An Intelligent Framework for Resilience Recovery of FANETs with Spatio-Temporal Aggregation and Multi-Head Attention Mechanism

Due to the time-varying topology and possible disturbances in a conflict environment,it is still challenging to maintain the mission performance of flying Ad hoc networks(FANET),which limits the application of Unmanned Aerial Vehicle(UAV)swarms in harsh environments.This paper proposes an intelligent framework to quickly recover the cooperative coveragemission by aggregating the historical spatio-temporal network with the attention mechanism.The mission resilience metric is introduced in conjunction with connectivity and coverage status information to simplify the optimization model.A spatio-temporal node pooling method is proposed to ensure all node location features can be updated after destruction by capturing the temporal network structure.Combined with the corresponding Laplacian matrix as the hyperparameter,a recovery algorithm based on the multi-head attention graph network is designed to achieve rapid recovery.Simulation results showed that the proposed framework can facilitate rapid recovery of the connectivity and coverage more effectively compared to the existing studies.The results demonstrate that the average connectivity and coverage results is improved by 17.92%and 16.96%,respectively compared with the state-of-the-art model.Furthermore,by the ablation study,the contributions of each different improvement are compared.The proposed model can be used to support resilient network design for real-time mission execution.

Structured Multi-Head Attention Stock Index Prediction Method Based Adaptive Public Opinion Sentiment Vector

The present study examines the impact of short-term public opinion sentiment on the secondary market,with a focus on the potential for such sentiment to cause dramatic stock price fluctuations and increase investment risk.The quantification of investment sentiment indicators and the persistent analysis of their impact has been a complex and significant area of research.In this paper,a structured multi-head attention stock index prediction method based adaptive public opinion sentiment vector is proposed.The proposedmethod utilizes an innovative approach to transform numerous investor comments on social platforms over time into public opinion sentiment vectors expressing complex sentiments.It then analyzes the continuous impact of these vectors on the market through the use of aggregating techniques and public opinion data via a structured multi-head attention mechanism.The experimental results demonstrate that the public opinion sentiment vector can provide more comprehensive feedback on market sentiment than traditional sentiment polarity analysis.Furthermore,the multi-head attention mechanism is shown to improve prediction accuracy through attention convergence on each type of input information separately.Themean absolute percentage error(MAPE)of the proposedmethod is 0.463%,a reduction of 0.294% compared to the benchmark attention algorithm.Additionally,the market backtesting results indicate that the return was 24.560%,an improvement of 8.202% compared to the benchmark algorithm.These results suggest that themarket trading strategy based on thismethod has the potential to improve trading profits.

Posture Detection of Heart Disease Using Multi-Head Attention Vision Hybrid(MHAVH)Model

Cardiovascular disease is the leading cause of death globally.This disease causes loss of heart muscles and is also responsible for the death of heart cells,sometimes damaging their functionality.A person’s life may depend on receiving timely assistance as soon as possible.Thus,minimizing the death ratio can be achieved by early detection of heart attack(HA)symptoms.In the United States alone,an estimated 610,000 people die fromheart attacks each year,accounting for one in every four fatalities.However,by identifying and reporting heart attack symptoms early on,it is possible to reduce damage and save many lives significantly.Our objective is to devise an algorithm aimed at helping individuals,particularly elderly individuals living independently,to safeguard their lives.To address these challenges,we employ deep learning techniques.We have utilized a vision transformer(ViT)to address this problem.However,it has a significant overhead cost due to its memory consumption and computational complexity because of scaling dot-product attention.Also,since transformer performance typically relies on large-scale or adequate data,adapting ViT for smaller datasets is more challenging.In response,we propose a three-in-one steam model,theMulti-Head Attention Vision Hybrid(MHAVH).Thismodel integrates a real-time posture recognition framework to identify chest pain postures indicative of heart attacks using transfer learning techniques,such as ResNet-50 and VGG-16,renowned for their robust feature extraction capabilities.By incorporatingmultiple heads into the vision transformer to generate additional metrics and enhance heart-detection capabilities,we leverage a 2019 posture-based dataset comprising RGB images,a novel creation by the author that marks the first dataset tailored for posture-based heart attack detection.Given the limited online data availability,we segmented this dataset into gender categories(male and female)and conducted testing on both segmented and original datasets.The training accuracy of our model reached an impressive 99.77%.Upon testing,the accuracy for male and female datasets was recorded at 92.87%and 75.47%,respectively.The combined dataset accuracy is 93.96%,showcasing a commendable performance overall.Our proposed approach demonstrates versatility in accommodating small and large datasets,offering promising prospects for real-world applications.

