A Lightweight Convolutional Neural Network with Hierarchical Multi-Scale Feature Fusion for Image Classification

Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.

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。

基于多尺度Scale-Unet的单样本图像翻译

随着生成对抗网络(GAN)的发展,基于单样本的无监督图像到图像翻译(UI2I)取得了重大进展。然而,以前方法无法捕获图像中的复杂纹理并保留原始内容信息。为解决这个问题,提出了一种基于尺度可变U-Net结构(Scale—Unet)的新型单样本图像翻译结构SUGAN。所提出的SUGAN使用Scale—Unet作为生成器,利用多尺度结构和渐进方法不断改进网络结构,以从粗到细地学习图像特征。同时,提出了尺度像素损失scale-pixel来更好地约束保留原始内容信息,防止信息丢失。实验表明,与SinGAN、TuiGAN、TSIT、StyTR2等公共数据集Summer■Winter、Horse■Zebra上的方法相比,该方法生成图像的SIFID值平均降低了30%。所提方法可更好地保留图像内容信息,同时生成详细逼真的高质量图像。

An FPGA-based LDPC decoder with optimized scale factor of NMS decoding algorithm

Considering that the hardware implementation of the normalized minimum sum(NMS)decoding algorithm for low-density parity-check(LDPC)code is difficult due to the uncertainty of scale factor,an NMS decoding algorithm with variable scale factor is proposed for the near-earth space LDPC codes(8177,7154)in the consultative committee for space data systems(CCSDS)standard.The shift characteristics of field programmable gate array(FPGA)is used to optimize the quantization data of check nodes,and finally the function of LDPC decoder is realized.The simulation and experimental results show that the designed FPGA-based LDPC decoder adopts the scaling factor in the NMS decoding algorithm to improve the decoding performance,simplify the hardware structure,accelerate the convergence speed and improve the error correction ability.

High Dimension Multivariate Data Analysis for Small Group Samples of Chemical Volatile Profiles of African Nightshade Species

Quantitative headspace analysis of volatiles emitted by plants or any other living organisms in chemical ecology studies generates large multidimensional data that require extensive mining and refining to extract useful information. More often the number of variables and the quantified volatile compounds exceed the number of observations or samples and hence many traditional statistical analysis methods become inefficient. Here, we employed machine learning algorithm, random forest (RF) in combination with distance-based procedure, similarity percentage (SIMPER) as preprocessing steps to reduce the data dimensionality in the chemical profiles of volatiles from three African nightshade plant species before subjecting the data to non-metric multidimensional scaling (NMDS). In addition, non-parametric methods namely permutational multivariate analysis of variance (PERMANOVA) and analysis of similarities (ANOSIM) were applied to test hypothesis of differences among the African nightshade species based on the volatiles profiles and ascertain the patterns revealed by NMDS plots. Our results revealed that there were significant differences among the African nightshade species when the data’s dimension was reduced using RF variable importance and SIMPER, as also supported by NMDS plots that showed S. scabrum being separated from S. villosum and S. sarrachoides based on the reduced data variables. The novelty of our work is on the merits of using data reduction techniques to successfully reveal differences in groups which could have otherwise not been the case if the analysis were performed on the entire original data matrix characterized by small samples. The R code used in the analysis has been shared herein for interested researchers to customise it for their own data of similar nature.

改进Multi-scale ResNet的蔬菜叶部病害识别

基于深度网络的蔬菜叶部病害图像识别模型虽然性能显著,但由于存在参数量巨大、训练时间长、存储成本与计算成本过高等问题,仍然难以部署到农业物联网的边缘计算设备、嵌入式设备、移动设备等硬件资源受限的领域。该研究在残差网络(ResNet18)的基础上,提出了改进型的多尺度残差(Multi-scale ResNet)轻量级病害识别模型,通过增加多尺度特征提取模块,改变残差层连接方式,将大卷积核分解,进行群卷积操作,显著减少了模型参数、降低了存储空间和运算开销。结果表明,在PlantVillage和AI Challenge2018中15种病害图像数据集中取得了95.95%的准确率,在自采集的7种真实环境病害图像数据中取得了93.05%的准确率,在准确率较ResNet18下降约3.72%的情况下,模型的训练参数减少93%左右,模型总体尺寸缩减约35%。该研究提出的改进型Multi-scale ResNet使蔬菜叶部病害识别模型具备了在硬件受限的场景下部署和运行的能力,平衡了模型的复杂度和识别精度,为基于深度网络模型的病害识别系统进行边缘部署提供了思路。

