Optimal tracking control for non-zero-sum games of linear discrete-time systems via off-policy reinforcement learning

In this article, a model-free off-policy reinforcement learning algorithm is applied to address the optimal tracking problem based on multiplayer non-zero-sum games for discrete-time linear systems. In contrast to the traditional method and the policy iteration method for solving the optimal tracking problems, the proposed algorithm operates with the system data rather than the knowledge of the system dynamics. For performing the proposed algorithm, an auxiliary augmented system is constructed via assembling the original system and the reference trajectory while a discount factor is introduced into the performance indexes. It is analyzed that the solutions of the proposed algorithm converge to the Nash equilibrium and the result is not influenced by the probing noise. Two simulations are presented to verify the feasibility and effectiveness of the proposed algorithm.     

Machine learning models for Parkinson’s disease detection and stage classification based on spatial-temporal gait parameters

BackgroundParkinson’s disease (PD) is a chronic and progressive neurodegenerative disease with no cure, presenting a challenging diagnosis and management. However, despite a significant number of criteria and guidelines have been proposed to improve the diagnosis of PD and to determine the PD stage, the gold standard for diagnosis and symptoms monitoring of PD is still mainly based on clinical evaluation, which includes several subjective factors. The use of machine learning (ML) algorithms in spatial-temporal gait parameters is an interesting advance with easy interpretation and objective factors that may assist in PD diagnostic and follow up.Research questionThis article studies ML algorithms for: i) distinguish people with PD vs. matched-healthy individuals; and ii) to discriminate PD stages, based on selected spatial-temporal parameters, including variability and asymmetry.MethodsGait data acquired from 63 people with PD with different levels of PD motor symptoms severity, and 63 matched-control group individuals, during self-selected walking speed, was study in the experiments.ResultsIn the PD diagnosis, a classification accuracy of 84.6 %, with a precision of 0.923 and a recall of 0.800, was achieved by the Naïve Bayes algorithm. We found four significant gait features in PD diagnosis: step length, velocity and width, and step width variability. As to the PD stage identification, the Random Forest outperformed the other studied ML algorithms, by reaching an Area Under the ROC curve of 0.786. We found two relevant gait features in identifying the PD stage: stride width variability and step double support time variability.SignificanceThe results showed that the studied ML algorithms have potential both to PD diagnosis and stage identification by analysing gait parameters.     

Tissue tracking of segmental strain as a predictor of provoked dynamic left ventricular outflow tract obstruction

BackgroundLeft ventricular outflow tract obstruction (LVOTO) is commonly observed in patients with hypertrophic cardiomyopathy (HCM) or left ventricular hypertrophy (LVH). Some patients develop LVOTO provoked by physical exertion, and hence termed dynamic LVOTO (DLVOTO). However, its precise prevalence and mechanism are still unclear.AimTwo-dimensional speckle tracking echocardiography (2D STE) seems to be helpful for the detection of early LV structural abnormalities. This study aimed to examine the possible role of segmental as well as global longitudinal strain in identifying DLVOTO non-HCM patients as detected by dobutamine stress echocardiography (DSE).Methods and resultsTwo hundred and fifty patients without structural heart disease had undergone conventional transthoracic echocardiography, 2D STE, and DSE. All patients with non-ischemic evidence were divided into two groups according to the DSE results; DLVOTO (+) and DLVOTO (?).Among 250 patients, 50 patients (36%) had shown DLVOTO after DSE (15 males, 35 females; mean age 55±7years). They were compared with 90 non -LVOTO obstruction patients (43 males, 47 females; mean age 57±6years). Based on multivariate logistic regression analysis, the independent predictors of provoked DLVOTO during DSE were resting basal septal longitudinal strain BS-LS _average (p < 0.001), resting LA reservoir strain (p < 0.001), and systolic LVOT diameter (p = 0.03). Resting BS-LS _average with cut-off - 17.5% was recognized as a critical indicator of DLVOTO, with sensitivity 78%, and specificity 95% (better than systolic LVOT diameter of sensitivity 76%, and specificity 15% and resting LA reservoir strain which showed poor AUC at ROC curve 0.007).ConclusionWe demonstrate that provoked LVOTO during DSE in non HCM symptomatic patients is directly correlated to resting regional LS, where the increased BS-LS of ≥ ?17.5% was a key determinant of LVOT gradient provocation. Assessment of baseline BS-LS _average might be a bedside simple tool for detection of patients with DLVOTO not able to do DSE.     

