Deep Learning Based Efficient Crowd Counting System

Estimation of crowd count is becoming crucial nowadays,as it can help in security surveillance,crowd monitoring,and management for different events.It is challenging to determine the approximate crowd size from an image of the crowd’s density.Therefore in this research study,we proposed a multi-headed convolutional neural network architecture-based model for crowd counting,where we divided our proposed model into two main components:(i)the convolutional neural network,which extracts the feature across the whole image that is given to it as an input,and(ii)the multi-headed layers,which make it easier to evaluate density maps to estimate the number of people in the input image and determine their number in the crowd.We employed the available public benchmark crowd-counting datasets UCF CC 50 and ShanghaiTech parts A and B for model training and testing to validate the model’s performance.To analyze the results,we used two metrics Mean Absolute Error(MAE)and Mean Square Error(MSE),and compared the results of the proposed systems with the state-of-art models of crowd counting.The results show the superiority of the proposed system.

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.

Lightweight Res-Connection Multi-Branch Network for Highly Accurate Crowd Counting and Localization

Crowd counting is a promising hotspot of computer vision involving crowd intelligence analysis,achieving tremendous success recently with the development of deep learning.However,there have been stillmany challenges including crowd multi-scale variations and high network complexity,etc.To tackle these issues,a lightweight Resconnection multi-branch network(LRMBNet)for highly accurate crowd counting and localization is proposed.Specifically,using improved ShuffleNet V2 as the backbone,a lightweight shallow extractor has been designed by employing the channel compression mechanism to reduce enormously the number of network parameters.A light multi-branch structure with different expansion rate convolutions is demonstrated to extract multi-scale features and enlarged receptive fields,where the information transmission and fusion of diverse scale features is enhanced via residual concatenation.In addition,a compound loss function is introduced for training themethod to improve global context information correlation.The proposed method is evaluated on the SHHA,SHHB,UCF-QNRF and UCF_CC_50 public datasets.The accuracy is better than those of many advanced approaches,while the number of parameters is smaller.The experimental results show that the proposed method achieves a good tradeoff between the complexity and accuracy of crowd counting,indicating a lightweight and high-precision method for crowd counting.

Counting of alpha particle tracks on imaging plate based on a convolutional neural network

Imaging plates are widely used to detect alpha particles to track information,and the number of alpha particle tracks is affected by the overlapping and fading effects of the track information.In this study,an experiment and a simulation were used to calibrate the efficiency parameter of an imaging plate,which was used to calculate the grayscale.Images were created by using grayscale,which trained the convolutional neural network to count the alpha tracks.The results demonstrated that the trained convolutional neural network can evaluate the alpha track counts based on the source and background images with a wider linear range,which was unaffected by the overlapping effect.The alpha track counts were unaffected by the fading effect within 60 min,where the calibrated formula for the fading effect was analyzed for 132.7 min.The detection efficiency of the trained convolutional neural network for inhomogeneous ^(241)Am sources(2π emission)was 0.6050±0.0399,whereas the efficiency curve of the photo-stimulated luminescence method was lower than that of the trained convolutional neural network.

RPNet: Rice plant counting after tillering stage based on plant attention and multiple supervision network

Rice is a major food crop and is planted worldwide. Climatic deterioration, population growth, farmland shrinkage, and other factors have necessitated the application of cutting-edge technology to achieve accurate and efficient rice production. In this study, we mainly focus on the precise counting of rice plants in paddy field and design a novel deep learning network, RPNet, consisting of four modules: feature encoder, attention block, initial density map generator, and attention map generator. Additionally, we propose a novel loss function called RPloss. This loss function considers the magnitude relationship between different sub-loss functions and ensures the validity of the designed network. To verify the proposed method, we conducted experiments on our recently presented URC dataset, which is an unmanned aerial vehicle dataset that is quite challenged at counting rice plants. For experimental comparison, we chose some popular or recently proposed counting methods, namely MCNN, CSRNet, SANet, TasselNetV2, and FIDTM. In the experiment, the mean absolute error(MAE), root mean squared error(RMSE), relative MAE(rMAE) and relative RMSE(rRMSE) of the proposed RPNet were 8.3, 11.2, 1.2% and 1.6%, respectively,for the URC dataset. RPNet surpasses state-of-the-art methods in plant counting. To verify the universality of the proposed method, we conducted experiments on the well-know MTC and WED datasets. The final results on these datasets showed that our network achieved the best results compared with excellent previous approaches. The experiments showed that the proposed RPNet can be utilized to count rice plants in paddy fields and replace traditional methods.

