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

3,425 篇 会议
54 篇 期刊文献
20 册 图书

馆藏范围

3,499 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

1,651 篇 工学
- 819 篇 电气工程
- 716 篇 计算机科学与技术...
- 509 篇 信息与通信工程
- 388 篇 控制科学与工程
- 377 篇 软件工程
- 179 篇 仪器科学与技术
- 170 篇 电子科学与技术（可...
- 91 篇 机械工程
- 77 篇 生物医学工程（可授...
- 55 篇 材料科学与工程（可...
- 50 篇 光学工程
- 49 篇 测绘科学与技术
- 42 篇 航空宇航科学与技...
- 39 篇 交通运输工程
- 34 篇 生物工程
- 27 篇 化学工程与技术
- 20 篇 动力工程及工程热...
- 20 篇 土木工程
- 18 篇 安全科学与工程
597 篇 理学
- 346 篇 物理学
- 206 篇 数学
- 62 篇 系统科学
- 43 篇 生物学
- 39 篇 统计学（可授理学、...
- 29 篇 化学
195 篇 管理学
- 164 篇 管理科学与工程(可...
- 35 篇 图书情报与档案管...
193 篇 医学
- 173 篇 临床医学
- 39 篇 基础医学(可授医学...
- 19 篇 药学(可授医学、理...
14 篇 教育学
9 篇 法学
8 篇 军事学
5 篇 经济学
5 篇 农学
4 篇 文学
2 篇 艺术学

主题

1,688 篇 signal processin...
549 篇 signal processin...
489 篇 estimation
475 篇 field programmab...
425 篇 modulation
425 篇 ofdm
424 篇 clocks
393 篇 filtration
274 篇 digital signal p...
173 篇 algorithm design...
159 篇 array signal pro...
156 篇 signal to noise ...
146 篇 feature extracti...
140 篇 hardware
130 篇 accuracy
106 篇 real-time system...
106 篇 image processing
98 篇 computer archite...
72 篇 testing
70 篇 optimization

机构

21 篇 tianjin key labo...
16 篇 tianjin key lab ...
14 篇 lovely professio...
8 篇 university of ch...
7 篇 cuny ny 10021 us...
7 篇 school of inform...
7 篇 the center for a...
7 篇 harbin inst tech...
6 篇 centre of resear...
6 篇 advanced technol...
6 篇 advanced signal ...
6 篇 tianjin key labo...
6 篇 institute of aer...
5 篇 department of el...
5 篇 us dept def ft g...
5 篇 beijing key labo...
5 篇 school of inform...
5 篇 michigan state u...
5 篇 institute of aco...
4 篇 university of sc...

作者

23 篇 renbiao wu
12 篇 cohen l
11 篇 andrzej cichocki
10 篇 joohwan chun
9 篇 m.a. bayoumi
8 篇 cichocki andrzej
7 篇 a. cichocki
7 篇 dan lu
7 篇 yao k
6 篇 ebrahimi touradj
6 篇 in-cheol park
6 篇 liu hong
5 篇 sangarapillai la...
5 篇 liu yang
5 篇 nelson dj
5 篇 zhigang su
5 篇 anon
5 篇 qingyan shi
5 篇 junfeng li
5 篇 amin mg

语言

3,437 篇 英文
46 篇 中文
18 篇 其他
1 篇 土耳其文

检索条件"任意字段=Conference on Advanced Signal Processing Algorithms"

共 3499 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：

Leveraging Graph Neural Networks for Complex Network Traffic signal processing

Leveraging Graph Neural Networks for Complex Network Traffic...

引用

Trends in Quantum Computing and Emerging Business Technologies (TQCEBT), International conference on

作者： S Vinod Kumar Anurag Shrivastava Aravinda K Lavish Kansal Ravi Kalra Hawraa Ali Sabah Institute of Aeronautical Engineering Hyderabad Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamilnadu Department of Electronics and Communication Engineering New Horizon College of Engineering Bangalore Lovely Professional University Phagwara Lloyd Institute of Engineering & Technology Knowledge Park II Greater Noida Uttar Pradesh College of Technical Engineering National University of Science and Technology Dhi Qar Iraq

