检索结果-南通市图书馆

Semantic segmentation via pixel-to-center similarity calculation

CAAI Transactions on Intelligence Technology 2024年第1期9卷 87-100页

作者： Dongyue Wu Zilin Guo Aoyan Li Changqian Yu Nong Sang Changxin Gao National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhanChina meituan inc. BeijingChina

Sinc. the fully convolutional network has achieved great success in semantic segmentation,lots of works have been proposed to extract discriminative pixel representations.However,the authors observe that existing methods still suffer from two typical challenges:(i)The intra-class feature variation between different scenes may be large,leading to the difficulty in maintaining the consistency between same-class pixels from different scenes;(ii)The inter-class feature distinc.ion in the same scene could be small,resulting in the limited performance to distinguish different classes in each scene.The authors first rethink se-mantic segmentation from a perspective of similarity between pixels and class centers.Each weight vector of the segmentation head represents its corresponding semantic class in the whole dataset,which can be regarded as the embedding of the class center.Thus,the pixel-wise classification amounts to computing similarity in the final feature space between pixels and the class centers.Under this novel view,the authors propose a Class Center Similarity(CCS)layer to address the above-mentioned challenges by generating adaptive class centers conditioned on each scenes and supervising the similarities between class centers.The CCS layer utilises the Adaptive Class Center Module to generate class centers conditioned on each scene,which adapt the large intra-class variation between different scenes.Specially designed Class Distance Loss(CD Loss)is introduced to control both inter-class and intra-class distances based on the predicted center-to-center and pixel-to-center similarity.Finally,the CCS layer outputs the processed pixel-to-center similarity as the segmentation prediction.Extensive experiments demonstrate that our model performs favourably against the state-of-the-art methods.

关键词： computer vision deep neural networks image segmentation scene understanding

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Effects of essential oils on economically important characteristics of ruminant species: A comprehensive review

引用

Animal Nutrition 2024年第1期16卷 1-10页

作者： Cara Wessels Wells Micro Bios Inc.

Essential oils derived from plants can provide biological impacts to livestock species. Scientific studies researching essential oils in livestock have investigated various essential oils for prevention and treatment of microbial infection and parasites as well as to enhance milk production, animal performance and rumen function. Despite the availability of several commercial products containing essential oils to promote animal health and production, the vast amount of essential oils, modes of application, and effective concentrations of the essential oils suggest there are more opportunities for essential oils to be utilized in commercial livestock production and veterinary medicine. The objective of this review is to contribute to the understanding of the value that essential oils can provide to the ruminant diet and to examine the biological impact of various essential oils on economically important production traits of ruminant species.

关键词： Essential oils Ruminant diet Non-antibiotic therapy

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

SMEC:Scene Mining for E-Commerce

引用

Journal of Computer Science & Technology 2024年第1期39卷 192-210页

作者：王罡李翔郭子义殷大伟马帅 State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China School of Data Science and Engineering East China Normal UniversityShanghai 200062China *** Inc.Beijing 100176China Baidu Inc.Beijing 100085China

Scene-based recommendation has proven its usefulness in E-commerce,by recommending commodities based on a given scene.However,scenes are typically unknown in advance,which necessitates scene discovery for E-commerce.In this article,we study scene discovery for E-commerce systems.We first formalize a scene as a set of commodity cate-gories that occur simultaneously and frequently in real-world situations,and model an E-commerce platform as a heteroge-neous information network(HIN),whose nodes and links represent different types of objects and different types of rela-tionships between objects,respectively.We then formulate the scene mining problem for E-commerce as an unsupervised learning problem that finds the overlapping clusters of commodity categories in the HIN.To solve the problem,we pro-pose a non-negative matrix factorization based method SMEC(Scene Mining for E-Commerce),and theoretically prove its convergence.Using six real-world E-commerce datasets,we finally conduct an extensive experimental study to evaluate SMEC against 13 other methods,and show that SMEC consistently outperforms its competitors with regard to various evaluation measures.

