Anti-Disturbance of Scale-Free Spiking Neural Network against Impulse Noise.

The bio-brain presents robustness function to external stimulus through its self-adaptive regulation and neural information processing. Drawing from the advantages of the bio-brain to investigate the robustness function of a spiking neural network (SNN) is conducive to the advance of brain-like intelligence. However, the current brain-like model is insufficient in biological rationality. In addition, its evaluation method for anti-disturbance performance is inadequate. To explore the self-adaptive regulation performance of a brain-like model with more biological rationality under external noise, a scale-free spiking neural network(SFSNN) is constructed in this study. Then, the anti-disturbance ability of the SFSNN against impulse noise is investigated, and the anti-disturbance mechanism is further discussed. Our simulation results indicate that: (i) our SFSNN has anti-disturbance ability against impulse noise, and the high-clustering SFSNN outperforms the low-clustering SFSNN in terms of anti-disturbance performance. (ii) The neural information processing in the SFSNN under external noise is clarified, which is a dynamic chain effect of the neuron firing, the synaptic weight, and the topological characteristic. (iii) Our discussion hints that an intrinsic factor of the anti-disturbance ability is the synaptic plasticity, and the network topology is a factor that affects the anti-disturbance ability at the level of performance.

OPP-Miner: Order-Preserving Sequential Pattern Mining for Time Series.

Traditional sequential pattern mining methods were designed for symbolic sequence. As a collection of measurements in chronological order, a time series needs to be discretized into symbolic sequences, and then users can apply sequential pattern mining methods to discover interesting patterns in time series. The discretization will not only cause the loss of some important information, which partially destroys the continuity of time series, but also ignore the order relations between time-series values. Inspired by order-preserving matching, this article explores a new method called order-preserving sequential pattern (OPP) mining, which does not need to discretize time series into symbolic sequences and represents patterns based on the order relations of time series. An inherent advantage of such representation is that the trend of a time series can be represented by the relative order of the values underneath time series. We propose an OPP-Miner algorithm to mine frequent patterns in time series with the same relative order. OPP-Miner employs the filtration and verification strategies to calculate the support and uses the pattern fusion strategy to generate candidate patterns. To compress the result set, we also study to find the maximal OPPs. Experimental results validate that OPP-Miner is not only efficient but can also discover similar subsequences in time series. In addition, case studies show that our algorithms have high utility in analyzing the COVID-19 epidemic by identifying critical trends and improve the clustering performance. The algorithms and data can be downloaded from https://github.com/wuc567/Pattern-Mining/tree/master/OPP-Miner.

Complex spiking neural networks with synaptic time-delay based on anti-interference function.

The research on a brain-like model with bio-interpretability is conductive to promoting its information processing ability in the field of artificial intelligence. Biological results show that the synaptic time-delay can improve the information processing abilities of the nervous system, which are an important factor related to the formation of brain cognitive functions. However, the synaptic plasticity with time-delay of a brain-like model still lacks bio-interpretability. In this study, combining excitatory and inhibitory synapses, we construct the complex spiking neural networks (CSNNs) with synaptic time-delay that more conforms biological characteristics, in which the topology has scale-free property and small-world property, and the nodes are represented by an Izhikevich neuron model. Then, the information processing abilities of CSNNs with different types of synaptic time-delay are comparatively evaluated based on the anti-interference function, and the mechanism of this function is discussed. Using two indicators of the anti-interference function and three kinds of noise, our simulation results consistently verify that: (i) From the perspective of anti-interference function, an CSNN with synaptic random time-delay outperforms an CSNN with synaptic fixed time-delay, which in turn outperforms an CSNN with synaptic none time-delay. The results imply that brain-like networks with more bio-interpretable synaptic time-delay have stronger information processing abilities. (ii) The synaptic plasticity is the intrinsic factor of the anti-interference function of CSNNs with different types of synaptic time-delay. (iii) The synaptic random time-delay makes an CSNN present better topological characteristics, which can improve the information processing ability of a brain-like network. It implies that synaptic time-delay is a factor that affects the anti-interference function at the level of performance.

