Distributed Stochastic Optimization with Compression for Non-Strongly Convex Objectives

We are investigating the distributed optimization problem,where a network of nodes works together to minimize a global objective that is a finite sum of their stored local functions.Since nodes exchange optimization parameters through the wireless network,large-scale training models can create communication bottlenecks,resulting in slower training times.To address this issue,CHOCO-SGD was proposed,which allows compressing information with arbitrary precision without reducing the convergence rate for strongly convex objective functions.Nevertheless,most convex functions are not strongly convex(such as logistic regression or Lasso),which raises the question of whether this algorithm can be applied to non-strongly convex functions.In this paper,we provide the first theoretical analysis of the convergence rate of CHOCO-SGD on non-strongly convex objectives.We derive a sufficient condition,which limits the fidelity of compression,to guarantee convergence.Moreover,our analysis demonstrates that within the fidelity threshold,this algorithm can significantly reduce transmission burden while maintaining the same convergence rate order as its no-compression equivalent.Numerical experiments further validate the theoretical findings by demonstrating that CHOCO-SGD improves communication efficiency and keeps the same convergence rate order simultaneously.And experiments also show that the algorithm fails to converge with low compression fidelity and in time-varying topologies.Overall,our study offers valuable insights into the potential applicability of CHOCO-SGD for non-strongly convex objectives.Additionally,we provide practical guidelines for researchers seeking to utilize this algorithm in real-world scenarios.

Effect of low-degree astigmatism on the objective visual quality

AIM:To evaluate the effect of low-degree astigmatism on objective visual quality through the Optical Quality Analysis System(OQAS).METHODS:This study enrolled 46 participants(aged 23 to 30y,90 eyes)with normal or corrected-to-normal vision.The cylindrical lenses(0,0.5,0.75,1.0,and 1.25 D)were placed at the axial direction(180°,45°,90°,and 135°)in front of the eyes with the best correction to form 16 types of regular low-degree astigmatism.OQAS was used to detect the objective visual quality,recorded as the objective scattering index(OSI),OQAS values at contrasts of 100%,20%,and 9%predictive visual acuity(OV100%,OV20%,and OV9%),modulation transfer function cut-off(MTFcut-off)and Strehl ratio(SR).The mixed effect linear model was used to compare objective visual quality differences between groups and examine associations between astigmatic magnitude and objective visual quality parameters.RESULTS:Apparent negative relationships between the magnitude of low astigmatism and objective visual quality were observed.The increase of OSI per degree of astigmatism at 180°,45°,90°,and 135°axis were 0.38(95%CI:0.35,0.42),0.50(95%CI:0.46,0.53),0.49(95%CI:0.45,0.54)and 0.37(95%CI:0.34,0.41),respectively.The decrease of MTFcut-off per degree of astigmatism at 180°,45°,90°,and 135°axis were-10.30(95%CI:-11.43,-9.16),-12.73(95%CI:-13.62,-11.86),-12.75(95%CI:-13.79,-11.70),and-9.97(95%CI:-10.92,-9.03),respectively.At the same astigmatism degree,OSI at 45°and 90°axis were higher than that at 0°and 135°axis,while MTFcut-off were lower.CONCLUSION:Low astigmatism of only 0.50 D can significantly reduce the objective visual quality.

Objective Model Selection in Physics: Exploring the Finite Information Quantity Approach

Traditional methods for selecting models in experimental data analysis are susceptible to researcher bias, hindering exploration of alternative explanations and potentially leading to overfitting. The Finite Information Quantity (FIQ) approach offers a novel solution by acknowledging the inherent limitations in information processing capacity of physical systems. This framework facilitates the development of objective criteria for model selection (comparative uncertainty) and paves the way for a more comprehensive understanding of phenomena through exploring diverse explanations. This work presents a detailed comparison of the FIQ approach with ten established model selection methods, highlighting the advantages and limitations of each. We demonstrate the potential of FIQ to enhance the objectivity and robustness of scientific inquiry through three practical examples: selecting appropriate models for measuring fundamental constants, sound velocity, and underwater electrical discharges. Further research is warranted to explore the full applicability of FIQ across various scientific disciplines.

