检索结果-内蒙古大学图书馆

Energy-Efficient-Enabled Edge-AI-IoT Integrated Traffic Incident Analysis and Avoidance of Secondary Incidents

IEEE Internet of Things Journal 2025年

作者： Chavhan, Suresh Deepika, Illa Sai Gupta, Deepak Rodrigues, Joel J P C Indian Institute of Science Education and Research Thiruvananthapuram School of Data Sciences India Indian Institute of Management Mumbai India Maharaja Agrasen Institute of Technology Dept. of Computer Science and Engineering Delhi India Chitkara University Chitkara University Institute of Engineering and Technology Punjab India Amazonas State University AM Manaus Brazil

Intelligent transportation systems (ITS) use information communication and technologies to provide road safety, traffic control, traffic congestion, accident avoidance, etc. Traffic accidents cause huge disruption of vehicle movements, road blockages, traffic jams, etc., known as secondary traffic incidents. These incidents in turn lead to huge CO2 emissions and fuel consumption, which directly impact the environment, reduce vehicle mileage, and unnecessary fuel waste. To reduce or avoid secondary traffic incidents, in this paper, we propose an Edge-AI-IoT integrated energy efficient system to detect, analyze, and predict the primary and secondary incidents. The proposed system uses the existing sensor technology like accelerometer, tilt, etc., to detect the accident and severity levels using Edge-AI-IoT, locally it analyzes and predicts the secondary incidents. The proposed system has been exhaustively simulated using real-time scenarios in OMENT++, Veins, and SUMO, and it was tested using the NVIDIA Jetson AGX Xavier edge device integrated with the ThingSpeak cloud platform. The proposed system is tested with performance parameters such as clearance time, accident detection, density of vehicles, speed of vehicles, CO2 emissions, and fuel consumption at different times of day. The simulation and real-time tested results show its real-time deployment. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Harnessing marine microbiomes to develop a sustainable,all-Atlantic bioeconomy

引用

mLife 2024年第2期3卷 163-166页

作者： Cristiane Thompson Alice C.Ortmann Henk Bolhuis Thulani Makhalanyane Fabiano Thompson Institute of Biology Federal University of Rio de Janeiro(UFRJ)Rio de JaneiroBrazil Fisheries and Oceans Canada Bedford Institute of OceanographyDartmouthNova ScotiaCanada Department of Marine Microbiology and Biogeochemistry Royal Netherlands Institute for Sea Research(NIOZ)The Netherlands Department of Microbiology School of Data Science and Computational ThinkingStellenbosch UniversityStellenboschSouth Africa

Marine microbiomes are integral to the functioning of a healthy ocean and have the potential to be key contributors toward an all-Atlantic sustainable blue bioeconomy(Figure 1).New compounds may be developed based on these *** Atlantic Ocean is a biodiversity *** All-Atlantic Ocean Research and Innovation Alliance(AAORIA)Declaration,signed in 2022 in Washington,DC,is a promising mechanism to move forward marine microbiome science,technology,and innovation.

关键词： Atlantic marine ocean

来源：评论

学校读者我要写书评

暂无评论

GEDI: A Graph-based End-to-end data Imputation Framework

GEDI: A Graph-based End-to-end Data Imputation Framework

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Katrina Chen Xiuqin Liang Zheng Ma Zhibin Zhang Dept. of Statistical and Actuarial Science University of Waterloo Waterloo Canada Data Science Center of Excellence Deloitte Consulting Beijing China Cheriton School of Computer Science University of Waterloo Waterloo Canada Chinese Academy of Sciences Institute of Computing Technology Beijing China

data imputation is an effective way to handle missing data, which is common in practical applications. In this study, we propose and test a novel data imputation process that achieves two important goals: 1) preserving the row-wise similarities among observations and column-wise contextual relationships among features in the feature matrix. 2) tailoring the imputation process to some specific downstream label prediction task. The proposed imputation process uses Transformer and graph structure learning to iteratively refine the contextual relationships among features and similarities among observations. Moreover, it implements a meta-learning framework to select features that are influential to the downstream prediction task of interest. We conduct experiments on real-world datasets, and show that the proposed method consistently improves imputation and label prediction performance over a variety of benchmark methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Curriculum Negative Mining For Temporal Networks

arXiv

引用

arXiv 2024年

作者： Chen, Ziyue Zheng, Tongya Song, Mingli Department of Economics University of California Berkeley BerkeleyCA United States Big Graph Center School of Computer and Computing Science Hangzhou City University Zhejiang Hangzhou China State Key Laboratory of Blockchain and Data Security Zhejiang University Zhejiang Hangzhou China Institute of Blockchain and Data Security Zhejiang Hangzhou China

