A multi-source information fusion layer counting method for penetration fuze based on TCN-LSTM

When employing penetration ammunition to strike multi-story buildings,the detection methods using acceleration sensors suffer from signal aliasing,while magnetic detection methods are susceptible to interference from ferromagnetic materials,thereby posing challenges in accurately determining the number of layers.To address this issue,this research proposes a layer counting method for penetration fuze that incorporates multi-source information fusion,utilizing both the temporal convolutional network(TCN)and the long short-term memory(LSTM)recurrent network.By leveraging the strengths of these two network structures,the method extracts temporal and high-dimensional features from the multi-source physical field during the penetration process,establishing a relationship between the multi-source physical field and the distance between the fuze and the target plate.A simulation model is developed to simulate the overload and magnetic field of a projectile penetrating multiple layers of target plates,capturing the multi-source physical field signals and their patterns during the penetration process.The analysis reveals that the proposed multi-source fusion layer counting method reduces errors by 60% and 50% compared to single overload layer counting and single magnetic anomaly signal layer counting,respectively.The model's predictive performance is evaluated under various operating conditions,including different ratios of added noise to random sample positions,penetration speeds,and spacing between target plates.The maximum errors in fuze penetration time predicted by the three modes are 0.08 ms,0.12 ms,and 0.16 ms,respectively,confirming the robustness of the proposed model.Moreover,the model's predictions indicate that the fitting degree for large interlayer spacings is superior to that for small interlayer spacings due to the influence of stress waves.

Multi-Modality and Feature Fusion-Based COVID-19 Detection Through Long Short-Term Memory

The Coronavirus Disease 2019(COVID-19)pandemic poses the worldwide challenges surpassing the boundaries of country,religion,race,and economy.The current benchmark method for the detection of COVID-19 is the reverse transcription polymerase chain reaction(RT-PCR)testing.Nevertheless,this testing method is accurate enough for the diagnosis of COVID-19.However,it is time-consuming,expensive,expert-dependent,and violates social distancing.In this paper,this research proposed an effective multimodality-based and feature fusion-based(MMFF)COVID-19 detection technique through deep neural networks.In multi-modality,we have utilized the cough samples,breathe samples and sound samples of healthy as well as COVID-19 patients from publicly available COSWARA dataset.Extensive set of experimental analyses were performed to evaluate the performance of our proposed approach.Several useful features were extracted from the aforementioned modalities that were then fed as an input to long short-term memory recurrent neural network algorithms for the classification purpose.Extensive set of experimental analyses were performed to evaluate the performance of our proposed approach.The experimental results showed that our proposed approach outperformed compared to four baseline approaches published recently.We believe that our proposed technique will assists potential users to diagnose the COVID-19 without the intervention of any expert in minimum amount of time.

Adjacent Segment Disease after Long Spinal Fusion Ending at L5 for Adult Spinal Deformity: A Retrospective Cohort Study

Study Design: This is a retrospective cohort study using data from the adult spinal deformity (ASD) database of a single institution. Purpose: To investigate the incidence of proximal junctional failure and distal junctional failure (DJF) after ASD surgery with a lower instrumented vertebra (LIV) at L5. Overview of Literature: Spinopelvic fixation from the lower thoracic vertebra to the pelvis is the current gold standard treatment for ASD. However, the LIV at L5 is acceptable in some cases. Methods: Fifty-six patients who underwent corrective surgery for ASD with LIV at L5 were included. The upper instrumented vertebra (UIV) was T7 in one patient, T9 in 14, T10 in three, T11 in four, T12 in eight, L1 in 10, and L2 in 16. Regarding clinical parameters, age, sex, curve types of Scoliosis Research Society-Schwab classification, number of levels fused, follow-up period, hip bone mallow density, revision surgery rate, and radiographic measurements were compared between the T (UIV: T7 - 10) and TL (UIV: T11 - L2) groups. Results: The revision surgery rate was 19.6% overall. In the T and TL groups, it was 27.8%, and 15.8%, respectively (p = 0.305). The rate of DJF in the T group (33.3%) was significantly higher than in the TL group (5.3%). The rate of proximal junctional kyphosis in the T group (55.6%) was higher than in the TL group (28.9%), with no significant difference. The mean global alignment, sagittal vertical axis, and C7 plumb line-central sacral vertical line were not different between both groups. Conclusions: ASD surgery with LIV set at L5 and UIV set at the thoracic vertebrae (T7 - T10) has a risk of adjacent segment disease.