ISBN: (数字)9798350384277

ISBN: (纸本)9798350384284

With the development of deep learning algorithms, automated interpretation has advanced significantly, but simultaneous interpretation of speech and sign language still presents a major obstacle. In order to close the communication gap between the hearing and the deaf populations, this study offers novel multimodal deep learning techniques for the simultaneous interpretation of speech and sign language. To analyze and interpret visual and aural input concurrently, the suggested approach combines cutting-edge neural network topologies with sophisticated signal processing methods. This study is centered on the innovative combination of recurrent neural networks (RNNs), namely Long Short-Term Memory (LSTM) networks for auditory speech processing, and convolutional neural networks (CNNs) for visual sign language interpretation. The extraction and integration of temporal and spatial data from both modalities is made easier by this combination. To improve the model's emphasis on relevant signals in a dynamic conversational setting, attention methods are also included. The model was trained and assessed using a large dataset that included a variety of spoken and sign languages. When compared to the current approaches, the findings show a considerable improvement in accuracy and efficiency. This work sheds light on the intricate structure of multimodal communication and its computer modelling, in addition to contributing to the area of automated *** creating new opportunities for inclusive communication technology, our study improves the effectiveness and accessibility of real-time, cross-modal interpretation.

关键词： Deep learning Sign language Visualization Recurrent neural networks Computational modeling Data processing Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Wireless Networks: Advancements in Hybrid Beamforming for Massive MIMO Systems

Next-Generation Wireless Networks: Advancements in Hybrid Be...

引用

advanced Computing Technologies (ICoACT), International conference on

作者： Sudhakar K Tejnithish S Thirupukal G Arsath Farves T S Electrions and Communication Engineering M. Kumarasamy College of Engineering Karur Tamilnadu

ISBN: (数字)9798331509859

ISBN: (纸本)9798331509866

Large-scale wireless communication systems are key enablers of next-generation networks, offering substantial improvements in capacity and data rates. However, the complexity and cost associated with these systems, particularly when implementing fully digital beamforming, present significant challenges. Reinforcement Learning (RL), a branch of machine learning, offers a novel and effective solution to address these challenges by dynamically optimizing beamforming strategies. This paper investigates the effectiveness of applying RL to three major beamforming architectures-analog, digital, and hybrid beamforming, with a primary focus on hybrid beamforming. RL frameworks allow the beamforming direction to be dynamically adjusted based on real-time feedback from channel state information (CSI). Through iterative learning, RL agents optimize system performance, adapting to varying channel conditions and minimizing power consumption. In hybrid beamforming, antennas share a single radio frequency (RF) chain, contrasting with digital beamforming where each antenna is connected to an individual RF chain. RL algorithms, such as Q-learning and deep reinforcement learning (DRL), are employed to select optimal beamforming weights, reducing computational complexity and enhancing energy efficiency while maintaining high data rates. This research evaluates the performance of RL-driven large-scale wireless communication systems across key metrics, including bit error rate (BER), signal-to-noise ratio (SNR), achievable sum rate, power consumption, and energy efficiency. By leveraging RL, the system learns to balance performance and complexity, achieving significant improvements over conventional methods. A detailed comparison of the three beamforming techniques is provided, highlighting the enhanced adaptability and efficiency of RL-driven hybrid beamforming. The findings demonstrate that RL-based hybrid beamforming achieves an optimal trade-off between performance and complexity, ma

关键词： Radio frequency Power demand Array signal processing Wireless networks System performance Energy efficiency Real-time systems Next generation networking Wideband signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

The Application of Quaternion-valued Nonlinear Adaptive Algorithm in Vector-Sensor Arrays

The Application of Quaternion-valued Nonlinear Adaptive Algo...