Temporal networks are effective in capturing the evolving interactions of networks over time, such as social networks and e-commerce networks. In recent years, researchers have primarily concentrated on developing specific model architectures for Temporal Graph Neural Networks (TGNNs) in order to improve the representation quality of temporal nodes and edges. However, limited attention has been given to the quality of negative samples during the training of TGNNs. When compared with static networks, temporal networks present two specific challenges for negative sampling: positive sparsity and positive shift. Positive sparsity refers to the presence of a single positive sample amidst numerous negative samples at each timestamp, while positive shift relates to the variations in positive samples across different timestamps. To robustly address these challenges in training TGNNs, we introduce Curriculum Negative Mining (CurNM), a model-aware curriculum learning framework that adaptively adjusts the difficulty of negative samples. Within this framework, we first establish a dynamically updated negative pool that balances random, historical, and hard negatives to address the challenges posed by positive sparsity. Secondly, we implement a temporal-aware negative selection module that focuses on learning from the disentangled factors of recently active edges, thus accurately capturing shifting preferences. Extensive experiments on 12 datasets and 3 TGNNs demonstrate that our method outperforms baseline methods by a significant margin. Additionally, thorough ablation studies and parameter sensitivity experiments verify the usefulness and robustness of our approach. Our code is available at https://***/zziyue83/CurNM. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Capsicum Flower Identification for Robotic Pollination in Greenhouses

Capsicum Flower Identification for Robotic Pollination in Gr...

引用

2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

作者： Sharma, Sunpreet Fang, Gu Chen, Zhong-Hua Obst, Oliver Tissue, David Zou, Ju Jia Liang, Weiguang School of Engineering Design and Built Environment Western Sydney University Australia School of Science Western Sydney University Australia School of Computer Data and Mathematical Sciences Western Sydney University Australia Hawkesbury Institute for the Environment Western Sydney University Australia National Vegetable Protected Cropping Centre Western Sydney University Australia

ISBN: (纸本)9798350303780

Due to restrictions on bees and the lack of wind in the greenhouse, pollination could be a labor-intensive activity. Hence, an automated pollination process is preferred to improve the productivity in greenhouse settings. This paper introduces an image-based pollination method applicable within the greenhouse. A stereo-vision camera and a You Only Look Once (YOLO)-based image processing technique are employed to identify and locate the pollination-ready capsicum flowers in the greenhouse. The detected flower's location is communicated to a robotic system for it to be maneuvered in front of the flower to finish the required pollination. When tested on the test dataset using Precision & Recall Curve (PRC), the proposed detection method achieves an average detection precision of 0.76 for the first class (CapFlower) and 0.61 for the other (Bud). © 2023 IEEE.

关键词： Greenhouses

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Materials Modeling at Quantum Accuracy: Ab Initio Simulations of Quasicrystals and Interacting Extended Defects in Metallic Alloys 23

Large-Scale Materials Modeling at Quantum Accuracy: Ab Initi...

引用

2023 International Conference for High Performance computing, Networking, Storage and Analysis, SC 2023

作者： Das, Sambit Kanungo, Bikash Subramanian, Vishal Panigrahi, Gourab Motamarri, Phani Rogers, David Zimmerman, Paul Gavini, Vikram Department of Mechanical Engineering University of Michigan Ann Arbor United States Department of Materials Science & Engineering University of Michigan Ann Arbor United States Department of Computational and Data Sciences Indian Institute of Science Bangalore India Scientific Computing Group Oak Ridge National Laboratory Oak Ridge United States Department of Chemistry University of Michigan Ann Arbor United States Department of Materials Science & Engineering University of Michigan Ann Arbor United States

