检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liang, Zixi Xu, Guowei Wu, Haifeng Huang, Ye Li, Wen Duan, Lixin Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China China School of Computer Science and Engineering University of Electronic Science and Technology of China China Sichuan Provincial Key Laboratory for Human Disease Gene Study The Center for Medical Genetics Department of Laboratory Medicine Sichuan Academy of Medical Sciences Sichuan Provincial People’s Hospital UESTC China

ISBN: (纸本)157735897X

Learning-based methods have become increasingly popular in 3D indoor scene synthesis (ISS), showing superior performance over traditional optimization-based approaches. These learning-based methods typically model distributions on simple yet explicit scene representations using generative models. However, due to the oversimplified explicit representations that overlook detailed information and the lack of guidance from multimodal relationships within the scene, most learning-based methods struggle to generate indoor scenes with realistic object arrangements and styles. In this paper, we introduce a new method, Scene Implicit Neural Field (S-INF), for indoor scene synthesis, aiming to learn meaningful representations of multimodal relationships, to enhance the realism of indoor scene synthesis. S-INF assumes that the scene layout is often related to the object-detailed information. It disentangles the multimodal relationships into scene layout relationships and detailed object relationships, fusing them later through implicit neural fields (INFs). By learning specialized scene layout relationships and projecting them into S-INF, we achieve a realistic generation of scene layout. Additionally, S-INF captures dense and detailed object relationships through differentiable rendering, ensuring stylistic consistency across objects. Through extensive experiments on the benchmark 3D-FRONT dataset, we demonstrate that our method consistently achieves state-of-the-art performance under different types of ISS. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Safe Reinforcement Learning for Social Motor Coordination in Two Dimensional Space 26

Safe Reinforcement Learning for Social Motor Coordination in...

引用

26th International Conference on Industrial technology, ICIT 2025

作者： Yang, Fan Huang, Yuening Zhai, Chao Zhang, Hehong China University of Geosciences School of Automation Wuhan Campus China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Rice University George R. Brown School of Engineering and Computing HoustonTX United States Fuzhou University School of Computer and Data Science Fuzhou China

ISBN: (纸本)9798331521950

This paper presents an interactive motion control method based on reinforcement learning, designed to assist children with autism who have social motor impairments through a mirror game intervention. The virtual teacher uses the Deep Deterministic Policy Gradient (DDPG) algorithm to optimize its actions, guiding the participant to follow a Lissajous trajectory. To ensure safety, a motion-correction mechanism was developed, which automatically adjusts actions when the predicted trajectory surpasses predefined safety boundaries. The reward function considers both the distance between the virtual teacher and the target trajectory, as well as the distance between the virtual teacher and the participant, with dynamic adjustments applied by the motion-correction mechanism. Experimental results demonstrate that the virtual teacher effectively guides the participant towards the target trajectory while adhering to safety constraints. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Branch-and-cut-and-price for agile earth observation satellite scheduling

引用

European Journal of Operational Research 2025年

作者： Peng, Guansheng Wang, Jianjiang Song, Guopeng Gunawan, Aldy Xing, Lining Vansteenwegen, Pieter School of Advanced Engineering and Great Bay Institute for Advanced Study Great Bay University Dongguan523000 China Defense Innovation Institute Chinese Academy of Military Science Beijing100071 China College of Systems Engineering National University of Defense Technology Changsha410073 China National Key Laboratory of Information Systems Engineering National University of Defense Technology Changsha410073 China School of Computing and Information Systems Singapore Management University Singapore178902 Singapore Research Institute of Intelligent Control and Manufacturing System Jiangsu University of Technology Changzhou213001 China KU Leuven Institute for Mobility - CIB Leuven3001 Belgium

The Agile Earth Observation Satellite scheduling selects and sequences satellite observations of possible targets on the Earth's surface, each with a specific profit and multiple time windows. The objective is to maximize the collected profit of all observations completed under some operational constraints. The problem can be modeled as a variant of the Team Orienteering Problem with Time Windows (TOPTW). The key differences with the regular TOPTW are twofold: first, a time-dependent transition time is required for each pair of consecutive observations to adjust the camera's look angles. Second, the time windows of each target vary during different observation cycles, called "orbits". Some targets are invisible during certain orbits. We call this variant the Time-dependent Team Orienteering Problem with Variable Time Windows. In this paper, we present an efficient branch-and-cut-and-price (BCP) algorithm that exploits the problem's characteristics to solve it to optimality. Some algorithmic enhancements have been implemented, such as a Lagrangian bound, an ng-path relaxation, a primal heuristic, and subset-row inequalities. Extensive experiments on different configurations of benchmark instances demonstrate the superior performance of the proposed BCP algorithm and its algorithmic enhancements. Moreover, the primal heuristic yields a high-quality lower bound and outperforms state-of-the-art heuristics. Finally, we adopt our framework to solve the well-known TOPTW, and our algorithm is much faster than state-of-the-art exact algorithms. © 2025 Elsevier B.V.