引用

IEEE advanced Information Management,Communicates,Electronic and Automation Control conference (IMCEC)

作者： Jianlin Huo Xingyu Yao Lei Zhang Mengdi Jiang Henan Special Equipment Inspection Technology Research Institute Kaifeng China School of Physics and Electronics Henan University Kaifeng China

ISBN: (纸本)9781665479691

In the optimization process of adaptive filtering algorithms, nonlinear objective functions are often encountered. Quaternion is used as a new mathematical model in the adaptive filtering algorithm based on vector sensing. A nonlinear adaptive filtering algorithm and its application based on quaternion-valued chain rules are proposed and implemented. Then the quaternion-valued hyperbolic tangent function is employed as the output nonlinear constraint function, the gradient of its cost function is solved, and then the iterative formula of the weight coefficient vector of array is obtained. As the input signal receiver of the vector sensor array, the crossed dipole antenna pairs have been used in the quaternion-valued nonlinear adaptive beamforming algorithm to form an array system to process incident signals. Through Matlab simulation results, it is verified that the quaternion-valued nonlinear adaptive beamforming algorithm can be applied in the vector-senor array to receive desired signals and suppress interferences.

关键词： Array signal processing Quaternions Simulation Adaptive arrays signal processing algorithms Receiving antennas Filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

Developing Audio Zoom in Virtual Environments: Real-World Soundscapes and Targeted Noise Detection

Developing Audio Zoom in Virtual Environments: Real-World So...

引用

International conference on Information Technologies (InfoTech)

作者： Stephen Stroud Karl O. Jones Gerard Edwards Colin Robinson Sebastian Chandler-Crnigoj David Ellis Applied Forensic Technology Research Group (AFTeR) School of Engineering Faculty of Engineering and Technology Liverpool John Moores University Liverpool United Kingdom

ISBN: (数字)9798350365689

ISBN: (纸本)9798350365696

This study presents an innovative beamforming method tailored for audio surveillance applications, developed through virtual simulations conducted at Liverpool John Moores University. Motivated by the growing need for advanced audio analysis techniques, this method focuses on segregating and enhancing particular sounds within acoustically cluttered environments, such as those presented in forensic scenarios, including criminal court cases. Utilising a time-delay beamforming algorithm, this study introduces a novel strategy to identify and magnify specific noises within intricate acoustic settings, addressing challenges often faced in surveillance and forensic audio examinations. The foundation of our technique lies in the strategic deployment of a robust omnidirectional microphone array, which is crucial for capturing environmental sounds. Our methodology involves the application of a MATLAB algorithm to process these sounds, followed by comprehensive evaluations to gauge the system's effectiveness in isolating targeted audio sources. The investigation examines the system's robustness against microphone array degradation, demonstrating its reliability even with compromised functionality. Simulations of real-world acoustic conditions reveal the algorithm's effectiveness in handling sound reflections and reverberations, crucial for urban acoustic landscapes. This study introduces a novel beamforming method for audio surveillance, with potential applications in broadcasting, advanced audio engineering, and wildlife conservation, highlighting its versatility. In summary, this research introduces a novel approach to audio surveillance, paving the way for numerous practical applications that could leverage improved audio isolation and analytical capabilities. Our results contribute significantly to the ongoing development of sophisticated surveillance technologies, offering valuable perspectives that could influence the future landscape of audio engineering and analysis.

关键词： Array signal processing Surveillance Forensics Noise Wildlife signal processing algorithms Interference Robustness Microphone arrays Environmental management

来源：评论

学校读者我要写书评

暂无评论

Studying the Impact of Varying Sample Length of ECG signal on Classification Accuracy

Studying the Impact of Varying Sample Length of ECG Signal o...

引用

International conference on Automation and Computing (ICAC)

作者： Hassan Raza Bukhari Yongqiang Cheng Qingde Li Department of Computer Science University of Hull Kingston upon Hull UK

ECG signals in digital format are being used for gathering various vital information and for predicting diseases in patients using advanced artificial intelligence and digital signal processing technologies. It is important to process the data sufficiently to get the optimal results. In addition to cleaning the dataset, it is important to select the right signal length. This study uses three publicly available datasets (namely autonomic aging dataset, PTB-XL dataset, and PTB Diagnostic dataset) to study the impact of varying sample lengths on classification accuracy i.e., understanding whether varying sample lengths can impact the accuracy and if so how different sample lengths for certain classification problems can affect it. The experiments performed used three machine learning algorithms which are Decision Tree Classifier, Random Forest Classifier, and State Vector Machine Classifier, and it was found that the signal length does impact the accuracy when predicting diseases using an ECG signal, and the behavior can vary depending on the type of data being used and the nature of classification problem, even if the same model is used.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Noval Real Time Sleep Apnea Detection

