基于时空特征融合的Encoder-Decoder多步4D短期航迹预测

航迹预测在确保空中交通安全、高效运行中扮演着至关重要的角色。所预测的航迹信息是航迹优化、冲突告警等决策工具的输入,而预测准确性取决于模型对航迹序列特征的提取能力。航迹序列数据是具有丰富时空特征的多维时间序列,其中每个变量都呈现出长短期的时间变化模式,并且这些变量之间还存在着相互依赖的空间信息。为了充分提取这种时空特征,本文提出了基于融合时空特征的编码器-解码器(Spatio-Temporal EncoderDecoder,STED)航迹预测模型。在Encoder中使用门控循环单元(Gated Recurrent Unit,GRU)、卷积神经网络(Convolutional Neural Network,CNN)和注意力机制(Attention,AT)构成的双通道网络来分别提取航迹时空特征,Decoder对时空特征进行拼接融合,并利用GRU对融合特征进行学习和递归输出,实现对未来多步航迹信息的预测。利用真实的航迹数据对算法性能进行验证,实验结果表明,所提STED网络模型能够在未来10 min预测范围内进行高精度的短期航迹预测,相比于LSTM、CNN-LSTM和AT-LSTM等数据驱动航迹预测模型具有更高的精度。此外,STED网络模型预测一个航迹点平均耗时为0.002 s,具有良好的实时性。

基于encoder-decoder框架的城镇污水厂出水水质预测

由于污水厂的出水水质指标繁多、污水处理过程中反应复杂、时序非线性程度高,基于机理模型的预测方法无法取得理想效果。针对此问题,提出基于深度学习的污水厂出水水质预测方法,并以吉林省某污水厂监测水质为来源数据,利用多种结合encoder-decoder结构的神经网络预测水质。结果显示,所提结构对LSTM和GRU网络预测能力都有一定提升,对长期预测能力提升更加显著,ED-GRU模型效果最佳,短期预测中的4个出水水质指标均方根误差(RMSE)为0.7551、0.2197、0.0734、0.3146,拟合优度(R2)为0.9013、0.9332、0.9167、0.9532,可以预测出水质局部变化,而长期预测中的4个指标RMSE为1.7204、1.7689、0.4478、0.8316,R2为0.4849、0.5507、0.4502、0.7595,可以预测出水质变化趋势,与顺序结构相比,短期预测RMSE降低10%以上,R2增加2%以上,长期预测RMSE降低25%以上,R2增加15%以上。研究结果表明,基于encoder-decoder结构的神经网络可以对污水厂出水水质进行准确预测,为污水处理工艺改进提供技术支撑。

Anomaly detection in smart grid based on encoder-decoder framework with recurrent neural network

Anomaly detection in smart grid is critical to enhance the reliability of power systems. Excessive manpower has to be involved in analyzing the measurement data collected from intelligent motoring devices while performance of anomaly detection is still not satisfactory. This is mainly because the inherent spatio-temporality and multi-dimensionality of the measurement data cannot be easily captured. In this paper, we propose an anomaly detection model based on encoder-decoder framework with recurrent neural network （RNN）. In the model, an input time series is reconstructed and an anomaly can be detected by an unexpected high reconstruction error. Both Manhattan distance and the edit distance are used to evaluate the difference between an input time series and its reconstructed one. Finally, we validate the proposed model by using power demand data from University of California, Riverside （UCR） time series classification archive and IEEE 39 bus system simulation data. Results from the analysis demonstrate that the proposed encoder-decoder framework is able to successfully capture anomalies with a precision higher than 95%.

