检索结果-南通市图书馆

Machine learning algorithm partially reconfigured on FPGA for an image edge detection system

在线全文

学校读者我要写书评

暂无评论

Journal of Electronic Science and Technology 2024年第2期22卷 48-68页

作者： Gracieth Cavalcanti Batista Johnny Oberg Osamu Saotome Haroldo F.de Campos Velho Elcio Hideiti Shiguemori Ingemar Soderquist Division of Electronic and Embedded Systems KTH Royal Institute of TechnologyStockholm 16440Sweden Electronic Engineering Division Aeronautics Institute of TechnologySao Josédos Campos SP 12228-900Brazil Laboratory of Applied Computing and Mathematics National Institute for Space ResearchSao Josédos Campos SP 12227-900Brazil Department of C4ISR Institute of Advanced StudiesSao Josédos Campos SP 12228-001Brazil Saab AB Linkoping 58188Sweden

Unmanned aerial vehicles(UAVs)have been widely used in military,medical,wireless communications,aerial surveillance,*** key topic involving UAVs is pose estimation in autonomous navigation.A standard procedure for this process is to combine inertial navigation system sensor information with the global navigation satellite system(GNSS)***,some factors can interfere with the GNSS signal,such as ionospheric scintillation,jamming,or *** alternative method to avoid using the GNSS signal is to apply an image processing approach by matching UAV images with georeferenced *** a high effort is required for image edge *** a support vector regression(SVR)model is proposed to reduce this computational load and processing *** dynamic partial reconfiguration(DPR)of part of the SVR datapath is implemented to accelerate the process,reduce the area,and analyze its granularity by increasing the grain size of the reconfigurable *** show that the implementation in hardware is 68 times faster than that in *** architecture with DPR also facilitates the low power consumption of 4 mW,leading to a reduction of 57%than that without *** is also the lowest power consumption in current machine learning hardware ***,the circuitry area is 41 times *** with Gaussian kernel shows a success rate of 99.18%and minimum square error of 0.0146 for testing with the planning *** system is useful for adaptive applications where the user/designer can modify/reconfigure the hardware layout during its application,thus contributing to lower power consumption,smaller hardware area,and shorter execution time.

关键词： Dynamic partial reconfiguration(DPR) Field programmable gate array(FPGA)implementation Image edge detection Support vector regression(SVR) Unmanned aerial vehicle(UAV) pose estimation

Combined CNN-LSTM Deep Learning Algorithms for Recognizing Human Physical Activities in Large and Distributed Manners:A Recommendation System

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 351-372页

作者： Ameni Ellouze Nesrine Kadri Alaa Alaerjan Mohamed Ksantini Control and Energy Management Laboratory National Engineering SchoolPreparatory Institute for Engineering StudiesUniversity of SfaxSfax3029Tunisia Higher institute of Computer Science and Communication Technologies University of SousseSousseBN19RHTunisia College of Computer and Information Sciences Jouf UniversityPO Box 2014SakakahSaudi Arabia

Recognizing human activity(HAR)from data in a smartphone sensor plays an important role in the field of health to prevent chronic *** and weekly physical activities are recorded on the smartphone and tell the user whether he is moving well or ***,smartphones and their associated sensing devices operate in distributed and unstable ***,collecting their data and extracting useful information is a significant *** this context,the aimof this paper is twofold:The first is to analyze human behavior based on the recognition of physical *** the results of physical activity detection and classification,the second part aims to develop a health recommendation system to notify smartphone users about their healthy physical behavior related to their physical *** system is based on the calculation of calories burned by each user during physical *** this way,conclusions can be drawn about a person’s physical behavior by estimating the number of calories burned after evaluating data collected daily or even weekly following a series of physical *** identify and classify human behavior our methodology is based on artificial intelligence models specifically deep learning techniques like Long Short-Term Memory(LSTM),stacked LSTM,and bidirectional *** human activity data contains both spatial and temporal information,we proposed,in this paper,to use of an architecture allowing the extraction of the two types of information *** Convolutional Neural Networks(CNN)has an architecture designed for spatial information,our idea is to combine CNN with LSTM to increase classification accuracy by taking into consideration the extraction of both spatial and temporal *** results obtained achieved an accuracy of 96%.On the other side,the data learned by these algorithms is prone to error and *** overcome this constraint and improve performance(96%),we proposed to use the

关键词： Human physical activities smartphone sensors deep learning distributed monitoring recommendation system uncertainty healthy calories

Creating a Better Future Together

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Today 2024年第10期73卷 48-53页

作者： LYU YUNMOU institute of European studies of the China institutes of Contemporary International Relations

China-Europe exchanges are of great significance not just for China and Europe,but also for the entire world as well.

