检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

2,978 篇 会议
164 篇 期刊文献
64 册 图书
6 篇 学位论文

馆藏范围

3,212 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,859 篇 工学
- 1,008 篇 计算机科学与技术...
- 548 篇 电气工程
- 546 篇 软件工程
- 457 篇 信息与通信工程
- 264 篇 光学工程
- 237 篇 电子科学与技术（可...
- 196 篇 仪器科学与技术
- 157 篇 生物医学工程（可授...
- 156 篇 控制科学与工程
- 150 篇 材料科学与工程（可...
- 109 篇 机械工程
- 92 篇 生物工程
- 49 篇 化学工程与技术
- 40 篇 测绘科学与技术
- 38 篇 动力工程及工程热...
- 38 篇 航空宇航科学与技...
- 33 篇 交通运输工程
- 32 篇 安全科学与工程
1,314 篇 理学
- 1,077 篇 物理学
- 247 篇 数学
- 107 篇 生物学
- 61 篇 化学
- 48 篇 系统科学
- 48 篇 统计学（可授理学、...
311 篇 医学
- 237 篇 临床医学
- 78 篇 特种医学
- 50 篇 基础医学(可授医学...
228 篇 管理学
- 152 篇 管理科学与工程(可...
- 88 篇 图书情报与档案管...
- 55 篇 工商管理
21 篇 法学
19 篇 经济学
16 篇 农学
11 篇 教育学
10 篇 军事学
3 篇 文学

主题

263 篇 image processing
257 篇 signal processin...
131 篇 signal processin...
108 篇 real-time system...
107 篇 image segmentati...
106 篇 optical sensors
94 篇 optical devices
94 篇 cameras
86 篇 sensors
76 篇 optical imaging
72 篇 data processing
71 篇 feature extracti...
71 篇 accuracy
70 篇 field programmab...
67 篇 internet of thin...
67 篇 detection and tr...
65 篇 optical signal p...
64 篇 digital signal p...
62 篇 neural networks
60 篇 optical filters

机构

11 篇 yonsei univ ctr ...
10 篇 yonsei univ dept...
7 篇 school of electr...
5 篇 yonsei univ cisd
5 篇 school of electr...
5 篇 univ calif san d...
5 篇 school of inform...
5 篇 state key labora...
5 篇 college of physi...
4 篇 school of inform...
4 篇 department of in...
4 篇 school of optica...
4 篇 state key labora...
4 篇 maharishi school...
4 篇 key laboratory o...
4 篇 stanford univ gi...
4 篇 samara national ...
4 篇 canadian space a...
4 篇 school of inform...
4 篇 mpb communicatio...

作者

16 篇 park no-cheol
14 篇 park young-pil
12 篇 park kyoung-su
11 篇 javidi b
8 篇 n.a. riza
7 篇 beyette fr
7 篇 song myeong-gyu
6 篇 kim choong
6 篇 zhaohui li
6 篇 fainman y.
5 篇 li peng
5 篇 nelson bn
5 篇 shastri bhavin j...
5 篇 li zheng yuan
5 篇 koo ja choon
5 篇 prucnal paul r.
5 篇 yang hyunseok
5 篇 nomura t
5 篇 huang hk
4 篇 minho lee

语言

3,106 篇 英文
67 篇 其他
38 篇 中文
2 篇 俄文
2 篇 土耳其文

检索条件"任意字段=Conference on Algorithms, Devices, and Systems for Optical Information Processing"

共 3212 条记录，以下是621-630 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Adapting Open-source Multimodal Large Language Models for Enhanced Vision Assistants

Adapting Open-source Multimodal Large Language Models for En...