关键词： graph clustering E-commerce heterogeneous information network(HIN) scene mining

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Changes in microorganisms and metabolites during long-term fermentation of commercially manufactured anchovy sauce

引用

Food Science and Human Wellness 2024年

作者： Daehyeon Kim Seong-Eun Park Eun-Ju Kim Seung-Ho Seo Kwang-Moon Cho Sun Jae Kwon Hong-Seok Son Department of Biotechnology College of Life Sciences and Biotechnology Korea University Sonlab inc. 3. AccuGene inc.

This study was performed to investigate the changes in microbial communities and metabolites during the long-term fermentation of commercially manufactured anchovy sauce. Samples of commercial anchovy sauce were collected from large-scale fermentation tanks with fermentation periods of up to 7.87 years. The complex bacterial community was simplified to two genera， Tetragenococcus and Halanaerobium， after approximately 0.55 years of fermentation. Although genera， such as Saccharomyces， Cladosporium， Candida， and Aspergillus， were relatively dominant， no clear pattern was identified in fungal community analysis. The longitudinal metabolite profile demonstrated that approximately half (55.8%) of the metabolites present in anchovy sauce were produced within a year of fermentation due to rapid fermentation. Despite the static microbial community， the contents of several metabolites inc.uding amino acids and biogenic amines changed continuously during the long-term fermentation of anchovy sauce. This study provides novel insights into the changes in microbiota and metabolites in fish sauce produced without any starter inoculation.

关键词：

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Modeling displacement flow inside a full-length casing string for well cementing

引用

Petroleum Research 2024年第1期9卷 1-16页

作者： Hu Dai Ali Eslami Jason Schneider Gefei Liu Fred Schwering Pegasus Vertex Inc.USA Laval University Canada Sanjel Energy Services Canada Athabasca Oil Corporation Canada

While computer modeling of annular displacement efficiency is widely applied in cementing engineering,modeling the displacement flow inside a casing or drill string for cementing operations has received less attention.Although predicting displacement efficiency inside a full-length pipe is desired by cementing engineers,the attempt of developing a model with both efficiency and accuracy faces challenges.Access to computer simulators for this purpose is limited.Compared with annular flow,the displacement flow inside pipe,although within a simpler geometry and without eccentricity effect,is not simpler in physics,modelling strategy and predictability,because a variety of flow patterns and flow instabilities can develop to create complicated fluid interfaces.In this paper,we present an integrated numerical model developed to simulate displacement flows inside a full-length pipe,which connects an existing annulus model to enable complete displacement simulations of cementing jobs.The model uses three-dimensional grid to solve fluid concentrations with degrees of mixing,and inc.rporates flow instability detection and flow regime determination.Applied in cementing,the model accounts for effects of pumping rate,well inc.ination,pipe rotation,fluid densities,rheological parameters and more.This computationally efficient model does not rely on high-resolution mesh as often required by conventional Computational Fluid Dynamics models,thus it is suitable to be implemented in a cementing software for daily use by well cementing engineers.The methodology of the model is discussed in detail in this paper.To validate the model,we examine simulation results against experimental results obtained in our laboratory tests and CFD simulations;acceptable agreement is found under different testing conditions.We also presented two case studies of real cementing jobs with cement evaluation logs compared to simulation results,showing that the model can predict consistent displacement efficiency results.

关键词： Inside pipe displacement Displacement efficiency Numerical model Primary cementing Displacement flow

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Optimal SOC Headroom of Pump Storage Hydropower for Maximizing Joint Revenue from Day-ahead and Real-time Markets Under Regional Transmission Organization Dispatch

引用

Journal of Modern Power Systems and Clean Energy 2024年第1期12卷 238-250页

作者： Yikui Liu Bing Huang Yang Lin Yonghong Chen Lei Wu Electrical and Computer Engineering Department Stevens Institute of TechnologyHobokenNJ 07030USA Midcontinent Independent System Operator Inc.CarmelIN 46032USA