关键词： Branch and bound method

来源：评论

学校读者我要写书评

暂无评论

Smart Ports Solutions for Cargo Container Tracking and Vessel Traffic Counting Systems using IoT and Cloud computing

Smart Ports Solutions for Cargo Container Tracking and Vesse...

引用

International Conference on Communications and Signal Processing

作者： S. Priya A. Sairam H. Azath S. K. Manivannan N. Mohankumar P Vedasundara Vinayagam Department of Electrical and Electronics Engineering Academy of Maritime Education and Training (AMET) Deemed to be University Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India School of Computing Science and Engineering VIT Bhopal University Bhopal India Faculty of Management SRM Institute of Science and Technology Kattankulathur Chennai Tamil Nadu India Symbiosis Institute of Technology Symbiosis International (Deemed University) Nagpur Maharashtra India Department of Electronics and Communication Engineering Adhiparasakthi Engineering College Melmaruvathur Tamil Nadu India

ISBN: (数字)9798350353068

ISBN: (纸本)9798350353075

This research examines current port operations that use Internet of Things (IoT) technologies for cargo container monitoring and vessel traffic counts. Effective port management is crucial for smooth commodities movement and congestion reduction as global commerce grows. Addressing these issues with IoT solutions is promising. It analyzes cargo container IoT sensors and devices for real-time location, condition, and security monitoring. These IoT-enabled containers provide port status data for better logistical planning and security. IoT devices are used to count and control vessel traffic in the research. Sensors and data analytics at important port locations provide real-time vessel tracking and traffic monitoring. This data improves safety and optimizes vessel traffic flow, lowering congestion and wait times. The pros and downsides of using IoT in port operations include data privacy, security, and infrastructure needs. Smart port technologies may enhance marine efficiency, cost savings, and sustainability. The IoT can revolutionize port operations, notably cargo container monitoring and vessel traffic counts. Port capacity, security, and the environmental and economic viability of worldwide trade may all be improved with the help of the IoT.

关键词： Costs Seaports Containers Real-time systems Safety Planning Internet of Things

来源：评论

学校读者我要写书评

暂无评论

IoT based Weather, Soil, Earthquake, Air pollution Monitoring System

IoT based Weather, Soil, Earthquake, Air pollution Monitorin...

引用

Innovative Practices in technology and Management (ICIPTM), International Conference on

作者： Kondireddy Muni Sankar B. Booba C Rangaswamy P. V. Pramila Sangita Rani Kar Ashok Kumar M. Sudhakar Department of Information Technology Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai India Department of Electronics and Communication SJC Institute of Technology Chickballapur India Department of Computer Science Saveetha School of Engineering Chennai India Department of Electrical and Electronics ITER Siksha ‘O’ Anusandhan University Khordha India Department of Computer Science Banasthali Vidyapith Rajasthan India Department of Mechanical Engineering Sri Sai Ram Engineering College Chennai India

This article provides IoT information on a great option for tracking local temperature variables and enabling the information accessible from any part of the planet. The dynamic changes in the weather are to blame for the severe flooding. Using the NODEMCU ESP8266, it accomplishes the creation of a flood observing arrangement for loading and recovering data from the arrangement. Ultrasonic sensors and LEDs are used to warn the authorities to the presence of heavy water. A crucial component of plant life, soil moisture will directly impact crop growth and output. A key component of the vegetation that directly affects the development and production of the harvest is soil moisture. It uses a microcontroller and sensor to carry out the advancement of soil dampness checking. The initial tremor of a large earthquake is picked up by an earthquake warning system employing a sensor. Because there are more businesses and vehicles on the road today, the air quality is poor, which has an impact on people. The importance of using IOT to evaluate the value of the air and the amount of pollutants in the environment cannot be overstated because the field has experienced a major development. It creates a system that uses the MQ135 sensor, which will be visible on the Cayenne platform, to measure the amount of harmful airborne pollutants such methane, alcohol, benzene, and CO2. Data is automatically stored in private channels by thing talk. The data obtained from the embedded scheme could be reachable over an internet from wherever in the sphere.