引用

International conference on Computer and information Technology (ICCIT)

作者： Md. Repon Islam Muhammad Sheikh Sadi Department of Computer Science and Engineering Khulna University of Engineering & Technology Khulna Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

This paper presents a novel wearable system designed to enhance the lives of visually impaired individuals by integrating advanced vision understanding through Multimodal Large Language Models (MLLMs) and optical Character Recognition (OCR). An open-source 8 billion parameters MLLM has been deployed on a consumer-grade GPU-enabled server which excels in interpreting visual data and delivering intelligent responses. The wearable device, powered by an Orange Pi 5B single-board computer (SBC), incorporates advanced OCR, Automatic Speech Recognition (ASR), Text-to-Speech (TTS), and an on-device 0.5B Large Language Model (LLM) for real-time interaction. Text recognition is achieved using PaddleOCR lite, optimized through a series of algorithms for edge performance. The on-device LLM handles offline question-answer or summarization tasks, while server integration provides a more powerful, multimodal understanding of the environment, based on user queries. This hybrid approach balances low-latency, real-time processing with the computational demands of advanced multimodal models, offering a scalable, cost-effective solution. Experimental evaluations demonstrate character recognition accuracy of 95.55% for OCR and efficient response generation at 18 tokens per second for LLM on the edge. The deployed MLLM scores 9.1 out of 10 on a carefully curated subset of the VizWiz VQA dataset, which consists of real-world image-question pairs captured by blind individuals across the globe based on their actual needs. The system represents a significant advancement in assistive technologies for the visually impaired community, leveraging a hybrid computing framework and state-of-the-art LMMs for robust, real-time support.

关键词： Visualization Accuracy Large language models optical character recognition Assistive technologies Real-time systems Servers Character recognition Wearable devices Thermal stability

来源：评论

学校读者我要写书评

暂无评论

Exploiting Functional Approximation on Decision-Tree Based Multiple Classifier systems

Exploiting Functional Approximation on Decision-Tree Based M...

引用

IFIP International conference on Very Large Scale Integration (VLSI-SoC)

作者： Mario Barbareschi Salvatore Barone Antonio Emmanuele Nicola Mazzocca Department of Electrical Engineering and Information Technologies University of Naples Federico II Naples Italy

ISBN: (数字)9798331539672

ISBN: (纸本)9798331539689

Multiple Classifier systems (MCSs) have been in-creasingly designed to take advantage of hardware features, such as high parallelism and computational power, to guarantee higher throughput and lower latency. Although the combination of multiple classifiers leads to high classification accuracy, the required area overhead makes the design of a hardware accelerator unfeasible, hindering the adoption of commercial configurable devices. For this reason, in this paper, we exploit the Approximate Computing (AxC) design paradigm to automatically generate approximated hardware implementations of MCSs by trading hardware area overhead off for classification accuracy. In particular, we propose an algorithm that identifies the resiliency source of the model and uses it to introduce approximation with minimum accuracy loss.

关键词： Accuracy Correlation Computational modeling Very large scale integration Parallel processing Throughput Classification algorithms Proposals Hardware acceleration Resilience

来源：评论

学校读者我要写书评

暂无评论

All-optical Computing for Super-Resolution Direction of Arrival Estimation

All-Optical Computing for Super-Resolution Direction of Arri...

引用

Asia Communications and Photonics conference and Exhibition (ACP)

作者： Sheng Gao Hang Chen Haiou Zhang Zhi Sun Yuan Shen Xing Lin Department of Electronic Engineering Tsinghua University Beijing China

ISBN: (数字)9798350379266

ISBN: (纸本)9798350379273

Direction of arrival estimation technology is the foundation for communications, radar, navigation, etc. However, conventional electronic devices for DOA estimation require expensive RF circuits, high-precision analogue-to-digital converters and complex digital signal processing algorithms. Here, we propose a super-resolution diffractive neural network (S-DNN) to directly process electromagnetic (EM) waves for super-resolution DOA estimation over a broadband frequency range. The multilayer meta-structures of the S-DNN produces super-oscillatory angular responses in local angular range, which can perform all-optical DOA estimation with angular resolution beyond the diffraction limit. Space-time multiplexing of passive and reconfigurable S-DNNs is used to achieve high-resolution DOA estimation over a wide field of view. Experiments show that the angular resolution of the S-DNN is four times higher than the diffraction limited resolution. The fabricated S-DNN can be used for superresolution DOA estimation of multiple coherent sources over a 5 GHz frequency bandwidth, with an estimation delay that is in principle two to four orders of magnitude lower than commercial devices. We also use the all-optical DOA estimation capability of the S-DNN to provide angular direction to reconfigurable intelligent surface, to achieve low-latency and low-power integrated sensing and communication. Our work is an important step towards enabling various wireless sensing and communication tasks using photonic computing processors that outperform electronic computing in both computational paradigm and performance.

