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

8,736 篇 会议
439 篇 期刊文献
19 篇 学位论文
3 篇 科技报告
2 册 图书
1 篇 专利

馆藏范围

9,200 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

5,627 篇 工学
- 2,389 篇 信息与通信工程
- 2,336 篇 电气工程
- 2,205 篇 计算机科学与技术...
- 1,245 篇 软件工程
- 627 篇 控制科学与工程
- 610 篇 电子科学与技术（可...
- 600 篇 仪器科学与技术
- 448 篇 航空宇航科学与技...
- 361 篇 测绘科学与技术
- 236 篇 机械工程
- 229 篇 生物医学工程（可授...
- 213 篇 光学工程
- 163 篇 生物工程
- 91 篇 化学工程与技术
- 90 篇 土木工程
- 85 篇 船舶与海洋工程
- 84 篇 材料科学与工程（可...
- 76 篇 建筑学
- 76 篇 交通运输工程
2,785 篇 理学
- 1,660 篇 物理学
- 777 篇 数学
- 301 篇 统计学（可授理学、...
- 245 篇 系统科学
- 193 篇 生物学
- 167 篇 化学
- 95 篇 地球物理学
816 篇 医学
- 747 篇 临床医学
- 73 篇 基础医学(可授医学...
312 篇 管理学
- 177 篇 管理科学与工程(可...
- 140 篇 图书情报与档案管...
58 篇 军事学
30 篇 经济学
30 篇 农学
28 篇 法学
18 篇 文学
15 篇 教育学
5 篇 艺术学

主题

1,271 篇 signal processin...
583 篇 signal processin...
464 篇 signal to noise ...
350 篇 target tracking
318 篇 object detection
305 篇 feature extracti...
275 篇 training data
231 篇 data mining
220 篇 radar
212 篇 training
202 篇 data processing
197 篇 array signal pro...
191 篇 neural networks
189 篇 sensors
164 篇 signal resolutio...
159 篇 radar tracking
153 篇 signal detection
152 篇 synthetic apertu...
152 篇 data models
150 篇 speech processin...

机构

59 篇 national laborat...
35 篇 school of inform...
25 篇 univ connecticut...
24 篇 nanjing research...
24 篇 duke univ dept e...
24 篇 school of electr...
21 篇 xidian univ natl...
20 篇 national key lab...
20 篇 xidian universit...
20 篇 national lab of ...
17 篇 school of inform...
17 篇 university of el...
17 篇 department of el...
16 篇 national key lab...
16 篇 beijing institut...
15 篇 xidian universit...
14 篇 college of elect...
13 篇 xidian univ natl...
13 篇 university of ch...
12 篇 univ chinese aca...

作者

28 篇 bar-shalom yaako...
23 篇 willett peter
21 篇 kirubarajan t.
19 篇 bar-shalom y
17 篇 jun wang
17 篇 blair wd
15 篇 drummond oliver ...
14 篇 xu shuwen
14 篇 liu hongwei
13 篇 collins leslie m...
13 篇 shui penglang
13 篇 bin yang
12 篇 wang wei
12 篇 torrione peter a...
12 篇 mengdao xing
12 篇 liao guisheng
11 篇 drummond oe
11 篇 abdelhak m. zoub...
10 篇 morton kenneth d...
10 篇 sinha a

语言

8,949 篇 英文
156 篇 中文
58 篇 其他
34 篇 土耳其文
2 篇 法文
2 篇 俄文

检索条件"任意字段=Conference on Signal and Data Processing of Small Targets"

共 9200 条记录，以下是151-160 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：

LEP: Leveraging Local Entropy Pruning for Sparsity in Large Language Models

LEP: Leveraging Local Entropy Pruning for Sparsity in Large ...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Yuli Chen Bo Cheng Yingying Zhang Shuhao Zhang Zhixuan Wu Fanshen Meng State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The application of Large Language Models (LLMs) is rapidly expanding in fields such as natural language processing and computer vision. However, due to the enormous number of model parameters, while their emergent capabilities enhance performance, they also incur significant computational and storage costs, particularly during inference. This makes it particularly challenging to deploy large models in resource-constrained environments. To address this issue, we propose an innovative pruning method based on local entropy, aimed at improving model performance while reducing computational costs. Our approach leverages a small amount of calibration data and calculates the importance of weights based on the local entropy of weights and input activations, applying it to both unstructured and semi-structured pruning without the need for complex weight updates or retraining. Experimental results demonstrate that our method shows superior performance across models of various scales. Specifically, at a sparsity rate of 50%, our method significantly reduces model perplexity without the need for weight updates and outperforms existing pruning techniques such as SparseGPT and Wanda in zero-shot tasks. The code is available at: this https URL.