A Deep Learning-Based Crowd Counting Method and System Implementation on Neural Processing Unit Platform

In this paper, a deep learning-based method is proposed for crowdcountingproblems. Specifically, by utilizing the convolution kernel densitymap, the ground truth is generated dynamically to enhance the featureextractingability of the generator model. Meanwhile, the “cross stage partial”module is integrated into congested scene recognition network (CSRNet) toobtain a lightweight network model. In addition, to compensate for the accuracydrop owing to the lightweight model, we take advantage of “structuredknowledge transfer” to train the model in an end-to-end manner. It aimsto accelerate the fitting speed and enhance the learning ability of the studentmodel. The crowd-counting system solution for edge computing is alsoproposed and implemented on an embedded device equipped with a neuralprocessing unit. Simulations demonstrate the performance improvement ofthe proposed solution in terms of model size, processing speed and accuracy.The performance on the Venice dataset shows that the mean absolute error(MAE) and the root mean squared error (RMSE) of our model drop by32.63% and 39.18% compared with CSRNet. Meanwhile, the performance onthe ShanghaiTech PartB dataset reveals that the MAE and the RMSE of ourmodel are close to those of CSRNet. Therefore, we provide a novel embeddedplatform system scheme for public safety pre-warning applications.

A new software for automated counting of glistenings in intraocular lenses in vivo

AIM:To assess the performance of a bespoke software for automated counting of intraocular lens(IOL)glistenings in slit-lamp images.METHODS:IOL glistenings from slit-lamp-derived digital images were counted manually and automatically by the bespoke software.The images of one randomly selected eye from each of 34 participants were used as a training set to determine the threshold setting that gave the best agreement between manual and automatic grading.A second set of 63 images,selected using randomised stratified sampling from 290 images,were used for software validation.The images were obtained using a previously described protocol.Software-derived automated glistenings counts were compared to manual counts produced by three ophthalmologists.RESULTS:A threshold value of 140 was determined that minimised the total deviation in the number of glistenings for the 34 images in the training set.Using this threshold value,only slight agreement was found between automated software counts and manual expert counts for the validating set of 63 images(κ=0.104,95%CI,0.040-0.168).Ten images(15.9%)had glistenings counts that agreed between the software and manual counting.There were 49 images(77.8%)where the software overestimated the number of glistenings.CONCLUSION:The low levels of agreement show between an initial release of software used to automatically count glistenings in in vivo slit-lamp images and manual counting indicates that this is a non-trivial application.Iterative improvement involving a dialogue between software developers and experienced ophthalmologists is required to optimise agreement.The results suggest that validation of software is necessary for studies involving semi-automatic evaluation of glistenings.

A Computer Vision-Based System for Metal Sheet Pick Counting

Inventory counting is crucial to manufacturing industries in terms of inventory management,production,and procurement planning.Many companies currently require workers to manually count and track the status of materials,which are repetitive and non-value-added activities but incur significant costs to the companies as well as mental fatigue to the employees.This research aims to develop a computer vision system that can automate the material counting activity without applying any marker on the material.The type of material of interest is metal sheet,whose shape is simple,a large rectangular shape,yet difficult to detect.The use of computer vision technology can reduce the costs incurred fromthe loss of high-value materials,eliminate repetitive work requirements for skilled labor,and reduce human error.A computer vision system is proposed and tested on a metal sheet picking process formultiple metal sheet stacks in the storage area by using one video camera.Our results show that the proposed computer vision system can count the metal sheet picks under a real situation with a precision of 97.83%and a recall of 100%.