Multi-Head Attention Spatial-Temporal Graph Neural Networks for Traffic Forecasting

Accurate traffic prediction is crucial for an intelligent traffic system (ITS). However, the excessive non-linearity and complexity of the spatial-temporal correlation in traffic flow severely limit the prediction accuracy of most existing models, which simply stack temporal and spatial modules and fail to capture spatial-temporal features effectively. To improve the prediction accuracy, a multi-head attention spatial-temporal graph neural network (MSTNet) is proposed in this paper. First, the traffic data is decomposed into unique time spans that conform to positive rules, and valuable traffic node attributes are mined through an adaptive graph structure. Second, time and spatial features are captured using a multi-head attention spatial-temporal module. Finally, a multi-step prediction module is used to achieve future traffic condition prediction. Numerical experiments were conducted on an open-source dataset, and the results demonstrate that MSTNet performs well in spatial-temporal feature extraction and achieves more positive forecasting results than the baseline methods.

Attention-based spatio-temporal graph convolutional network considering external factors for multi-step traffic flow prediction

Traffic flow prediction is an important part of the intelligent transportation system. Accurate multi-step traffic flow prediction plays an important role in improving the operational efficiency of the traffic network. Since traffic flow data has complex spatio-temporal correlation and non-linearity, existing prediction methods are mainly accomplished through a combination of a Graph Convolutional Network (GCN) and a recurrent neural network. The combination strategy has an excellent performance in traffic prediction tasks. However, multi-step prediction error accumulates with the predicted step size. Some scholars use multiple sampling sequences to achieve more accurate prediction results. But it requires high hardware conditions and multiplied training time. Considering the spatiotemporal correlation of traffic flow and influence of external factors, we propose an Attention Based Spatio-Temporal Graph Convolutional Network considering External Factors (ABSTGCN-EF) for multi-step traffic flow prediction. This model models the traffic flow as diffusion on a digraph and extracts the spatial characteristics of traffic flow through GCN. We add meaningful time-slots attention to the encoder-decoder to form an Attention Encoder Network (AEN) to handle temporal correlation. The attention vector is used as a competitive choice to draw the correlation between predicted states and historical states. We considered the impact of three external factors (daytime, weekdays, and traffic accident markers) on the traffic flow prediction tasks. Experiments on two public data sets show that it makes sense to consider external factors. The prediction performance of our ABSTGCN-EF model achieves 7.2%–8.7% higher than the state-of-the-art baselines.

基于Multi-head Attention和Bi-LSTM的实体关系分类

关系分类是自然语言处理领域的一项重要任务,能够为知识图谱的构建、问答系统和信息检索等提供技术支持.与传统关系分类方法相比较,基于神经网络和注意力机制的关系分类模型在各种关系分类任务中都获得了更出色的表现.以往的模型大多采用单层注意力机制,特征表达相对单一.因此本文在已有研究基础上,引入多头注意力机制(Multi-head attention),旨在让模型从不同表示空间上获取关于句子更多层面的信息,提高模型的特征表达能力.同时在现有的词向量和位置向量作为网络输入的基础上,进一步引入依存句法特征和相对核心谓词依赖特征,其中依存句法特征包括当前词的依存关系值和所依赖的父节点位置,从而使模型进一步获取更多的文本句法信息.在SemEval-2010 任务8 数据集上的实验结果证明,该方法相较之前的深度学习模型,性能有进一步提高.

Multi-head attention-based long short-term memory model for speech emotion recognition

To fully make use of information from different representation subspaces,a multi-head attention-based long short-term memory(LSTM)model is proposed in this study for speech emotion recognition(SER).The proposed model uses frame-level features and takes the temporal information of emotion speech as the input of the LSTM layer.Here,a multi-head time-dimension attention(MHTA)layer was employed to linearly project the output of the LSTM layer into different subspaces for the reduced-dimension context vectors.To provide relative vital information from other dimensions,the output of MHTA,the output of feature-dimension attention,and the last time-step output of LSTM were utilized to form multiple context vectors as the input of the fully connected layer.To improve the performance of multiple vectors,feature-dimension attention was employed for the all-time output of the first LSTM layer.The proposed model was evaluated on the eNTERFACE and GEMEP corpora,respectively.The results indicate that the proposed model outperforms LSTM by 14.6%and 10.5%for eNTERFACE and GEMEP,respectively,proving the effectiveness of the proposed model in SER tasks.