A Noval Real Time Sleep Apnea Detection

引用

International conference on Power, Energy, Control and Transmission Systems (ICPECTS)

作者： S. Susila Sakthy T. P. Rani Dhoorika Anurega TR Department of Information Technology Sri Sairam Engineering College Chennai India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508852

Sleep apnea is a prevalent sleep disorder characterized by repetitive interruptions in breathing during sleep. Timely detection and monitoring of sleep apnea are crucial for effective diagnosis and treatment. We propose a novel approach for sleep apnea detection using Ultra-Wideband (UWB) sensor technology. The UWB sensor system offers several advantages, including high precision, low power consumption, and the ability to penetrate through different materials. By leveraging these features, we aim to develop a non-intrusive and cost-effective method to detect sleep apnea events accurately. Our research focuses on designing a wearable UWB sensor device that can be comfortably placed near the user’s sleeping area. The sensor system utilizes UWB technology to measure and analyze subtle movements and physiological signals during sleep, such as oxygen and heart rate variability. To detect sleep apnea events, we employ advanced signal processing algorithm, By extracting specific features from the UWB sensor data, we can identify the characteristic patterns associated with sleep apnea episodes. The proposed system has the potential to provide an accessible and effective solution for early detection and continuous monitoring of sleep apnea, leading to improved diagnosis, treatment, and overall patient care. Further research on creating a website for hospitals to monitor the apnea patients.

关键词： Power demand signal processing algorithms Process control Feature extraction Sleep apnea Sensor systems Real-time systems Biomedical monitoring Monitoring Ultra wideband technology

来源：评论

学校读者我要写书评

暂无评论

XAI-Based Identification of EEG Features of Inhibition and Working Memory Activation

XAI-Based Identification of EEG Features of Inhibition and W...

引用

Metrology for Extended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE), IEEE International conference on

作者： Pasquale Arpaia Ciro Ivan De Girolamo Matteo De Luca Allegra Fullin Ludovica Gargiulo Luigi Maffei Nicola Moccaldi Rachele Robbio Paolo De Blasiis Department of Electrical Engineering and Information Technology (DIETI) University of Naples Federico II Naples Italy Dep. of Advanced Biomedical Sciences University of Naples Federico II Naples Italy Dep. of Electrical Engineering and Information Technology (DIETI) University of Naples Federico II Naples Italy University of Basilicata Potenza Italy

ISBN: (数字)9798350378009

ISBN: (纸本)9798350378016

The most informative electroencephalographic (EEG) features related to basic Executive Functions (EFs) were identified by exploiting the SHapley Additive exPlanations (SHAP), an eXplainable Artificial Intelligence (XAI) method. In particular, Working Memory (WM) and Inhibitory Control (IC) were tested by exposing participants to N-Back and Go-NoGo tasks. Currently, eXplainable AI (XAI) methods are scarcely investigated in the framework of EEG signal processing. Specific EEG features of EFs activation are still poorly explored. EEG data from 13 healthy participants were gathered during rest condition and cognitive task executions. In particular, N-Back (activating WM) and Go-NoGo (activating IC) tasks were administered with two difficulty levels. SHAP identified Absolute Delta Power in Fp1 and Fp2 as the two most significant features for both WM and IC, when the two experiments were analyzed separately. The same two features emerged as the most significative when SHAP was applied on a classification problem involving the two tasks at the highest difficulty level. Absolute power of Delta Fp1 and Fp2 resulted statistically significantly lower in the Go-NoGo task compared to the N-Back. These results are consistent with a condition of suppression of irrelevant sensory stimuli common to the two tasks and particularly to the more challenging N-back task. The research contributes to the development of solutions for the cognitive rehabilitation of patients suffering from neurodegenerative diseases.

