Improved edge lightweight YOLOv4 and its application in on-site power system work

A“cloud-edge-end”collaborative system architecture is adopted for real-time security management of power system on-site work,and mobile edge computing equipment utilizes lightweight intelligent recognition algorithms for on-site risk assessment and alert.Owing to its lightweight and fast speed,YOLOv4-Tiny is often deployed on edge computing equipment for real-time video stream detection;however,its accuracy is relatively low.This study proposes an improved YOLOv4-Tiny algorithm based on attention mechanism and optimized training methods,achieving higher accuracy without compromising the speed.Specifically,a convolution block attention module branch is added to the backbone network to enhance the feature extraction capability and an efficient channel attention mechanism is added in the neck network to improve feature utilization.Moreover,three optimized training methods:transfer learning,mosaic data augmentation,and label smoothing are used to improve the training effect of this improved algorithm.Finally,an edge computing equipment experimental platform equipped with an NVIDIA Jetson Xavier NX chip is established and the newly developed algorithm is tested on it.According to the results,the speed of the improved YOLOv4-Tiny algorithm in detecting on-site dress code compliance datasets is 17.25 FPS,and the mean average precision(mAP)is increased from 70.89%to 85.03%.

Aerodynamic design on high-speed trains

Compared with the traditional train,the operational speed of the high-speed train has largely improved,and thedynamicenvironmentofthetrainhaschangedfromoneof mechanical domination to one of aerodynamic domination.The aerodynamic problem has become the key technological challenge of high-speed trains and significantl affects the economy,environment,safety,and comfort.In this paper,the relationships among the aerodynamic design principle,aerodynamic performance indexes,and design variables are firs studied,and the research methods of train aerodynamics are proposed,including numerical simulation,a reducedscale test,and a full-scale test.Technological schemes of train aerodynamics involve the optimization design of the streamlined head and the smooth design of the body surface.Optimization design of the streamlined head includes conception design,project design,numerical simulation,and a reduced-scale test.Smooth design of the body surface is mainly used for the key parts,such as electric-current collecting system,wheel truck compartment,and windshield.The aerodynamic design method established in this paper has been successfully applied to various high-speed trains（CRH380A,CRH380 AM,CRH6,CRH2 G,and the Standard electric multiple unit（EMU）） that have met expected design objectives.The research results can provide an effective guideline for the aerodynamic design of high-speed trains.

Analysis of torque transmitting behavior and wheel slip prevention control during regenerative braking for high speed EMU trains

The wheel-rail adhesion control for regenerative braking systems of high speed electric multiple unit trains is crucial to maintaining the stability,improving the adhesion utilization,and achieving deep energy recovery.There remain technical challenges mainly because of the nonlinear,uncertain,and varying features of wheel-rail contact conditions.This research analyzes the torque transmitting behavior during regenerative braking,and proposes a novel methodology to detect the wheel-rail adhesion stability.Then,applications to the wheel slip prevention during braking are investigated,and the optimal slip ratio control scheme is proposed,which is based on a novel optimal reference generation of the slip ratio and a robust sliding mode control.The proposed methodology achieves the optimal braking performancewithoutthewheel-railcontactinformation.Numerical simulation results for uncertain slippery rails verify the effectiveness of the proposed methodology.

Hybrid Model of Power Transformer Fault Classification Using C-set and MFCM – MCSVM

This paper aims to increase the diagnosis accuracy of the fault classification of power transformers by introducing a new off-line hybrid model based on a combination subset of the et method(C-set)&modified fuzzy C-mean algorithm(MFCM)and the optimizable multiclass-SVM(MCSVM).The innovation in this paper is shown in terms of solving the predicaments of outliers,boundary proportion,and unequal data existing in both traditional and intelligence models.Taking into consideration the closeness of dissolved gas analysis(DGA)data,the C-set method is implemented to subset the DGA data samples based on their type of faults within unrepeated subsets.Then,the MFCM is used for removing outliers from DGA samples by combining highly similar data for every subset within the same cluster to obtain the optimized training data(OTD)set.It is also used to minimize dimensionality of DGA samples and the uncertainty of transformer condition monitoring.After that,the optimized MCSVM is trained by using the(OTD).The proposed model diagnosis accuracy is 93.3%.The obtained results indicate that our model significantly improves the fault identification accuracy in power transformers when compared with other conventional and intelligence models.