NetNMSP: Nonoverlapping maximal sequential pattern mining.

Nonoverlapping sequential pattern mining, as a kind of repetitive sequential pattern mining with gap constraints, can find more valuable patterns. Traditional algorithms focused on finding all frequent patterns and found lots of redundant short patterns. However, it not only reduces the mining efficiency, but also increases the difficulty in obtaining the demand information. To reduce the frequent patterns and retain its expression ability, this paper focuses on the Nonoverlapping Maximal Sequential Pattern (NMSP) mining which refers to finding frequent patterns whose super-patterns are infrequent. In this paper, we propose an effective mining algorithm, Nettree for NMSP mining (NetNMSP), which has three key steps: calculating the support, generating the candidate patterns, and determining NMSPs. To efficiently calculate the support, NetNMSP employs the backtracking strategy to obtain a nonoverlapping occurrence from the leftmost leaf to its root with the leftmost parent node method in a Nettree. To reduce the candidate patterns, NetNMSP generates candidate patterns by the pattern join strategy. Furthermore, to determine NMSPs, NetNMSP adopts the screening method. Experiments on biological sequence datasets verify that not only does NetNMSP outperform the state-of-the-arts algorithms, but also NMSP mining has better compression performance than closed pattern mining. On sales datasets, we validate that our algorithm guarantees the best scalability on large scale datasets. Moreover, we mine NMSPs and frequent patterns in SARS-CoV-1, SARS-CoV-2 and MERS-CoV. The results show that the three viruses are similar in the short patterns but different in the long patterns. More importantly, NMSP mining is easier to find the differences between the virus sequences.

Top-k Self-Adaptive Contrast Sequential Pattern Mining.

For sequence classification, an important issue is to find discriminative features, where sequential pattern mining (SPM) is often used to find frequent patterns from sequences as features. To improve classification accuracy and pattern interpretability, contrast pattern mining emerges to discover patterns with high-contrast rates between different categories. To date, existing contrast SPM methods face many challenges, including excessive parameter selection and inefficient occurrences counting. To tackle these issues, this article proposes a top- k self-adaptive contrast SPM, which adaptively adjusts the gap constraints to find top- k self-adaptive contrast patterns (SCPs) from positive and negative sequences. One of the key tasks of the mining problem is to calculate the support (the number of occurrences) of a pattern in each sequence. To support efficient counting, we store all occurrences of a pattern in a special array in a Nettree, an extended tree structure with multiple roots and multiple parents. We employ the array to calculate the occurrences of all its superpatterns with one-way scanning to avoid redundant calculation. Meanwhile, because the contrast SPM problem does not satisfy the Apriori property, we propose Zero and Less strategies to prune candidate patterns and a Contrast-first mining strategy to select patterns with the highest contrast rate as the prefix subpattern and calculate the contrast rate of all its superpatterns. Experiments validate the efficiency of the proposed algorithm and show that contrast patterns significantly outperform frequent patterns for sequence classification. The algorithms and datasets can be downloaded from https://github.com/wuc567/Pattern-Mining/tree/master/SCP-Miner.

Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks.

Constant monitoring of road surfaces helps to show the urgency of deterioration or problems in the road construction and to improve the safety level of the road surface. Conditional generative adversarial networks (cGAN) are a powerful tool to generate or transform the images used for crack detection. The advantage of this method is the highly accurate results in vector-based images, which are convenient for mathematical analysis of the detected cracks at a later time. However, images taken under established parameters are different from images in real-world contexts. Another potential problem of cGAN is that it is difficult to detect the shape of an object when the resulting accuracy is low, which can seriously affect any further mathematical analysis of the detected crack. To tackle this issue, this paper proposes a method called improved cGAN with attention gate (ICGA) for roadway surface crack detection. To obtain a more accurate shape of the detected target object, ICGA establishes a multi-level model with independent stages. In the first stage, everything except the road is treated as noise and removed from the image. These images are stored in a new dataset. In the second stage, ICGA determines the cracks. Therefore, ICGA focuses on the redistribution of cracks, not the auxiliary elements in the image. ICGA adds two attention gates to a U-net architecture and improves the segmentation capacities of the generator in pix2pix. Extensive experimental results on dashboard camera images of the Unsupervised Llamas dataset show that our method has better performance than other state-of-the-art methods.

