Intelligent Network-Connected New Energy Vehicle Technology and Application Under the Dual-Carbon Strategy

In responding to the“dual carbon”strategy,intelligent networked new energy vehicle technology plays a crucial role.This type of vehicle combines the advantages of new energy technology and intelligent network technology,effectively reduces carbon emissions in the transportation sector,improves energy utilization efficiency,and contributes to the green transportation system through intelligent transportation management and collaborative work between vehicles,making significant contributions.This article aims to explore the development of intelligent network-connected new energy vehicle technology and applications under the dual-carbon strategy and lay the foundation for the future development direction of the automotive industry.

MSADCN:Multi-Scale Attentional Densely Connected Network for Automated Bone Age Assessment

Bone age assessment(BAA)helps doctors determine how a child’s bones grow and develop in clinical medicine.Traditional BAA methods rely on clinician expertise,leading to time-consuming predictions and inaccurate results.Most deep learning-based BAA methods feed the extracted critical points of images into the network by providing additional annotations.This operation is costly and subjective.To address these problems,we propose a multi-scale attentional densely connected network(MSADCN)in this paper.MSADCN constructs a multi-scale dense connectivity mechanism,which can avoid overfitting,obtain the local features effectively and prevent gradient vanishing even in limited training data.First,MSADCN designs multi-scale structures in the densely connected network to extract fine-grained features at different scales.Then,coordinate attention is embedded to focus on critical features and automatically locate the regions of interest(ROI)without additional annotation.In addition,to improve the model’s generalization,transfer learning is applied to train the proposed MSADCN on the public dataset IMDB-WIKI,and the obtained pre-trained weights are loaded onto the Radiological Society of North America(RSNA)dataset.Finally,label distribution learning(LDL)and expectation regression techniques are introduced into our model to exploit the correlation between hand bone images of different ages,which can obtain stable age estimates.Extensive experiments confirm that our model can converge more efficiently and obtain a mean absolute error(MAE)of 4.64 months,outperforming some state-of-the-art BAA methods.

Minimizing Maximum Risk for Fair Network Connection with Interval Data

In this paper we introduce a minimax model for network connection problems with interval parameters. We consider how to connect given nodes in a network with a path or a spanning tree under a given budget, where each link is associated with an interval and can be established at a cost of any value in the interval. The quality of an individual link （or the risk of link failure, etc.） depends on its construction cost and associated interval. To achieve fairness of the network connection, our model aims at the minimization of the maximum risk over all links used. We propose two algorithms that find optimal paths and spanning trees in polynomial time, respectively. The polynomial solvability indicates salient difference between our minimax model and the model of robust deviation criterion for network connection with interval data, which gives rise to NP-hard optimization problems.

Artificial neural network-based subgrid-scale models for LES of compressible turbulent channel flow

Fully connected neural networks(FCNNs)have been developed for the closure of subgrid-scale(SGS)stress and SGS heat flux in large-eddy simulations of compressible turbulent channel flow.The FCNNbased SGS model trained using data with Mach number Ma=3.0 and Reynolds number Re=3000 was applied to situations with different Mach numbers and Reynolds numbers.The input variables of the neural network model were the filtered velocity gradients and temperature gradients at a single spatial grid point.The a priori test showed that the FCNN model had a correlation coefficient larger than 0.91 and a relative error smaller than 0.43,with much better reconstructions of SGS unclosed terms than the dynamic Smagorinsky model(DSM).In a posteriori test,the behavior of the FCNN model was marginally better than that of the DSM in predicting the mean velocity profiles,mean temperature profiles,turbulent intensities,total Reynolds stress,total Reynolds heat flux,and mean SGS flux of kinetic energy,and outperformed the Smagorinsky model.