Eclipse计划系统MU Objective工具在鼻咽癌容积调强放射治疗计划中的应用研究

目的:探讨Varian Eclipse计划系统MU Objective工具在鼻咽癌容积调强放射治疗(VMAT)计划中的应用,旨在保证治疗计划质量的同时降低治疗计划的机器跳数(MU)。方法:选取已接受容积调强放射治疗技术的21例鼻咽癌患者,在未使用MU Objective工具的情况下给每例患者设计治疗参考计划(MU_(ref));将使用MU Objective工具对MU_(ref)进行重新优化,分别设置MU_(ref)的MU的30%、50%、70%、90%和120%,分别命名为MU_(30%)、MU_(50%)、MU_(70%)、MU_(90%)和MU_(120%)。将治疗计划MU_(30%)、MU_(50%)、MU_(70%)、MU_(90%)和MU_(120%)分别与MU_(ref)进行配对t检验统计分析,比较两种治疗计划的靶区、危及器官(OAR)剂量分布和计划的MU。结果:使用MU Objective工具对参考计划优化MU后,与参考计划相比部分靶区和OAR剂量体积参数差异虽有统计学意义,但无临床意义。治疗计划参数为MU_(30%)、MU_(50%)、MU_(70%)和MU_(90%)时,与MU_(ref)比较计划MU平均分别减少21.5%、19.5%、16.6%和8%,差异有统计学意义(t=9.652,t=8.843,t=8.963,t=11.323;P<0.05)。在MU_(120%)时,治疗计划MU平均增加1.7%,但未显著提高靶区剂量覆盖。结论:对于鼻咽癌VMAT计划,使用Eclipse计划系统的MU Objective工具在减少计划MU的同时可获得与参考计划相似的剂量分布。MU Objective工具可作为鼻咽癌或其他部位VMAT计划的常规使用工具,以保证计划质量同时减少放射治疗计划的MU。

Objective Identification and Climatic Characteristics of Heavy-Precipitation Northeastern China Cold Vortexes

The northeastern China cold vortex(NCCV)plays an important role in regional rainstorms over East Asia.Using the National Centers for Environmental Prediction Final reanalysis dataset and the Global Precipitation Measurement product,an objective algorithm for identifying heavy-precipitation NCCV(HPCV)events was designed,and the climatological features of 164 HPCV events from 2001 to 2019 were investigated.The number of HPCV events showed an upward linear trend,with the highest frequency of occurrence in summer.The most active region of HPCV samples was the Northeast China Plain between 40°–55°N.Most HPCV events lasted 3–5 days and had radii ranging from 250 to 1000 km.The duration of HPCV events with larger sizes was longer.About half of the HPCV events moved into(moved out of)the definition region(35°–60°N,115°–145°E),and half initiated(dissipated)within the region.The initial position was close to the western boundary of the definition region,and the final position was mainly near the eastern boundary.The locations associated with the precipitation were mostly concentrated within 2000 km southeast of the HPCV systems,and they were farther from the center in the cold season than in the warm season.

Multi‐objective particle swarm optimisation of complex product change plan considering service performance

Design change is an inevitable part of the product development process.This study proposes an improved binary multi‐objective PSO algorithm guided by problem char-acteristics(P‐BMOPSO)to solve the optimisation problem of complex product change plan considering service performance.Firstly,a complex product multi‐layer network with service performance is established for the first time to reveal the impact of change effect propagation on the product service performance.Secondly,the concept of service performance impact(SPI)is defined by decoupling the impact of strongly associated nodes on the service performance in the process of change affect propagation.Then,a triple‐objective selection model of change nodes is established,which includes the three indicators:SPI degree,change cost,and change time.Furthermore,an integer multi‐objective particle swarm optimisation algorithm guided by problem characteristics is developed to solve the model above.Experimental results on the design change problem of a certain type of Skyworth TV verify the effectiveness of the established optimisation model and the proposed P‐BMOPSO algorithm.