Noise suppression ability and its mechanism analysis of scale-free spiking neural network under white Gaussian noise.

With the continuous improvement of automation and informatization, the electromagnetic environment has become increasingly complex. Traditional protection methods for electronic systems are facing with serious challenges. Biological nervous system has the self-adaptive advantages under the regulation of the nervous system. It is necessary to explore a new thought on electromagnetic protection by drawing from the self-adaptive advantage of the biological nervous system. In this study, the scale-free spiking neural network (SFSNN) is constructed, in which the Izhikevich neuron model is employed as a node, and the synaptic plasticity model including excitatory and inhibitory synapses is employed as an edge. Under white Gaussian noise, the noise suppression abilities of the SFSNNs with the high average clustering coefficient (ACC) and the SFSNNs with the low ACC are studied comparatively. The noise suppression mechanism of the SFSNN is explored. The experiment results demonstrate that the following. (1) The SFSNN has a certain degree of noise suppression ability, and the SFSNNs with the high ACC have higher noise suppression performance than the SFSNNs with the low ACC. (2) The neural information processing of the SFSNN is the linkage effect of dynamic changes in neuron firing, synaptic weight and topological characteristics. (3) The synaptic plasticity is the intrinsic factor of the noise suppression ability of the SFSNN.

NetNCSP: Nonoverlapping closed sequential pattern mining.

Sequential pattern mining (SPM) has been applied in many fields. However, traditional SPM neglects the pattern repetition in sequence. To solve this problem, gap constraint SPM was proposed and can avoid finding too many useless patterns. Nonoverlapping SPM, as a branch of gap constraint SPM, means that any two occurrences cannot use the same sequence letter in the same position as the occurrences. Nonoverlapping SPM can make a balance between efficiency and completeness. The frequent patterns discovered by existing methods normally contain redundant patterns. To reduce redundant patterns and improve the mining performance, this paper adopts the closed pattern mining strategy and proposes a complete algorithm, named Nettree for Nonoverlapping Closed Sequential Pattern (NetNCSP) based on the Nettree structure. NetNCSP is equipped with two key steps, support calculation and closeness determination. A backtracking strategy is employed to calculate the nonoverlapping support of a pattern on the corresponding Nettree, which reduces the time complexity. This paper also proposes three kinds of pruning strategies, inheriting, predicting, and determining. These pruning strategies are able to find the redundant patterns effectively since the strategies can predict the frequency and closeness of the patterns before the generation of the candidate patterns. Experimental results show that NetNCSP is not only more efficient but can also discover more closed patterns with good compressibility. Furtherly, in biological experiments NetNCSP mines the closed patterns in SARS-CoV-2 and SARS viruses. The results show that the two viruses are of similar pattern composition with different combinations.

Orientin protects myocardial cells against hypoxia-reoxygenation injury through induction of autophagy.

Orientin, a flavonoid exists in Chinese traditional herbal Polygonum orientale L., has been previously demonstrated to protect against myocardial ischemia reperfusion injury (MIRI) through inhibition of apoptosis. However, the underlying mechanisms remain to be elucidated and we therefore in this study investigated the effects of orientin on autophagy during MIRI in rats. The results indicate that orientin, at the concentrations of 10 and 30 µM in the cultures of neonatal rat cardiomyocytes, promoted the induction of autophagy, increasing the formation of autophagosomes and enhancing the expression of LC3 puncta, LC3-II/LC3-I ratio and Beclin 1 after hypoxia/reoxygenation. The induction of autophagy by orientin correlated with enhanced cell viability and decreased apoptosis, which was significantly attenuated by autophagy inhibitor wortmannin, a phosphatidylinositol-3-kinase (PI3K) inhibitor. Moreover, application of orientin increased the activation of AMPK and Akt, downregulated the phosphorylation of mammalian target of rapamycin (mTOR) and the expression of Raptor, and enhanced the interaction between Beclin 1 and Bcl-2 in endoplasmic reticulum due to increased phosphorylation of Beclin 1 and decreased phosphorylation of Bcl-2. Our investigation suggests that the cardioprotective effects of orientin during MIRI may be mediated through the balance of autophagy through regulating AMPK, Akt, mTOR, and Bcl-2 associated signaling pathways.