关键词： Together exchanges eating

Westward Migration of Tropical Cyclone Activity in the Western North Pacific during 1982–2020:Features and Possible Causes

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 Meteorological Research 2024年第1期38卷 1-9页

作者： Jian ZHONG Huadong DU Yuqin WU Yuehua PENG China Satellite Maritime Tracking and Control Department Jiangyin 2144312 College of Advanced Interdisciplinary studies National University of Defense TechnologyChangsha 4100733 Dalian Naval Academy Dalian 1160184 institute of Atmospheric Physics Chinese Academy of SciencesBeijing 100029

The westward migration of tropical cyclone(TC)activity has been identified in the western North Pacific(WNP),but the related features and causes remain ***,based on the best track data from China,Japan,and the US,and the NCEP–NCAR reanalysis data in 1982–2020,we investigate characteristics of the westward migration of the WNP TC activity with various metrics,and reveal possible causes for the migration of TC tracks through analyzing its seasonality and dependence on environmental *** results show that the WNP TCs show significant westward migrations in a number of metrics,including location of tracks,genesis,the first track point at which TC reaches its lifetime-maximum intensity,and the last track point in the TC *** is found that TC tracks exhibit more significant westward migrations in the easterly steering flow than in the westerly steering ***,the TC longitude shift shows notable seasonal variations,for which the TCs in the easterlies move further west than those in the westerlies during July–September,vice versa during October–*** dependence of the westward migration of TC tracks on background steering flow is associated with the different environmental *** westward shift in the westerly steering is mainly due to the reduced vertical wind shear(VWS),while the weakened zonal easterly steering and reduced VWS are both closely related to the westward migration in the easterly *** results have important implications for understanding current and future variations in TC longitude shift.

关键词： tropical cyclone westward migration steering flow vertical wind shear

Relations with Neighboring Countries, Neighboring Region and China’s Neighborhood Environment

在线全文

学校读者我要写书评

暂无评论

Contemporary World 2024年第2期 2-7页

作者： Zhang Yunling institute of International studies of Shandong University Chinese Academy of Social Sciences

The Chinese government released the Outlook on China’s Foreign Policy on Its Neighborhood In the New Era in October 2023,which explicitly stated that“the neighborhood is where China survives and thrives and the foundation of its development and prosperity”.Such a high positioning of the neighborhood indicates that China attaches great importance to its neighborhood and is resolutely determined to deal well with *** neighborhood relationship features a dual structure:one is the state-to-state relations,meaning the bilateral relations between China and its neighboring countries;the other is regional relations,meaning relationship between China and its neighboring countries as a coexisting region,which collectively make up the overall neighborhood *** a sound neighborhood environment is imperative to China’s security and development.

关键词： neighborhood Neighborhood collective

Mechanisms to explain soil liquefaction triggering,development, and persistence during an earthquake

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Earthquake Science 2024年第06期 558-573页

作者： Fernando Teixeira MED–Mediterranean institute for Agriculture Environment and Development Institute for Advanced Studies and ResearchUniversidade de évora