ISBN: (纸本)9798400701092

Ab initio electronic-structure has remained dichotomous between achievable accuracy and length-scale. Quantum many-body (QMB) methods realize quantum accuracy but fail to scale. Density functional theory (DFT) scales favorably but remains far from quantum accuracy. We present a framework that breaks this dichotomy by use of three interconnected modules: (i) invDFT: a methodological advance in inverse DFT linking QMB methods to DFT;(ii) MLXC: a machine-learned density functional trained with invDFT data, commensurate with quantum accuracy;(iii) DFT-FE-MLXC: an adaptive higher-order spectral finite-element (FE) based DFT implementation that integrates MLXC with efficient solver strategies and HPC innovations in FE-specific dense linear algebra, mixed-precision algorithms, and asynchronous compute-communication. We demonstrate a paradigm shift in DFT that not only provides an accuracy commensurate with QMB methods in ground-state energies, but also attains an unprecedented performance of 659.7 PFLOPS (43.1% peak FP64 performance) on 619,124 electrons using 8,000 GPU nodes of Frontier supercomputer. © 2023 ACM.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

GSEK: Graph Structured Neural Networks with Energy Graph Kernel 21

GSEK: Graph Structured Neural Networks with Energy Graph Ker...

引用

21st International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2023

作者： Xu, Wei Cui, Qing-Zhe Ge, Wei Zhou, Biao Wang, Xiao-Feng Tong, He Xu, Li-Xiang Tang, Yuan-Yan College of Artificial Intelligence and Big Data Hefei University Hefei230601 China Chinese people's Liberation Army Aviation School Department of Basic Beijing101123 China Zhuhai UM Science and Technology Research Institute FST University of Macau Macau China

ISBN: (纸本)9798350303810

Graph neural networks (GNNs) have become an increasingly popular framework for describing graph-structured data using deep learning. However, traditional GNNs may not accurately map features for graphs that contain noise or missing information. In order to address this issue, we propose a new method called Graph Structured Neural Networks with Energy Graph Kernel (GSEK) for classification. GSEK defines energy properties for nodes and extracts node subgraphs using maximum energy random wandering to ensure the centrality of the subgraphs' structure. It then uses Wasserstein Weisfeiler-Lehman (WWL) graph kernel to calculate isomorphism coefficients for subgraphs of different node pairs, which are used to define weight matrices and achieve graph reconstruction. Unlike traditional methods that solely focus on node features, GSEK places greater emphasis on the local structure of the graph. Our experiments on six publicly available graph classification datasets demonstrate that our proposed model outperforms other benchmark models. © 2023 IEEE.

关键词： Graph classification Graph kernel Graph neural networks Graph structure learning

来源：评论

学校读者我要写书评

暂无评论

Socioeconomic Changes Based Climate Training for Agricultural Application Using Deep Learning Model

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 399-410页

作者： Sunitha, M. Durairaj, M. Rajalingam, A. Yusoff, Siti Khalidah Mohd Prasad, S. Hari Chandra Malluvalasa, S. N. Lakshmi Kiran, Ajmeera Department of CSE Vasavi College of Engineering Hyderabad India Department of ECE Saveetha School of Engineering SIMATS Chennai India Department of Engineering University of Technology and Applied Sciences-Shinas and Saveetha Institute of Medical and Technical Sciences Chennai India Management and Science University Selangor Shah Alam Malaysia Department of Electronics & amp Communication Engineering Aditya University Surampalem India Department of Artificial Intelligence & amp Data Science Koneru Lakshmaiah Education Foundation Guntur Dist. Andhra PradeshVaddeswaram 522302 India Department of Computer Science and Engineering MLR Institute of Technology Dundigal Telangana Hyderabad 500043 India

In socioeconomic factor studies, the use of the logit and probit models has the disadvantage of representing random variation in preference for unobserved components and time-linked errors. The agricultural sector in the coastal nations of South-East Asia is facing mounting strain due to the adverse effects of climate change. Anticipating and controlling climate variables is challenging and necessitates expensive fixes. Based on social and economic shifts and the use of a deep learning model to detect climate change, the two main facets of agricultural application have been examined in this study. The suggested model focusses on these two factors because the economics and climate are crucial components of agriculture. Initially, financial flow–based data analysis employing recurrent LSTM spatial neural networks for text data analysis was used to assess the social economic analysis for those countries with minimal agricultural development. The study of crop growth data based on climate change is then done using Boltzmann Markov quantile regression neural networks. In terms of training accuracy, sensitivity specificity, and ROC, a performance study is conducted for crop growth data based on climatic change and agricultural development based on economic data. The proposed approach in this instance produced training accuracy of 79%, specificity of 83%, ROC of 84%, and sensitivity of 80% for economic data–based agricultural development;the suggested method achieved 75% training accuracy, 73% specificity, 80% ROC, and 84% SENSITIVITY for climate change–based crop growth data. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Agricultural application Climate change detection Deep learning model Quantile regression Social economic changes

