检索结果-南通市图书馆

Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第2期21卷 318-330页

作者： yu-Cheng Chou bowen Li Deng-Ping Fan Alan yuille Zongwei Zhou Department of Computer Science Johns Hopkins UniversityBaltimore 21218USA Computer Vision Lab ETH ZurichZurich 8001Switzerland

Creating large-scale and well-annotated datasets to train AI algorithms is crucial for automated tumor detection and localization.However,with limited resources,it is challenging to determine the best type of annotations when annotating massive amounts of unlabeled data.To address this issue,we focus on polyps in colonoscopy videos and pancreatic tumors in abdominal CT scans;Both applications require significant effort and time for pixel-wise annotation due to the high dimensional nature of the data,involving either temporary or spatial dimensions.In this paper,we develop a new annotation strategy,termed Drag&Drop,which simplifies the annotation process to drag and drop.This annotation strategy is more efficient,particularly for temporal and volumetric imaging,than other types of weak annotations,such as per-pixel,bounding boxes,scribbles,ellipses and points.Furthermore,to exploit our Drag&Drop annotations,we develop a novel weakly supervised learning method based on the watershed algorithm.Experimental results show that our method achieves better detection and localization performance than alternative weak annotations and,more importantly,achieves similar performance to that trained on detailed per-pixel annotations.Interestingly,we find that,with limited resources,allocating weak annotations from a diverse patient population can foster models more robust to unseen images than allocating per-pixel annotations for a small set of images.In summary,this research proposes an efficient annotation strategy for tumor detection and localization that is less accurate than per-pixel annotations but useful for creating large-scale datasets for screening tumors in various medical modalities.

关键词： Weak annotation detection localization segmentation colonoscopy abdomen

A Predictive Energy Management Strategies for Mining Dump Trucks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy Engineering 2024年第3期121卷 769-788页

作者： Yixuan yu yulin Wang Qingcheng Li bowen Jiao College of Mechanical and Electrical Engineering Qingdao UniversityQingdao266071China

The plug-in hybrid vehicles(PHEV)technology can effectively address the issues of poor dynamics and higher energy consumption commonly found in traditional mining dump trucks.Meanwhile,plug-in hybrid electric trucks can achieve excellent fuel economy through efficient energy management strategies(EMS).Therefore,a series hybrid system is constructed based on a 100-ton mining dump truck in this paper.And inspired by the dynamic programming(DP)algorithm,a predictive equivalent consumption minimization strategy(P-ECMS)based on the DP optimization result is proposed.Based on the optimal control manifold and the SOC reference trajectory obtained by the DP algorithm,the P-ECMS strategy performs real-time stage parameter optimization to obtain the optimal equivalent factor(EF).Finally,applying the equivalent consumption minimization strategy(ECMS)realizes real-time control.The simulation results show that the equivalent fuel consumption of the P-ECMS strategy under the experimentally collected mining cycle conditions is 150.8 L/100 km,which is 10.9%less than that of the common CDCS strategy(169.3 L/100 km),and achieves 99.47%of the fuel saving effect of the DP strategy(150 L/100 km).

关键词： Mining dump truck energy management strategy plug-in hybrid electric vehicle equivalent consumption minimization strategy dynamic programming

Effects of coal-fired power plants on soil microbial diversity and community structures

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2024年第3期137卷 206-223页

作者： bowen Sun Renbin Zhu yu Shi Wanying Zhang Zeming Zhou Dawei Ma Runfang Wang Haitao Dai Chenshuai Che Institute of Polar Environment&Anhui Key Laboratory of Polar Environment and Global Change School of Earth and Space SciencesUniversity of Science and Technology of ChinaHefei 230026China State Key Laboratory of Crop Stress Adaptation and Improvement School of Life SciencesHenan UniversityKaifeng 450046China State Grid Anhui Electric Power Research Institute Hefei 230601China