Deep Bimodal Fusion Approach for Apparent Personality Analysis

Personality distinguishes individuals’ patterns of feeling, thinking,and behaving. Predicting personality from small video series is an excitingresearch area in computer vision. The majority of the existing research concludespreliminary results to get immense knowledge from visual and Audio(sound) modality. To overcome the deficiency, we proposed the Deep BimodalFusion (DBF) approach to predict five traits of personality-agreeableness,extraversion, openness, conscientiousness and neuroticism. In the proposedframework, regarding visual modality, the modified convolution neural networks(CNN), more specifically Descriptor Aggregator Model (DAN) areused to attain significant visual modality. The proposed model extracts audiorepresentations for greater efficiency to construct the long short-termmemory(LSTM) for the audio modality. Moreover, employing modality-based neuralnetworks allows this framework to independently determine the traits beforecombining them with weighted fusion to achieve a conclusive prediction of thegiven traits. The proposed approach attains the optimal mean accuracy score,which is 0.9183. It is achieved based on the average of five personality traitsand is thus better than previously proposed frameworks.

Adult Congenital Lumbar Kyphosis Requiring Anteroposterior Correction and Fusion: A Case Report with 32-Year Follow-Up

Congenital pure kyphosis due to failure of vertebral body segmentation is a relatively rare entity, and surgical intervention is infrequent compared to that for failure of vertebral body formation [1] [2]. There are very few reports of long-term follow-up of surgical treatment in patients with congenital pure kyphosis, and all the reported cases were diagnosed as failure of formation and had an age at the time of surgery of less than 18 years. It is important for orthopedic surgeons to follow the postoperative course of rare cases over 30 years. Here, we present a surgically treated case with ultra-long term follow-up of a 50-year-old patient with congenital pure kyphosis of the lumbar spine. Imaging of the lumbar spine showed six vertebrae and an unsegmented bar at L3-4 causing a pure kyphosis of 54°. The wedge-shaped block vertebra had 4 pedicles with the neural foramen between the pedicles without concomitant disc space, with compensatory thoracic hypokyphosis and lower lumbar hyperlordosis. One-stage correction and fusion surgery using anterior opening and posterior closing osteotomy was successfully performed. Both clinical and radiographic results were excellent and have been maintained for over 30 years postoperatively. The basic principle in the surgical treatment of adult spinal deformity is to achieve and maintain a good global sagittal balance over time. This case reaffirms the importance of spinopelvic harmony.

基于多源信息融合和WOA-CNN-LSTM的外脚手架隐患分类预警研究

面对施工现场外脚手架隐患信息的多样性,传统的基于传感器监测的单一信号预警研究存在容错力不佳、含有信息有限等问题。针对施工现场外脚手架“图像+监测”数据,提出一种基于数据层和特征层信息融合的脚手架隐患分类预警方法。首先,利用Revit三维建模软件建立外脚手架实体模型,对不同初始隐患下的外脚手架进行有限元分析,划分隐患预警等级;其次,利用无迹卡尔曼滤波算法(Unscented Kalman Filter,UKF)及卷积长短时记忆网络(Convolutional Neural Network-Long Short Term Memory Network,CNN-LSTM)实现脚手架同类信息数据层融合及异类信息特征层融合;最后,通过实时收集西安市某在建项目落地式双排扣件式钢管脚手架隐患信息,对其进行分类预警,并使用鲸鱼优化算法(Whale Optimization Algorithm,WOA)对CNN-LSTM网络进行参数优化,发现隐藏节点个数为30、学习率为0.0072、正则化系数为1×10^(-4)时分类效果最佳,优化后预警精度达到了91.4526%。通过可视化WOA-CNN-LSTM、CNN-LSTM、CNN-SVM(Support Vector Machine,支持向量机)及CNN-GRU(Gate Recurrent Unit,门控循环单元)分类预警结果,证实了优化后的CNN-LSTM网络在脚手架分类预警方面的优越性。

基于长短路融合及数据平衡的SAR船舶检测算法

针对SAR图像检测船舶任务中的目标小、近岸样本目标检测困难等问题,文章提出一种名为长短路特征融合网络(Long and Short path Feature Fusion Network,LSFF-Net)的船舶检测网络。该网络通过长短路特征融合模块有效协调了大目标与小目标检测,避免小目标特征信息的丢失。网络中应用结构重参数化结构提高了模块学习能力。为了满足多尺度目标检测,加入特征金字塔网络,融合多尺度特征。为了应对近岸样本目标检测,设计数据重分配算法,提高了对近岸样本目标的检测精度。实验结果表明:在公开数据集检测时,算法的平均精度(Average Precision,AP)达到97.50%,优于主流目标检测算法。该方法为提高SAR图像中小目标和近岸样本目标检测精度提供了新的实现方案。