来源：评论

学校读者我要写书评

暂无评论

Bridge-IF: learning inverse protein folding with Markov bridges 24

Bridge-IF: learning inverse protein folding with Markov brid...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yiheng Zhu Jialu Wu Qiuyi Li Jiahuan Yan Mingze Yin Wei Wu Mingyang Li Jieping Ye Zheng Wang Jian Wu College of Computer Science & Technology and Liangzhu Laboratory Zhejiang University College of Pharmaceutical Sciences Zhejiang University Alibaba Cloud Computing School of Public Health Zhejiang University School of Artificial Intelligence and Data Science University of Science and Technology of China College of Computer Science & Technology and Liangzhu Laboratory Zhejiang University and School of Public Health Zhejiang University and The Second Affiliated Hospital Zhejiang University School of Medicine

ISBN: (纸本)9798331314385

Inverse protein folding is a fundamental task in computational protein design, which aims to design protein sequences that fold into the desired backbone structures. While the development of machine learning algorithms for this task has seen significant success, the prevailing approaches, which predominantly employ a discriminative formulation, frequently encounter the error accumulation issue and often fail to capture the extensive variety of plausible sequences. To fill these gaps, we propose Bridge-IF, a generative diffusion bridge model for inverse folding, which is designed to learn the probabilistic dependency between the distributions of backbone structures and protein sequences. Specifically, we harness an expressive structure encoder to propose a discrete, informative prior derived from structures, and establish a Markov bridge to connect this prior with native sequences. During the inference stage, Bridge-IF progressively refines the prior sequence, culminating in a more plausible design. Moreover, we introduce a reparameterization perspective on Markov bridge models, from which we derive a simplified loss function that facilitates more effective training. We also modulate protein language models (PLMs) with structural conditions to precisely approximate the Markov bridge process, thereby significantly enhancing generation performance while maintaining parameter-efficient training. Extensive experiments on well-established benchmarks demonstrate that Bridge-IF predominantly surpasses existing baselines in sequence recovery and excels in the design of plausible proteins with high foldability. The code is available at https://***/violet-sto/Bridge-IF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BackdoorBench: A Comprehensive Benchmark of Backdoor Learning

arXiv

引用

arXiv 2022年

作者： Wu, Baoyuan Chen, Hongrui Zhang, Mingda Zhu, Zihao Wei, Shaokui Yuan, Danni Shen, Chao School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China School of Cyber Science and Engineering Xi'an Jiaotong University China

Backdoor learning is an emerging and vital topic for studying deep neural networks' vulnerability (DNNs). Many pioneering backdoor attack and defense methods are being proposed, successively or concurrently, in the status of a rapid arms race. However, we find that the evaluations of new methods are often unthorough to verify their claims and accurate performance, mainly due to the rapid development, diverse settings, and the difficulties of implementation and reproducibility. Without thorough evaluations and comparisons, it is not easy to track the current progress and design the future development roadmap of the literature. To alleviate this dilemma, we build a comprehensive benchmark of backdoor learning called BackdoorBench. It consists of an extensible modular-based codebase (currently including implementations of 8 state-of-the-art (SOTA) attacks and 9 SOTA defense algorithms) and a standardized protocol of complete backdoor learning. We also provide comprehensive evaluations of every pair of 8 attacks against 9 defenses, with 5 poisoning ratios, based on 5 models and 4 datasets, thus 8,000 pairs of evaluations in total. We present abundant analysis from different perspectives about these 8,000 evaluations, studying the effects of different factors in backdoor learning. All codes and evaluations of BackdoorBench are publicly available at https://***. © 2022, CC BY-NC-ND.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：