Attention-based neural network for end-to-end music separation

The end-to-end separation algorithm with superior performance in the field of speech separation has not been effectively used in music separation.Moreover,since music signals are often dual channel data with a high sampling rate,how to model longsequence data and make rational use of the relevant information between channels is also an urgent problem to be solved.In order to solve the above problems,the performance of the end-to-end music separation algorithm is enhanced by improving the network structure.Our main contributions include the following:(1)A more reasonable densely connected U-Net is designed to capture the long-term characteristics of music,such as main melody,tone and so on.(2)On this basis,the multi-head attention and dualpath transformer are introduced in the separation module.Channel attention units are applied recursively on the feature map of each layer of the network,enabling the network to perform long-sequence separation.Experimental results show that after the introduction of the channel attention,the performance of the proposed algorithm has a stable improvement compared with the baseline system.On the MUSDB18 dataset,the average score of the separated audio exceeds that of the current best-performing music separation algorithm based on the time-frequency domain(T-F domain).

Interpretation and characterization of rate of penetration intelligent prediction model

Accurate prediction of the rate of penetration(ROP)is significant for drilling optimization.While the intelligent ROP prediction model based on fully connected neural networks(FNN)outperforms traditional ROP equations and machine learning algorithms,its lack of interpretability undermines its credibility.This study proposes a novel interpretation and characterization method for the FNN ROP prediction model using the Rectified Linear Unit(ReLU)activation function.By leveraging the derivative of the ReLU function,the FNN function calculation process is transformed into vector operations.The FNN model is linearly characterized through further simplification,enabling its interpretation and analysis.The proposed method is applied in ROP prediction scenarios using drilling data from three vertical wells in the Tarim Oilfield.The results demonstrate that the FNN ROP prediction model with ReLU as the activation function performs exceptionally well.The relative activation frequency curve of hidden layer neurons aids in analyzing the overfitting of the FNN ROP model and determining drilling data similarity.In the well sections with similar drilling data,averaging the weight parameters enables linear characterization of the FNN ROP prediction model,leading to the establishment of a corresponding linear representation equation.Furthermore,the quantitative analysis of each feature's influence on ROP facilitates the proposal of drilling parameter optimization schemes for the current well section.The established linear characterization equation exhibits high precision,strong stability,and adaptability through the application and validation across multiple well sections.

A NewMalicious Code ClassificationMethod for the Security of Financial Software

The field of finance heavily relies on cybersecurity to safeguard its systems and clients from harmful software.The identification of malevolent code within financial software is vital for protecting both the financial system and individual clients.Nevertheless,present detection models encounter limitations in their ability to identify malevolent code and its variations,all while encompassing a multitude of parameters.To overcome these obsta-cles,we introduce a lean model for classifying families of malevolent code,formulated on Ghost-DenseNet-SE.This model integrates the Ghost module,DenseNet,and the squeeze-and-excitation(SE)channel domain attention mechanism.It substitutes the standard convolutional layer in DenseNet with the Ghost module,thereby diminishing the model’s size and augmenting recognition speed.Additionally,the channel domain attention mechanism assigns distinctive weights to feature channels,facilitating the extraction of pivotal characteristics of malevolent code and bolstering detection precision.Experimental outcomes on the Malimg dataset indicate that the model attained an accuracy of 99.14%in discerning families of malevolent code,surpassing AlexNet(97.8%)and The visual geometry group network(VGGNet)(96.16%).The proposed model exhibits reduced parameters,leading to decreased model complexity alongside enhanced classification accuracy,rendering it a valuable asset for categorizing malevolent code.

Visual Analysis of Epilepsy Diagnosis Based on Brain Functional Connections

Epilepsy is a transient neurological disorder associated with changes in the functional connections of the brain. Abnormal electrical discharges can be observed during an epileptic seizure. However, in the absence of an epileptic seizure, the anatomical structure of the brain and the electrical waves of the brain are not observed, making it difficult to explain the cause. This paper deals with together weighted imaging (DWI) sequence data in functional magnetic resonance imaging (FMRI) of epileptic patients before seizure, using Anatomical Automatic Labeling (AAL) template extracted 116 brain regions and the introduction of time series, a matrix of 116 × 116. Pearson correlation coefficient was calculated to investigate the pathological condition of brain function in epilepsy patients, using of neural network visualization system of innovative visual display and compared with the normal epileptic brain function to connect the image, with 38 cases of epilepsy by 187 cases of normal DWI experiment data, and can confirm the existence of brain function in patients with epilepsy connections. Cerebral neural network visualization system showed partial functional connection loss between frontal lobe and temporal lobe in epileptic group compared with normal control group.