关键词： Wireless communication Radio frequency Wireless sensor networks Direction-of-arrival estimation Program processors Diffraction Superresolution Neural networks Estimation Photonics

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework based on a Hybrid Vision Transformer and Deep Neural Network for Deepfake Detection

A Novel Framework based on a Hybrid Vision Transformer and D...

引用

IEEE SSD International Multi-conference on systems, Signals and devices

作者： Mohammed Shahin Mohamed Deriche AIRC College of Engineering and Information Technology Ajman University Ajman UAE

ISBN: (数字)9798350374131

ISBN: (纸本)9798350374148

Generative Adversarial Networks (GANs) have enabled the creation of photo-realistic images from random noise. GAN based technologies however, led to the dissemination of synthetic images, often containing inappropriate and miss leading content, on social media. Detecting such manipulated images is crucial, yet challenging. The issue is compounded by the fact that GAN-generated images can be indistinguishable from authentic ones, rendering traditional forgery detection techniques ineffective. Deepfake images further exacerbate this problem, posing threats to news integrity, legal proceedings, and societal security. To address these challenges, we harness the potential of Vision Transformer (ViT) in conjunction with Convolutional Autoencoders (CAE) to craft innovative Framework for image analysis and deepfake detection. We introduce two distinct models, each offering unique insights into image processing. The proposed models yield excellent accuracy rate of approximately 87%, reaffirming the robustness and consistency of the proposed approach and enhanced performance compared to state of the art.

关键词： Performance evaluation Deepfakes Machine learning algorithms Social networking (online) Transformers Generative adversarial networks Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

WildPose: HRNet-based Lightweight and Efficient Wildlife Pose Estimation

WildPose: HRNet-based Lightweight and Efficient Wildlife Pos...

引用

Asia-Pacific Signal and information processing Association Annual Summit and conference (APSIPA)

作者： Sibusiso Reuben Bakana Yongfei Zhang Bhekisipho Twala School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Faculty of Information and Communication Technology Tshwane University of Technology Tshwane South Africa

ISBN: (数字)9798350367331

ISBN: (纸本)9798350367348

Lightweight and efficient wildlife monitoring algorithms, including pose estimation, that can operate on edge devices with limited computational resources are urgently needed for wildlife studies and protections. To reduce computational costs while maintaining accuracy in animal pose estimation, this paper introduces WildPose, an HRNet-w32 based model, designed, which integrates Efficient Channel Attention (ECA) to enhance important feature representations without complex operations, Non-Local Blocks (NLB) to capture long-range contextual information and handle occlusions, and Depthwise Convolutions (DWConv) to reduce computational complexity and parameters. Additionally, the Online Hard Keypoint Mining with Mean Squared Error (OHKMSE) loss function is employed to improve accuracy for occluded keypoints detection by focusing on harder keypoints. When evaluated on the largest wildlife dataset of Animal Kingdom, WildPose demonstrated a nice trade-off between accuracy and efficiency, 75% reduction in parameters and 65% reduction in GFLOPs, while achieving an increased Percentage of Correct Keypoints (PCK) for occluded keypoints such as the hip, ankle, and tail. Therefore, WildPose can serve as a practical solution for real-time wildlife monitoring and artificial intelligence-based ecological studies, especially in resource-constrained environments.

关键词： Accuracy Biological system modeling Computational modeling Wildlife Pose estimation Tail Real-time systems Computational efficiency Monitoring Hip

来源：评论

学校读者我要写书评

暂无评论

Edge-Mapping of Service Function Trees for Sensor Event processing

Edge-Mapping of Service Function Trees for Sensor Event Proc...