Multi-Objective Optimization with Artificial Neural Network Based Robust Paddy Yield Prediction Model

Agriculture plays a vital role in the food production process that occupies nearly one-third of the total surface of the earth.Rice is propagated from the seeds of paddy and it is a stable food almost used byfifty percent of the total world population.The extensive growth of the human population alarms us to ensure food security and the country should take proper food steps to improve the yield of food grains.This paper concentrates on improving the yield of paddy by predicting the factors that influence the growth of paddy with the help of Evolutionary Computation Techniques.Most of the researchers used to relay on historical records of meteorological parameters to predict the yield of paddy.There is a lack in analyzing the day to day impact of meteorological parameters such as direction of wind,relative humidity,Instant Wind Speed in paddy cultivation.The real time meteorological data collected and analysis the impact of weather parameters from the day of paddy sowing to till the last day of paddy harvesting with regular time series.A Robust Optimized Artificial Neural Network(ROANN)Algorithm with Genetic Algorithm(GA)and Multi Objective Particle Swarm Optimization Algorithm(MOPSO)proposed to predict the factors that to be concentrated by farmers to improve the paddy yield in cultivation.A real time paddy data collected from farmers of Tamilnadu and the meteorological parameters were matched with the cropping pattern of the farmers to construct the database.The input parameters were optimized either by using GA or MOPSO optimization algorithms to reconstruct the database.Reconstructed database optimized by using Artificial Neural Network Back Propagation Algorithm.The reason for improving the growth of paddy was identified using the output of the Neural Network.Performance metrics such as Accuracy,Error Rate etc were used to measure the performance of the proposed algorithm.Comparative analysis made between ANN with GA and ANN with MOPSO to identify the recommendations for improving the paddy yield.

Salient Object Detection Based on a Novel Combination Framework Using the Perceptual Matching and Subjective-Objective Mapping Technologies

The integrity and fineness characterization of non-connected regions and contours is a major challenge for existing salient object detection.The key to address is how to make full use of the subjective and objective structural information obtained in different steps.Therefore,by simulating the human visual mechanism,this paper proposes a novel multi-decoder matching correction network and subjective structural loss.Specifically,the loss pays different attentions to the foreground,boundary,and background of ground truth map in a top-down structure.And the perceived saliency is mapped to the corresponding objective structure of the prediction map,which is extracted in a bottom-up manner.Thus,multi-level salient features can be effectively detected with the loss as constraint.And then,through the mapping of improved binary cross entropy loss,the differences between salient regions and objects are checked to pay attention to the error prone region to achieve excellent error sensitivity.Finally,through tracking the identifying feature horizontally and vertically,the subjective and objective interaction is maximized.Extensive experiments on five benchmark datasets demonstrate that compared with 12 state-of-the-art methods,the algorithm has higher recall and precision,less error and strong robustness and generalization ability,and can predict complete and refined saliency maps.

基于改进Deformable DETR的无人机视频流车辆目标检测算法

针对无人机视频流检测中小目标数量多、因图像传输质量较低而导致的上下文语义信息不充分、传统算法融合特征推理速度慢、数据集类别样本不均衡导致的训练效果差等问题,提出一种基于改进Deformable DETR的无人机视频流车辆目标检测算法。在模型结构方面,该算法设计了跨尺度特征融合模块以增大感受野,提升小目标检测能力,并采用针对object_query的挤压-激励模块提升关键目标的响应值,减少重要目标的漏检与错检率;在数据处理方面,使用了在线困难样本挖掘技术,改善数据集中类别样本分布不均的问题。在UAVDT数据集上进行了实验,实验结果表明,改进后的算法相较于基线算法在平均检测精度上提升了1.5%,在小目标检测精度上提升了0.8%,并在保持参数量较少增长的情况下,维持了原有的检测速度。

Automatic detection of small bowel lesions with different bleeding risks based on deep learning models

BACKGROUND Deep learning provides an efficient automatic image recognition method for small bowel(SB)capsule endoscopy(CE)that can assist physicians in diagnosis.However,the existing deep learning models present some unresolved challenges.AIM To propose a novel and effective classification and detection model to automatically identify various SB lesions and their bleeding risks,and label the lesions accurately so as to enhance the diagnostic efficiency of physicians and the ability to identify high-risk bleeding groups.METHODS The proposed model represents a two-stage method that combined image classification with object detection.First,we utilized the improved ResNet-50 classification model to classify endoscopic images into SB lesion images,normal SB mucosa images,and invalid images.Then,the improved YOLO-V5 detection model was utilized to detect the type of lesion and its risk of bleeding,and the location of the lesion was marked.We constructed training and testing sets and compared model-assisted reading with physician reading.RESULTS The accuracy of the model constructed in this study reached 98.96%,which was higher than the accuracy of other systems using only a single module.The sensitivity,specificity,and accuracy of the model-assisted reading detection of all images were 99.17%,99.92%,and 99.86%,which were significantly higher than those of the endoscopists’diagnoses.The image processing time of the model was 48 ms/image,and the image processing time of the physicians was 0.40±0.24 s/image(P<0.001).CONCLUSION The deep learning model of image classification combined with object detection exhibits a satisfactory diagnostic effect on a variety of SB lesions and their bleeding risks in CE images,which enhances the diagnostic efficiency of physicians and improves the ability of physicians to identify high-risk bleeding groups.

