A2A01037365,RS-2023-00207970)KAINEET Institute Seed Money Project,Post-AI Research Institute.
文摘With increasing personalized healthcare,fiber-based wearable temperature sensors that can be incorporated into textiles have attracted more attention in the field of wearable electronics.Here,we present a flexible,well-passivated,polymer–nanocomposite–based fiber temperature sensor fabricated by a thermal drawing process of multiple materials.We engineered a preform to optimize material processability and sensor performance by considering the rheological and functional properties of the preform materials.The fiber temperature sensor consisted of a temperature-sensing core made from a conductive polymer composite of thermoplastic polylactic acid,a conductive carbon filler,reduced graphene oxide,and a highly flexible linear low-density polyethylene passivation layer.Our fiber temperature sensor exhibited adequate sensitivity(−0.285%/℃)within a temperature range of 25–45℃with rapid response and recovery times of 11.6 and 14.8 s,respectively.In addition,it demonstrated a consistent and reliable temperature response under repeated mechanical and chemical stresses,which satisfied the requirements for the long-term application of wearable fiber sensors.Furthermore,the fiber temperature sensor sewn onto a daily cloth and hand glove exhibited a highly stable performance in response to body temperature changes and temperature detection by touch.These results indicate the great potential of this sensor for applications in wearable,electronic skin,and other biomedical devices.
基金supported by the World Class University Program funded by the Ministry of Education, Science, and Technology through the National Research Foundation of Korea (No. R31-10008)supported in part by NIH (No. BRP 1R01 EB 007969- 01)
文摘An integrated microball lens fiber catheter probe is demonstrated, which has better lateral resolution and longer working distance than a corresponding bare fiber probe with diverging beam for Fourier domain optical coherence tomography （FDOCT）. Simulation results are shown to gain the effect of the distance between the mieroball lens and the bare fiber to the focusing plane and beam width. The freedom of modifying the working distance and lateral resolution is shown. This is achieved by changing the gap distance between the single-mode fiber and the microball lens within the packaged surgical needle catheter without using an additional beam expander having a fixed length. The probe successfully acquired crosssectional images of ocular tissues from an animal sample with the proposed miniaturized imaging probe.
基金supported by the National Natural Science Foundation of China(No.61972251).
文摘Background:The type Ⅲ secreted effectors(T3SEs)are one of the indispensable proteins in the growth and reproduction of Gram-negative bacteria.In particular,the pathogenesis of Gram-negative bacteria depends on the type Ⅲ secreted effectors,and by injecting T3SEs into a host cell,the host cell's immunity can be destroyed.The high diversity of T3SE sequences and the lack of defined secretion signals make it difficult to identify and predict.Moreover,the related study of the pathological system associated with T3SE remains a hot topic in bioinformatics.Some computational tools have been developed to meet the growing demand for the recognition of T3SEs and the studies of type Ⅲ secretion systems(T3SS).Although these tools can help biological experiments in certain procedures,there is still room for improvement,even for the current best model,as the existing methods adopt handdesigned feature and traditional machine learning methods.Methods:In this study,we propose a powerful predictor based on deep learning methods,called WEDeepT3.Our work consists mainly of three key steps.First,we train word embedding vectors for protein sequences in a large-scale amino acid sequence database.Second,we combine the word vectors with traditional features extracted from protein sequences,like PSSM,to construct a more comprehensive feature representation.Finally,we construct a deep neural network model in the prediction of type Ⅲ secreted effectors.Results:The feature representation of WEDeepT3 consists of both word embedding and position-specific features.Working together with convolutional neural networks,the new model achieves superior performance to the state-ofthe-art methods,demonstrating the effectiveness of the new feature representation and the powerful learning ability of deep models.Conclusion:WEDeepT3 exploits both semantic information of Ar-mer fragments and evolutional information of protein sequences to accurately difYerentiate between T3SEs and non-T3SEs.WEDeepT3 is available at bcmi.sjtu.edu.cn/~yangyang/WEDeepT3.html.
文摘It is attractive to formulate problems in computer vision and related fields in term of probabilis- tic estimation where the probability models are defined over graphs, such as grammars. The graphical struc- tures, and the state variables defined over them, give a rich knowledge representation which can describe the complex structures of objects and images. The proba- bility distributions defined over the graphs capture the statistical variability of these structures. These proba- bility models can be learnt from training data with lim- ited amounts of supervision. But learning these models suffers from the difficulty of evaluating the normaliza- tion constant, or partition function, of the probability distributions which can be extremely computationally demanding. This paper shows that by placing bounds on the normalization constant we can obtain compu- rationally tractable approximations. Surprisingly, for certain choices of loss functions, we obtain many of the standard max-margin criteria used in support vector machines （SVMs） and hence we reduce the learning to standard machine learning methods. We show that many machine learning methods can be obtained in this way as approximations to probabilistic methods including multi-class max-margin, ordinal regression, max-margin Markov networks and parsers, multiple- instance learning, and latent SVM. We illustrate this work by computer vision applications including image labeling, object detection and localization, and motion estimation. We speculate that rained by using better bounds better results can be ob- and approximations.