Lightweight Fish Bait Particle Counting Method Based on Pruning and Shift Quantization

In the process of aquaculture,monitoring the number of fish bait particles is of great significance to improve the growth and welfare of fish.Although the counting method based on onvolutional neural network(CNN)achieve good accuracy and applicability,it has a high amount of parameters and computation,which limit the deployment on resource-constrained hardware devices.In order to solve the above problems,this paper proposes a lightweight bait particle counting method based on shift quantization and model pruning strategies.Firstly,we take corresponding lightweight strategies for different layers to flexibly balance the counting accuracy and performance of the model.In order to deeply lighten the counting model,the redundant and less informative weights of the model are removed through the combination of model quantization and pruning.The experimental results show that the compression rate is nearly 9 times.Finally,the quantization candidate value is refined by introducing a power-of-two addition term,which improves the matches of the weight distribution.By analyzing the experimental results,the counting loss at 3 bit is reduced by 35.31%.In summary,the lightweight bait particle counting model proposed in this paper achieves lossless counting accuracy and reduces the storage and computational overhead required for running convolutional neural networks.

Robust Counting in Overcrowded Scenes Using Batch-Free Normalized Deep ConvNet

The analysis of overcrowded areas is essential for flow monitoring,assembly control,and security.Crowd counting’s primary goal is to calculate the population in a given region,which requires real-time analysis of congested scenes for prompt reactionary actions.The crowd is always unexpected,and the benchmarked available datasets have a lot of variation,which limits the trained models’performance on unseen test data.In this paper,we proposed an end-to-end deep neural network that takes an input image and generates a density map of a crowd scene.The proposed model consists of encoder and decoder networks comprising batch-free normalization layers known as evolving normalization(EvoNorm).This allows our network to be generalized for unseen data because EvoNorm is not using statistics from the training samples.The decoder network uses dilated 2D convolutional layers to provide large receptive fields and fewer parameters,which enables real-time processing and solves the density drift problem due to its large receptive field.Five benchmark datasets are used in this study to assess the proposed model,resulting in the conclusion that it outperforms conventional models.

Improvement of Counting Sorting Algorithm

By analyzing the internal features of counting sorting algorithm. Two improvements of counting sorting algorithms are proposed, which have a wide range of applications and better efficiency than the original counting sort while maintaining the original stability. Compared with the original counting sort, it has a wider scope of application and better time and space efficiency. In addition, the accuracy of the above conclusions can be proved by a large amount of experimental data.

Fatigue Safety Assessment of Concrete Continuous Rigid Frame Bridge Based on Rain Flow Counting Method and Health Monitoring Data

The fatigue of concrete structures will gradually appear after being subjected to alternating loads for a long time,and the accidents caused by fatigue failure of bridge structures also appear from time to time.Aiming at the problem of degradation of long-span continuous rigid frame bridges due to fatigue and environmental effects,this paper suggests a method to analyze the fatigue degradation mechanism of this type of bridge,which combines long-term in-site monitoring data collected by the health monitoring system(HMS)and fatigue theory.In the paper,the authors mainly carry out the research work in the following aspects:First of all,a long-span continuous rigid frame bridge installed with HMS is used as an example,and a large amount of health monitoring data have been acquired,which can provide efficient information for fatigue in terms of equivalent stress range and cumulative number of stress cycles;next,for calculating the cumulative fatigue damage of the bridge structure,fatigue stress spectrum got by rain flow counting method,S-N curves and damage criteria are used for fatigue damage analysis.Moreover,it was considered a linear accumulation damage through the Palmgren-Miner rule for the counting of stress cycles.The health monitoring data are adopted to obtain fatigue stress data and the rain flow counting method is used to count the amplitude varying fatigue stress.The proposed fatigue reliability approach in the paper can estimate the fatigue damage degree and its evolution law of bridge structures well,and also can help bridge engineers do the assessment of future service duration.

基于Count Sketch的预处理贪婪Kaczmarz方法

在贪婪Kaczmarz方法中,通过对系数矩阵进行正交三角分解引入右预处理子能够提高贪婪Kaczmarz方法的收敛速率。但在系数矩阵的行数远大于列数的情况下,正交三角分解的成本过高。为降低预处理的成本,通过引入Count Sketch变换,提出了基于Count Sketch的预处理贪婪Kaczmarz方法,并对新方法进行了收敛性分析。理论分析说明了新方法在系数矩阵条件数较大时比已有方法具有更好的收敛速率。数值实验验证了新方法的有效性。

Preparation of the Ag_2O_2-PbO_2 Modified Electrode and Its Application towards Escherichia coli Fast Counting in Water

A novel nano crystalline Ag2O2-PbO2 film chemically modified electrode (CME) was prepared and the CME was characterized by X-ray diffractometer (XRD) and atomic force microscope (AFM). By chronoamperometry, the nano Ag2O2-PbO2 CME was used as bioelectro- chemical sensor to determine the population of Escherichia coli (E. coli) in water. Compared with conventional methods, it is found that the technique we used is fast and convenient in counting E. coli.