Morphology Similarity Distance for Bearing Fault Diagnosis Based on Multi-Scale Permutation Entropy

Bearings are crucial components in rotating machines,which have direct effects on industrial productivity and safety.To fast and accurately identify the operating condition of bearings,a novel method based on multi⁃scale permutation entropy(MPE)and morphology similarity distance(MSD)is proposed in this paper.Firstly,the MPE values of the original signals were calculated to characterize the complexity in different scales and they constructed feature vectors after normalization.Then,the MSD was employed to measure the distance among test samples from different fault types and the reference samples,and achieved classification with the minimum MSD.Finally,the proposed method was verified with two experiments concerning artificially seeded damage bearings and run⁃to⁃failure bearings,respectively.Different categories were considered for the two experiments and high classification accuracies were obtained.The experimental results indicate that the proposed method is effective and feasible in bearing fault diagnosis.

融合Multi-scale CNN和Bi-LSTM的人脸表情识别研究

为了有效改善现有人脸表情识别模型中存在信息丢失严重、特征信息之间联系不密切的问题,提出一种融合多尺度卷积神经网络(Multi-scale CNN)和双向长短期记忆(Bi-LSTM)的模型。Bi-LSTM可以增强特征信息间的联系与信息的维持,在Multi-scale CNN中通过不同尺度的卷积核可以提取到更加丰富的特征信息,并通过加入批标准化(BN)层与特征融合处理,从而加快网络的收敛速度,有利于特征信息的重利用,再将两者提取到的特征信息进行融合,最后将改进的正则化方法应用到目标函数中,减小网络复杂度和过拟合。在JAFFE和FER-2013公开数据集上进行实验,准确率分别达到了95.455%和74.115%,由此证明所提算法的有效性和先进性。

基于Encoder-Decoder LSTM的电梯制动滑移量预测方法研究

电梯曳引系统的可靠性是电梯安全性能评估中的重要部分,紧急制动滑移量是其重要反映指标,对滑移量进行时序预测能有利保证电梯安全,具有重要意义。采用结合Encoder-Decoder的LSTM模型学习电梯紧急制动滑移量的增长过程,进行多步预测来获得未来区间内滑移预测数据。通过与RNN和LSTM模型预测结果的对比,表明Encoder-Decoder LSTM模型针对电梯紧急制动滑移量的预测具有较好的精度,可以作为电梯曳引能力评估的重要手段。

基于长短时记忆网络的Encoder-Decoder多步交通流预测模型

交通流序列多为单步预测。为实现交通流序列的多步预测,提出一种基于编码器解码器(encoder-decoder,ED)框架的长短期记忆网络(long short-term memory,LSTM)模型,即ED LSTM模型。将自回归滑动平均、支持向量回归机、XGBOOST、循环神经网络、卷积神经网络、LSTM作为对照组进行实验验证。实验结果表明,当预测时间步长增加时,ED框架能够减缓模型性能的下降趋势,LSTM能够充分挖掘时间序列中的非线性关系。除此之外,在单变量输入的情况下,在PEMS-04数据集上,当预测时间步长为t+1到t+12的12个时间步时,ED LSTM模型的均方根误差(root mean squard error,RMSE)及平均绝对误差(mean absolute error,MAE)分别下降0.210~5.422、0.061~0.191。相较于单因素输入,多因素输入的ED LSTM模型在12个预测时间步长下,RMSE、MAE分别下降0.840、0.136。实验证明了ED LSTM模型能够有效地用于交通流序列的多步及单因素、多因素预测任务。