利用Encoder-Decoder框架的深度学习网络实现绕射波分离及成像

利用单纯绕射波场实现地下地质异常体的识别具有坚实的理论基础,对应的实施方法得到了广泛研究,且有效地应用于实际勘探。但现有技术在微小尺度异常体成像方面收效甚微,相关研究多数以射线传播理论为基础,对于影响绕射波分离成像精度的因素分析并不完备。相较于反射波,由于存在不连续构造而产生的绕射波能量微弱并且相互干涉,同时环境干扰使得绕射波进一步湮没。因此,更高精度的波场分离及单独成像是现阶段基于绕射波超高分辨率处理、解释的重点研究方向。为此,首先针对地球物理勘探中地质异常体的准确定位,以携带高分辨率信息的绕射波为研究对象,系统分析在不同尺度、不同物性参数的异常体情况下绕射波的能量大小及形态特征,掌握绕射波与其他类型波叠加的具体形式;然后根据相应特征性质提出基于深度学习技术的绕射波分离成像方法,即利用Encoder-Decoder框架的空洞卷积网络捕获绕射波场特征,从而实现绕射波分离,基于速度连续性原则构建单纯绕射波场的偏移速度模型并完成最终成像。数据测试表明,该方法最终可满足微小地质异常体高精度识别的需求。

Underwater Acoustic Signal Noise Reduction Based on a Fully Convolutional Encoder-Decoder Neural Network

Noise reduction analysis of signals is essential for modern underwater acoustic detection systems.The traditional noise reduction techniques gradually lose efficacy because the target signal is masked by biological and natural noise in the marine environ-ment.The feature extraction method combining time-frequency spectrograms and deep learning can effectively achieve the separation of noise and target signals.A fully convolutional encoder-decoder neural network(FCEDN)is proposed to address the issue of noise reduc-tion in underwater acoustic signals.The time-domain waveform map of underwater acoustic signals is converted into a wavelet low-frequency analysis recording spectrogram during the denoising process to preserve as many underwater acoustic signal characteristics as possible.The FCEDN is built to learn the spectrogram mapping between noise and target signals that can be learned at each time level.The transposed convolution transforms are introduced,which can transform the spectrogram features of the signals into listenable audio files.After evaluating the systems on the ShipsEar Dataset,the proposed method can increase SNR and SI-SNR by 10.02 and 9.5dB,re-spectively.

基于Encoder-Decoder-ILSTM模型的瓦斯浓度预测研究

近年来,神经网络在各领域均发挥了巨大作用,同样在煤矿瓦斯浓度预测当中也有应用。为了提高模型的预测精度和实时性,结合Encoder-Decoder结构、长短期记忆形成、蛇优化算法提出了一种新的神经网络,为促进煤矿安全生产提供了技术支持。

Dynamic interactive bitwise meta-holography with ultra-high computational and display frame rates

Interactive holography offers unmatched levels of immersion and user engagement in the field of future display.Despite of the substantial progress has been made in dynamic meta-holography,the realization of real-time,highly smooth interactive holography remains a significant challenge due to the computational and display frame rate limitations.In this study,we introduced a dynamic interactive bitwise meta-holography with ultra-high computational and display frame rates.To our knowledge,this is the first reported practical dynamic interactive metasurface holographic system.We spa-tially divided the metasurface device into multiple distinct channels,each projecting a reconstructed sub-pattern.The switching states of these channels were mapped to bitwise operations on a set of bit values,which avoids complex holo-gram computations,enabling an ultra-high computational frame rate.Our approach achieves a computational frame rate of 800 kHz and a display frame rate of 23 kHz on a low-power Raspberry Pi computational platform.According to this methodology,we demonstrated an interactive dynamic holographic Tetris game system that allows interactive gameplay,color display,and on-the-fly hologram creation.Our technology presents an inspiration for advanced dynamic meta-holography,which is promising for a broad range of applications including advanced human-computer interaction,real-time 3D visualization,and next-generation virtual and augmented reality systems.

Resilience-incorporated seismic risk assessment of precast concrete frames with“dry”connections