基于字词向量融合的民航智慧监管短文本分类

为解决民航监管事项所产生的检查记录仅依靠人工进行分类分析导致效率低的问题,提出一种基于数据增强与字词向量融合的双通道特征提取的短文本分类模型,探讨民航监管事项的分类,包括与人、设备设施环境、制度程序和机构职责等相关问题。为解决类别不平衡问题,采用数据增强算法在原始文本上进行变换,生成新的样本,使各个类别的样本数量更加均衡。将字向量和词向量按字融合拼接,得到具有词特征信息的字向量。将字词融合的向量分别送入到文本卷积神经网络(TextCNN)和双向长短期记忆(BiLSTM)模型中进行不同维度的特征提取,从局部的角度和全局的角度分别提取特征,并在民航监管事项检查记录数据集上进行试验。结果表明:该模型准确率为0.9837,F 1值为0.9836。与一些字嵌入模型和词嵌入模型相对比,准确率提升0.4%。和一些常用的单通道模型相比,准确率提升3%,验证了双通道模型提取的特征具有全面性和有效性。

多特征融合的无人艇视觉目标长时相关鲁棒跟踪

[目的]针对显著海浪遮挡、相机剧烈晃动引起的无人艇视觉目标跟踪脱靶问题,提出一种基于多特征融合的长时相关鲁棒跟踪算法。[方法]首先,采用多特征融合技术,增强目标特征表达,提高目标模型鲁棒性;其次,利用高维特征降维和响应图子网格插值,提高目标跟踪的效率与精度;然后,设计水面目标重识别机制,解决目标完全脱离视野时的稳定跟踪问题;最后,采用多个代表性视频数据集进行验证和比较分析。[结果]实验结果表明,相较于传统的长时相关跟踪算法,平均成功率提升15.7%,平均距离精度指标提升30.3%,F-Score指标提升7.0%。[结论]所提算法能够处理恶劣海况下的目标脱靶问题,对于提升无人船艇及海洋机器人智能感知能力,具有重要技术支撑意义。

基于多模型融合的中长期径流集成预测方法

中长期水文预报是流域水资源规划与合理配置的重要依据。为提高中长期径流预测精度,提出了一种基于多模型融合的水库中长期径流集成预测方法。该方法将ARMA、BP、LSTM、RF和SVR等5个异质预测模型进行融合,同时采用超参数优化方法确定各模型的最优参数。将其用于青海省龙羊峡水库的中长期径流预报中,结果表明,通过Stacking融合算法建立的集成预测模型相较于单一模型,取得了更高的预测精度(R2值由0.71提升至0.82)。此方法可为提升流域中长期径流预测精度提供一定参考。

基于多尺度融合和时空特征的网络入侵检测模型

针对入侵检测模型提取特征能力不足,且流量数据中含冗余噪声的问题,提出一种基于多尺度融合和时空特征的ML-PFN入侵检测模型。采用多尺度特征融合技术分别提取数据中浅层特征信息和深层特征信息,使模型学习的特征更加丰富;采用软阈值函数和注意力机制自动选择合适的阈值,减少噪声及不相关信息对模型的干扰;融合时空特征构成多尺度空间特征提取长短时记忆-并行特征网络(MSFE LSTM-parallel feature network, ML-PFN)模型,并应用于网络入侵检测。通过3个公开数据集进行性能评估,实验结果表明,ML-PFN模型对比其它5种分类模型各项指标效果最好,在训练时长适中的同时准确率达到96.45%。

面向文本识别的CRNN模型的改进

复杂场景下文本识别因阴影、残缺、模糊、虚化等因素会出现识别精度下降问题。鉴于此,提出一种基于特征融合与双向简化门结构的CRNN模型。首先引入特征融合机制改进卷积神经网络(CNN)模型,利用特征金字塔结构,多加一条自底向上的路径,将低层特征与高层特征融合在一起,以保留更多低层细节特征,提高场景文本识别精度;其次通过合并遗忘门与输入门,得到结构更简单、计算量和参数量更少的简化门结构替换长短期记忆(LSTM)网络改进循环神经网络(RNN)模型部分;最后设计消融实验验证改进后模型的有效性。三个数据集的测试结果表明:在ResNet50做主干网络时,与原始模型相比,改进后模型准确率提升了1.5%以上;在MobileNetV3做主干网络时,准确率提升了1.4%以上。