Application of Multi-Scale Tracking Radar Echoes Scheme in Quantitative Precipitation Nowcasting

A new radar echo tracking algorithm known as multi-scale tracking radar echoes by cross-correlation （MTREC） was developed in this study to analyze movements of radar echoes at different spatial scales. Movement of radar echoes, particularly associated with convective storms, exhibits different characteristics at various spatial scales as a result of complex interactions among meteorological systems leading to the formation of convective storms. For the null echo region, the usual correlation technique produces zero or a very small magnitude of motion vectors. To mitigate these constraints, MTREC uses the tracking radar echoes by correlation （TREC） technique with a large ＂box＂ to determine the systematic movement driven by steering wind, and MTREC applies the TREC technique with a small ＂box＂ to estimate small-scale internal motion vectors. Eventually, the MTREC vectors are obtained by synthesizing the systematic motion and the small-scale internal motion. Performance of the MTREC technique was compared with TREC technique using case studies： the Khanun typhoon on 11 September 2005 observed by Wenzhou radar and a squall-line system on 23 June 2011 detected by Beijing radar. The results demonstrate that more spatially smoothed and continuous vector fields can be generated by the MTREC technique, which leads to improvements in tracking the entire radar reflectivity pattern. The new multi-scMe tracking scheme was applied to study its impact on the performance of quantitative precipitation nowcasting. The location and intensity of heavy precipitation at a 1-h lead time was more consistent with quantitative precipitation estimates using radar and rain gauges.

基于改进Multi-Scale AlexNet的番茄叶部病害图像识别

番茄同种病害在不同发病阶段表征差异明显,不同病害又表现出一定的相似性,传统模式识别方法不能体现病害病理表征的动态变化,实用性较差。针对该问题,基于卷积神经网络提出一种适用于移动平台的多尺度识别模型,并基于此模型开发了面向农业生产人员的番茄叶部病害图像识别系统。该文详细描述了AlexNet的结构,分析其不足,结合番茄病害叶片图像特点,去除局部响应归一化层、修改全连接层、设置不同尺度卷积核提取特征,设计了基于AlexNet的多感受野识别模型,并基于Android实现了使用此模型的番茄叶部病害图像识别系统。Multi-ScaleAlexNet模型运行所耗内存为29.9MB,比原始AlexNet的内存需求652MB降低了95.4%,该模型对番茄叶部病害及每种病害早中晚期的平均识别准确率达到92.7%,基于此模型的Andriod端识别系统在田间的识别率达到89.2%,能够满足生产实践中移动平台下的病害图像识别需求。研究结果可为基于卷积神经网络的作物病害图像识别提供参考,为作物病害的自动化识别和工程化应用参考。

Multi-scale Cyclone Activity in the Changjiang River–Huaihe River Valleys during Spring and Its Relationship with Rainfall Anomalies

Based on the recognition framework of the outermost closed contours of cyclones, an automated identification algorithm capable of identifying the multi-scale cyclones that occur during spring in the Changjiang River-Huaihe River valleys （CHV） were developed. We studied the characteristics of the multi-scale cyclone activity that affects CHV and its relationship with rainfall during spring since 1979. The results indicated that the automated identification algorithm for cyclones proposed in this paper could intuitively identify multi-scale cyclones that affect CHV. The algorithm allows for effectively describing the shape and coverage area of the closed contours around the periphery of cyclones. We found that, compared to the meso- and sub-synoptic scale cyclone activities, the synoptic-scale cyclone activity showed more intimate correlation with the overall activity intensity of multi-scale CHV cyclones during spring. However, the frequency of occurrence of sub-synoptic scale cyclones was the highest, and their effect on changes in CHV cyclone activity could not be ignored. Based on the area of impact and the depth of the cyclones, the sub-synoptic scale, synoptic scale and comprehensive cyclone intensity indices were further defined, which showed a positive correlation with rainfall in CHV during spring. Additionally, the comprehensive cyclone intensity index was a good indicator of strong rainfall events.