Mechanisms have been proposed to explain the triggering, development, and persistence of soil liquefaction. The mechanism explaining the horizontal failure plane(triggering) and its depth below the phreatic surface is governed by the flux properties and effective stress at that plane. At the failure plane, the pore water pressure was higher than the effective stress, and the volume change was the highest. The pore water pressure is a function of the soil profile features(particularly the phreatic zone width) and bedrock motion(horizontal acceleration). The volume change at the failure plane is a function of the intrinsic permeability of the soil and bedrock displacement. The failure plane was predicted to occur during the oscillation with the highest amplitude, disregarding further bedrock motion, which was consistent with low seismic energy densities. Two mechanisms were proposed to explain the persistence of soil liquefaction. The first is the existence of low-permeability layers in the depth range in which the failure planes are predicted to occur. The other allows for the persistence and development of soil liquefaction; it is consistent with homogeneous soils and requires water inflow from bedrock water springs. The latter explains many of the features of soil liquefaction observed during earthquakes, namely, surficial effects, “instant” liquefaction, and the occurrence of short-and long-term changes in the level of the phreatic surfaces. This model(hypothesis), the relationship between the flux characteristics and loss of soil shear strength, provides self-consistent constraints on the depth below the phreatic surfaces where the failure planes are observed(expected to occur). It requires further experimental and observational evidence. Similar reasoning can be used to explain other saturated soil phenomena.

关键词：

Radical innovation breakthroughs of biodegradation of plastics by insects:history,present and future perspectives

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Environmental Science & Engineering 2024年第6期18卷 127-165页

作者： Shan-Shan Yang Wei-Min Wu Federica Bertocchini Mark Eric Benbow Suja P.Devipriya Hyung Joon Cha Bo-Yu Peng Meng-Qi Ding Lei He Mei-Xi Li Chen-Hao Cui Shao-Nan Shi Han-Jun Sun Ji-Wei Pang Defu He Yalei Zhang Jun Yang Deyi Hou De-Feng Xing Nan-Qi Ren Jie Ding Craig S.Criddle State Key Laboratory of Urban Water Resource and Environment School of EnvironmentHarbin Institute of TechnologyHarbin 150090China Department of Civil and Environmental Engineering William&Cloy Codiga Resource Recovery CenterStanford UniversityStanfordCA 94305USA Plasticentropy rue Thiers 28Reims 51100France Department of Entomology and Department of Osteopathic Medical Specialties Michigan State UniversityEast LansingMI 48824USA School of Environmental studies Cochin University of Science and TechnologyKochi 682022India Department of Chemical Engineering Pohang University of Science and TechnologyPohang 37673Republic of Korea School of Environmental Science and Engineering Tongji UniversityShanghai 200092China China Energy Conservation and Environmental Protection Group CECEP Talroad Technology Co.Ltd.Beijing 100096China School of Ecological and Environmental Sciences East China Normal UniversityShanghai 200241China Research institute for Frontier Science Beihang UniversityBeijing 100191China School of Environment Tsinghua UniversityBeijing 100084China

Insects damaging and penetrating plastic packaged materials has been reported since the *** innovation breakthroughs of plastic biodegradation have been initiated since the discovery of biodegradation of plastics by Tenebrio molitor larvae in 2015 followed by Galleria mellonella in *** we review updated studies on the insect-mediated biodegradation of *** biodegradation by insect larvae,mainly by some species of darkling beetles(Tenebrionidae)and pyralid moths(Pyralidae)is currently a highly active and potentially transformative area of *** the past eight years,publications have increased explosively,including discoveries of the ability of different insect species to biodegrade plastics,biodegradation performance,and the contribution of host and microbiomes,impacts of polymer types and their physic-chemical properties,and responsible enzymes secreted by the host and gut *** date,almost all major plastics including polyethylene(PE),polypropylene(PP),polyvinyl chloride(PVC),polyethylene terephthalate(PET),polyurethane(PUR),and polystyrene(PS)can be biodegraded by *** and ten other insect species representing the Tenebrionidae and Pyralidae *** biodegradation processes are symbiotic reactions or performed by synergistic efforts of both host and gut-microbes to rapidly depolymerize and biodegrade plastics with hourly *** digestive ezymens and bioreagents screted by the insects play an essential role in plasatic biodegradation in certain species of Tenebrionidae and Pyralidae *** research on the insect itself,gut microbiomes,transcriptomes,proteomes and metabolomes has evaluated the mechanisms of plastic biodegradation in *** conclude this review by discussing future research perspectives on insect-mediated biodegradation of plastics.