基于DirectShow与DMO的视频采集与编码实现

主要介绍了使用DirectShow实现视频采集和使用DirectXMediaObjects(DMO)实现视频编码的方法,并提供在IP组播视频会议系统研究中的具体实现代码。这些方法适用于视频会议系统、远程监控、远程医疗、可视电话等多媒体通信应用。

Efficient Ship:A Hybrid Deep Learning Framework for Ship Detection in the River

Optical image-based ship detection can ensure the safety of ships and promote the orderly management of ships in offshore waters.Current deep learning researches on optical image-based ship detection mainly focus on improving one-stage detectors for real-time ship detection but sacrifices the accuracy of detection.To solve this problem,we present a hybrid ship detection framework which is named EfficientShip in this paper.The core parts of the EfficientShip are DLA-backboned object location(DBOL)and CascadeRCNN-guided object classification(CROC).The DBOL is responsible for finding potential ship objects,and the CROC is used to categorize the potential ship objects.We also design a pixel-spatial-level data augmentation(PSDA)to reduce the risk of detection model overfitting.We compare the proposed EfficientShip with state-of-the-art(SOTA)literature on a ship detection dataset called Seaships.Experiments show our ship detection framework achieves a result of 99.63%(mAP)at 45 fps,which is much better than 8 SOTA approaches on detection accuracy and can also meet the requirements of real-time application scenarios.

Road Traffic Monitoring from Aerial Images Using Template Matching and Invariant Features

Road traffic monitoring is an imperative topic widely discussed among researchers.Systems used to monitor traffic frequently rely on cameras mounted on bridges or roadsides.However,aerial images provide the flexibility to use mobile platforms to detect the location and motion of the vehicle over a larger area.To this end,different models have shown the ability to recognize and track vehicles.However,these methods are not mature enough to produce accurate results in complex road scenes.Therefore,this paper presents an algorithm that combines state-of-the-art techniques for identifying and tracking vehicles in conjunction with image bursts.The extracted frames were converted to grayscale,followed by the application of a georeferencing algorithm to embed coordinate information into the images.The masking technique eliminated irrelevant data and reduced the computational cost of the overall monitoring system.Next,Sobel edge detection combined with Canny edge detection and Hough line transform has been applied for noise reduction.After preprocessing,the blob detection algorithm helped detect the vehicles.Vehicles of varying sizes have been detected by implementing a dynamic thresholding scheme.Detection was done on the first image of every burst.Then,to track vehicles,the model of each vehicle was made to find its matches in the succeeding images using the template matching algorithm.To further improve the tracking accuracy by incorporating motion information,Scale Invariant Feature Transform(SIFT)features have been used to find the best possible match among multiple matches.An accuracy rate of 87%for detection and 80%accuracy for tracking in the A1 Motorway Netherland dataset has been achieved.For the Vehicle Aerial Imaging from Drone(VAID)dataset,an accuracy rate of 86%for detection and 78%accuracy for tracking has been achieved.