A resilience-incorporated risk assessment framework is proposed and demonstrated in this study to manifest the advantageous seismic resilience of precast concrete frame(PCF)structures with“dry”connections in terms of their low damage and rapid recovery.The framework integrates various uncertainties in the seismic hazard,fragility,capacity,demand,loss functions,and post-earthquake recovery.In this study,the PCF structures are distinguished from ordinary reinforced concrete frame(RCF)structures by characterizing multiple limit states for the PCF based on its unique damage mechanisms.Accordingly,probabilistic story-wise pushover analyses are performed to yield story-wise capacities for the predefined limit states.In the seismic resilience analysis,a step-wise recovery model is proposed to idealize the functionality recovery process,with separate considerations of the repair and non-repair events.The recovery model leverages the economic loss and downtime to delineate the stochastic post-earthquake recovery curves for the resilience loss estimation.As such,contingencies in the probabilistic post-earthquake repairs are incorporated and the empirical judgments on the recovery parameters are largely circumvented.The proposed framework is demonstrated through a comparative study between two“dry”connected PCFs and one RCF designed as alternative structural systems for a prototype building.The results from the risk quantification indicate that the PCFs show reduced loss hazards and lower expected losses relative to the RCF.Particularly,the PCF equipped with energy dissipation devices at the“dry”connections largely reduces the expected economic loss,downtime,and resilience loss by 29%,56%,and 60%,respectively,compared to the RCF.

Experimental and numerical study regarding H-steel all-bolted connection steel frame with composite wall boards

H-steel all-bolted connection steel frame structures with heat preservation and decoration composite wall boards were investigated and the seismic performances of three scaled specimens were studied.The failure modes,hysteresis curves,bearing capacity,ductility,energy dissipation capacity,stiffness degradation and strain distribution were discussed.The calculation method of structural theoretical internal force was presented.The results showed that the overall structural seismic performance was better,and the structural ductility met the demands of elastic-plastic inter-story drift angle for seismic design.The H-steel weak-axis connection structure obtained better energy dissipation capacity,and its bearing capacity and stiffness were slightly different from the strong-axis connection.The heat preservation and decoration performance of composite wallboard and the all-bolted connection of the steel frame realized prefabrication during the whole construction period.The plastic hinge of the steel beam can be moved outwards because of the L-angles,which effectively avoids stress concentration in joint areas and expands the plastic hinge range.The errors between the theoretical structural capacity calculated by the plastic analysis method and the test results were within 2.44%.In addition,structural failure mechanisms and bearing capacities were verified by the finite element(FE)analysis,and the effects of the main parameters on the structures were investigated.The FE verification results were the same as in the test.The research results provide theoretical support and technical guidance for the application of thermal insulation and decorative composite wall panels in H-shaped steel all-bolted steel frames.

Cascaded ELM-Based Joint Frame Synchronization and Channel Estimation over Rician Fading Channel with Hardware Imperfections

Due to the interdependency of frame synchronization(FS)and channel estimation(CE),joint FS and CE(JFSCE)schemes are proposed to enhance their functionalities and therefore boost the overall performance of wireless communication systems.Although traditional JFSCE schemes alleviate the influence between FS and CE,they show deficiencies in dealing with hardware imperfection(HI)and deterministic line-of-sight(LOS)path.To tackle this challenge,we proposed a cascaded ELM-based JFSCE to alleviate the influence of HI in the scenario of the Rician fading channel.Specifically,the conventional JFSCE method is first employed to extract the initial features,and thus forms the non-Neural Network(NN)solutions for FS and CE,respectively.Then,the ELMbased networks,named FS-NET and CE-NET,are cascaded to capture the NN solutions of FS and CE.Simulation and analysis results show that,compared with the conventional JFSCE methods,the proposed cascaded ELM-based JFSCE significantly reduces the error probability of FS and the normalized mean square error(NMSE)of CE,even against the impacts of parameter variations.

Frame Length Dependency for Fundamental Frequency Extraction in Noisy Speech

The fundamental frequency plays a significant part in understanding and perceiving the pitch of a sound. The pitch is a fundamental attribute employed in numerous speech-related works. For fundamental frequency extraction, several algorithms have been developed which one to use relies on the signal’s characteristics and the surrounding noise. Thus, the algorithm’s noise resistance becomes more critical than ever for precise fundamental frequency estimation. Nonetheless, numerous state-of-the-art algorithms face struggles in achieving satisfying outcomes when confronted with speech recordings that are noisy with low signal-to-noise ratio (SNR) values. Also, most of the recent techniques utilize different frame lengths for pitch extraction. From this point of view, This research considers different frame lengths on male and female speech signals for fundamental frequency extraction. Also, analyze the frame length dependency on the speech signal analytically to understand which frame length is more suitable and effective for male and female speech signals specifically. For the validation of our idea, we have utilized the conventional autocorrelation function (ACF), and state-of-the-art method BaNa. This study puts out a potent idea that will work better for speech processing applications in noisy speech. From experimental results, the proposed idea represents which frame length is more appropriate for male and female speech signals in noisy environments.