关键词： Earthquakes Soil moisture Vegetation mapping Sensor systems Sensors Internet of Things Floods

来源：评论

学校读者我要写书评

暂无评论

HAMMF: Hierarchical attention-based multi-task and multi-modal fusion model for computer-aided diagnosis of Alzheimer's disease

引用

computers in Biology and Medicine 2024年 176卷 108564-108564页

作者： Liu, Xiao Li, Weimin Miao, Shang Liu, Fangyu Han, Ke Bezabih, Tsigabu T. School of Computer Engineering and Science Shanghai University Shanghai China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Chinese Academy of Sciences Beijing China BGI-Shenzhen Shenzhen China Medical and Health Center Liaocheng People's Hospital LiaoCheng China

Alzheimer's disease (AD) is a progressive neurodegenerative condition, and early intervention can help slow its progression. However, integrating multi-dimensional information and deep convolutional networks increases the model parameters, affecting diagnosis accuracy and efficiency and hindering clinical diagnostic model deployment. Multi-modal neuroimaging can offer more precise diagnostic results, while multi-task modeling of classification and regression tasks can enhance the performance and stability of AD diagnosis. This study proposes a Hierarchical Attention-based Multi-task Multi-modal Fusion model (HAMMF) that leverages multi-modal neuroimaging data to concurrently learn AD classification tasks, cognitive score regression, and age regression tasks using attention-based techniques. Firstly, we preprocess MRI and PET image data to obtain two modal data, each containing distinct information. Next, we incorporate a novel Contextual Hierarchical Attention Module (CHAM) to aggregate multi-modal features. This module employs channel and spatial attention to extract fine-grained pathological features from unimodal image data across various dimensions. Using these attention mechanisms, the Transformer can effectively capture correlated features of multi-modal inputs. Lastly, we adopt multi-task learning in our model to investigate the influence of different variables on diagnosis, with a primary classification task and a secondary regression task for optimal multi-task prediction performance. Our experiments utilized MRI and PET images from 720 subjects in the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. The results show that our proposed model achieves an overall accuracy of 93.15% for AD/NC recognition, and the visualization results demonstrate its strong pathological feature recognition performance. © 2024 Elsevier Ltd

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

CL-MIL: Multi-Instance Learning on Whole-Slide Images with Self-Supervised Contrastive Learning

CL-MIL: Multi-Instance Learning on Whole-Slide Images with S...

引用

International Conference on computer and Communications (ICCC)

作者： Pengfei Xiu Dongying Liu Sheng Wang Hongliang Wang Wei Wang Shun Li Shenyang Institute of Computing Technology Chinese Academy of Science Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Department of Gastroenterology Shengjing Hospital of China Medical University Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Histopathological examination of tissue slides is considered the gold standard for clinical cancer diagnosis. However, it heavily relies on pathologists' subjective judgment and involves substantial workload. Existing convolutional neural network (CNN)-based whole slide image (WSI) diagnostic methods suffer from high annotation costs and complex data acquisition processes. Therefore, this study proposes a weakly supervised multiple instance learning method based on self-supervised contrastive learning (CL-MIL) for WSI classification. By integrating self-supervised contrastive learning strategies, leveraging data augmentation through H&E stain separation, and introducing causal intervention via backdoor adjustment to mitigate dataset bias, our approach significantly enhances feature representation and classification performance in pathological images. Experimental results on the Camelyon16 and TCGA lung cancer datasets demonstrate that our method outperforms other comparable WSI classification models across various evaluation metrics, achieving higher diagnostic efficiency and accuracy. Additionally, our method exhibits good interpretability, enabling precise localization of pathological regions and providing robust technical support for clinical applications.

关键词： Measurement Location awareness Pathology Accuracy Weak supervision Lung cancer Contrastive learning Feature extraction Standards Image classification

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Approach for Detecting and Classifying Loitering Events in Fishing Vessels Using Supervised and Semi-Supervised Learning

A Comprehensive Approach for Detecting and Classifying Loite...