关键词： Knowledge engineering Explainable AI Statistical analysis Extended reality signal processing algorithms Neural engineering signal processing Metrology Electroencephalography Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Radar signal Modulation Recognition based on 1-D CNN

Radar Signal Modulation Recognition based on 1-D CNN

引用

IEEE advanced Information Management,Communicates,Electronic and Automation Control conference (IMCEC)

作者： Dongming Wu Fangzheng Liu Shilong Wu Zhenzhong Han National University of Defense Technology Hefei China

ISBN: (纸本)9781665479691

In order to solve the problems of low recognition accuracy and high computation complexity of radar signal processing under low signal-to-noise ratio (SNR), this paper studies a neural network based on 1-D convolution for radar intra-pulse modulation recognition. First, we generate seven different types of radar continuous FM signals and phase coded signals (LFM, NLFM, Frank, P1, P2, P3, P4). Then, the three-dimensional convolutional network suitable for image processing is improved into a one-dimensional convolutional network which will process the generated radar signal in an end-to-end approach. The simulation results show that the recognition algorithm using one-dimensional (1-D) MobileNetV2 network can effectively extract the essential characteristics of radar signal under the condition of low SNR, avoid the huge calculation caused by using time-frequency method, and achieve over 85% recognition accuracy at −6dB.

关键词： Time-frequency analysis Convolution signal processing algorithms Radar Radar imaging Feature extraction Radar signal processing

来源：评论

学校读者我要写书评

暂无评论

Development and Application of Transformer State Perception Terminals Based on Artificial Intelligence and Edge Computing

Development and Application of Transformer State Perception ...

引用

Energy Engineering and Power Systems (EEPS), International conference on

作者： Xintong Wang Xin Chen Xuexing Zhang Zhendong Tang State grid Jibei Electric Power Co. Ltd. Tangshan power supply company Tangshan China

ISBN: (数字)9798350366914

ISBN: (纸本)9798350366921

The arrival of the global digital and intelligent revolution has profoundly changed the fundamental structure and operational basis of various industries, making the energy transition and digital development of power systems an inevitable trend. However, the rapid development of sensor and communication technologies has increasingly highlighted the bottleneck in data processing capabilities. With the widespread installation of sensors, power equipment continuously generates massive amounts of state monitoring data, and traditional data analysis algorithms are unable to cope with the growing backlog of data. To address this challenge, this paper explores the feasibility of integrating advanced artificial intelligence technologies on the edge computing platform for efficient real-time processing and analysis at the data source. The paper focuses on the development and application of edge computing terminals for current transformer state perception. By analyzing the problems and challenges in the current operation and control of current transformers, an edge computing service framework suitable for current transformer state detection is constructed based on edge computing. In conjunction with actual application needs, this paper proposes effective edge computing implementation solutions. The research results show that this solution significantly improves data processing efficiency and accuracy, playing an important role in promoting the intelligent monitoring and maintenance of current transformers.

关键词： Current transformers Soft sensors Computational modeling Real-time systems Power systems Convolutional neural networks Artificial intelligence signal analysis Monitoring Edge computing

来源：评论

学校读者我要写书评

暂无评论

Stepwise DOA Estimation for Coherent and Uncorrelated Mixed signals on Coprime Array

Stepwise DOA Estimation for Coherent and Uncorrelated Mixed ...

引用

IEEE advanced Information Management,Communicates,Electronic and Automation Control conference (IMCEC)

作者： Heng Jiang Lichun Li Hailong Zhang Hongyi Pan Xue Li College of Information System Engineering Information Engineering University Zhengzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781665479691

The coprime array constructs virtual array to obtain higher degrees of freedom (DOF), but the premise of doing so is that the signals are independent of each other. Once there are coherent signals, the signal model of virtual array is destroyed and the method fails. To solve these problems, we propose the stepwise estimation of the Direction of Arrival (DOA) for a mixture of coherent and uncorrelated signals. Firstly, the symmetry of the two coprime subarrays is used to eliminate the uncorrelated signals, and combined with the properties of prime numbers, the coherent source DOA is jointly estimated. The obtained coherent source DOA was combined with the optimization algorithm to remove the coherent signal in the mixed signal. Finally, the virtual domain signal processing method was used to estimate the independent source DOA. This method can effectively reduce the influence of coherent signals on the accuracy of DOA estimation without loss of degrees of freedom. In this paper, the feasibility of the proposed method is proved by theoretical derivation, and the effectiveness of the method is also verified by experimental simulations.

关键词： Direction-of-arrival estimation Automation Simulation Estimation signal processing algorithms Interference signal processing

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350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：