Enhancing Human Action Recognition with Adaptive Hybrid Deep Attentive Networks and Archerfish Optimization

In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant attention.Previously developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic features.The images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human actions.Poor lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging task.The unimodal-based HAR approaches are not suitable in a real-time environment.Therefore,an updated HAR model is developed using multiple types of data and an advanced deep-learning approach.Firstly,the required signals and sensor data are accumulated from the standard databases.From these signals,the wave features are retrieved.Then the extracted wave features and sensor data are given as the input to recognize the human activity.An Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition process.Additionally,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition process.An experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR model.The EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,respectively.The result proved that the developed model is effective in recognizing human action by taking less time.Additionally,it reduces the computation complexity and overfitting issue through using an optimization approach.

基于1-D CNN的二阶段OFDM系统定时同步方法

针对存在多径干扰的正交频分复用系统的定时同步准确性低的问题,提出基于一维卷积神经网络(1-D CNN)的二阶段OFDM系统定时同步方法。在第一阶段,利用经典互相关方法实现路径特征初始抽取,捕获可分辨路径上的定时辅助同步点;基于定时辅助同步点构建1-D CNN网络学习第二阶段中的定时偏移;最后,结合两阶段处理,获得系统最终的定时同步偏移估计。相比于基于压缩感知的定时同步方法和基于极限学习机的定时同步方法,所研究的二阶段OFDM系统定时同步方法提高了定时同步准确性,并有效地降低计算复杂度与处理延迟。

Chaotic Neural Network Technique for "0-1" Programming Problems

0-1 programming is a special case of the integer programming, which is commonly encountered in many optimization problems. Neural network and its general energy function are presented for 0-1 optimization problem. Then, the 0-1 optimization problems are solved by a neural network model with transient chaotic dynamics (TCNN). Numerical simulations of two typical 0-1 optimization problems show that TCNN can overcome HNN's main drawbacks that it suffers from the local minimum and can search for the global optimal solutions in to solveing 0-1 optimization problems.

Intelligent method to develop constitutive relationship of Ti-6Al-2Zr-1Mo-1V alloy

The isothermal compression tests were carried out in the Thermecmastor-Z thermo-simulator at temperatures of 800, 850, 900, 950, 1000 and 1050 ℃ and the strain rates of 0.01, 0.1, 1 and 10 s-1. The influence of deformation temperature and strain rate on the flow stress of Ti-6Al-2Zr-IMo-IV alloy was studied. Based on the experimental data sets, the high temperature deformation behavior of Ti-6A1-2Zr-IMo-IV alloy was presented using the intelligent method of artificial neural network （ANN）. The results indicate that the predicted flow stress values by ANN model is quite consistent with the experimental results, which implies that the artificial neural network is an effective tool for studying the hot deformation behavior of the present alloy. In addition, the development of graphical user interface is implemented using Visual Basic programming language.

Estrogen affects neuropathic pain through upregulating N-methyl-D-aspartate acid receptor 1 expression in the dorsal root ganglion of rats

Estrogen affects the generation and transmission of neuropathic pain,but the specific regulatory mechanism is still unclear.Activation of the N-methyl-D-aspartate acid receptor 1（NMDAR1） plays an important role in the production and maintenance of hyperalgesia and allodynia.The present study was conducted to determine whether a relationship exists between estrogen and NMDAR1 in peripheral nerve pain.A chronic sciatic nerve constriction injury model of chronic neuropathic pain was established in rats.These rats were then subcutaneously injected with 17β-estradiol,the NMDAR1 antagonist D（-）-2-amino-5-phosphonopentanoic acid（AP-5）,or both once daily for 15 days.Compared with injured drug na？ve rats,rats with chronic sciatic nerve injury that were administered estradiol showed a lower paw withdrawal mechanical threshold and a shorter paw withdrawal thermal latency,indicating increased sensitivity to mechanical and thermal pain.Estrogen administration was also associated with increased expression of NMDAR1 immunoreactivity（as assessed by immunohistochemistry） and protein（as determined by western blot assay） in spinal dorsal root ganglia.This 17β-estradiol-induced increase in NMDAR1 expression was blocked by co-administration with AP-5,whereas AP-5 alone did not affect NMDAR1 expression.These results suggest that 17β-estradiol administration significantly reduced mechanical and thermal pain thresholds in rats with chronic constriction of the sciatic nerve,and that the mechanism for this increased sensitivity may be related to the upregulation of NMDAR1 expression in dorsal root ganglia.