引用

Innovation in technology (ASIANCON), Asian Conference on

作者： Rishi Kumar Sira Irthiqua Moin Tanjavur Guru Prasad. M S Abraham Rajan Laxman Mohan Kumar T G Dept. of Computer Science and Engg. Grapic Era (Deemed to be University) Dehradun India Dept. of Computer Science and Engg. Nagarjuna College of Engineering and Technology Bengaluru India School of Computing and Information Technology REVA University Bengaluru India Dept. of Information Science and Engg. Nitte Meenakshi Institute of Technology Bengaluru India

Illegal, unreported, and unregulated (IUU) fishing practices pose significant threats to marine ecosystems and global fisheries sustainability. The detection and classification of loitering events, where fishing vessels spend an extended period in a specific area, are critical for identifying potential IUU activities. This research proposes a comprehensive approach that combines supervised and semi-supervised learning techniques to effectively detect and classify loitering events. By leveraging various machine learning algorithms, including logistic regression, Gaussian mixture models, support vector machines, and random forests, accurate predictions can be made to enhance surveillance and combat IUU fishing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pre-Equalization Aided Grant-Free Massive Access in Massive MIMO System

arXiv

引用

arXiv 2025年

作者： Wang, Yueqing Mei, Yikun Gao, Zhen Wan, Ziwei Ning, Boyu Mi, De Muhaidat, Sami School of Information and Electronics Beijing Institute of Technology Beijing100081 China MIIT Key Laboratory of Complex-Field Intelligent Sensing Beijing Institute of Technology Beijing100081 China Jiaxing314019 China Advanced Technology Research Institute Beijing Institute of Technology Jinan250307 China National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China Chengdu611731 China School of Computing and Digital Technology Birmingham City University BirminghamB55JU United Kingdom KU 6G Research Center Department of Computer and Information Engineering Khalifa University Abu Dhabi United Arab Emirates

The spatial diversity and multiplexing advantages of massive multi-input-multi-output (mMIMO) can significantly improve the capacity of massive non-orthogonal multiple access (NOMA) in machine type communications. However, state-of-the-art grant-free massive NOMA schemes for mMIMO systems require accurate estimation of random access channels to perform activity detection and the following coherent data demodulation, which suffers from excessive pilot overhead and access latency. To address this, we propose a pre-equalization aided grant-free massive access scheme for mMIMO systems, where an iterative detection scheme is conceived. Specifically, the base station (BS) firstly activates one of its antennas (i.e., beacon antenna) to broadcast a beacon signal, which facilitates the user equipment (UEs) to perform downlink channel estimation and pre-equalize the uplink random access signal with respect to the channels associated with the beacon antenna. During the uplink transmission stage, the BS detects UEs’ activity and data by using the proposed iterative detection algorithm, which consists of three modules: coarse data detection (DD), data-aided channel estimation (CE), and fine DD. In the proposed algorithm, the joint activity and DD is firstly performed based on the signals received by the beacon antenna. Subsequently, the DD is further refined by iteratively performing data-aided CE module and fine DD module using signals received by all BS antennas. Our simulation results demonstrate that the proposed scheme outperforms state-of-the-art mMIMO-based grant-free massive NOMA schemes with the same access latency. Simulation codes are provided to reproduce the results in this article: https://***/owenwang517/tvt-2025. Copyright © 2025, The Authors. All rights reserved.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

An Automation Innovation of Gearbox Vehicle Control by Using Machine Learning Based Robotic Operation

An Automation Innovation of Gearbox Vehicle Control by Using...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Ramakrishna M M Nageswara Rao Atyam Nikhil Chaurasia L Sahaya Senthamil Mohd Asif Shah V. L. Raja Dept of ECE/ICE Dr. M.G.R Educational and Research Institute Chennai Tamil Nadu India Electrical and Electronics Department CMR Institute of Technology Bengaluru Karnataka India Department of Computer Science & Engineering Sage University Bhopal Madhya Pradesh India Electrical and Electronics Engineering PSNA College of Engineering and Technology Dindigul Tamil Nadu India University School of Business Chandigarh University Mohali Punjab India School of Computing Science Vels Institute of Science Technology and Advanced Studies (VISTAS) Pallavaram Chennai Tamil Nadu India

There are many vehicle exchanges around the world are using the manual transmission and automatic transmission are the most popular. At this time, many popular manufacturers have started using the robot version in their new products. The gearbox of the robot is, in fact, mechanical; it has an additional automatic clutch and gear shift. Accordingly, the operation of the transmission is not completely dependent on the driver, as in other options, but on the electronic control unit. For the proper functioning of the transmission the driver needs to correctly transmit only the incoming information. In this paper an automation innovation was proposed to control the vehicle gear shifting functions by using the machine learning based on the robotic operation model. An automaton or robot, after some time, must first learn the device of a new invention. The automatic gearbox received a friction type clutch. It is a disk set or a built-in separate mechanism. The most reliable and durable design can be called the double clutch design.

关键词：

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：