检索结果-内蒙古大学图书馆

6th International Conference on Recent Innovations in computing, ICRIC 2023

作者： Veer, V. Druva Priya, S. Baghavathi Tamilselvi, M. Department of Computer Science and Engineering Amrita School of Computing AmritaVishwaVidyapeetham Chennai India Information Technology Department University of Technology and Applied Sciences Nizwa Oman

ISBN: (纸本)9789819778614

A chest X-ray is a common diagnostic tool for many thoracic illnesses. Interpreting these images and coming up with accurate diagnostic results is a difficult and time-consuming task for radiologists. Recent results using deep learning approaches to automate the analysis of chest X-rays are promising. This paper provides a comprehensive description of deep learning techniques used to chest X-ray processing for the diagnosis of several diseases, including TB, pneumonia, and COVID-19. This paper provide a summary of the primary deep learning architectures, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and attention models, that are used for disease classification, localization, segmentation, and report generation from chest X-rays. This paper also discuss explainability techniques that are used to offer transparency and increase trust in model predictions. Along with existing issues, future directions are taken into consideration, such as multimodal learning, few-shot learning, and model evaluation. This paper explains the model which takes less time and give the optimal results. In order to facilitate future research into developing AI systems that are more accurate, understandable, and advantageous from a medical standpoint, this article provides an overview of the most current developments in deep learning techniques for automated chest X-ray diagnosis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Integrated Simulation Research of Multi-natural Energy-driven Unmanned Surface Vehicle

Integrated Simulation Research of Multi-natural Energy-drive...

引用

2023 International Conference on Applied Mathematics and Digital Simulation, AMDS 2023

作者： Chen, Ao Chen, Tianding He, Hong Wang, Hui Fan, Yimei Yu, Xin School of Physics and Information Engineering Minnan Normal University Fujian Province China School of Computing and Information Science Fuzhou Institute of Technology Fujian Province China School of Data and Computer Science Xiamen Institute of Technology Fujian Province China

In response to the limitations of existing unmanned surface vehicles in complex marine environments, where they often fail to meet the requirements for extended endurance, broad operational range, offshore missions, and prolonged operational durations, an autonomous Unmanned Surface Vehicle (NUSV) has been designed and developed. The NUSV is propelled by wind, solar, and wave energy sources. Concerning wind energy, a micro wind energy storage mechanism based on a spiral spring has been designed to enable power generation in low-wind conditions. A wave energy transmission device, complete with a dynamic model, has been devised for wave energy. This device converts torque generated from wave action in different directions into a unified torque, providing continuous power to drive the generator. Solar energy is harnessed using Maximum Power Point Tracking (MPPT) algorithms to ensure optimal operation of the solar panels. The electrical energy generated from these three natural sources is stored using Pulse Width Modulation (PWM) and DC-DC Boost converters. A programmable logic controller manages and allocates this stored electrical energy for the NUSV's equipment, including underwater propulsion systems, surface cameras, laser radar, GPS, and other electronic devices. This integration of wind, solar, and wave energy sources enables the NUSV to meet power demands, allowing for long-duration operations at sea, extended offshore missions, wide operational ranges, and prolonged mission durations. © Published under licence by IOP Publishing Ltd.

关键词： DC-DC converters

来源：评论

学校读者我要写书评

暂无评论

StarMFND: Star Topology Multi-Domain Fake News Detection 7

StarMFND: Star Topology Multi-Domain Fake News Detection

引用

7th International Conference on Data science and information technology, DSIT 2024

作者： Gu, Pengfei Chen, Yibing Bing, Wanlong Liu, Yahui Ma, Hongliang Wang, Wei Shihezi University School of Information Science and Technology Shihezi China Xinjiang Production and Construction Corps Key Laboratory of Computing Intelligence and Network Information Security Shihezi China Beijing Jiaotong University School of Computer Science and Information Technology Beijing China

ISBN: (纸本)9798350384093

The proliferation of the Internet and the emergence of social media platforms have greatly accelerated the speed and scope of information dissemination, while also introducing the peril of fake news propagation, particularly in political, economic, health, and other domains. Many scholars have conducted research on fake news detection, and most of this research focuses on domain-specific single-domain fake news detection or mixed-domain detection without considering domain information. Most existing multi-domain fake news detection approaches model the domains of fake news implicitly and do not pay attention to the domain seesaw phenomenon. To solve the above problems, this paper proposes a Star Topology Multi-Domain Fake News Detection Model (StarMFND), which explicitly models the domains of fake news using a star topology, and simultaneously leverages the data from all the domains to obtain the common and specific features associated with fake news across different domains. Experiments on Chinese and English datasets demonstrated the good performance of StarMFND for multi-domain fake news detection. © 2024 IEEE.