Changes in brain functional network connectivity after stroke

Studies have shown that functional network connection models can be used to study brain net- work changes in patients with schizophrenia. In this study, we inferred that these models could also be used to explore functional network connectivity changes in stroke patients. We used independent component analysis to find the motor areas of stroke patients, which is a novel way to determine these areas. In this study, we collected functional magnetic resonance imaging datasets from healthy controls and right-handed stroke patients following their first ever stroke. Using independent component analysis, six spatially independent components highly correlat- ed to the experimental paradigm were extracted. Then, the functional network connectivity of both patients and controls was established to observe the differences between them. The results showed that there were 11 connections in the model in the stroke patients, while there were only four connections in the healthy controls. Further analysis found that some damaged connections may be compensated for by new indirect connections or circuits produced after stroke. These connections may have a direct correlation with the degree of stroke rehabilitation. Our findings suggest that functional network connectivity in stroke patients is more complex than that in hea- lthy controls, and that there is a compensation loop in the functional network following stroke. This implies that functional network reorganization plays a very important role in the process of rehabilitation after stroke.

Change of stream network connectivity and its impact on flood control

AbstUrbanization can alter the hydrogeomorphology of streams and rivers,change stream network structures,and reduce stream network connectivity,which leads to a decrease in the storage capacity of stream networks and aggravates flood damage.Therefore,investigation of the ways in which stream network connectivity impacts flood storage capacity and flood control in urbanized watersheds can provide significant benefits.This study developed a framework to assess stream network connectivity and its impact on flood control.First,a few connectivity indices were adopted to assess longitudinal stream network connectivity.Afterward,the static and dynamic storage capacities of stream networks were evaluated using storage capacity indices and a one-dimensional hydrodynamic model.Finally,the impact of stream network connectivity change on flood control was assessed by investigating the changes in stream network connectivity and storage capacity.This framework was applied to the Qinhuai River Basin,China,where intensive urbanization has occurred in the last few decades.The results show that stream network storage capacity is affected by stream network connectivity.Increasing stream network connectivity enhances stream network storage capacity.©2020 Hohai University.Production and hosting by Elsevier B.V.This is an open access article under the CC BY-NC-ND license(http://creativecommons.org/licenses/by-nc-nd/4.0/).

Global Functional Network Connectivity Disturbances in Parkinson’s Disease with Mild Cognitive Impairment by Resting-State Functional MRI

Examining the spontaneous BOLD activity to understand the neural mechanism of Parkinson’s disease(PD)with mild cognitive impairment(MCI)is a focus in resting-state functional MRI(rs-fMRI)studies.This study aimed to investigate the alteration of brain functional connectivity in PD with MCI in a systematical way at two levels:functional connectivity analysis within resting state networks(RSNs)and functional network connectivity(FNC)analysis.Using group independent component analysis(ICA)on rs-fMRI data acquired from 30 participants(14 healthy controls and 16 PD patients with MCI),16 RSNs were identified,and functional connectivity analysis within the RSNs and FNC analysis were carried out between groups.Compared to controls,patients with PD showed decreased functional connectivity within putamen network,thalamus network,cerebellar network,attention network,and self-referential network,and increased functional connectivity within execution network.Globally disturbed,mostly increased functional connectivity of FNC was observed in PD group,and insular network and execution network were the dominant network with extensively increased functional connectivity with other RSNs.Cerebellar network showed decreased functional connectivity with caudate network,insular network,and self-referential network.In general,decreased functional connectivity within RSNs and globally disturbed,mostly increased functional connectivity of FNC may be characteristics of PD.Increased functional connectivity within execution network may be an early marker of PD.The multi-perspective study based on RSNs may be a valuable means to assess functional changes corresponding to specific RSN,contributing to the understanding of the neural mechanism of PD.