Using Recurrent Neural Network Structure and Multi-Head Attention with Convolution for Fraudulent Phone Text Recognition

Fraud cases have been a risk in society and people’s property security has been greatly threatened.In recent studies,many promising algorithms have been developed for social media offensive text recognition as well as sentiment analysis.These algorithms are also suitable for fraudulent phone text recognition.Compared to these tasks,the semantics of fraudulent words are more complex and more difficult to distinguish.Recurrent Neural Networks(RNN),the variants ofRNN,ConvolutionalNeuralNetworks(CNN),and hybrid neural networks to extract text features are used by most text classification research.However,a single network or a simple network combination cannot obtain rich characteristic knowledge of fraudulent phone texts relatively.Therefore,a new model is proposed in this paper.In the fraudulent phone text,the knowledge that can be learned by the model includes the sequence structure of sentences,the correlation between words,the correlation of contextual semantics,the feature of keywords in sentences,etc.The new model combines a bidirectional Long-Short Term Memory Neural Network(BiLSTM)or a bidirectional Gate Recurrent United(BiGRU)and a Multi-Head attention mechanism module with convolution.A normalization layer is added after the output of the final hidden layer.BiLSTM or BiGRU is used to build the encoding and decoding layer.Multi-head attention mechanism module with convolution(MHAC)enhances the ability of the model to learn global interaction information and multi-granularity local interaction information in fraudulent sentences.A fraudulent phone text dataset is produced by us in this paper.The THUCNews data sets and fraudulent phone text data sets are used in experiments.Experiment results show that compared with the baseline model,the proposed model(LMHACL)has the best experiment results in terms of Accuracy,Precision,Recall,and F1 score on the two data sets.And the performance indexes on fraudulent phone text data sets are all above 0.94.

Discharge Summaries Based Sentiment Detection Using Multi-Head Attention and CNN-BiGRU

Automatic extraction of the patient’s health information from the unstructured data concerning the discharge summary remains challenging.Discharge summary related documents contain various aspects of the patient health condition to examine the quality of treatment and thereby help improve decision-making in the medical field.Using a sentiment dictionary and feature engineering,the researchers primarily mine semantic text features.However,choosing and designing features requires a lot of manpower.The proposed approach is an unsupervised deep learning model that learns a set of clusters embedded in the latent space.A composite model including Active Learning(AL),Convolutional Neural Network(CNN),BiGRU,and Multi-Attention,called ACBMA in this research,is designed to measure the quality of treatment based on discharge summaries text sentiment detection.CNN is utilized for extracting the set of local features of text vectors.Then BiGRU network was utilized to extract the text’s global features to solve the issues that a single CNN cannot obtain global semantic information and the traditional Recurrent Neural Network(RNN)gradient disappearance.Experiments prove that the ACBMA method can demonstrate the effectiveness of the suggested method,achieve comparable results to state-of-arts methods in sentiment detection,and outperform them with accurate benchmarks.Finally,several algorithm studies ultimately determined that the ACBMA method is more precise for discharge summaries sentiment analysis.

Study on the fusion emotion classification of multiple characteristics based on attention mechanism

The current research on emotional classification uses many methods that combine the attention mechanism with neural networks.However,the effect is unsatisfactory when dealing with complex text.An emotional classification model is proposed,which combines multi-head attention(MHA)with improved structured-self attention(SSA).The model makes several different linear transformations of input by introducing MHA mechanism and can extract more comprehensive high-level phrase representation features from the word embedded vector.Meanwhile,it can realize the parallelization calculation and ensure the training speed of the model.The improved SSA structure uses matrices to represent different parts of a sentence to extract local key information,to ensure that the degree of dependence between words is not affected by time and sentence length,and generate the overall semantics of the sentence.Experiment results show that the current model effectively obtains global structural information and improves classification accuracy.

一种多模态隐喻数据集的构建和验证方法

隐喻的目的是启发理解、说服他人。目前,隐喻呈现文本、图像、视频等多模态融合的趋势,因此,识别多模态信息中蕴含的隐喻语义对互联网内容安全具有研究价值。由于缺乏多模态隐喻数据集,难以建立研究模型,因此,当前学者更关注基于文本的隐喻检测。针对这一不足,作者首先从图像-文本、隐喻出现、情感表达和作者意图等角度构建新型多模态隐喻数据集;其次,对数据集的标注者进行Kappa分数计算;最后,借助预训练模型和注意力机制融合图像属性特征、图像实体对象特征和文本特征,构建多模态隐喻检测模型,验证多模态数据集的质量和价值。实验结果表明:具有情感和意图表达的隐喻数据集可提升隐喻模型检测效果,多模态信息间相互关系有助于隐喻的理解。