关键词： Fake News Detection Multi-Domain Learning Multi-Task Learning Social Media

来源：评论

学校读者我要写书评

暂无评论

Trust Assessment Under the Integrated Air-Space-Ground Network Environment

引用

Tsinghua science and technology 2023年第2期28卷 405-420页

作者： Zhe Liu Yinghao Yuan Bo Zhao Xiaoyan Peng Key Laboratory of Aerospace Information Security and Trust Computing Ministry of EducationSchool of Cyber Science and EngineeringWuhan UniversityWuhan 430072China Shanghai Academy of Spaceflight Technology Shanghai 210000China

While playing an increasing role in the field of air-space integrated networks,terminal entities are exposed to more serious security risks than ordinary terminal entities on the ground,including but not limited to astronomical risks(e.g.,solar activity),link disruptions,and malicious *** the integrated air-space-space network,after the terminal entity is loaded into the rocket for launch,real-time monitoring measures are implemented on the ground site for all links to the intended *** top of the real-time monitoring measures,the need for a comprehensive evaluation of the air-space integration network is *** this paper,we further classify the security requirements and evaluation benchmarks of the terminal entities of the air-space integration network around the security evaluation requirements of the air-space integration *** this basis,the relevant concept of trust value is introduced to assess the security status of terminal entities of air-space-sky integrated networks,and on this basis,a security assessment system of air-space-sky integrated network terminals is *** exploration and development of field applications are initially realized.

关键词： air-space-ground integrated network terminal security trust elements sensitivity real-time judgment

来源：评论

学校读者我要写书评

暂无评论

Breaking the Edge: Enabling Efficient Neural Network Inference on Integrated Edge Devices

引用

IEEE Transactions on Cloud computing 2025年第2期13卷 694-710页

作者： Zhang, Feng Zhang, Chenyang Guan, Jiawei Zhou, Qiangjun Chen, Kuangyu Zhang, Xiao He, Bingsheng Zhai, Jidong Du, Xiaoyong School of Information Beijing100872 China Tsinghua University Department of Computer Science and Technology Beijing100084 China University of California Department of Computer Science and Engineering RiversideCA92507 United States National University of Singapore School of Computing 119077 Singapore

Edge computing has gained widespread attention in cloud computing due to the increasing demands of AIoT applications and the evolution of edge architectures. One prevalent application in this domain is neural network inference on edge for computing and processing. This paper presents an in-depth exploration of inference on integrated edge devices and introduces EdgeNN, a groundbreaking solution for inference specifically designed for CPU-GPU integrated edge devices. EdgeNN offers three key innovations. First, EdgeNN adaptively employs zero-copy optimization by harnessing unified physical memory. Second, EdgeNN introduces an innovative approach to CPU-GPU hybrid execution tailored for inference tasks. This technique enables concurrent CPU and GPU operation, effectively leveraging edge platforms’ computational capabilities. Third, EdgeNN adopts a finely tuned adaptive inference tuning technique that analyzes complex inference structures. It divides computations into sub-tasks, intelligently assigning them to the two processors for better performance. Experimental results demonstrate EdgeNN’s superiority across six popular neural network inference processing. EdgeNN delivers average speed improvements of 3.97×, 4.10×, 3.12×, and 8.80× when compared to inference on four distinct edge CPUs. Furthermore, EdgeNN achieves significant time advantages compared to the direct execution of original programs. This improvement is attributed to better unified memory utilization (44.37%) and the innovative CPU-GPU hybrid execution approach (17.91%). Additionally, EdgeNN exhibits superior energy efficiency, providing 29.14× higher energy efficiency than edge CPUs and 5.70× higher energy efficiency than discrete GPUs. © 2013 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts 41

MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Exp...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhou, Jianan Cao, Zhiguang Wu, Yaoxin Song, Wen Ma, Yining Zhang, Jie Xu, Chi College of Computing and Data Science Nanyang Technological University Singapore School of Computing and Information Systems Singapore Management University Singapore Department of Information Systems Eindhoven University of Technology Netherlands Institute of Marine Science and Technology Shandong University China Singapore

Learning to solve vehicle routing problems (VRPs) has garnered much ***, most neural solvers are only structured and trained independently on a specific problem, making them less generic and *** this paper, we aim to develop a unified neural solver that can cope with a range of VRP variants ***, we propose a multi-task vehicle routing solver with mixture-of-experts (MVMoE), which greatly enhances the model capacity without a proportional increase in *** further develop a hierarchical gating mechanism for the MVMoE, delivering a good trade-off between empirical performance and computational ***, our method significantly promotes zero-shot generalization performance on 10 unseen VRP variants, and showcases decent results on the few-shot setting and real-world benchmark *** further conduct extensive studies on the effect of MoE configurations in solving VRPs, and observe the superiority of hierarchical gating when facing out-of-distribution *** source code is available at: https://***/RoyalSkye/Routing-MVMoE. Copyright 2024 by the author(s)

关键词： Vehicle routing

来源：评论

学校读者我要写书评

暂无评论

Nocturne - A Real-Time Driving Assistant at Night for Sri Lanka 50

Nocturne - A Real-Time Driving Assistant at Night for Sri La...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Mohomed, Mohamed Safrullah Ashar, Mohammed Ashfaq Vilcassim, Abdul Qadir Kavishan, Sukumar Karunanayaka, Kasun Wickramasinghe, Manjusri Cheok, Adrian David University of Colombo School of Computing Sri Lanka Nanjing University of Information Science and Technology China Imagineering Institute Malaysia

ISBN: (纸本)9781665464543

Nighttime driving presents significant challenges, including detecting pedestrians, cyclists, and potholes in low-visibility conditions, leading to frequent road accidents. In Sri Lanka, there is a lack of automated systems capable of addressing these challenges. This research proposes a system leveraging AI and real-time video processing to enhance driver safety by improving pedestrian and cyclist visibility and developing a reliable pothole detection system for night time. These enhancements rely on extensive data collection and preprocessing for training specialized computer vision and machine learning models tailored for real-time, low-light scenarios. The application provides realtime alerts and visual cues to reduce nighttime driving accidents. Additionally, a software framework is proposed to offer real-time feedback for drivers leveraging available hardware capabilities, enhancing awareness of vulnerable road users. Through rigorous data collection, testing, and development, this approach significantly helps to enhance nighttime driving safety in Sri Lanka. © 2024 IEEE.

关键词： Bicycles

来源：评论

学校读者我要写书评

暂无评论

SoyNet: Deep Learning Approaches for Automated Soybean Seed Quality Assessment 2

SoyNet: Deep Learning Approaches for Automated Soybean Seed ...

引用

2nd International Conference on Advancement in Computation and Computer Technologies, InCACCT 2024

作者： Pratap, Harshita Guru Prasad, M.S. Agarwal, Poorvi Bhardwaj, Ayushi Mehra, Ayushi Mathpati, Shilpa Dept. of Computer Science and Engg Dehradun India Reva University School of computing & Information Technology Bengaluru India

ISBN: (纸本)9798350371314

In the realm of agriculture, soybeans have played a vital role in diets for centuries, providing a consistent source of plant protein. Beyond protein, soybeans offer essential components like fibres, vitamins (including B vitamins), minerals (such as iron, calcium, and magnesium), and antioxidants. This necessitates precise quality assessment for factors like size, shape, colour, and damage. Leveraging advanced machine learning techniques such as VGG16, AlexNet and CNN, the model aims to automate the identification and categorization of soybean quality. To implement the proposed work the standard soybean dataset is considered. It consists of five soybean seed types complete, spotted, immature, broken, and skin-damaged. The proposed work effectively categories the quality of soybean seeds and it has the potential to improve the agricultural process as compared to traditional work. In this work different pretrained models are experimented in that VGG16 provides the highest of all showing accuracy 90%, AlexNet accuracy 78.49% and CNN accuracy 74.55%. © 2024 IEEE.