A Multi-Scale Urban Atmospheric Dispersion Model for Emergency Management

To assist emergency management planning and prevention in case of hazardous chemical release into the atmosphere,especially in densely built-up regions with large populations,a multi-scale urban atmospheric dispersion model was established.Three numerical dispersion experiments,at horizontal resolutions of 10 m,50 m and 3000 m,were performed to estimate the adverse effects of toxic chemical release in densely built-up areas.The multi-scale atmospheric dispersion model is composed of the Weather Forecasting and Research （WRF） model,the Open Source Field Operation and Manipulation software package,and a Lagrangian dispersion model.Quantification of the adverse health effects of these chemical release events are given by referring to the U.S.Environmental Protection Agency＇s Acute Exposure Guideline Levels.The wind fields of the urban-scale case,with 3 km horizontal resolution,were simulated by the Beijing Rapid Update Cycle system,which were utilized by the WRF model.The sub-domain-scale cases took advantage of the computational fluid dynamics method to explicitly consider the effects of buildings.It was found that the multi-scale atmospheric dispersion model is capable of simulating the flow pattern and concentration distribution on different scales,ranging from several meters to kilometers,and can therefore be used to improve the planning of prevention and response programs.

Crustal structure beneath the Qilian Orogen Zone from multiscale seismic tomography

The Qilian Orogen Zone(QOZ), located in the north margin of the Tibetan Plateau, is the key area for understanding the deformation and dynamics process of Tibet. Numerous geological and geophysical studies have been carried out on the mechanics of the Tibetan Plateau deformation and uplift; however, the detailed structure and deformation style of the Qilian Orogen Zone have remained uncertain due to poor geophysical data coverage and limited resolution power of inversion algorithms. In this study, we analyze the P-wave velocity structure beneath the Qilian Orogen Zone, obtained by applying multi-scale seismic tomography technique to P-wave arrival time data recorded by regional seismic networks. The seismic tomography algorithm used in this study employs sparsity constraints on the wavelet representation of the velocity model via L1-norm regularization. This algorithm can deal efficiently with uneven-sampled volumes, and can obtain multi-scale images of the velocity model. Our results can be summarized as follows:(1) The crustal velocity structure is strongly inhomogeneous and consistent with the surface geological setting. Significant low-velocity anomalies exist in the crust of northeastern Tibet, and slight high-velocity anomalies exist beneath the Qaidam Basin and Alxa terrane.(2)The Qilian Orogen Zone can be divided into two main parts by the Laji Shan Faults: the northwestern part with a low-velocity feature, and the southeastern part with a high-velocity feature at the upper and middle crust.(3) Our tomographic images suggest that northwestern and southeastern Qilian Orogen Zones have undergone different tectonic processes. In the northwest Qilian Orogen Zone, the deformation and growth of the Northern Tibetan Plateau has extended to the Heli Shan and Beida Shan region by northward overthrusting at the upper crust and thickening in the lower crust. We speculate that in the southeast Qilian Orogen Zone the deformation and growth of the Northern Tibet Plateau were of strike-slip style at the upper crust; in the lower crust, the evidence suggests ductile shear extrusion style and active frontage extension to the Alxa terrane.(4) The multi-scale seismic tomography technique provides multiscale analysis and sparse constraints, which has allowed to us obtain stable, high-resolution results.

Study on Multi-Scale Blending Initial Condition Perturbations for a Regional Ensemble Prediction System