Genomic selection in plant breeding:Key factors shaping two decades of progress

Genomic selection,the application of genomic prediction(GP)models to select candidate individuals,has significantly advanced in the past two decades,effectively accelerating genetic gains in plant breeding.This article provides a holistic overview of key factors that have influenced GP in plant breeding during this period.We delved into the pivotal roles of training population size and genetic diversity,and their relationship with the breeding population,in determining GP accuracy.Special emphasis was placed on optimizing training population size.We explored its benefits and the associated diminishing returns beyond an optimum size.This was done while considering the balance between resource allocation and maximizing prediction accuracy through current optimization algorithms.The density and distribution of single-nucleotide polymorphisms,level of linkage disequilibrium,genetic complexity,trait heritability,statistical machine-learning methods,and non-additive effects are the other vital factors.Using wheat,maize,and potato as examples,we summarize the effect of these factors on the accuracy of GP for various traits.The search for high accuracy in GP—theoretically reaching one when using the Pearson’s correlation as a metric—is an active research area as yet far from optimal for various traits.We hypothesize that with ultra-high sizes of genotypic and phenotypic datasets,effective training population optimization methods and support from other omics approaches(transcriptomics,metabolomics and proteomics)coupled with deep-learning algorithms could overcome the boundaries of current limitations to achieve the highest possible prediction accuracy,making genomic selection an effective tool in plant breeding.

Computer-aided diabetic retinopathy diagnostic model using optimal thresholding merged with neural network

Purpose-Diabetic retinopathy(DR)is a central root of blindness all over the world.Though DR is tough to diagnose in starting stages,and the detection procedure might be time-consuming even for qualified experts.Nowadays,intelligent disease detection techniques are extremely acceptable for progress analysis and recognition of various diseases.Therefore,a computer-aided diagnosis scheme based on intelligent learning approaches is intended to propose for diagnosing DR effectively using a benchmark dataset.Design/methodology/approach-The proposed DR diagnostic procedure involves four main steps:(1)image pre-processing,(2)blood vessel segmentation,(3)feature extraction,and(4)classification.Initially,the retinal fundus image is taken for pre-processing with the help of Contrast Limited Adaptive Histogram Equalization(CLAHE)and average filter.In the next step,the blood vessel segmentation is carried out using a segmentation process with optimized gray-level thresholding.Once the blood vessels are extracted,feature extraction is done,using Local Binary Pattern(LBP),Texture Energy Measurement(TEM based on Laws of Texture Energy),and two entropy computations-Shanon’s entropy,and Kapur’s entropy.These collected features are subjected to a classifier called Neural Network(NN)with an optimized training algorithm.Both the gray-level thresholding and NN is enhanced by the Modified Levy Updated-Dragonfly Algorithm(MLU-DA),which operates to maximize the segmentation accuracy and to reduce the error difference between the predicted and actual outcomes of the NN.Finally,this classification error can correctly prove the efficiency of the proposed DR detection model.Findings-The overall accuracy of the proposed MLU-DA was 16.6%superior to conventional classifiers,and the precision of the developed MLU-DA was 22%better than LM-NN,16.6%better than PSO-NN,GWO-NN,and DA-NN.Finally,it is concluded that the implemented MLU-DA outperformed state-of-the-art algorithms in detecting DR.Originality/value-This paper adopts the latest optimization algorithm called MLU-DA-Neural Network with optimal gray-level thresholding for detecting diabetic retinopathy disease.This is the first work utilizes MLU-DA-based Neural Network for computer-aided Diabetic Retinopathy diagnosis.

Robust train speed trajectory optimization: A stochastic constrained shortest path approach

Train speed trajectory optimization is a significant issue in railway traffic systems, and it plays a key role in determining energy consumption and travel time of trains. Due to the complexity of real-world operational environments, a variety of factors can lead to the uncertainty in energy-consumption. To appropriately characterize the uncertainties and generate a robust speed trajectory, this study specifically proposes distance-speed networks over the inter-station and treats the uncertainty with respect to energy consumption as discrete samplebased random variables with correlation. The problem of interest is formulated as a stochastic constrained shortest path problem with travel time threshold constraints in which the expected total energy consumption is treated as the evaluation index. To generate an approximate optimal solution, a Lagrangian relaxation algorithm combined with dynamic programming algorithm is proposed to solve the optimal solutions. Numerical examples are implemented and analyzed to demonstrate the performance of proposed approaches.

Micro-channel etching characteristics enhancement by femtosecond laser processing high-temperature lattice in fused silica glass

A fused silica glass micro-channel can be formed by chemical etching after femtosecond laser irradiation, and the successful etching probability is only 48%. In order to improve the micro-channel fabrication success probability,the method of processing a high-temperature lattice by a femtosecond laser pulse train is provided. With the same pulse energy and scanning speed, the success probability can be increased to 98% by optimizing pulse delay.The enhancement is mainly caused by the nanostructure, which changes from a periodic slabs structure to some intensive and loose pore structures. In this Letter, the optimum pulse energy distribution ratio to the etching is also investigated.