基于集合Kalman滤波的中长期径流预报

为降低中长期径流预报的不确定性,增加水电站水库的发电效益,针对现有方法侧重于提高单一预报模型确定性预报结果的准确性以降低径流预报不确定性的问题,提出一种基于集合Kalman滤波的入库径流确定性预报方法。以旬为预见期的锦西水库实例验证结果表明:相比传统的单一预报模型和传统的信息融合预报模型,基于集合Kalman滤波的中长期径流预报可使RMSE降低4.78 m^(3)/s,合格率可提高0.56%,且更有效地降低了汛期预报的不确定性,得到了更加准确、可靠的确定性径流预报结果,可为开展流域梯级水电站优化调度提供技术支持。

时空融合的堆石坝变形预测模型及在安全监测中的应用

变形预测是堆石坝安全监测与健康诊断的重要手段,现有研究多根据堆石坝监测数据建立单测点预测模型,未充分考虑测点之间相关性进行整体建模,且现有模型难以对漂移数据进行长期精准预测。本文考虑堆石坝变形序列的时序依赖性和测点之间的协同相关性,提出了基于图卷积和循环神经网络、引入概率预测与全过程训练的时空融合变形预测模型。该模型首先采用图卷积网络对多测点特征进行自适应汇聚,然后利用循环神经网络中细胞状态与隐层记忆沿时间轴的传递性,实现对时空信息的挖掘与融合,最后通过线性层得到概率预测参数,提高了模型对监测数据噪声的鲁棒性。采用全过程训练方式,提高模型对影响因子与累积变形量内在关系的学习能力,实现对漂移数据的长期精准预测。最后以水布垭面板堆石坝为例,进行了模型对比实验与消融实验,介绍了该模型在堆石坝安全监测和健康诊断中的三种具体应用。结果表明,本文模型有效融合了时空信息,在预测精度方面显著高于现有模型,解决了现有模型对大坝整体变形规律学习能力差、漂移数据预测精度低的问题,可用于堆石坝变形长期预测、测点异常检测与缺损数据补全。

基于场景图感知的跨模态图像描述模型

针对图像描述方法中对图像文本信息的遗忘及利用不充分问题,提出了基于场景图感知的跨模态交互网络(SGC-Net)。首先,使用场景图作为图像的视觉特征并使用图卷积网络(GCN)进行特征融合,从而使图像的视觉特征和文本特征位于同一特征空间;其次,保存模型生成的文本序列,并添加对应的位置信息作为图像的文本特征,以解决单层长短期记忆(LSTM)网络导致的文本特征丢失的问题;最后,使用自注意力机制提取出重要的图像信息和文本信息后并对它们进行融合,以解决对图像信息过分依赖以及对文本信息利用不足的问题。在Flickr30K和MSCOCO(MicroSoft Common Objects in COntext)数据集上进行实验的结果表明,与Sub-GC相比,SGC-Net在BLEU1(BiLingual Evaluation Understudy with 1-gram)、BLEU4(BiLingual Evaluation Understudy with 4-grams)、METEOR(Metric for Evaluation of Translation with Explicit ORdering)、ROUGE(Recall-Oriented Understudy for Gisting Evaluation)和SPICE(Semantic Propositional Image Caption Evaluation)指标上分别提升了1.1、0.9、0.3、0.7、0.4和0.3、0.1、0.3、0.5、0.6。可见,SGC-Net所使用的方法能够有效提升模型的图像描述性能及生成描述的流畅度。

基于多源数据融合的分布式光伏聚合超短期预测方法

分布式光伏聚合发电的超短期预测是支撑其功率快速调节的前提保障,由于规模化接入的分布式光伏容量小、分布广,其发电时序特性差异性大、非平稳性强,导致其超短期预测精度难以保证。为此,文章提出基于多源数据融合的分布式光伏聚合超短期预测方法。该方法基于变分模态分解法,充分挖掘分布式光伏聚合发电非平稳性特性,并采用核主成分分析法对引发光伏发电非平稳性的影响因素即温度、湿度、光照、云量等多源数据进行量化解析,同时结合改进的长短期记忆神经网络,创建了多源数据融合方法,实现了分布式光伏聚合发电超短期预测。仿真结果表明,该方法有效提升了模型的预测精度。与传统方法相比,提出的预测方法对随机性波动严重的光伏超短期预测具有显著优势。