Enhanced Object Detection and Classification via Multi-Method Fusion

Advances in machine vision systems have revolutionized applications such as autonomous driving,robotic navigation,and augmented reality.Despite substantial progress,challenges persist,including dynamic backgrounds,occlusion,and limited labeled data.To address these challenges,we introduce a comprehensive methodology toenhance image classification and object detection accuracy.The proposed approach involves the integration ofmultiple methods in a complementary way.The process commences with the application of Gaussian filters tomitigate the impact of noise interference.These images are then processed for segmentation using Fuzzy C-Meanssegmentation in parallel with saliency mapping techniques to find the most prominent regions.The Binary RobustIndependent Elementary Features(BRIEF)characteristics are then extracted fromdata derived fromsaliency mapsand segmented images.For precise object separation,Oriented FAST and Rotated BRIEF(ORB)algorithms areemployed.Genetic Algorithms(GAs)are used to optimize Random Forest classifier parameters which lead toimproved performance.Our method stands out due to its comprehensive approach,adeptly addressing challengessuch as changing backdrops,occlusion,and limited labeled data concurrently.A significant enhancement hasbeen achieved by integrating Genetic Algorithms(GAs)to precisely optimize parameters.This minor adjustmentnot only boosts the uniqueness of our system but also amplifies its overall efficacy.The proposed methodologyhas demonstrated notable classification accuracies of 90.9%and 89.0%on the challenging Corel-1k and MSRCdatasets,respectively.Furthermore,detection accuracies of 87.2%and 86.6%have been attained.Although ourmethod performed well in both datasets it may face difficulties in real-world data especially where datasets havehighly complex backgrounds.Despite these limitations,GAintegration for parameter optimization shows a notablestrength in enhancing the overall adaptability and performance of our system.

Adaptive Resource Allocation Algorithm for 5G Vehicular Cloud Communication

The current resource allocation in 5G vehicular networks for mobile cloud communication faces several challenges,such as low user utilization,unbalanced resource allocation,and extended adaptive allocation time.We propose an adaptive allocation algorithm for mobile cloud communication resources in 5G vehicular networks to address these issues.This study analyzes the components of the 5G vehicular network architecture to determine the performance of different components.It is ascertained that the communication modes in 5G vehicular networks for mobile cloud communication include in-band and out-of-band modes.Furthermore,this study analyzes the single-hop and multi-hop modes in mobile cloud communication and calculates the resource transmission rate and bandwidth in different communication modes.The study also determines the scenario of one-way and two-way vehicle lane cloud communication network connectivity,calculates the probability of vehicle network connectivity under different mobile cloud communication radii,and determines the amount of cloud communication resources required by vehicles in different lane scenarios.Based on the communication status of users in 5G vehicular networks,this study calculates the bandwidth and transmission rate of the allocated channels using Shannon’s formula.It determines the adaptive allocation of cloud communication resources,introduces an objective function to obtain the optimal solution after allocation,and completes the adaptive allocation process.The experimental results demonstrate that,with the application of the proposed method,the maximum utilization of user communication resources reaches approximately 99%.The balance coefficient curve approaches 1,and the allocation time remains under 2 s.This indicates that the proposed method has higher adaptive allocation efficiency.

CamShift算法的研究及其DirectShow实现

提出了一种全新的基于Microsoft DriectShow构架的连续自适应均值移动跟踪算法(CamShift)的实现模式。该技术创新地将DirectShow filter技术融入到CamShift自动跟踪算法的实现中,在模块化的软件构架下实现了CamShift算法在复杂视频场景下对视频对象的全实时跟踪。利用该技术开发的CamShift算法模块具有良好的灵活性和高效率,可以集成到各类基于DirectShow技术开发的应用程序中。此外,所提出的技术构架有很好的延展性,可以广泛应用在视频和图像信号处理领域。

Nab-paclitaxel plus capecitabine as first-line treatment for advanced biliary tract cancers:An open-label,non-randomized,phase II clinical trial

BACKGROUND Biliary tract cancers(BTCs)are a heterogeneous group of tumors with high malignancy,poor prognosis,and limited treatment options.AIM To explore the efficacy and safety of nab-paclitaxel plus capecitabine as first-line treatment for advanced and metastatic BTCs.METHODS This open-label,non-randomized,double-center,phase II clinical trial recruited systemic therapy-naive patients with unresectable or metastatic BTCs between April 2019 and June 2022 at Beijing Cancer Hospital and the First Hospital of China Medical University.Eligible patients were administered nab-paclitaxel(150 mg/m2,day 1)and capecitabine(2000 mg/m2,twice daily,days 1-7)in 14-day cycles until experiencing intolerable toxicity or disease progression.The primary outcome was the objective response rate(ORR).The secondary outcomes included the disease control rate(DCR),overall survival(OS),progression-free survival(PFS),and safety.RESULTS A total of 44 patients successfully completed the trial,with a median age of 64.00 years(interquartile range,35.00-76.00),and 26(59.09%)were females.Tumor response assessment was impeded for one patient due to premature demise from tumor hemorrhage.Among the remaining 43 patients undergoing at least one imaging assessment,the ORR was 23.26%[95%confidence interval(CI):11.80%-38.60%],and the DCR was 69.77%(95%CI:53.90%-82.80%).The median OS was 14.1 months(95%CI:8.3-19.9),and the median PFS was 4.4 months(95%CI:2.5-6.3).A total of 41 patients(93.18%)experienced at least one adverse event(AE),with 10 patients(22.73%)encountering grade≥3 AEs,and the most frequent AEs of any grade were alopecia(79.50%),leukopenia(54.55%),neutropenia(52.27%),and liver dysfunction(40.91%),and no treatment-related deaths were documented.CONCLUSION Nab-paclitaxel plus capecitabine may be an effective and safe first-line treatment strategy for patients with advanced or metastatic BTCs.