A New Searching Strategy for the Lost Plane Based on RBF Neural Network Model and Global Optimization Model

In this paper, we construct two models for the searching task for a lost plane. Model 1 determines the searching area. We predict the trajectory of floats generated after the disintegration of the plane by using RBF neural network model, and then determine the searching area according to the trajectory. With the pass of time, the searching area will also be constantly moving along the trajectory. Model 2 develops a maritime search plan to achieve the purpose of completing the search in the shortest time. We optimize the searching time and transform the problem into the 0-1 knapsack problem. Solving this problem by improved genetic algorithm, we can get the shortest searching time and the best choice for the search power.

From masses and radii of neutron stars to EOS of nuclear matter through neural network

The equation of state(EOS)of dense nuclear matter is a key factor for determining the internal structure and properties of neutron stars.However,the EOS of high-density nuclear matter has great uncertainty,mainly because terrestrial nuclear experiments cannot reproduce matter as dense as that in the inner core of a neutron star.Fortunately,continuous improvements in astronomical observations of neutron stars provide the opportunity to inversely constrain the EOS of high-density nuclear matter.Several methods have been proposed to implement this inverse constraint,including the Bayesian analysis algorithm,the Lindblom’s approach,and so on.Neural network algorithm is an effective method developed in recent years.By employing a set of isospin-dependent parametric EOSs as the training sample of a neural network algorithm,we set up an effective way to reconstruct the EOS with relative accuracy using a few mass-radius data.Based on the obtained neural network algorithms and according to the NICER observations on masses and radii of neutron stars with assumed precision,we obtain the inversely constrained EOS and further calculate the corresponding macroscopic properties of the neutron star.The results are basically consistent with the constraint on EOS in Huth et al.[Nature 606,276(2022)]based on Bayesian analysis.Moreover,the results show that even though the neural network algorithm was obtained using the finite parameterized EOS as the training set,it is valid for any rational parameter combination of the parameterized EOS model.

轻量级(2+1)D卷积结构的动态手势识别研究

目前,基于卷积神经网络的动态手势识别方法取得了巨大的进展,但神经网络模型具有很大的参数量,计算成本和内存占用较大,很难应用在设备资源有限的场合.以减少计算量和参数量为出发点,提出了一种轻量级(2+1)D卷积结构.该结构在(2+1)D卷积结构的基础上,将其中的3D卷积替换为3D深度可分离卷积,在输出向量维度不变的前提下,进一步减少了(2+1)D卷积结构的计算量和参数量.为了弥补时空特征在表征动态手势上的不足,融合注意力机制模块,专注于对运动特征的提取,结合轻量级(2+1)D卷积结构提取的时空特征,可以更好地表征手势动作.实验结果表明,注意力机制模块的插入,在不增加太多额外计算和空间成本的前提下,进一步提高了模型的识别精度.基于以上结构构建的模型,在20BN-jester、EgoGesture和IsoGD数据集上分别取得了96.62%、91.83%和60.1%的识别精度,模型参数量和浮点计算量分别为5.05M和12.81GFLOPs,相比于其他手势识别模型,计算成本和内存占用大大减少,实时手势识别速度达到每秒70帧.

W^(1,2)(Ω)-and X^(1,2)(Ω)-stability of reactiondiffusion cellular neural networks with delay

With Poincare＇s inequality and auxiliary function applied in a class of retarded cellular neural networks with reaction-diffusion, the conditions of the systems＇ W^1,2（Ω）-exponential and X^1,2（Ω）-asmptotic stability are obtained. The stability conditions containing diffusion term are different from those obtained in the previous papers in their exponential stability conditions. One example is given to illustrate the feasibility of this method in the end.

Audiovisual speech recognition based on a deep convolutional neural network

Audiovisual speech recognition is an emerging research topic.Lipreading is the recognition of what someone is saying using visual information,primarily lip movements.In this study,we created a custom dataset for Indian English linguistics and categorized it into three main categories:(1)audio recognition,(2)visual feature extraction,and(3)combined audio and visual recognition.Audio features were extracted using the mel-frequency cepstral coefficient,and classification was performed using a one-dimension convolutional neural network.Visual feature extraction uses Dlib and then classifies visual speech using a long short-term memory type of recurrent neural networks.Finally,integration was performed using a deep convolutional network.The audio speech of Indian English was successfully recognized with accuracies of 93.67%and 91.53%,respectively,using testing data from 200 epochs.The training accuracy for visual speech recognition using the Indian English dataset was 77.48%and the test accuracy was 76.19%using 60 epochs.After integration,the accuracies of audiovisual speech recognition using the Indian English dataset for training and testing were 94.67%and 91.75%,respectively.