Real-Time Mosaic Method of Aerial Video Based on Two-Stage Key Frame Selection Method

A two-stage automatic key frame selection method is proposed to enhance stitching speed and quality for UAV aerial videos. In the first stage, to reduce redundancy, the overlapping rate of the UAV aerial video sequence within the sampling period is calculated. Lagrange interpolation is used to fit the overlapping rate curve of the sequence. An empirical threshold for the overlapping rate is then applied to filter candidate key frames from the sequence. In the second stage, the principle of minimizing remapping spots is used to dynamically adjust and determine the final key frame close to the candidate key frames. Comparative experiments show that the proposed method significantly improves stitching speed and accuracy by more than 40%.

基于注意力机制的Encoder-Decoder光伏发电预测模型

影响光伏发电系统出力的天气因素具有很大的波动性和不连续性,因此需要创建合适的预测模型来对光伏出力特性进行精准预测,从而保证电网系统的有效运行。本文通过最大信息系数选择合适的历史光伏发电数据,将其作为特征之一进行输入数据重构,并在由LSTM神经元构建的Encoder-Decoder模型上引入注意力机制,最终得到结合注意力机制的Encoder-Decoder光伏发电预测模型。经实际光伏电厂算例分析,验证了所提模型在光伏发电预测方面的准确性和适用性。

A Road Extraction Method for Remote Sensing Image Based on Encoder-Decoder Network

According to the characteristics of the road features,an Encoder-Decoder deep semantic segmentation network is designed for the road extraction of remote sensing images.Firstly,as the features of the road target are rich in local details and simple in semantic features,an Encoder-Decoder network with shallow layers and high resolution is designed to improve the ability to represent detail information.Secondly,as the road area is a small proportion in remote sensing images,the cross-entropy loss function is improved,which solves the imbalance between positive and negative samples in the training process.Experiments on large road extraction datasets show that the proposed method gets the recall rate 83.9%,precision 82.5%and F1-score 82.9%,which can extract the road targets in remote sensing images completely and accurately.The Encoder-Decoder network designed in this paper performs well in the road extraction task and needs less artificial participation,so it has a good application prospect.

一种基于模板匹配的芯片Frame图像分割算法

针对背景复杂、边界模糊以及芯片相连等特征的芯片Frame图像,提出了一种基于模板匹配的芯片Frame图像分割算法。首先,对整幅芯片Frame图像预分割出多个区域模块;然后,基于区域模块图像采取模板匹配算法匹配单芯片图像;最后,通过合并单芯片的重叠匹配框并记录合并框的坐标信息的方式分割出单芯片图像。实验结果表明:选取合适的模板和阈值,能使该算法的分割准确率达到100%,并且比不基于区域模块匹配的分割算法节省了至少45.76%的分割时间,满足芯片Frame高精度和高速度的分割需求,为芯片图像分割算法的研究提供了一种新思路。

Encoder-Decoder Based LSTM Model to Advance User QoE in 360-Degree Video

The development of multimedia content has resulted in a massiveincrease in network traffic for video streaming. It demands such types ofsolutions that can be addressed to obtain the user’s Quality-of-Experience(QoE). 360-degree videos have already taken up the user’s behavior by storm.However, the users only focus on the part of 360-degree videos, known as aviewport. Despite the immense hype, 360-degree videos convey a loathsomeside effect about viewport prediction, making viewers feel uncomfortablebecause user viewport needs to be pre-fetched in advance. Ideally, we canminimize the bandwidth consumption if we know what the user motionin advance. Looking into the problem definition, we propose an EncoderDecoder based Long-Short Term Memory (LSTM) model to more accuratelycapture the non-linear relationship between past and future viewport positions. This model takes the transforming data instead of taking the direct inputto predict the future user movement. Then, this prediction model is combinedwith a rate adaptation approach that assigns the bitrates to various tiles for360-degree video frames under a given network capacity. Hence, our proposedwork aims to facilitate improved system performance when QoE parametersare jointly optimized. Some experiments were carried out and compared withexisting work to prove the performance of the proposed model. Last but notleast, the experiments implementation of our proposed work provides highuser’s QoE than its competitors.