An initial conditions （ICs） perturbation method was developed with the aim to improve an operational regional ensemble prediction system （REPS）. Three issues were identified and investigated： （1） the impacts of perturbation scale on the ensemble spread and forecast skill of the REPS; （2） the scale characteristic of the IC perturbations of the REPS; and （3） whether the REPS＇s skill could be improved by adding large-scale information to the IC perturbations. Numerical experiments were conducted to reveal the impact of perturbation scale on the ensemble spread and forecast skill. The scales of IC perturbations from the REPS and an operational global ensemble prediction system （GEPS） were analyzed. A ＂multi-scale blending＂ （MSB） IC perturbation scheme was developed, and the main findings can be summarized as follows： The growth rates of the ensemble spread of the REPS are sensitive to the scale of the IC perturbations; the ensemble forecast skills can benefit from large-scale perturbations; the global ensemble IC perturbations exhibit more power at larger scales, while the regional ensemble IC perturbations contain more power at smaller scales; the MSB method can generate IC perturbations by combining the small-scale component from the REPS and the large-scale component from the GEPS; the energy norm growth of the MSB-generated perturbations can be appropriate at all forecast lead times; and the MSB-based REPS shows higher skill than the original system, as determined by ensemble forecast verification.

The Multi-Scale Numerical Modeling System for Research on the Relationship between Urban Planning and Meteorological Environment

Considering the urban characteristics, a customized multi-scale numerical modeling system is established to simulate the urban meteorological environment. The system mainly involves three spatial scales: the urban scale, urban sub-domain scale, and single to few buildings scale. In it, different underlying surface types are employed, the building drag factor is used to replace its roughness in the influence on the urban wind field, the effects of building distribution, azimuth and screening of shortwave radiation are added, and the influence of anthropogenic heating is also taken into account. All the numerical tests indicate that the simulated results are reasonably in agreement with the observational data, so the system can be used to simulate the urban meteorological environment. Making use of it, the characteristics of the meteorological environment from the urban to urban sub-domain scales, even the among-buildings scale, can be recognized. As long as the urban planning scheme is given, the corresponding simulated results can be obtained so as to meet the need of optimizing urban planning.

基于Multi-Light模型的奶牛个体识别研究

为了解决大规模智能化奶牛养殖场对奶牛个体识别存在模型大、识别速度慢的问题,试验构建了一种用于识别奶牛个体的多尺度轻量化卷积神经网络(Multi-Light)模型,将拍摄的奶牛图像经过标注后利用DeepLab V3模型从复杂背景中分割出单头奶牛图像;在Multi-Light模型中引入空洞卷积,保证该模型参数量不变的同时增强提取图像全局信息的能力;加入多尺度卷积模块增强该模型对不同尺度特征点的检测能力,在该模型中使用短路连接以保证特征不丢失,提升模型的识别精度;此外,利用通道注意力机制提高了该模型识别精度,同时使该模型具有更多的非线性;最后将分割得到的奶牛图像数据集输入Multi-Light模型进行训练。结果表明:Multi-Light模型对奶牛个体识别的精度达98.51%,高于其他经典模型对奶牛个体的识别率;与轻量级模型对比,Multi-Light模型的大小为5.86 MB,在具备高识别精度的前提下参数量较少。说明试验所搭建的Multi-Light模型克服了传统方法中需要对特征进行人为提取、提取特征方法不够鲁棒、识别模型参数量大及识别速度慢的缺点,为奶牛个体轻量化识别提供了参考。

Multi-scale Fractal Characteristics of Atmospheric Boundary-Layer Turbulence

The turbulence data are decomposed to multi-scales and its respective fractal dimensions are computed. The conclusions are drawn from investigating the variation of fractal dimensions. With the level of decomposition increasing, the low-frequency part extracted from the turbulence signals tends to be simple and smooth, the dimensions decrease; the high-frequency part shows complex, the dimensions are fixed, about 1.70 on the average, which indicates clear self-similarity characteristics.

Multi-scale variability of subsurface temperature in the South China Sea

Using Morlet wavelet transform and harmonic analysis the multi-scale variability of subsurface temperature in the South China Sea is studied by analyzing one-year (from April 1998 to April 1999) ATLAS mooring data. By wavelet transform, annual and semi-annual cycle as well as intrasea-sonal variations are found, with different dominance, in subsurface temperature. For annual harmonic cycle, both the downward net surface heat flux and thermocline vertical movement partially control the subsurface temperature variability. For semi-annual cycle and intraseasonal variability, the subsurface temperature variability is mainly linked to the vertical displacement of thermocline.