Automatic Classification of Swedish Metadata Using Dewey Decimal Classification:A Comparison of Approaches

Purpose:With more and more digital collections of various information resources becoming available,also increasing is the challenge of assigning subject index terms and classes from quality knowledge organization systems.While the ultimate purpose is to understand the value of automatically produced Dewey Decimal Classification(DDC)classes for Swedish digital collections,the paper aims to evaluate the performance of six machine learning algorithms as well as a string-matching algorithm based on characteristics of DDC.Design/methodology/approach:State-of-the-art machine learning algorithms require at least 1,000 training examples per class.The complete data set at the time of research involved 143,838 records which had to be reduced to top three hierarchical levels of DDC in order to provide sufficient training data(totaling 802 classes in the training and testing sample,out of 14,413 classes at all levels).Findings:Evaluation shows that Support Vector Machine with linear kernel outperforms other machine learning algorithms as well as the string-matching algorithm on average;the string-matching algorithm outperforms machine learning for specific classes when characteristics of DDC are most suitable for the task.Word embeddings combined with different types of neural networks(simple linear network,standard neural network,1 D convolutional neural network,and recurrent neural network)produced worse results than Support Vector Machine,but reach close results,with the benefit of a smaller representation size.Impact of features in machine learning shows that using keywords or combining titles and keywords gives better results than using only titles as input.Stemming only marginally improves the results.Removed stop-words reduced accuracy in most cases,while removing less frequent words increased it marginally.The greatest impact is produced by the number of training examples:81.90%accuracy on the training set is achieved when at least 1,000 records per class are available in the training set,and 66.13%when too few records(often less than A Comparison of Approaches100 per class)on which to train are available—and these hold only for top 3 hierarchical levels(803 instead of 14,413 classes).Research limitations:Having to reduce the number of hierarchical levels to top three levels of DDC because of the lack of training data for all classes,skews the results so that they work in experimental conditions but barely for end users in operational retrieval systems.Practical implications:In conclusion,for operative information retrieval systems applying purely automatic DDC does not work,either using machine learning(because of the lack of training data for the large number of DDC classes)or using string-matching algorithm(because DDC characteristics perform well for automatic classification only in a small number of classes).Over time,more training examples may become available,and DDC may be enriched with synonyms in order to enhance accuracy of automatic classification which may also benefit information retrieval performance based on DDC.In order for quality information services to reach the objective of highest possible precision and recall,automatic classification should never be implemented on its own;instead,machine-aided indexing that combines the efficiency of automatic suggestions with quality of human decisions at the final stage should be the way for the future.Originality/value:The study explored machine learning on a large classification system of over 14,000 classes which is used in operational information retrieval systems.Due to lack of sufficient training data across the entire set of classes,an approach complementing machine learning,that of string matching,was applied.This combination should be explored further since it provides the potential for real-life applications with large target classification systems.

Synthesis,structure and dielectric properties of a novel Gd coordination polymer based on 2-(pyridin-4-yl)-1H-imidazole-4,5-dicarboxylate

A new Gd coordination polymer based on 2-（pyridin-4-yl）-I H-imidazole-4,5-dicarboxylate （H3PIDC） has been synthesized under hydrothermal conditions, formulated as {[Gd3（HPIDC）3（PIDC）（H2O）4].3H2O}n （1）. The compound crystallizes in the monoclinic system, space group C2/c with a=20.951（7）, b = 9.515（3）, c = 27.483（10） A,β= 106.176（6）°, Z = 4, V= 5262（3） A3, C40 H45 Gd3 N12 O30, Dc = 2.071 g/cm3, Mr=1645.63, λ （MoKa）=0.71073A, μ=3.846mm-1, F（000）=3204, the final R=0.0390 and wR= 0.1332. Complex 1 is a two-dimensional MOF built up from T-shaped 3-connected HPIDC2 , PIDC3 and 4-connected metal nodes. Dielectric constant of complex 1 was measured at different frequencies with temperature variation.

基于线性内插神经网络的雷达目标一维距离像识别

本文提出一种新颖的神经网络模型——线性内插神经网络(Linear InterpolationNeural Network,LINN)用于雷达目标一维距离像识别。它可避开提取不变特征的难点,利用目标一维距离像特征随姿态变化的信息来提高目标识别性能。实验结果表明,采用LINN很好地解决了在大的姿态角范围内识别目标时所存在的计算量与识别率的矛盾,提高了雷达对任意姿态目标的识别性能。