Long-term deposition of atmospheric pollutants emitted from coal combustion and their effects on the eco-environment have been extensively studied around coal-fired power plants.However,the effects of coal-fired power plants on soil microbial communities have received little attention through atmospheric pollutant deposition and coal-stacking.Here,we collected the samples of power plant soils(PS),coal-stacking soils(CSS)and agricultural soils(AS)around three coal-fired power plants and background control soils(BG)in Huainan,a typical mineral resource-based city in East China,and investigated the microbial diversity and community structures through a high-throughput sequencing technique.Coal-stacking significantly increased(p<0.05)the contents of total carbon,total nitrogen,total sulfur and Mo in the soils,whereas the deposition of atmospheric pollutants enhanced the levels of V,Cu,Zn and Pb.Proteobacteria,Actinobacteria,Thaumarchaeota,Thermoplasmata,Ascomycota and Basidiomycota were the dominant taxa in all soils.The bacterial community showed significant differences(p<0.05)among PS,CSS,AS and BG,whereas archaeal and fungal communities showed significant differences(p<0.01)according to soil samples around three coal-fired power plants.The predominant environmental variables affecting soil bacterial,archaeal and fungal communities were Mo-TN-TS,Cu-V-Mo,and organic matter(OM)-Mo,respectively.Certain soil microbial genera were closely related to multiple key factors associated with stacking coal and heavy metal deposition from power plants.This study provided useful insight into better understanding of the relationships between soil microbial communities and long-term disturbances from coal-fired power plants.

关键词： Coal-fired power plants Soil microbial communities Coal-stacking Heavy metals Environmental variables

Deep Learning-Based Secure Transmission Strategy with Sensor-Transmission-Computing Linkage for Power Internet of Things

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第3期78卷 3267-3282页

作者： Bin Li Linghui Kong Xiangyi Zhang Bochuo Kou Hui yu bowen Liu State Grid Beijing Urban District Power Supply Company Beijing100034China

The automatic collection of power grid situation information, along with real-time multimedia interaction between the front and back ends during the accident handling process, has generated a massive amount of power grid data. While wireless communication offers a convenient channel for grid terminal access and data transmission, it is important to note that the bandwidth of wireless communication is limited. Additionally, the broadcast nature of wireless transmission raises concerns about the potential for unauthorized eavesdropping during data transmission. To address these challenges and achieve reliable, secure, and real-time transmission of power grid data, an intelligent security transmission strategy with sensor-transmission-computing linkage is proposed in this paper. The primary objective of this strategy is to maximize the confidentiality capacity of the system. To tackle this, an optimization problem is formulated, taking into consideration interruption probability and interception probability as constraints. To efficiently solve this optimization problem, a low-complexity algorithm rooted in deep reinforcement learning is designed, which aims to derive a suboptimal solution for the problem at hand. Ultimately, through simulation results, the validity of the proposed strategy in guaranteed communication security, stability, and timeliness is substantiated. The results confirm that the proposed intelligent security transmission strategy significantly contributes to the safeguarding of communication integrity, system stability, and timely data delivery.

关键词： Secure transmission deep learning power Internet of Things sensor-transmission-computing

Damage evolution of rock-encased-backfill structure under stepwise cyclic triaxial loading

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Rock Mechanics and Geotechnical Engineering 2024年第2期16卷 597-615页

作者： Xin yu yuye Tan Weidong Song John Kemeny Shengwen Qi bowen Zheng Songfeng Guo Key Laboratory of Shale Gas and Geoengineering Institute of Geology and GeophysicsChinese Academy of SciencesBeijing100089China Innovation Academy for Earth Science Chinese Academy of SciencesBeijing100089China University of Chinese Academy of Sciences Beijing100049China School of Civil and Resources Engineering University of Science and Technology BeijingBeijing100083China Key Laboratory of High-Efficient Mining and Safety of Metal Mines(Ministry of Education of China) University of Science and Technology BeijingBeijing100083China Department of Mining and Geological Engineering University of ArizonaTucsonAZ86721USA