融合外部注意力机制的序列到点非侵入式负荷分解

非侵入式负荷分解可以深度挖掘用户电力消耗数据蕴含的信息价值,为电力设备故障监测、需求响应等决策分析提供重要参考.为有效解决非侵入式负荷分解算法训练时间成本与分解精度间的冲突,提出一种融合外部注意力机制的序列到点非侵入式负荷分解算法.首先,将总负荷功率消耗序列进行数据清理、标准化等预处理,以固定窗口长度构建训练输入数据,输入数据通过编码层自动提取设备特征;然后,设计外部注意力机制增强重要特征权值;最终,输入到解码层得到负荷分解结果.利用REDD与UK-DALE两种公开数据集进行模型仿真计算,在信号聚合误差、平均绝对误差、标准化分解误差指标、模型分解曲线、特征图和用户耗能等方面进行对比分析,本文模型克服了卷积层注意力分散的缺点,增强了对有效信息的提取与利用能力,在未增加训练时间成本的前提下具有更高的分解精度.

基于高斯偏置自注意力和交叉注意力的医学图像分割模型

为解决医学图像分割中目标之间存在特征差异、不同切片图像中存在同一解剖结构的相似表征和器官与背景的区分度低造成冗余信息过多的问题,提出了一种基于高斯偏置自注意力和交叉注意力的网络模型(Gaussian bias and Contextual cross Attention U-Net,GCA-UNet)。采用残差模块建立空间先验假设,通过高斯偏置自注意力&外注意力模块的高斯偏置自注意力来学习空间先验假设和强化相邻区域的特征表示,并利用外注意力机制学习同一样本下不同切片之间的相关性;上下文交叉注意力门控利用多尺度特征提取来强化结构和边界信息,同时对上下文语义信息进行重新校准并筛除冗余信息。实验结果表明,在Synapse腹腔CT多器官分割数据集和ACDC心脏MRI数据集上,GCA-UNet网络的分割精度指标Mean Dice分别达到了81.37%和91.69%,在Synapse数据集上边界分割精度指标Mean hd95达到16.01。相比其他先进医学影像分割模型,GCA-Unet分割精度更高,具有更清晰的组织边界。

融合外部注意力的扩散模型巡检图像去雾

为降低雾天对输电线路巡检图像造成的影响,针对目前主流去雾算法存在计算成本高、图像去雾后检测性能差和难以部署的问题,提出了一种雾天输电线路巡检图像去雾方法Diff-EaT。该方法采用融合Transformer的扩散模型结构,为降低体征提取模块中多头自注意力在ViT中的计算复杂度,使用多头外部注意力代替多头自注意力以减少计算负荷和增强特征学习。同时,设计了一个混合尺度门控前馈网络,在输入特征的深度可分离卷积之后集成了选通机制以改善局部信息捕获。在合成数据集和真实数据集上进行对比试验,定量指标和定量指标都证明其有效性,复原图像细节更加清晰。在去雾检测系统中,对真实巡检图像去雾后使用YOLOv7进行检测,mAP@0.5、召回率、查准率分别提升6.92%、9.58%、4.11%,本文方法去雾后有效提高检测置信度,去雾检测系统可应用于实际场景。同时在消融实验中,证明了改进的有效性。

用于方面级情感分析的多信息增强图卷积网络

方面级情感分析旨在预测句子中特定方面的情感极性。然而,现阶段的研究依然存在语义信息不充分利用的问题,一方面大多数现有工作侧重于学习上下文词到方面词之间的依存信息,没有充分利用句子的语义信息;另一方面现有研究没有专注于依存树的语法构建,从而没有充分利用语法结构信息去补充语义信息。针对以上问题,提出多信息增强图卷积神经网络(MIE-GCN)模型。主要包括两部分:一是通过方面感知注意力、自注意力和外部常识形成多信息融合层充分利用语义信息;二是根据单词间不同的语法距离构造句子的语法掩码矩阵,通过获得全面语法结构信息来补充语义信息。利用图卷积神经网络增强节点表示。在基准数据集上的实验结果表明,提出的模型均比对比模型有一定的提升。

企业成本黏性、关键审计事项披露与审计费用

企业成本管理不当所造成的成本黏性在增加企业风险的同时,也加大了审计工作难度。本文利用沪深A股上市公司2016—2022年的年报数据,从关键审计事项披露视角出发,实证检验企业成本黏性与审计费用之间的关系及其实现路径。研究发现,企业成本黏性会显著增加审计费用,关键审计事项披露在其中起到部分中介作用。进一步检验发现,高内部控制质量和高外部分析师关注能够有效抑制企业成本黏性与审计费用之间的正向关系。本文实证结果既丰富了相关研究成果,也为企业加强成本管理、审计师优化审计程序提供了一定的理论依据。