The prevalence of canine Leishmania infantum infection in Sichuan Province, southwestern China detected by real time PCR.

BACKGROUND: Visceral leishmaniasis (VL) is endemic in western China, and becoming an important public health concern. Infected dogs are the main reservoir for Leishmania infantum, and a potential sentinel for human VL in endemic areas. In the present study we investigated the prevalence of Leishmania DNA in dogs from Wenchuan, Heishui and Jiuzhaigou County in Sichuan Province, southwestern China, which are important endemic areas of zoonotic VL, detected by real time PCR. The results will help to design control strategies against visceral leishmaniasis in dogs and humans. RESULTS: The overall prevalence of Leishmania DNA in dogs was 24.8% (78/314) in Sichuan Province, with the positive rate of 23.5% (23/98) in Wenchuan County, 28.2% (20/71) in Heishui County, and 24.1% (35/145) in Jiuzhaigou County, and no significant difference was observed among the three counties (P > 0.05). The dogs were further allocated to different groups based on sexes, ages and external clinical symptoms. The logistic regression analysis revealed that a higher prevalence was found in older and external symptomatic dogs, compared to that of younger and asymptomatic dogs (P < 0.05). CONCLUSIONS: The results revealed that L. infantum infection in dogs is widespread in Sichuan Province, southwestern China, which has a public health significance, due to its contribution to the transmission of the infection to humans by sandflies. It is necessary to take measures, including treatment or eradication of infected dogs, to control canine leishmaniasis, which could be helpful to reduce human VL in this area.

Research on the segmentation of MRI image based on multi-classification support vector machine.

In head MRI image, the boundary of each encephalic tissue is highly complicated and irregular. It is a real challenge to traditional segmentation algorithms. As a new kind of machine learning, Support Vector Machine (SVM) based on Statistical Learning Theory (SLT) has high generalization ability, especially for dataset with small number of samples in high dimensional space. SVM was originally developed for two-class classification. It is extended to solve multi-class classification problem. In this paper, 57 dimensional feature vectors for MRI image are selected as input for SVM. The segmentation of MRI image based on the Multi-Classification SVM (MCSVM) is investigated. As our experiment demonstrates, the boundaries of 7 kinds of encephalic tissues are extracted successfully, and it can reach satisfactory generalization accuracy. Thus, SVM exhibits its great potential in image segmentation.

Research on 3D modeling for head MRI image based on immune sphere-shaped support vector machine.

In head MRI image sequences, the boundary of each encephalic tissue is highly complicated and irregular. It is a real challenge to traditional 3D modeling algorithms. Support Vector Machine (SVM) based on statistical learning theory has solid theoretical foundation. Sphere-Shaped SVM (SSSVM) was originally developed for solving some special classification problems. In this paper, it is extended to image 3D modeling which tries to find the smallest hypersphere enclosing target data in high dimensional space by kernel function. However, selecting parameter is a complicated problem which directly affects modeling accuracy. Immune Algorithm (IA), mainly applied to optimization, is used to search optimal parameter for SSSVM. So, Immune SSSVM (ISSSVM) is proposed to construct the 3D models for encephalic tissues. As our experiment demonstrates, the models are constructed and reach satisfactory modeling accuracies. Theory and experiment indicate ISSSVM exhibits its great potential in image 3D modeling.

Tissue conductivity estimation in two-dimension head model based on support vector machine.