Quantitative characterization of irregular microfracture network and its effect on the permeability of porous media

Based on the comprehensive understanding on microfractures and matrix pores in reservoir rocks,numerical algorithms are used to construct fractured porous media and fracture-pore media models.Connectivity coefficient and strike factor are introduced into the models to quantitatively characterize the connectivity and strike of fracture network,respectively.The influences of fracture aperture,fracture strike and fracture connectivity on the permeability of porous media are studied by using multi-relaxation-time lattice Boltzmann model to simulate fluid flow in them.The greater the strike factor and the smaller the tortuosity of the fractured porous media,the greater the permeability of the fractured porous media.The greater the connectivity coefficient of the fracture network is,the greater the permeability of the fracture-pore media is,and the more likely dominant channel effect occurs.The fracture network connectivity has stronger influence on seepage ability of fracture-pore media than fracture aperture and fracture strike.The tortuosity and strike factor of fracture network in fractured porous media are in polynomial relation,while the permeability and fracture network connectivity coefficient of the fracture-pore media meet an exponential relation.

Fully Connected Feedforward Neural Networks Based CSI Feedback Algorithm

In modern wireless communication systems,the accurate acquisition of channel state information(CSI)is critical to the performance of beamforming,non-orthogonal multiple access(NOMA),etc.However,with the application of massive MIMO in 5G,the number of antennas increases by hundreds or even thousands times,which leads to excessive feedback overhead and poses a huge challenge to the conventional channel state information feedback scheme.In this paper,by using deep learning technology,we develop a system framework for CSI feedback based on fully connected feedforward neural networks(FCFNN),named CF-FCFNN.Through learning the training set composed of CSI,CF-FCFNN is able to recover the original CSI from the compressed CSI more accurately compared with the existing method based on deep learning without increasing the algorithm complexity.

An Efficient Connectivity Restoration Technique(ECRT)for Wireless Sensor Network

Node failure in Wireless Sensor Networks(WSNs)is a fundamental problem because WSNs operate in hostile environments.The failure of nodes leads to network partitioning that may compromise the basic operation of the sensor network.To deal with such situations,a rapid recovery mechanism is required for restoring inter-node connectivity.Due to the immense importance and need for a recovery mechanism,several different approaches are proposed in the literature.However,the proposed approaches have shortcomings because they do not focus on energy-efficient operation and coverage-aware mechanisms while performing connectivity restoration.Moreover,most of these approaches rely on the excessive mobility of nodes for restoration connectivity that affects both coverage and energy consumption.This paper proposes a novel technique called ECRT(Efficient Connectivity Restoration Technique).This technique is capable of restoring connectivity due to single and multiple node failures.ECRT achieves energy efficiency by transmitting a minimal number of control packets.It is also coverage-aware as it relocates minimal nodes while trying to restore connectivity.With the help of extensive simulations,it is proven that ECRT is effective in connectivity restoration for single and multiple node failures.Results also show that ECRT exchanges a much smaller number of packets than other techniques.Moreover,it also yields the least reduction in field coverage,proving its versatility for connectivity restoration.

Network Structure and Chemical Durability of Non-alkali Aluminoborosilicate Glasses Containing ZnO

The structure and chemical durability of non-alkali aluminoborosilicate glasses with various contents of ZnO were investigated.As the replacement of MgO by ZnO increases from 0 to 3.2mol%,the average number of bridge oxygen per tetrahedron (BO/T) as a measure of network connectivity increases from 2.84 to 3.04,and the chemical durability improved.The weight loss ratio (WLR) of glass etched in 10vol% HF (20 ℃,20 min) solution decreased from 4.809 to 4.509,and in 5wt% NaOH (95 ℃,6 h) solution decreased from 1.201 to 0.994.The replacement of MgO by ZnO further increased to 6.4mol%,the value of BO/T decreased to 3.04 instead,and thus the chemical durability deteriorated.The WLR of HF-acid and NaOH-alkali corrosion increased to 6.683 and 1.994,respectively.The chemical durability shows strongly dependent on the network connectivity and exhibits mixed intermediate effects during the replacement of MgO by ZnO.