引用

IEEE International conference on Web Services (ICWS)

作者： Babar Shahzaad Alistair Barros Colin Fidge School of Information Systems Queensland University of Technology Australia

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

Fog computing offers increased performance and efficiency for Industrial Internet of Things (IIoT) applications through distributed data processing in nearby proximity to sensors. Given resource constraints and their contentious use in IoT networks, current strategies strive to optimise which data processing tasks should be selected to run on fog devices. In this paper, we advance a more effective data processing architecture for optimisation purposes. Specifically, we consider the distinct functions of sensor data streaming, multi-stream data aggregation and event handling, required by IoT applications for identifying actionable events. We retrofit this event processing pipeline into a logical architecture, structured as a service function tree (SFT), comprising service function chains. We present a novel algorithm for mapping the SFT into a fog network topology in which nodes selected to process SFT functions (microservices) have the requisite resource capacity and network speed to meet their event processing deadlines. We used simulations to validate the algorithm’s effectiveness in finding a successful SFT mapping to a physical network. Overall, our approach overcomes the bottlenecks of single service placement strategies for fog computing through composite service placements of SFTs.

关键词： Machine learning algorithms Computational modeling Pipelines Microservice architectures Computer architecture Data processing Sensors Optimization Industrial Internet of Things Edge computing

来源：评论

学校读者我要写书评

暂无评论

Regression-Based Uplink Interference Modeling Using Area-Limited information

Regression-Based Uplink Interference Modeling Using Area-Lim...

引用

IEEE conference on Wireless Communications and Networking

作者： Yijing Niu Tao Peng Yichen Guo Yujie Zhao Wenbo Wang Wireless Signal Processing and Networks Laboratory (WSPN) Key Laboratory of Universal Wireless Communication Ministry of Education Beijing University of Posts and Telecommunications (BUPT) Beijing P.R. China

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

The proliferation of connected devices in wireless systems result in severe intercell interference (ICI). To mitigate ICI, an accurate interference model of link-granularity is highly beneficial. The data generated by wireless devices during networks operation can contribute to mining the interference relationship if properly utilized. Existing frameworks of data-driven interference modeling require data collected from the entire network. Such data are unobtainable in a large network due to the communication constraints of a single network node. This paper proposes an uplink interference modeling algorithm that takes as input area-limited wireless big data instead of global data. With interference modeling formulated as a supervised learning task, the proposed algorithm can precisely model the interference relationship between an interested user equipment (UE) and any of its primary interfering users. Simulation shows that under high interference scenario the proposed algorithm achieves the same signal to interference plus noise ratio (SINR) prediction accuracy with significant reduction in training complexity compared to baseline algorithms.

关键词： Wireless communication Training Accuracy Computational modeling Supervised learning Interference Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Integrated optical Sensing, Communication, and Computation System for Quadruped Robots

Integrated Optical Sensing, Communication, and Computation S...

引用

International conference on Wireless Communications and Signal processing (WCSP)

作者： Chen Zhu Zhouxiang Zhao Jianrong Bao Zhaohui Yang Chongwen Huang Zhaoyang Zhang School of Communication Engineering Hangzhou Dianzi University Hangzhou China Polytechnic Institute Zhejiang University Hangzhou China College of Information Science and Electronic Engineering Zhejiang University Hangzhou China