Detecting the core of a network by the centralities of the nodes

Many networks exhibit the core/periphery structure.Core/periphery structure is a type of meso-scale structure that consists of densely connected core nodes and sparsely connected peripheral nodes.Core nodes tend to be well-connected,both among themselves and to peripheral nodes,which tend not to be well-connected to other nodes.In this brief report,we propose a new method to detect the core of a network by the centrality of each node.It is discovered that such nodes with non-negative centralities often consist in the core of the networks.The simulation is carried out on different real networks.The results are checked by the objective function.The checked results may show the effectiveness of the simulation results by the centralities of the nodes on the real networks.Furthermore,we discuss the characters of networks with the single core/periphery structure and point out the scope of the application of our method at the end of this paper.

Two-Layer Attention Feature Pyramid Network for Small Object Detection

Effective small object detection is crucial in various applications including urban intelligent transportation and pedestrian detection.However,small objects are difficult to detect accurately because they contain less information.Many current methods,particularly those based on Feature Pyramid Network(FPN),address this challenge by leveraging multi-scale feature fusion.However,existing FPN-based methods often suffer from inadequate feature fusion due to varying resolutions across different layers,leading to suboptimal small object detection.To address this problem,we propose the Two-layerAttention Feature Pyramid Network(TA-FPN),featuring two key modules:the Two-layer Attention Module(TAM)and the Small Object Detail Enhancement Module(SODEM).TAM uses the attention module to make the network more focused on the semantic information of the object and fuse it to the lower layer,so that each layer contains similar semantic information,to alleviate the problem of small object information being submerged due to semantic gaps between different layers.At the same time,SODEM is introduced to strengthen the local features of the object,suppress background noise,enhance the information details of the small object,and fuse the enhanced features to other feature layers to ensure that each layer is rich in small object information,to improve small object detection accuracy.Our extensive experiments on challenging datasets such as Microsoft Common Objects inContext(MSCOCO)and Pattern Analysis Statistical Modelling and Computational Learning,Visual Object Classes(PASCAL VOC)demonstrate the validity of the proposedmethod.Experimental results show a significant improvement in small object detection accuracy compared to state-of-theart detectors.

Carbon efficiency evaluation method for urban energy system with multiple energy complementary

Urban energy systems(UESs)play a pivotal role in the consumption of clean energy and the promotion of energy cascade utilization.In the context of the construction and operation strategy of UESs with multiple complementary energy resources,a comprehensive assessment of the energy efficiency is of paramount importance.First,a multi-dimensional evaluation system with four primary indexes of energy utilization,environmental protection,system operation,and economic efficiency and 21 secondary indexes is constructed to comprehensively portray the UES.Considering that the evaluation system may contain a large number of indexes and that there is overlapping information among them,an energy efficiency evaluation method based on data processing,dimensionality reduction,integration of combined weights,and gray correlation analysis is proposed.This method can effectively reduce the number of calculations and improve the accuracy of energy efficiency assessments.Third,a demonstration project for a UES in China is presented.The energy efficiency of each scenario is assessed using six operational scenarios.The results show that Scenario 5,in which parks operate independently and investors build shared energy-storage equipment,has the best results and is best suited for green and low-carbon development.The results of the comparative assessment methods show that the proposed method provides a good energy efficiency assessment.This study provides a reference for the optimal planning,construction,and operation of UESs with multiple energy sources.