In response to the inc.easing penetration of volatile and uncertain renewable energy,the regional transmission organizations(RTOs)have been recently focusing on enhancing the models of pump storage hydropower(PSH)plants,which are one of the key flexibility assets in the day-ahead(DA)and real-time(RT)markets,to further boost their flexibility provision potentials.Inspired by the recent research works that explored the potential benefits of excluding PSHs’cost-related terms from the objective functions of the DA market clearing model,this paper completes a rolling RT market scheme that is compatible with the DA market.Then,with the vision that PSHs could be permitted to submit state-of-charge(SOC)headrooms in the DA market and to release them in the RT market,this paper uncovers that PSHs could inc.ease the total revenues from the two markets by optimizing their SOC headrooms,assisted by the proposed tri-level optimal SOC headroom model.Specifically,in the proposed tri-level model,the middle and lower levels respectively mimic the DA and RT scheduling processes of PSHs,and the upper level determines the optimal headrooms to be submitted to the RTO for maximizing the total revenue from the two markets.Numerical case studies quantify the profitability of the optimal SOC headroom submissions as well as the associated financial risks.

关键词： Pump storage hydropower energy market state-of-charge(SOC) headroom market revenue tri-level problem

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A reinforcement learning approach for thermostat setpoint preference learning

引用

Building Simulation 2024年第1期17卷 131-146页

作者： Hussein Elehwany Mohamed Ouf Burak Gunay Nunzio Cotrufo Jean-Simon Venne Department of Environmental Engineering Carleton UniversityOttawaCanada Departmentof Building Civiland Environmental EngineeringConcordia UniversityMontrealCanada BrainBox Al inc. MontrealCanada

Occupant-centric controls(OcC)is an indoor climate control approach whereby occupant feedback is used in the sequence of operation of building energy systems.While OcC has been used in a wide range of building applications,an OcC category that has received considerable research interest is learning occupants'thermal preferences through their thermostat interactions and adapting temperature setpoints accordingly.Many recent studies used reinforcement learning(RL)as an agent for OcC to optimize energy use and occupant comfort.These studies depended on predicted mean vote(PMV)models or constant comfort ranges to represent comfort,while only few of them used thermostat interactions.This paper addresses this gap by introducing a new off-policy reinforcement learning(RL)algorithm that imitates the occupant behaviour by utilizing unsolicited occupant thermostat overrides.The algorithm is tested with a number of synthetically generated occupant behaviour models implemented via the Python APl of EnergyPlus.The simulation results indicate that the RL algorithm could rapidly learn preferences for all tested occupant behaviour scenarios with minimal exploration events.While substantial energy savings were observed with most occupant scenarios,the impact on the energy savings varied depending on occupants'preferences and thermostat use behaviour stochasticity.

关键词： reinforcement learning preference learning occupant-centric controls smart thermostats off-policy learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A novel alternative for pyrogen detection based on a transgenic cell line

引用

Signal Transduction and Targeted Therapy 2024年第3期9卷 1221-1229页

作者： Qing He Chuan-Fei Yu Gang Wu Kai-Qin Wang Yong-Bo Ni Xiao Guo Zhi-Hao Fu Lan Wang De-Jiang Tan Hua Gao Can Wang Gang Chen Xu-Hong Chen Bo Chen Jun-Zhi Wang National Institutes for Food and Drug Control BeijingChina School of Life Science and Biopharmaceutics Shenyang Pharmaceutical UniversityShenyangChina Shanghai Institute for Food and Drug Control ShanghaiChina KeyMed Biosciences inc. ChengduChina