基于数据挖掘、网络药理学和分子对接的中药治疗牙周疾病的用药规律与作用机制

目的 通过数据挖掘、网络药理学和分子对接探讨中药复方治疗牙周疾病的用药规律及其作用机制。方法 首先,数据挖掘搜索治疗牙周疾病的单味药材,并筛选活性成分及其作用靶点。然后,利用疾病靶点数据库下载牙周疾病发病机制相关的靶点,与中药复方的作用靶点去映射,获取被认为中药复方治疗牙周疾病的潜在靶点,并对潜在靶点进行基因本体功能和信号通路分析。潜在靶点再通过筛选获取治疗牙周疾病的关键靶点。最后,将活性成分与关键靶点进行分子对接。结果 治疗牙周疾病的中药复方中熟地黄、牡丹皮、当归、茯苓、金银花、山药、知母等药材的出现频率最高,筛选得到43个活性成分及其118个作用靶点,并与856个疾病靶点进行交集得到52个潜在靶点。潜在靶点可能参与的分子功能和生物学过程主要集中在维生素D生物合成过程和对RNA聚合酶Ⅱ调控,并涉及96条信号通路。52个潜在靶点通过网络拓扑参数分析,得到11个关键靶点。分子对接结果表明,活性成分与α-丝氨酸/苏氨酸蛋白激酶(RAC-alpha serine/threonine-protein kinase,AKT1)、细胞肿瘤抗原p53(cellular tumor antigen p53,TP53)和丝裂原活化蛋白激酶-1(mitogen-activated protein kinase-1,MAPK-1)等关键靶点具有较好的结合活性。结论 中药复方可能通过抑制牙槽骨吸收、抗菌、抗炎和促进组织修复功能,从而发挥治疗牙周疾病的作用,为中药复方的有效治疗牙周疾病提供更加科学性的参考。

树形级联SOM网络用于雷达目标一维距离像识别

在雷达目标识别中，由于雷达目标一维像特征提取容易，而且具有较好的识别效果，因此近来逐渐得到应用．但由于它是以散射点分布模型为依据的，对姿态变化非常敏感，为了提高对姿态变化范围较大的目标一维距离像的识别能力，在本文中，我们基于子波变换的多分辨分析理论及树形分层理论，提出一种级联SOM网络结构用于高分辨一维距离像的识别，并获得了令人满意的结果．

一维细胞神经网络的完全稳定性分析

运用Lyapunov函数方法,讨论了一维细胞神经网络模型的完全稳定性问题,给出了四组使模型具有完全稳定的充分条件。

基于SANC和一维卷积神经网络的齿轮箱轴承故障诊断

近来以深度学习算法为代表的滚动轴承特征智能提取和故障辨识技术被广泛研究,但目前研究大多局限于无强干扰的轴承故障。在齿轮箱存在较强齿轮振动干扰条件下,基于此类算法的轴承故障辨识率将显著降低。为提高在较强齿轮振动信号干扰下齿轮箱轴承故障智能辨识的准确率,提出了一种基于自参考自适应噪声消除技术(SANC)和一维卷积神经网络(1D-CNN)的齿轮箱轴承故障诊断方法。首先利用SANC将齿轮箱振动信号分离为周期性信号分量成分和随机信号分量,抑制齿轮等周期强干扰成分,再通过1D-CNN对包含轴承故障特征的随机信号成分进行智能特征提取和识别,实现在齿轮振动干扰下齿轮箱轴承故障辨识率的提高。通过与不同方法的对比验证了本文所提方法的优势和有效性。

(2+1)D多时空信息融合模型及在行为识别的应用

针对常规的卷积神经网络时空感受野尺度单一,难以提取视频中多变的时空信息的问题,利用(2+1)D模型将时间信息和空间信息在一定程度上解耦的特性,提出了(2+1)D多时空信息融合的卷积残差神经网络,并用于人体行为识别.该模型以3×3空间感受野为主,1×1空间感受野为辅,与3种不同时域感受野交叉组合构建了6种不同尺度的时空感受野.提出的多时空感受野融合模型能够同时获取不同尺度的时空信息,提取更丰富的人体行为特征,因此能够更有效识别不同时间周期、不同动作幅度的人体行为.另外提出了一种视频时序扩充方法,该方法能够同时在空间信息和时间序列扩充视频数据集,丰富训练样本.提出的方法在公共视频人体行为数据集UCF101和HMDB51上子视频的识别率超过或接近最新的视频行为识别方法.

Convergence of neutral type proportional-delayed HCNNs with D operators

This paper is concerned with neutral type high-order cellular neural networks(HCNNs)involving proportional delays and D operators.Some criteria are established for the global exponential convergence of the addressed models by using differential inequality techniques.Moreover,an example and its numerical simulations are employed to illustrate the main results.

A NEW ALGORITHM FOR PURX O-1 LINEAR PROGRAMS WITH INEQUALITY CONSTRAINTS

ＡＮＥＷＡＬＧＯＲＩＴＨＭＦＯＲＰＵＲＸＯ－１ＬＩＮＥＡＲＰＲＯＧＲＡＭＳＷＩＴＨＩＮＥＱＵＡＬＩＴＹＣＯＮＳＴＲＡＩＮＴＳ￥ＣＨＥＮＪｉａｎｆｅｉ（ＢｉｏｃｈｅｍｉｃａｌＥｎｇｉｎｅｅｒｉｎｇＳｔａｔｅＫｅｙＬａｂｏｒａｔｏｒｙ，Ｂｅｉｊｉｎｇ１０...