施肥对旱作盐碱地线虫群落与燕麦产量的影响

本研究以线虫作为指示生物,探索不同肥料长期施用对旱作盐碱瘠薄土壤微食物网的影响。依托5年定位试验,设置单施醋糟(VR)、有机肥(OM)、菌肥(BM)、化肥(CF)及醋糟/粉煤灰配施(VRF)和有机肥/化肥配施(OCF)、不施肥(CK)7个处理,选取燕麦苗期、抽穗期和收获期的耕层土壤样品,分析土壤线虫群落、土壤性状及燕麦产量。结果表明:大部分施肥处理降低了土壤pH和容重,显著提升了有机质、硝态氮含量以及微生物数量(P<0.05)。除BM外,各施肥处理的燕麦均显著增产(P<0.05),增幅为44.5%~92.3%,其中OM和CF显著高于其他施肥处理(P<0.05)。施肥显著提高了土壤线虫的数量和丰富度(P<0.05),OM处理线虫群落达到结构化状态,食物网稳定,但植物寄生线虫占比较高(36.2%);相比其他肥料,CF处理则会显著增加线虫优势属数量,显著降低线虫多样性(P<0.05);而两者配施的OCF一定程度上弥补了各自的不足。VRF和VR处理均显著提高了食微线虫占比(P<0.05),降低了植物寄生性线虫占比,VRF处理自由生活线虫成熟度指数显著最高(P<0.05)。土壤有机质、有效磷和微生物是土壤线虫数量变化的主要因素,土壤pH、EC、容重是燕麦增产的主要限制因素,而土壤线虫数量与燕麦产量无显著相关。有机肥/化肥和醋糟/粉煤灰配施较肥料单施更利于土壤微生态环境的健康稳定。

多传感器融合和MHA-LSTM的电机轴承剩余寿命预测

轴承作为电机的核心部件,主要起到支撑引导轴、减小设备摩擦、连接不同设备等作用,其剩余寿命预测对系统健康管理起着十分重要的作用。针对单一传感器信号通常难以全面描述系统的潜在退化机制,论文提出一种基于多头注意力机制和长短时记忆神经网络的电机轴承剩余寿命预测模型。首先,基于马氏距离确定轴承性能退化起始点,将滚动轴承全寿命周期分为正常阶段与退化阶段;其次,使用自编码器自动提取振动信号特征,并将其与电机电流、轴承温度融合,构成多源信息特征矩阵;然后基于多头注意力机制和长短时记忆网络模型动态选择相关度较高的特征,提高寿命预测的准确性。最后,采用实验数据进行验证,结果表明所提出的模型具有更高的准确性。

基于电子鼻和电子舌与1D-CNN-LSTM模型的花椒产地快速溯源检测

针对不同产地花椒产品的溯源问题,提出一种基于电子鼻和电子舌结合一维卷积神经网络(One Dimension-Convolutional Neural Networks,1D-CNN)-长短期记忆网络(Long Short-Term Memory,LSTM)混合模型的花椒产地快速检测方法。以5个不同产地的花椒为试验对象,采用电子舌和电子鼻分别采集花椒样本的味觉和嗅觉指纹图谱信息,根据信号特点分别设计1D-CNN提取味觉和嗅觉信号中的局部空间特征,然后采用LSTM捕捉信号的时间序列特征,最后采用多层感知机融合两种特征并进行分类识别。实验结果表明,电子鼻与电子舌信息融合对不同产地花椒的分辨准确率优于单一设备,与其他深度模型相比,所提的模型分类准确性更高,其准确率、精确率、召回率、F1分数分别达到99.0%、99.1%、99.0%、0.989。以上研究将为不同产地花椒的快速鉴定提供新的方法,并为其他农产品的产地溯源检测提供新的研究思路。

基于特征层融合的EEG-NIRS识别方法研究

针对目前卷积神经网络对时序序列识别率较低、单模态数据信息量不充足等问题,提出了一种基于特征层融合的卷积神经网络(CNN)和双向长短期记忆(BiLSTM)网络组合的方法。首先在毒品成瘾患者的脑电图和近红外光谱数据上,利用全新的CNN和BiLSTM组合网络分别对双模态数据进行特征提取,将最后一层BiLSTM的输出作为特征并进行特征串联,然后对串联特征进行分类识别。特征融合实验结果表明,文章提出的CNNBiLSTM模型的分类效果最高准确率达到97.3%,并且双模融合方法进一步提高了分类准确率。