Pyrogen,often as a contaminant,is a key indicator affecting the safety of almost all parenteral drugs(inc.uding biologicals,chemicals,traditional Chinese medicines and medical devices).It has become a goal to completely replace the in vivo rabbit pyrogen test by using the in vitro pyrogen test based on the promoted‘reduction,replacement and refinement’princ.ple,which has been highly considered by regulatory agencies from different countries.We used NF-κB,a central signalling molecule mediating inflammatory responses,as a pyrogenic marker and the monocyte line THP-1 transfected with a luciferase reporter gene regulated by NF-κB as an in vitro model to detect pyrogens by measuring the intensity of a fluorescence signal.Here,we show that this test can quantitatively and sensitively detect endotoxin(lipopolysaccharide from different strains)and nonendotoxin(lipoteichoic acid,zymosan,peptidoglycan,lectin and glucan),has good stability in terms of NF-κB activity and cell phenotypes at 39 cell passages and can be applied to detect pyrogens in biologicals(group A&C meningococcal polysaccharide vaccine;basiliximab;rabies vaccine(Vero cells)for human use,freeze-dried;Japanese encephalitis vaccine(Vero cells),inactivated;insulin aspart injection;human albumin;recombinant human erythropoietin injection(CHO Cell)).The within-laboratory reproducibility of the test in three independent laboratories was 85%,80%and 80%and the interlaboratory reproducibility among laboratories was 83.3%,95.6%and 86.7%.The sensitivity(true positive rate)and specificity(true negative rate)of the test were 89.9%and 90.9%,respectively.In summary,the test provides a novel alternative for pyrogen detection.

关键词： pyrogen rabbit replace

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

SAM3D: zero-shot 3D object detection via the segment anything model

引用

Science China(Information Sciences) 2024年第4期67卷 331-332页

作者： Dingyuan ZHANG Dingkang LIANG Hongcheng YANG Zhikang ZOU Xiaoqing YE Zhe LIU Xiang BAI School of Artificial Intelligence and Automation Huazhong University of Science and Technology Baidu inc. School of Electronic Information and Communication Huazhong University of Science and Technology

In the past few years, foundation models have thrived and succeeded in linguistic and visual tasks, showing astonishing zero-shot and few-shot capabilities. Their advances encourage researchers and industries to extend the boundaries of what artificial intelligence can do and have shown some fantastic products(e.g., ChatGPT [1]) with the potential to change the world.

关键词：

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Few-Shot Graph Classification with Structural-Enhanced Contrastive Learning for Graph Data Copyright Protection

引用

Tsinghua Science and Technology 2024年第2期29卷 605-616页

作者： Kainan Zhang DongMyung Shin Daehee Seo Zhipeng Cai Department of Computer Science Georgia State UniversityAtlantaGA 30303USA LSWare inc. Seoul 08504Republic of Korea College of Intelligence Information Engineering Sangmyung UniversitySeoul 03016Republic of Korea

Open-source licenses can promote the development of machine learning by allowing others to access,modify,and redistribute the training dataset.However,not all open-source licenses may be appropriate for data sharing,as some may not provide adequate protections for sensitive or personal information such as social network data.Additionally,some data may be subject to legal or regulatory restrictions that limit its sharing,regardless of the licensing model used.Hence,obtaining large amounts of labeled data can be difficult,time-consuming,or expensive in many real-world scenarios.Few-shot graph classification,as one application of meta-learning in supervised graph learning,aims to classify unseen graph types by only using a small amount of labeled data.However,the current graph neural network methods lack full usage of graph structures on molecular graphs and social network datasets.Sinc. structural features are known to correlate with molecular properties in chemistry,structure information tends to be ignored with sufficient property information provided.Nevertheless,the common binary classification task of chemical compounds is unsuitable in the few-shot setting requiring novel labels.Hence,this paper focuses on the graph classification tasks of a social network,whose complex topology has an uncertain relationship with its nodes'attributes.With two multi-class graph datasets with large node-attribute dimensions constructed to facilitate the research,we propose a novel learning framework that integrates both meta-learning and contrastive learning to enhance the utilization of graph topological information.Extensive experiments demonstrate the competitive performance of our framework respective to other state-of-the-art methods.

关键词： few-shot learning contrastive learning data copyright protection

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：