Studies of an event-building algorithm of the readout system for the twin TPCs in HFRS

The High-energy Fragment Separator(HFRS),which is currently under construction,is a leading international radioactive beam device.Multiple sets of position-sensitive twin time projection chamber(TPC)detectors are distributed on HFRS for particle identification and beam monitoring.The twin TPCs'readout electronics system operates in a trigger-less mode due to its high counting rate,leading to a challenge of handling large amounts of data.To address this problem,we introduced an event-building algorithm.This algorithm employs a hierarchical processing strategy to compress data during transmission and aggregation.In addition,it reconstructs twin TPCs'events online and stores only the reconstructed particle information,which significantly reduces the burden on data transmission and storage resources.Simulation studies demonstrated that the algorithm accurately matches twin TPCs'events and reduces more than 98%of the data volume at a counting rate of 500 kHz/channel.

控制营养状态(CONUT)评分与脑出血后临床结局相关性研究

研究CONUT评分所反映的营养状态与脑出血后临床结局的关联。方法 选择我院在2019至2023年之间收治的脑出血住院患者。回顾性的收集病例表一般信息采用斯皮尔曼等级相关系数、多变量logistic分析确定各COUNT评分及其他指标与患者3个月预后结局的相关性。结果 本次研究共纳入576名患者,多变量 logistic 分析显示,年龄(OR 1.08,95% CI 1.06–1.10,P < 0.001),入院时NIHSS分数(OR 1.21,95% CI 1.17–1.25,P < 0.001),初始血肿量(OR 1.03,95% CI 1.01–1.05,P = 0.002),CONUT评分(OR 1.29,95% CI 1.11–1.49,P = 0.001)与不良结局独立相关。即使在添加吸入性肺炎和血肿扩张等指标后,较高的CONUT评分仍与不良结局相关(OR 1.28,95% CI 1.09–1.49,P = 0.002)。结论 CONUT评分与脑出血患者不良结局相关,可被认为是预测脑出血患者预后更简单、更客观的营养指标。营养不良与脑出血患者不良预后呈正相关。

Research on the correlation between the dual diffusion behavior of zinc in InGaAs/InP single-photon avalanche photodiodes and device performance

The development of InGaAs/InP single-photon avalanche photodiodes(SPADs)necessitates the utiliza-tion of a two-element diffusion technique to achieve accurate manipulation of the multiplication width and the dis-tribution of its electric field.Regarding the issue of accurately predicting the depth of diffusion in InGaAs/InP SPAD,simulation analysis and device development were carried out,focusing on the dual diffusion behavior of zinc atoms.A formula of X_(j)=k√t-t_(0)+c to quantitatively predict the diffusion depth is obtained by fitting the simulated twice-diffusion depths based on a two-dimensional(2D)model.The 2D impurity morphologies and the one-dimensional impurity profiles for the dual-diffused region are characterized by using scanning electron micros-copy and secondary ion mass spectrometry as a function of the diffusion depth,respectively.InGaAs/InP SPAD devices with different dual-diffusion conditions are also fabricated,which show breakdown behaviors well consis-tent with the simulated results under the same junction geometries.The dark count rate(DCR)of the device de-creased as the multiplication width increased,as indicated by the results.DCRs of 2×10^(6),1×10^(5),4×10^(4),and 2×10^(4) were achieved at temperatures of 300 K,273 K,263 K,and 253 K,respectively,with a bias voltage of 3 V,when the multiplication width was 1.5µm.These results demonstrate an effective prediction route for accu-rately controlling the dual-diffused zinc junction geometry in InP-based planar device processing.