二维斑点追踪技术评价低温兔左室纵向功能

目的:探讨应用二维斑点追踪技术评价低温条件下兔左心室纵向功能的价值。方法:30只新西兰兔随机分成对照组(n=10),低温组A(n=10),低温组B(n=10)。先行常规心脏数据测量,然后采用组织多普勒(TDI),之后应用斑点追踪成像(STI)中的获取基底段、中间段、心尖段及整体水平SL、SrLs.SrL E,SrL A及分层应变技术获取3个长轴切面心内膜下、中层和心外膜下心肌收缩期纵向峰值应变(SL)。结果:①与对照组相比,A组心内膜下心肌LS值的减低,差异有统计学意义(P<0.05),B组3层心肌SL值的减低明显,差异有统计学意义(P<0.01)②与对照组相比,A组大部分纵向应变及应变率减低(P<0.05);B组基底段、中间段、心尖段及整体水平SL,SrL S、SrLE、SrLA均减低(P<0.01)结论:随低温时间延长,左室壁3层心肌SL值受累程度不同,心内膜应变较心外膜更加敏感,二维班点追踪技术比LVEF及TDI更早发现左室功能减低。     

Prospective comparative study of intraoperative “Towel clip test” and “Vertical patella test” assessing lateral retinaculum tightness in patients undergoing TKA

BackgroundProper patellar tracking is one of the most important aspect of TKA to ensure good functional outcome. A patellar tracking problem noted intraoperatively serves as a warning sign and should prompt the surgeon to reassess position of each component. Various tests are there to assess lateral retinaculum tightness viz. "No thumb test", "Towel clip test". A new test "Vertical patella test" is described to assess lateral retinaculum tightness. A study was conducted to assess the effectiveness, correlation and validity of two techniques.Materials & MethodsPatients >50 years of age and with diagnosis of Osteoarthritis knee having less than 30 varus and flexion deformity going in for primary TKA were selected with a sample size of 100 knees in a tertiary care centre. Revision cases or patients with flexion contracture more than 30, complex knee surgery; with pre existing patellar tilt were excluded from study.ResultsResults of both tests were found to correlate in 75% of case with sensitivity of 96.65% and specificity of 75.00%. Kappa came out to be 0.634 which shows good agreement of vertical patella test and towel clip test. Result was computed using excel and SPSS and was found to be significant with p value< 0.05. Lateral retinaculum release was done in 8 knees.ConclusionsVertical patella test correlates with towel clip test, is easy to perform and saves time. The limitation of our study was small sample size.     

State and output feedback design for robust tracking of linear systems with rate limited actuators

A design technique (Control of Uncertain Systems with Bounded Inputs, Tarbouriech S, Garcia G, (Eds), Lecture Notes in Control and Information Sciences, vol. 227 , Springer: Berlin, 1997; 173–186) recently proposed for stabilization of a linear system with rate‐limited actuators is utilized to design feedback laws that cause the system output to track a desired command signal. This design technique combines two design techniques recently developed for linear systems with position limited actuators, piecewise‐linear LQ control (Automatica, 1994; 30 : 403–416) and low‐and‐high gain feedback (IEEE Trans. Automat. Control, 1996; 41 : 368–378), and hence takes advantage of both design techniques, while avoiding their disadvantages. In the case that only the output is available for feedback, the performance of the state feedback law is preserved by the use of a fast observer. An open‐loop exponentially unstable fighter aircraft is used to demonstrate the effectiveness of the proposed control design method. Copyright © 2002 John Wiley & Sons, Ltd.     

应用HMM和加权距离判别法的真核基因识别程序研究

根据现代科学对基因的认识，应用了隐马尔科夫模型(HMM)的算法，以大量核酸序列为信息来源，通过计算机计算来寻找未知基因的大体位置；再通过基因的固有结构特征及密码子使用的偏向性，使用加权距离判别法来准确地定位基因，以图形及文本的形式输出，从而极大地方便了实验室的研究工作。考虑到基因的许多特征还不为人们所了解，而且不同物种之间基因结构又有一定的差异，所以还开发了程序自学习功能，不断地存储已知的基因，再据此改变一些已有固有数据，以便更好地适应和了解不同生物基因结构的特异性，更加准确地寻找未知基因的位置。     

Lung function development in the first 2 yr of life is independent of allergic diseases by 2 yr

The aim of the study was to assess if lung function at birth predicts lung function at 2 yr and secondly, if lung function development was influenced by the common phenotypes of recurrent bronchial obstruction (rBO) or atopic eczema (AE) by 2 yr. Lung function was assessed at birth (n = 802) and at 2 yr within the prospective birth cohort study 'the Environment and Childhood Asthma Study' in Oslo. The 135 children with lung function measured at birth by tidal flow volume (TFV) loops and passive respiratory mechanics, who were included in a nested case-control study were reinvestigated at 2 yr with clinical examination, TFV loops (n = 90) (mean age 26.6 (3.7 s.d.) months), skin prick test and parental interview. Children were categorized into quartiles (lower, middle two, upper) according to time to peak tidal expiratory flow/total expiratory time (t(PTEF)/t(E)) at birth as well as clinical phenotype based on the presence of rBO and/or AE (ever) by 2 yr. The observed reduction in mean t(PTEF)/t(E) from birth to 2 yr within the quartiles, were not significantly different after controlling for 'regression to the mean'. t(PTEF)/t(E) at birth correlated significantly with t(PTEF)/t(E) at 2 yr, (r = 0.475, p < 0.001). Children with both rBO and AE by 2 yr had significantly lower t(PTEF)/t(E) at 2 yr (p = 0.002) and at birth (p = 0.027), compared with children with no rBO or AE. Clinical phenotype at 2 yr did not influence the change in t(PTEF)/t(E) from birth to 2 yr. This study demonstrates a clear tracking of lung function from birth, not influenced by rBO or AE by 2 yr.