Analysis on Economic Resilience of the Guangdong-Hong Kong-Macao Greater Bay Area:A Perspective from the Economic Connection Network

In the face of an increasingly complex and unstable external development environment,enhancing economic resilience has become a key task in the construction of the Guangdong-Hong Kong-Macao Greater Bay Area.This paper analyzes the changes in the economic resilience of the Guangdong-Hong Kong-Macao Greater Bay Area and its constituent cities after the 2008 global financial crisis by virtue of the regional economic resilience assessment method proposed by Martin et al.It constructs an economic connection network for the Guangdong-Hong Kong-Macao Greater Bay Area using the data from corporate headquarters and branches of A-share listed companies to analyze its impact on the economic resilience of the Area.The study reveals the three following conclusions.Firstly,the economic resilience of the Guangdong-Hong Kong-Macao Greater Bay Area generally outperforms the national average level,seeing a rapid boost over the recent years and exceeding the level witnessed during the 2008 financial crisis.However,there are marked disparities in the economic resilience ofvarious cities within the Greater Bay Area,with Shenzhen,Guangzhou,and Dongguan emerging as the most robust in this regard.Secondly,the economic connection network has a positive impact on the economic resilience of the cities in the Guangdong-Hong Kong-Macao Greater Bay Area.Specifically,there is a positive correlation between a city's economic resilience and its centrality in the economic connectionnetwork.Suchcentrality exerts a positive spillover effect on the economic resilience of surrounding cities.Thirdly,from the perspective of industryspecific networks,circulation and service industry networks are more conducive to improving the economic resilience of a city.Given the significant role of the economic connection network in shaping regional and urban economic resilience,it is imperative for the Guangdong-Hong Kong-Macao Greater Bay Area to prioritize ensuring economic development security and enhancing economic resilience,promote the development of the economic connection network,and enhance the network centrality of its constituent cities.This can improve the economic resilience of itselfand its constituentcities inaneffective manner.

联结主义引论

联结主义与符号主义是认知科学的两个主要流派，起源干人们对于大脑结构与工作原理的研究。本文介绍并讨论了联结主义的基本理论，包括联结主义与符号主义的区别、联结主义与大脑神经生理的关系、联结主义模型中节点的工作原理以及单向输入网络模型、简单循环网络模型和交互式激活网络模型三种主要的联结主义网络模型。

联结主义理论对学习英语词汇搭配的启示

联结主义理论是认知科学的理论之一,其神经网络模型与大脑的结构及工作原理相类似,强调外部环境的学习以及单元或节点之间的联系方式。因此,近些年来被越来越多地用于解释学习这一认知过程,包括语言学习和语言理解的过程。词汇学习一直是英语学习中的重点,贯穿整个英语学习的过程。在英语学习的高级阶段,学习者正确地使用英语词汇搭配是英语学习成功与否的关键因素。联结主义的学习观为了解学习者学习英语词汇搭配的过程提供了理论依据,它在实践中的应用对掌握正确的学习方法、提高学习效率给予了很大的启示。

关联主义视角下学习型社交网站的构建

社交网站(SNS)是Web2.0时代一个标志性的网络服务新模式。它以人为核心,以社会关系链为基础,利用诸如网络聊天(IM),交友,开博客、记日志,建相册,参与群组,玩SNS游戏,分享日记等活动在人与人之间传播信息,创造内容,维系关系,培育感情。这不仅改变了人们的社交方式,同时也改变了人们的学习方式。基于关联主义的理论观点,从技术维度、社会维度、知识维度三个方面探讨了学习型社交网站的创建应该遵循和坚守的创建理念和原则,其研究结果对促进社交网站在教育教学中的有效应用具有理论指导价值。

联接主义智能控制综述

综述了近年来联接主义智能控制的理论和应用上的研究进展 ,覆盖了神经网络的逼近和泛化能力、神经网络与混沌、监督学习算法等基本性质 ,以及神经网络建模、预测、优化和控制等联接主义智能控制系统的各个部分 ,并对今后的研究发展提出了展望 .