ISBN: (数字)9798350390643

ISBN: (纸本)9798350390650

This paper develops an integrated optical sensing, communication, and computation system for quadruped robot with virtual-real interaction based on digital twin technology. The system is designed to address key challenges in robotics technology, including real-time performance, low-latency control, high-precision multi-sensor data fusion, stable network transmission, user-friendly interaction interface, system scalability, and maintainability. The system comprises a number of functional modules, including a three-dimensional (3D) modeling module, a positioning perception module, a virtual interaction module, a wise sensing-transmission module, and a cloud server. The 3D modeling module is responsible for constructing the virtual quadruped robot and motion space scenarios. The positioning perception module integrates LiDAR and inertial measurement unit (IMU) data, utilizing Point-light detection and ranging inertial odometry (LIO) and HDL-localization algorithms for high-precision environmental perception and positioning. The virtual interaction module provides a user-friendly control inter-face through computer software and the HoloLens headset. The wise sensing-transmission module employs WiFi and 5G links to ensure low-latency and high-bandwidth data transmission. The optical signal, sensed via camera and LiDAR, is computed at the quadruped robot and subsequently transmitted to the cloud server via the wise sensing-transmission module, which facilitates integrated optical sensing, communication, and computation. The system is designed to run on Ubuntu 20.04 platform, offering excellent scalability and maintainability.

关键词： Cloud computing Three-dimensional displays Robot kinematics Robot sensing systems Real-time systems Digital twins Quadrupedal robots Servers optical sensors Robots

来源：评论

学校读者我要写书评

暂无评论

FPGA accelerated DeepSORT object tracking

FPGA accelerated DeepSORT object tracking

引用

International Carpathian Control conference (ICCC)

作者： Péter Szántó Tamás Kiss Károly János Sipos Department of Measurement and Information Systems Budapest University of Technology and Economics Budapest Hungary

Object detection and tracking is one of the most important vision algorithms in intelligent environments, applications based on it are the driving force behind the growing deployment of edge devices. As FPGAs can implement application specific hardware accelerators, they not only offer outstanding performance but also increased energy efficiency which is a very important factor in edge devices and the most recent FPGA families include processing elements which greatly increase the efficiency and performance of AI inference. In this paper we present a heterogeneous FPGA based implementation of the popular DeepSORT tracking algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enabling Smart Road Safety: Constrained Device Utilization for Accident Prevention in Traffic Congestion

Enabling Smart Road Safety: Constrained Device Utilization f...

引用

Multimedia University Engineering conference (MECON)

作者： Amna Khatoon Asad Ullah Ishfaq Ahmed Ayesha Aslam Mardeni Bin Roslee Shabeer Ahmad School of Information Engineering Chang'an University Xi'an China School of Information Engineering Xi’ an Eurasia University Xi’ an Shaanxi China School of Marine Science Northwestern Polytechnical University Xi’ an China Faculty of Engineering Multimedia Multimedia University University Cyberjaya Malaysia School of Electronic Engineering Beijing University of posts and Telecommunications

ISBN: (数字)9798331530747

ISBN: (纸本)9798331530754

Computer Vision (CV) analysis on constrained devices plays a crucial role in enhancing road safety and mitigating traffic congestion. This study demonstrates the integration of image segmentation and classification techniques into traffic monitoring systems on devices with limited computational power, such as dashboard cameras, smartphones, and IoT sensors. These technologies enable efficient real-time data collection and processing in densely populated urban areas, facilitating the immediate detection of irregular traffic patterns and potential collision points by leveraging edge computing and optimized algorithms. By implementing these analyses directly on constrained devices strategically placed within traffic systems, our approach provides timely responses to dynamic conditions, significantly reducing accident risks through early warnings and adaptive route suggestions. Our research also shows that CV systems can monitor driver behavior, detect attention or weariness, and give timely signals to improve driver response times. The data supports improving traffic signal timings, which might reduce vehicle idle times and improve traffic flow, thus increasing road safety and reducing environmental impact. The study provides a comprehensive methodology for implementing high-quality CV technologies in resource-constrained environments, highlighting advancements in edge computing and energy-efficient hardware. These advances underscore the importance of CV in building sustainable, resilient transport networks and its versatility in municipal and vehicle traffic management, enabling proactive measures to reduce accidents.

关键词： Computer vision Data collection Road safety Real-time systems Vehicle dynamics Traffic congestion Monitoring Edge computing Accidents Vehicles

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共322页 << < 59 60 61 62 63 64 65 66 67 68 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：