外部注意力增强语义交互的阅读理解模型

针对传统抽取式阅读理解模型未充分考虑问答样本之间潜在相关性的问题,通过RoBERTa对问题与段落进行编码,利用外部注意力Exatt增强语义交互层特征获取能力,提出外部注意力增强语义交互的阅读理解模型,捕获问题与段落中蕴涵的语义特征和不同问答样本之间的潜在相关性。实验结果表明,在CMRC2018和构建的电力安规问答数据集上,在评价指标EM和F1两方面,该方法较基线模型分别最高提高了0.737%和2.556%。

基于改进YOLOv5s的输电线路防外力破坏行为检测识别

电力系统的安全对于整个能源传输过程至关重要;针对输电线路下超大工程车辆和烟火为主要的外力破坏行为,对单阶段目标检测算法YOLOv5s进行改进,首先针对输电线路多雨雾烟尘等工作环境,引入限制对比度自适应直方图均衡算法CLAHE对图片进行去雾处理,提升图片对比度;针对检测目标距离较远的问题,在YOLOv5s网络的基础上添加CA注意力机制,提升了模型对目标的定位能力;将原网络中的最邻近差值采样方式替换为轻量级通用上采样算子CARAFE,更好地捕捉特征图的同时引入较小的参数量;最后在网络的特征融合层,使用具有通道混洗思想的GSConv卷积模块代替标准卷积模块,减少模型参数量,再利用slim_neck特征融合结构,强化目标关注度,达到减少模型参数量同时提升检测精度的效果;实验结果表明:改进后的YOLOv5s网络,mAP提升了4.4%,参数量减少了3.4%,权重模型内存减小了2.7%,证明了算法的有效性。

基于双分支多头注意力的场景图生成方法

针对已有场景图生成模型获取上下文信息有限的问题,提出一种有效的上下文融合模块,即双分支多头注意力(dual-stream multi-head attention, DMA)模块,并将DMA分别用于物体分类阶段和关系分类阶段,基于此提出基于双分支多头注意力的场景图生成网络(dual-stream multi-head attention-based scene graph generation network, DMA-Net)。该网络由目标检测、物体语义解析和关系语义解析3个模块组成。首先,通过目标检测模块定位图像中的物体并提取物体特征;其次,使用物体语义解析模块中的节点双分支多头注意力(object dual-stream multi-head attention, O-DMA)获取融合了节点上下文的特征,该特征经过物体语义解码器获得物体类别标签;最后,通过关系语义解析模块中的边双分支多头注意力(relationship dual-stream multi-head attention, R-DMA)输出融合了边上下文的特征,该特征经过关系语义解码器输出关系类别标签。在公开的视觉基因组(visual genome, VG)数据集上分别计算了DMA-Net针对场景图检测、场景图分类和谓词分类3个子任务的图约束召回率和无图约束召回率,并与主流的场景图生成方法进行比较。实验结果表明,所提出的方法能够充分挖掘场景中的上下文信息,基于上下文增强的特征表示有效提升了场景图生成任务的精度。

基于YOLO-2MCS的输电线路走廊隐患目标检测方法

输电线路在跨越高速铁路、高速公路和重要输电通道场景下易受到外力破坏,可能严重影响输电线路安全可靠运行。针对此问题,该文通过构建输电线路走廊隐患目标数据集,提出新模型YOLO-2MCS用于输电线路走廊隐患目标检测。使用混合数据增强策略对数据集进行有效扩充,以提高模型在复杂场景下的泛化性和鲁棒性;在EfficientRep骨干网络引入卷积注意力机制模块,有效提升模型对多尺度目标的检测能力;构建使用softplus激活函数的双向特征金字塔结构加强模型特征学习能力;在检测头使用SIoU损失函数进一步提升模型检测精度。实验结果表明,相较于原YOLOv6网络,该模型在0.5:0.95的严苛阈值下平均精度均值提升4.4%;将该模型与主流的检测模型FasterR-CNN、YOLOX、YOLOv5和YOLOv7分别进行对比评估,该模型的检测精度、检测速度、模型复杂度均获得最优性能,其平均检测速度高达约300帧/s,且内存仅为40.7 MB,同时满足在边缘计算设备上部署的要求。