Rock-encased-backfill(RB)structures are common in underground mining,for example in the cut-andfill and stoping methods.To understand the effects of cyclic excavation and blasting activities on the damage of these RB structures,a series of triaxial stepwise-increasing-amplitude cyclic loading experiments was conducted with cylindrical RB specimens(rock on outside,backfill on inside)with different volume fractions of rock(VF=0.48,0.61,0.73,and 0.84),confining pressures(0,6,9,and 12 MPa),and cyclic loading rates(200,300,400,and 500 N/s).The damage evolution and meso-crack formation during the cyclic tests were analyzed with results from stress-strain hysteresis loops,acoustic emission events,and post-failure X-ray 3D fracture morphology.The results showed significant differences between cyclic and monotonic loadings of RB specimens,particularly with regard to the generation of shear microcracks,the development of stress memory and strain hardening,and the contact forces and associated friction that develops along the rock-backfill interface.One important finding is that as a function of the number of cycles,the elastic strain increases linearly and the dissipated energy increases exponentially.Also,compared with monotonic loading,the cyclic strain hardening characteristics are more sensitive to rising confining pressures during the initial compaction stage.Another finding is that compared with monotonic loading,more shear microcracks are generated during every reloading stage,but these microcracks tend to be dispersed and lessen the likelihood of large shear fracture formation.The transition from elastic to plastic behavior varies depending on the parameters of each test(confinement,volume fraction,and cyclic rate),and an interesting finding was that the transformation to plastic behavior is significantly lower under the conditions of 0.73 rock volume fraction,400 N/s cyclic loading rate,and 9 MPa confinement.All the findings have important practical implications on the ability of backfill to support underground ex

关键词： Rock and backfill Triaxial cyclic loading Volume fraction Damage evolution 3D visualization

Genome-Wide Association Study of Cooked Rice Textural Attributes and Starch Physicochemical Properties in indica Rice

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Rice science 2024年第3期31卷 300-316,I0018-I0041页

作者： DENG bowen ZHANG Yanni ZHANG Fan WANG Wensheng XU Jianlong ZHANG yu BAO Jinsong Institute of Nuclear Agricultural Sciences Key Laboratory of Nuclear Agricultural Sciences of Ministry of Agriculture and Zhejiang ProvinceCollege of Agriculture and BiotechnologyZhejiang UniversityHangzhou 310058China Hainan Institute Zhejiang UniversitySanya 572025China Institute of Crop Sciences Chinese Academy of Agricultural SciencesBeijing 100081China

Rice cooking and eating qualities(CEQ)are mainly determined by cooked rice textural parameters and starch physicochemical properties.However,the genetic bases of grain texture and starch properties in rice have not been fully understood.We conducted a genome-wide association study for apparent amylose content(AAC),starch pasting viscosities,and cooked rice textural parameters using 279 indica rice accessions from the 3000 Rice Genome Project.We identified 26 QTLs in the whole population and detected single nucleotide polymorphisms(SNPs)with the lowest P-value at the Waxy(Wx)locus for all traits except pasting temperature and cohesiveness.Additionally,we detected significant SNPs at the SUBSTANDARD STARCH GRAIN6(SSG6)locus for AAC,setback(SB),hardness,adhesiveness,chewiness(CHEW),gumminess(GUM),and resilience.We subsequently divided the population using a SNP adjacent to the Waxy locus,and identified 23 QTLs and 12 QTLs in two sub-panels,WxT and WxA,respectively.In these sub-panels,SSG6 was also identified to be associated with pasting parameters,including peak viscosity,hot paste viscosity,cold paste viscosity,and consistency viscosity.Furthermore,a candidate gene encoding monosaccharide transporter 5(OsMST5)was identified to be associated with AAC,breakdown,SB,CHEW,and GUM.In total,39 QTLs were co-localized with known genes or previously reported QTLs.These identified genes and QTLs provide valuable information for genetic manipulation to improve rice CEQ.

关键词： cooking and eating quality genome-wide association study rice Waxy gene

Unravelling the nature of the active species as well as the Mn doping effect over gamma-Al_(2)O_(3) catalyst for eliminating AsH_(3) and PH_(3)

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2024年第2期136卷 213-225页

作者： bowen Xu Jiaxin Qu Xueqian Wang Langlang Wang yu Pu Ping Ning Yibing Xie Yixing Ma Qiang Ma Faculty of Environmental Science and Engineering Kunming University of Science and TechnologyKunming 650500China School of Architecture and Civil Engineering Chengdu UniversityChengdu 610106China

To investigate the enhancing effect of Mn on the performance of simultaneous catalytic oxidation of AsH_(3)and PH_(3)by CuO-Al_(2)O_(3)in a reducing atmosphere under micro-oxygen conditions,Cu-Mn modifiedγ-Al_(2)O_(3)catalysts were prepared.The characteristics of the catalysts showed that Mn reduced the crystallinity of the active CuO component,increased the number of oxygen vacancies and acidic sites on the catalyst surface,enhanced the mobility of surface oxygen,and the interaction between copper and manganese promoted the redox cycling ability of the catalysts and improved their oxidation performance,which increased the conversion frequency(TOF)by 2.54×10^(-2)to 3.07×10^(-2)sec^(-1).On the other hand,the introduction of Mn reduced the production of phosphate and As_(2)O_(3)on the catalyst surface by30.96%and 44.9%,which reduced the coverage and inerting of the active sites by phosphate and As_(2)O_(3),resulting in an 8 hr(6 hr)improvement in the stability of PH_(3)(AsH_(3))removal.