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

Real-Time Helmet Detection System with Vehicle Number Extraction for Two-Wheeler Vehicles using YOLOv8 2

Real-Time Helmet Detection System with Vehicle Number Extrac...

引用

2nd International Conference on Advancement in Computation and Computer Technologies, InCACCT 2024

作者： Kumar, Abhash Guru Prasad, M.S. Soni, Dheeraj Rani, Vibha Arora, Kanika Ganesh, D.R. Dept. of Computer Science & Engineering Dehradun India REVA University School of Computing and Information Technology Bengaluru India

ISBN: (纸本)9798350371314

In the face of increasing two-wheeler usage and the persistent issue of riders neglecting helmet compliance, this paper proposes a groundbreaking Real-Time Helmet Detection System with Vehicle Number Extraction. The existing literature on helmet detection systems is reviewed, revealing a range of methodologies, accuracies, and limitations in current approaches. Building upon this foundation, the three-stage detector combines the efficiency of YOLO (You Only Look Once) for object detection with a specialized number plate extraction system. The system aims to provide real-time detection of two-wheeler riders, classification of helmet usage, and extraction of vehicle numbers. The proposed methodology, utilizing a pre-trained YOLO model for object detection and EasyOCR library, demonstrates an accuracy rate of 64% for vehicle detection, 78% for helmet detection, and 92% for number plate extraction. The practical implementation of this system showcases its potential for enhancing road safety, automating traffic management, and promoting regulatory enforcement. While showing potential, the ongoing research and development face challenges such as limitation of computational resources and privacy considerations. The Real-Time Helmet Detection System stands as a promising solution for improving road safety, with the potential for broader use in traffic management and safety enforcement. Continuous improvement and adaptation will guarantee its effectiveness in contributing to a safer and more controlled traffic environment. © 2024 IEEE.

关键词： Accident prevention

来源：评论

学校读者我要写书评

暂无评论

Boosting the dimensionality of frequency entanglement using a reconfigurable microring resonator

引用

science China(Physics,Mechanics & Astronomy) 2023年第5期66卷 79-88页

作者： Chao Wu Qilin Zheng Yingwen Liu Yang Wang Jiangfang Ding Pingyu Zhu Shichuan Xue Miaomiao Yu Weihong Luo Kaikai Zhang Anqi Huang Mingtang Deng Junjie Wu Ping Xu Institute for Quantum Information State Key Laboratory of High Performance ComputingCollege of Computer Science and TechnologyNational University of Defense TechnologyChangsha 410073China National Laboratory of Solid State Microstructures School of PhysicsNanjing UniversityNanjing 210093China

Integrated quantum frequency combs(QFCs)based on microring resonators supplies as an essential resource for expanding the Hilbert-space dimensionality for high-dimensional quantum computing and information *** this work,we propose and demonstrate a reconfigurable ring resonator with tunable quality factors to efficiently increase the dimensionality of frequency entanglement,simultaneously,ensuring a high on-chip pair generation rate(PGR)and coincidence-to-accidental ratio(CAR).Our method exploits the asymmetric Mach-Zehnder interferometer instead of the traditional straight waveguide as the coupler of resonators which offer a tunable external coupling coefficient to modulate the quality factor to enlarge the QFCs’bandwidth and thus increase the dimensionality of frequency *** measured the QFCs’joint spectral intensity of 28 frequency pairs under various quality factors ranging from 16.6×10^(4) to 3.4×10^(4).Meanwhile,the measured Schmidt number increased from 11.01 to 24.77,denoting a huge expansion of the Hilbert-space dimensionality from 121 to a record number of 613 dimensions,which agrees well with our theoretical *** addition,the PGR and CAR-another two key parameters for high-quality QFCs-were all measured under different quality factors to verify that our method can significantly increase the Schmidt number and CAR while maintaining a high *** fact,bright QFCs with a total PGR of 4.3 MHz under a 0.48 mW pump power and a mean CAR of 1578 were simultaneously obtained at the highest Schmidt *** method is widely applicable to other material-based ring resonators and can act as a general solution for high-dimensional QFCs.

关键词： reconfigurable resonator quantum frequency comb Hilbert-space dimensionality

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：