Dynamic neural network-based robust observers for uncertain nonlinear systems

A dynamic neural network (DNN) based robust observer for uncertain nonlinear systems is developed. The observer structure consists of a DNN to estimate the system dynamics on-line, a dynamic filter to estimate the unmeasurable state and a sliding mode feedback term to account for modeling errors and exogenous disturbances. The observed states are proven to asymptotically converge to the system states of high-order uncertain nonlinear systems through Lyapunov-based analysis. Simulations and experiments on a two-link robot manipulator are performed to show the effectiveness of the proposed method in comparison to several other state estimation methods.     

Cross-person activity recognition using reduced kernel extreme learning machine

Activity recognition based on mobile embedded accelerometer is very important for developing human-centric pervasive applications such as healthcare, personalized recommendation and so on. However, the distribution of accelerometer data is heavily affected by varying users. The performance will degrade when the model trained on one person is used to others. To solve this problem, we propose a fast and accurate cross-person activity recognition model, known as TransRKELM (Transfer learning Reduced Kernel Extreme Learning Machine) which uses RKELM (Reduced Kernel Extreme Learning Machine) to realize initial activity recognition model. In the online phase OS-RKELM (Online Sequential Reduced Kernel Extreme Learning Machine) is applied to update the initial model and adapt the recognition model to new device users based on recognition results with high confidence level efficiently. Experimental results show that, the proposed model can adapt the classifier to new device users quickly and obtain good recognition performance.     

Kernel learning at the first level of inference

Kernel learning methods, whether Bayesian or frequentist, typically involve multiple levels of inference, with the coefficients of the kernel expansion being determined at the first level and the kernel and regularisation parameters carefully tuned at the second level, a process known as model selection. Model selection for kernel machines is commonly performed via optimisation of a suitable model selection criterion, often based on cross-validation or theoretical performance bounds. However, if there are a large number of kernel parameters, as for instance in the case of automatic relevance determination (ARD), there is a substantial risk of over-fitting the model selection criterion, resulting in poor generalisation performance. In this paper we investigate the possibility of learning the kernel, for the Least-Squares Support Vector Machine (LS-SVM) classifier, at the first level of inference, i.e. parameter optimisation. The kernel parameters and the coefficients of the kernel expansion are jointly optimised at the first level of inference, minimising a training criterion with an additional regularisation term acting on the kernel parameters. The key advantage of this approach is that the values of only two regularisation parameters need be determined in model selection, substantially alleviating the problem of over-fitting the model selection criterion. The benefits of this approach are demonstrated using a suite of synthetic and real-world binary classification benchmark problems, where kernel learning at the first level of inference is shown to be statistically superior to the conventional approach, improves on our previous work (Cawley and Talbot, 2007) and is competitive with Multiple Kernel Learning approaches, but with reduced computational expense.     

Design of hybrid radial basis function neural networks (HRBFNNs) realized with the aid of hybridization of fuzzy clustering method (FCM) and polynomial neural networks (PNNs)

In this study, we propose Hybrid Radial Basis Function Neural Networks (HRBFNNs) realized with the aid of fuzzy clustering method (Fuzzy C-Means, FCM) and polynomial neural networks. Fuzzy clustering used to form information granulation is employed to overcome a possible curse of dimensionality, while the polynomial neural network is utilized to build local models. Furthermore, genetic algorithm (GA) is exploited here to optimize the essential design parameters of the model (including fuzzification coefficient, the number of input polynomial fuzzy neurons (PFNs), and a collection of the specific subset of input PFNs) of the network. To reduce dimensionality of the input space, principal component analysis (PCA) is considered as a sound preprocessing vehicle. The performance of the HRBFNNs is quantified through a series of experiments, in which we use several modeling benchmarks of different levels of complexity (different number of input variables and the number of available data). A comparative analysis reveals that the proposed HRBFNNs exhibit higher accuracy in comparison to the accuracy produced by some models reported previously in the literature.     

妊娠期糖尿病孕妇产后阴道微生态状况分析

目的探讨妊娠期糖尿病孕妇产后阴道微生态的状况,为孕妇产后恢复阴道微生态提供重要实验依据。方法回顾性分析2018年1-12月在武汉市江汉区妇幼保健院进行体检的128例妊娠期糖尿病孕妇(实验组)与120例健康孕妇(对照组)产后阴道微生态状况,比较两组间阴道微生态形态学(阴道优势菌、阴道菌群密集度、阴道菌群多样性、阴道清洁度、Donders评分、其他病原微生物及Nugent评分等)与功能学(阴道pH值、过氧化氢、凝固酶、β-葡萄糖醛酸苷酶、唾液酸苷酶、白细胞酯酶)的差异变化。结果实验组产后阴道优势菌以革兰阳性球菌(48.44%)和革兰阴性杆菌(34.38%)为主,对照组以革兰阳性杆菌(88.33%)为主,两组间比较差异有统计学意义(P<0.05)。实验组菌群密集度较低,以Ⅰ级和Ⅱ级为主,而对照组密集度则以Ⅲ级和Ⅳ级为主,差异有统计学意义(P<0.05),且两组间菌群构成及多样性也明显不同,差异有统计学意义(P<0.05)。与对照组相比,实验组阴道清洁度较差,白细胞数目明显增多,阴道病原菌感染率为91.41%,以细菌性阴道病及混合感染患者居多,其中有症状者为84.38%,显著高于对照组,差异有统计学意义(P<0.05)。实验组阴道pH值较对照组显著升高,实验组过氧化氢、凝固酶、β-葡萄糖醛酸苷酶、唾液酸苷酶和白细胞酯酶阳性率显著高于对照组,差异有统计学意义(P<0.05)。结论妊娠期糖尿病孕妇产后阴道菌群较健康孕妇有明显异常,阴道微生态失衡,需恢复正常阴道微生态,减少阴道病原菌感染的发生。     