Estimating head tissue conductivity for each layer is a high dimensional, non-linear and ill-posed problem which is part of Electrical Impedance Tomography (EIT) inverse problem. Traditional methods have many difficulties in resolving this problem. Support Vector Machine (SVM) based on Statistical Learning Theory (SLT) is a new kind of learning method including Support Vector Classification (SVC) and Support Vector Regression (SVR). A new method using SVR is proposed to solve the problem in multi-input and multi-output system named Multi-SVM (MSVM). Tissue conductivity for each layer in 2-D head model is estimated effectively by MSVM. Compared with wavelet neural network method, MSVM not only obtains higher accuracy of learning, it also has greater generalization ability and faster computing speed as our experiment demonstrates.

Adaptive template filtering method for MRI.

Denoising is an important step for image processing. One of the most important characteristics of MRI (MRI) is the complicated changes of gray level. For MRI, preservation of useful information is more important than simple improvement of Signal-Noise Ratio (SNR). Traditional filtering algorithms are not fit for MRI. Adaptive Template Filtering Method (ATFM) can dynamically match the best template from the predetermined multi templates based on local texture characteristics for each pixel. In this paper, detail algorithm and analysis are given. Compared with other filtering methods, the performance of ATFM is better than that of other filtering methods as our experiment demonstrates. It can both effectively suppresses noise and best preserve useful information at the same time for MRI. Thus, ATFM can meet the need of clinical diagnosis and image processing.

Combining nonlinear dimensionality reduction with wavelet network to solve EEG inverse problem.

An integrated multi-method system to analyze the neuroelectric source parameters of electroencephalography (EEG) signal is presented. In order to handle the large-scale high dimension data efficiently and provide a real-time localizer in EEG inverse problem, an improved isometric mapping algorithm is used to find the low dimensional manifolds from high dimensional recorded EEG. Then, based on reduced dimension data, a single-scaling radial-basis wavelet network module is employed to determine the parameters of different type of EEG source models. In our simulation experiments, satisfactory results are obtained.

Threshold optimization of adaptive template filtering for MRI based on intelligent optimization algorithm.

Intelligent Optimization Algorithm (IOA) mainly includes Immune Algorithm (IA) and Genetic Algorithm (GA). One of the most important characteristics of MRI is the complicated changes of gray level. Traditional filtering algorithms are not fit for MRI. Adaptive Template Filtering Method (ATFM) is an appropriate denoising method for MRI. However, selecting threshold for ATFM is a complicated problem which directly affects the denoising result. Threshold selection has been based on experience. Thus, it was lack of solid theoretical foundation. In this paper, 2 kinds of IOA are proposed for threshold optimization respectively. As our experiment demonstrates, they can effectively solve the problem of threshold selection and perfect ATFM. Through algorithm analysis, the performance of IA surpasses the performance of GA. As a new kind of IOA, IA exhibits its great potential in image processing.

SVM for Solving Forward Problems of EIT.

Support Vector Machine (SVM) can be seen as a new machine learning way which is based on the idea of VC dimensions and the principle of structural risk minimization rather than empirical risk minimization. SVM can be used for classification and regression. Support Vector Regression (SVR) is a very important branch of Support Vector Machine. Partial Differential Equations (PDEs) have been successfully treated by using SVR in previous works. The forward problems of EIT are the basis of EIT inverse problems. The forward problem's essence is to solve PDEs. The method has been successfully tested on the forward problems of EIT and has yielded accurate results.

Research on Medical Diagnosis Decision Support System for Acid-base Disturbance Based on Support Vector Machine.

Support Vector Machine (SVM) is a new learning technique based on Statistical Learning Theory (SLT). In this paper, a Medical Diagnosis Decision System (MDDSS) based on SVM has been established to intellectively diagnose 4 types of acid-base disturbance. SVM was originally developed for two-class classification. It is extended to solve multi-class classification problem named hierarchical SVM with clustering algorithm based on stepwise decomposition. Compared with other classical classification techniques, SVM not only has more solid theoretical foundation, it also has greater generalization ability as our experiment demonstrates. Thus, SVM exhibits its great potential in MDDSS.