关键词： Plastics Biodegradation Insects Gut microbiomes Enzymes

Upgraded durian genome reveals the role of chromosome reshuffling during ancestral karyotype evolution,lignin biosynthesis regulation,and stress tolerance

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Life Sciences) 2024年第6期67卷 1266-1279页

作者： Wanwan Li Xin Chen Jianing Yu Yuxian Zhu College of Life Sciences Shaanxi Normal UniversityXi’an 710119China The State Key Laboratory of Protein and Gene Research College of Life SciencesPeking UniversityBeijing 100871China The institute for Advanced studies Wuhan UniversityWuhan 430072China

Durian(Durio zibethinus)is a tropical fruit that has a unique flavor and *** occupies a significant phylogenetic position within the Malvaceae *** core-eudicot plants are reported to share seven ancestral karyotypes that have undergone reshuffling,resulting in an abundant genomic ***,the ancestral karyotypes of the Malvaceae family,as well as the evolution trajectory leading to the28 chromosomes in durian,remain poorly ***,we report the high-quality assembly of the durian genome with comprehensive comparative genomic *** analyzing the collinear blocks between cacao and durian,we inferred 11 Malvaceae ancestral *** blocks were present in a single-copy form in cacao and mainly in triplicates in durian,possibly resulting from a recent whole genome triplication(WGT)event that led to hexaploidization of the durian genome around 20(17–24)million years ago.A large proportion of the duplicated genes in durian,such as those involved in the lignin biosynthesis module for phenylpropane biosynthesis,are derived directly from whole genome duplication,which makes it an important force in reshaping its genomic *** studies have revealed that genes involved in feruloyl-Co A formations were highly preferentially expressed in fruit peels,indicating that the thorns produced on durian fruit may comprise guaiacyl and syringyl *** all the analyzed transcription factors(TFs),members of the heat shock factor family(HSF)were the most significantly upregulated under heat *** subfamilies of genes encoding heat shock proteins(HSPs)in the durian genome appear to have undergone *** potential interactions between HSF Dzi05.397 and HSPs were examined and experimentally *** study provides a high-quality durian genome and reveals the reshuffling mechanism of ancestral Malvaceae chromosomes to produce the durian *** also provide insights into the mechanism underlying lignin bi

关键词： Durio zibethinus whole genome duplication whole genome triplication Malvaceae ancestral karyotypes chromosome reshuffling lignin biosynthesis heat stress

Evolutionary Decision-Making and Planning for Autonomous Driving Based on Safe and Rational Exploration and Exploitation

在线全文

学校读者我要写书评

暂无评论

Engineering 2024年第2期33卷 108-120页

作者： Kang Yuan Yanjun Huang Shuo Yang Zewei Zhou Yulei Wang Dongpu Cao Hong Chen College of Electronic and Information Engineering Tongji UniversityShanghai 201804China Shanghai institute of Intelligent Science and Technology Tongji UniversityShanghai 201210China School of Automotive studies Tongji UniversityShanghai 201804China School of Vehicle and Mobility Tsinghua UniversityBeijing 100084China

Decision-making and motion planning are extremely important in autonomous driving to ensure safe driving in a real-world *** study proposes an online evolutionary decision-making and motion planning framework for autonomous driving based on a hybrid data-and model-driven ***,a data-driven decision-making module based on deep reinforcement learning(DRL)is developed to pursue a rational driving performance as much as ***,model predictive control(MPC)is employed to execute both longitudinal and lateral motion planning *** constraints are defined according to the vehicle’s physical limit to meet the driving task ***,two principles of safety and rationality for the self-evolution of autonomous driving are proposed.A motion envelope is established and embedded into a rational exploration and exploitation scheme,which filters out unreasonable experiences by masking unsafe actions so as to collect high-quality training data for the DRL *** with a high-fidelity vehicle model and MATLAB/Simulink co-simulation environment are conducted,and the results show that the proposed online-evolution framework is able to generate safer,more rational,and more efficient driving action in a real-world environment.

关键词： Autonomous driving Decision-making Motion planning Deep reinforcement learning Model predictive control