关键词： AsH_(3)-PH_(3)removal Oxygen activation Mn doping Stability enhancement

Comparative analysis of thermodynamic and mechanical responses between underground hydrogen storage and compressed air energy storage in lined rock caverns

在线全文

学校读者我要写书评

暂无评论

International Journal of Mining Science and Technology 2024年第4期34卷 531-543页

作者： bowen Hu Liyuan yu Xianzhen Mi Fei Xu Shuchen Li Wei Li Chao Wei Tao Zhang State Key Laboratory of Intelligent Construction and Healthy Operation and Maintenance of Deep Underground Engineering China University of Mining and TechnologyXuzhou 221116China Key Laboratory of Large Structure Health Monitoring and Control Shijiazhuang Tiedao UniversityShijiazhuang 050043China School of Mechanics and Civil Engineering China University of Mining and TechnologyXuzhou 221116China

Underground hydrogen storage(UHS)and compressed air energy storage(CAES)are two viable largescale energy storage technologies for mitigating the intermittency of wind and solar power.Therefore,it is meaningful to compare the properties of hydrogen and air with typical thermodynamic storage processes.This study employs a multi-physical coupling model to compare the operations of CAES and UHS,integrating gas thermodynamics within caverns,thermal conduction,and mechanical deformation around rock caverns.Gas thermodynamic responses are validated using additional simulations and the field test data.Temperature and pressure variations of air and hydrogen within rock caverns exhibit similarities under both adiabatic and diabatic simulation modes.Hydrogen reaches higher temperature and pressure following gas charging stage compared to air,and the ideal gas assumption may lead to overestimation of gas temperature and pressure.Unlike steel lining of CAES,the sealing layer(fibre-reinforced plastic FRP)in UHS is prone to deformation but can effectively mitigates stress in the sealing layer.In CAES,the first principal stress on the surface of the sealing layer and concrete lining is tensile stress,whereas UHS exhibits compressive stress in the same areas.Our present research can provide references for the selection of energy storage methods.

关键词： Underground hydrogen storage Compressed air energy storage Mechanical response Thermodynamic response Lined rock caverns

A semantic vector map-based approach for aircraft positioning in GNSS/GPS denied large-scale environment

在线全文

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2024年第4期34卷 1-10页

作者： Chenguang Ouyang Suxing Hu Fengqi Long Shuai Shi Zhichao yu Kaichun Zhao Zheng You Junyin Pi bowen Xing State Key Laboratory of Precision Measurement Technology and Instruments Tsinghua UniversityBeijing 100084China School of Mechanical and Information Engineering China University of Mining and Technology(Beijing)Beijing 100083China

Accurate positioning is one of the essential requirements for numerous applications of remote sensing data,especially in the event of a noisy or unreliable satellite signal.Toward this end,we present a novel framework for aircraft geo-localization in a large range that only requires a downward-facing monocular camera,an altimeter,a compass,and an open-source Vector Map(VMAP).The algorithm combines the matching and particle filter methods.Shape vector and correlation between two building contour vectors are defined,and a coarse-to-fine building vector matching(CFBVM)method is proposed in the matching stage,for which the original matching results are described by the Gaussian mixture model(GMM).Subsequently,an improved resampling strategy is designed to reduce computing expenses with a huge number of initial particles,and a credibility indicator is designed to avoid location mistakes in the particle filter stage.An experimental evaluation of the approach based on flight data is provided.On a flight at a height of 0.2 km over a flight distance of 2 km,the aircraft is geo-localized in a reference map of 11,025 km~2using 0.09 km~2aerial images without any prior information.The absolute localization error is less than 10 m.

关键词： Large-scale positioning Building vector matching Improved particle filter GPS-Denied Vector map