Classification of Arrhythmia Based on Convolutional Neural Networks and Encoder-Decoder Model

As a common and high-risk type of disease,heart disease seriously threatens people’s health.At the same time,in the era of the Internet of Thing(IoT),smart medical device has strong practical significance for medical workers and patients because of its ability to assist in the diagnosis of diseases.Therefore,the research of real-time diagnosis and classification algorithms for arrhythmia can help to improve the diagnostic efficiency of diseases.In this paper,we design an automatic arrhythmia classification algorithm model based on Convolutional Neural Network(CNN)and Encoder-Decoder model.The model uses Long Short-Term Memory(LSTM)to consider the influence of time series features on classification results.Simultaneously,it is trained and tested by the MIT-BIH arrhythmia database.Besides,Generative Adversarial Networks(GAN)is adopted as a method of data equalization for solving data imbalance problem.The simulation results show that for the inter-patient arrhythmia classification,the hybrid model combining CNN and Encoder-Decoder model has the best classification accuracy,of which the accuracy can reach 94.05%.Especially,it has a better advantage for the classification effect of supraventricular ectopic beats(class S)and fusion beats(class F).

Robust Cultivated Land Extraction Using Encoder-Decoder

Cultivated land extraction is essential for sustainable development and agriculture.In this paper,the network we propose is based on the encoder-decoder structure,which extracts the semantic segmentation neural network of cultivated land from satellite images and uses it for agricultural automation solutions.The encoder consists of two part:the first is the modified Xception,it can used as the feature extraction network,and the second is the atrous convolution,it can used to expand the receptive field and the context information to extract richer feature information.The decoder part uses the conventional upsampling operation to restore the original resolution.In addition,we use the combination of BCE and Loves-hinge as a loss function to optimize the Intersection over Union(IoU).Experimental results show that the proposed network structure can solve the problem of cultivated land extraction in Yinchuan City.

CHARACTEIZATIONS OF WOVENT g-FRAMES AND WEAVING g-FRAMES IN HILBERT SPACESS AND C^(*)-MODULES

In this paper,using Parseval frames we generalize Sun’s results to g-frames in Hilbert C^(*)-modules.Moreover,for g-frames in Hilbert spaces,we present some characterizations in terms of a family of frames,not only for orthonormal bases.Also,we have a note about a comment and a relation in the proof of Proposition 5.3 in[D.Li et al.,On weaving g-frames for Hilbert spaces,Complex Analysis and Operator Theory,2020].Finally,we have some results for g-Riesz bases,woven and P-woven g-frames.

Experimental and Numerical Study on Progressive Collapse Analysis of a Glulam Frame Structure:I.Side Column Exposed to Fire

This paper presents experimental and numerical investigations on progressive collapse behavior of a two-story glulam frame when the side column is exposed to ISO834 standard fire.The collapse mechanism initiated by fire is identified.The experimental results show that the progressive collapse of a glulam frame could be described for three stages,namely bending effect stage,catenary effect stage and failure stage,respectively.These stages are discussed in detail to understand the structural behavior before and during collapse.It is demonstrated that the entire frame slopes towards the side of the heated column,and the“overturning”collapse occurs eventually.The catenary effect of beams is the main reason for the progressive collapse of the frame.In addition,a finite element model of a glulam frame is established to simulate the progressive collapse behavior.The effects of axial loads on the columns are summarized.The numerical simulation results agree well with the experimental results,which could verify the effectiveness and practicability of finite element simulation.Furthermore,the progressive collapse resistance of the frame in practical design were proposed.