Deep-learning super-resolution light-sheet add-on microscopy (Deep-SLAM) for easy isotropic volumetric imaging of large biological specimens

Isotropic 3D histological imaging of large biological specimens is highly desired but remains highly challenging to current fluorescence microscopy technique. Here we present a new method, termed deep-learning super-resolution light-sheet add-on microscopy (Deep-SLAM), to enable fast, isotropic light-sheet fluorescence imaging on a conventional wide-field microscope. After integrating a minimized add-on device that transforms an inverted microscope into a 3D light-sheet microscope, we further integrate a deep neural network (DNN) procedure to quickly restore the ambiguous z-reconstructed planes that suffer from still insufficient axial resolution of light-sheet illumination, thereby achieving isotropic 3D imaging of thick biological specimens at single-cell resolution. We apply this easy and cost-effective Deep-SLAM approach to the anatomical imaging of single neurons in a meso-scale mouse brain, demonstrating its potential for readily converting commonly-used commercialized 2D microscopes to high-throughput 3D imaging, which is previously exclusive for high-end microscopy implementations.     

Dynamic programming in parallel boundary detection with application to ultrasound intima-media segmentation

Segmentation of carotid artery intima-media in longitudinal ultrasound images for measuring its thickness to predict cardiovascular diseases can be simplified as detecting two nearly parallel boundaries within a certain distance range, when plaque with irregular shapes is not considered. In this paper, we improve the implementation of two dynamic programming (DP) based approaches to parallel boundary detection, dual dynamic programming (DDP) and piecewise linear dual dynamic programming (PL-DDP). Then, a novel DP based approach, dual line detection (DLD), which translates the original 2-D curve position to a 4-D parameter space representing two line segments in a local image segment, is proposed to solve the problem while maintaining efficiency and rotation invariance. To apply the DLD to ultrasound intima-media segmentation, it is imbedded in a framework that employs an edge map obtained from multiplication of the responses of two edge detectors with different scales and a coupled snake model that simultaneously deforms the two contours for maintaining parallelism. The experimental results on synthetic images and carotid arteries of clinical ultrasound images indicate improved performance of the proposed DLD compared to DDP and PL-DDP, with respect to accuracy and efficiency.     

HPV-DNA与TCT联合检测相关性分析

目的分析HPV-DNA、液基薄层细胞学检查(TCT)在宫颈癌检测中的相互作用。方法对从2009年9月到2010年4月检测的537例标本进行HPV-DNA与TCT联合检测。结果 2009年9月至2010年4月检测的537例标本中HPV阳性标本74例,其中TCT异常17例,异常率为23.0%;HPV阴性标本463例,其中TCT异常58例,异常率为12.5%。结论 HPV感染者中TCT异常者较多,感染者需重视TCT检测结果,定期检查以防宫颈病变恶化。     

Gap junctional coupling in the vertebrate retina: Variations on one theme?

Gap junctions connect cells in the bodies of all multicellular organisms, forming either homologous or heterologous (i.e. established between identical or different cell types, respectively) cell-to-cell contacts by utilizing identical (homotypic) or different (heterotypic) connexin protein subunits. Gap junctions in the nervous system serve electrical signaling between neurons, thus they are also called electrical synapses. Such electrical synapses are particularly abundant in the vertebrate retina where they are specialized to form links between neurons as well as glial cells. In this article, we summarize recent findings on retinal cell-to-cell coupling in different vertebrates and identify general features in the light of the evergrowing body of data. In particular, we describe and discuss tracer coupling patterns, connexin proteins, junctional conductances and modulatory processes. This multispecies comparison serves to point out that most features are remarkably conserved across the vertebrate classes, including (i) the cell types connected via electrical synapses; (ii) the connexin makeup and the conductance of each cell-to-cell contact; (iii) the probable function of each gap junction in retinal circuitry; (iv) the fact that gap junctions underlie both electrical and/or tracer coupling between glial cells. These pan-vertebrate features thus demonstrate that retinal gap junctions have changed little during the over 500 million years of vertebrate evolution. Therefore, the fundamental architecture of electrically coupled retinal circuits seems as old as the retina itself, indicating that gap junctions deeply incorporated in retinal wiring from the very beginning of the eye formation of vertebrates. In addition to hard wiring provided by fast synaptic transmitter-releasing neurons and soft wiring contributed by peptidergic, aminergic and purinergic systems, electrical coupling may serve as the ‘skeleton’ of lateral processing, enabling important functions such as signal averaging and synchronization.