Predictive value of preoperative routine examination for the prognosis of patients with pT2N0M0 or pT3N0M0 colorectal cancer

BACKGROUND In recent years,the incidence of colorectal cancer(CRC)has been increasing.With the popularization of endoscopic technology,a number of early CRC has been diagnosed.However,despite current treatment methods,some patients with early CRC still experience postoperative recurrence and metastasis.AIM To search for indicators associated with early CRC recurrence and metastasis to identify high-risk populations.METHODS A total of 513 patients with pT2N0M0 or pT3N0M0 CRC were retrospectively enrolled in this study.Results of blood routine test,liver and kidney function tests and tumor markers were collected before surgery.Patients were followed up through disease-specific database and telephone interviews.Tumor recurrence,metastasis or death were used as the end point of study to find the risk factors and predictive value related to early CRC recurrence and metastasis.RESULTS We comprehensively compared the predictive value of preoperative blood routine,blood biochemistry and tumor markers for disease-free survival(DFS)and overall survival(OS)of CRC.Cox multivariate analysis demonstrated that low platelet count was significantly associated with poor DFS[hazard ratio(HR)=0.995,95% confidence interval(CI):0.991-0.999,P=0.015],while serum carcinoembryonic antigen(CEA)level(HR=1.008,95%CI:1.001-1.016,P=0.027)and serum total cholesterol level(HR=1.538,95%CI:1.026-2.305,P=0.037)were independent risk factors for OS.The cutoff value of serum CEA level for predicting OS was 2.74 ng/mL.Although the OS of CRC patients with serum CEA higher than the cutoff value was worse than those with lower CEA level,the difference between the two groups was not statistically significant(P=0.075).CONCLUSION For patients with T2N0M0 or T3N0M0 CRC,preoperative platelet count was a protective factor for DFS,while serum CEA level was an independent risk factor for OS.Given that these measures are easier to detect and more acceptable to patients,they may have broader applications.

Clinical comprehensive treatment protocol for managing diabetic foot ulcers:A retrospective cohort study

BACKGROUND Diabetic foot ulcers(DFUs)are a common complication of diabetes,often leading to severe infections,amputations,and reduced quality of life.The current standard treatment protocols for DFUs have limitations in promoting efficient wound healing and preventing complications.A comprehensive treatment approach targeting multiple aspects of wound care may offer improved outcomes for patients with DFUs.The hypothesis of this study is that a comprehensive treatment protocol for DFUs will result in faster wound healing,reduced amputation rates,and improved overall patient outcomes compared to standard treatment protocols.AIM To compare the efficacy and safety of a comprehensive treatment protocol for DFUs with those of the standard treatment protocol.METHODS This retrospective study included 62 patients with DFUs,enrolled between January 2022 and January 2024,randomly assigned to the experimental(n=32)or control(n=30)group.The experimental group received a comprehensive treatment comprising blood circulation improvement,debridement,vacuum sealing drainage,recombinant human epidermal growth factor and anti-inflammatory dressing,and skin grafting.The control group received standard treatment,which included wound cleaning and dressing,antibiotics administration,and surgical debridement or amputation,if necessary.Time taken to reduce the white blood cell count,number of dressing changes,wound healing rate and time,and amputation rate were assessed.RESULTS The experimental group exhibited significantly better outcomes than those of the control group in terms of the wound healing rate,wound healing time,and amputation rate.Additionally,the comprehensive treatment protocol was safe and well tolerated by the patients.CONCLUSION Comprehensive treatment for DFUs is more effective than standard treatment,promoting granulation tissue growth,shortening hospitalization time,reducing pain and amputation rate,improving wound healing,and enhancing quality of life.

T lymphocyte proportion in Alzheimer’s disease prognosis

Bai et al investigate the predictive value of T lymphocyte proportion in Alzheimer's disease(AD)prognosis.Through a retrospective study involving 62 AD patients,they found that a decrease in T lymphocyte proportion correlated with a poorer prognosis,as indicated by higher modified Rankin scale scores.While the study highlights the potential of T lymphocyte proportion as a prognostic marker,it suggests the need for larger,multicenter studies to enhance generalizability and validity.Additionally,future research could use cognitive exams when evaluating prognosis and delve into immune mechanisms underlying AD progression.Despite limitations inherent in retrospective designs,Bai et al's work contributes to understanding the immune system's role in AD prognosis,paving the way for further exploration in this under-researched area.