关键词： Uniform resource locators Measurement Costs Computational modeling Large language models signal processing Entropy Natural language processing Speech processing Hardware acceleration

来源：评论

学校读者我要写书评

暂无评论

Defying Imbalanced Forgetting for Class Incremental Learning

Defying Imbalanced Forgetting for Class Incremental Learning

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Yu Feng Linqiang Deng Huizi Yan Xiaofan Li Wenhao Wang Yan Chang Fuzhong Li Weiqi Zhang School of Software Shanxi Agricultural University Taiyuan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In class incremental learning, deep neural networks often experience catastrophic forgetting, where performance on old classes deteriorates as new classes are learned. Existing approaches to this problem keep a memory buffer to store a small amount of old class data for replay during new class learning, but this causes a severe imbalance between old and new classes. This imbalance hampers the preservation of old class features and learning relationships between old and new classes. Based on this, we propose an asymmetric augmented contrastive method that alleviates class imbalance and strengthens the learning of contrastive relationships between old and new classes. We also introduce class-sensitive feature whitening, which suppresses the model’s dependence on features sensitive to class changes, aiding in class-invariant feature exploration, and mitigating catastrophic forgetting by preserving old inter-class relationships. Experiments show that our method effectively alleviates catastrophic forgetting, particularly in settings with smaller memory buffers, significantly surpassing baselines.

关键词： Incremental learning Memory management Artificial neural networks signal processing Stability analysis Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Adaptive Flight Stabilization System using Proportional Integral Derivative (PID) Control and Sensors

Adaptive Flight Stabilization System using Proportional Inte...

引用

Trends in Material Science and Inventive Materials (ICTMIM), International conference on

作者： Divya Dharshini M Muthuselvi S Ramya R Devaki M Department of Electrical and Electronics Engineering Velammal College of Engineering and Technology Madurai

ISBN: (数字)9798331501488

ISBN: (纸本)9798331501495

This paper presents the design and development of a low-cost flight stabilizer using an Arduino microcontroller and an MPU- 6050 accelerometer and gyroscope sensor to address instability issues in small unmanned aerial vehicles (UAVs). The primary challenge tackled in this study is the accurate measurement and real- time compensation of external disturbances affecting aircraft orientation. To achieve this, the proposed system continuously acquires accelerometer and gyroscope data to compute pitch, roll, and yaw, which are processed through a PID (Proportional- Integral-Derivative) control algorithm for precise motor adjustments. Key challenges such as sensor calibration errors, noise filtering, and response lag are systematically analyzed and mitigated through optimized signal processing techniques. Experimental results validate the system’s effectiveness in maintaining stable flight under dynamic conditions, demonstrating that low-cost embedded systems can provide reliable flight stabilization for small UAV applications.

关键词： Accelerometers Accuracy signal processing algorithms Autonomous aerial vehicles Stability analysis Real-time systems Gyroscopes Aircraft Vehicle dynamics Monitoring

来源：评论

学校读者我要写书评

暂无评论

OPFormer: Real-Time Optimal Power Flow with CNN-Based Transformer

OPFormer: Real-Time Optimal Power Flow with CNN-Based Transf...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Kaijie Xu Xilin Dai Lin Qiu ZJU-UIUC Institute Zhejiang University Hangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the global energy crisis, optimal power flow (OPF) has attracted increasing attention as a tool for power system analysis and energy conservation. However, due to the non-convex and nonlinear nature of the OPF problem, it is often challenging to solve. This paper proposes a data-driven approach based on Convolutional Neural Networks (CNN) and transformers for predicting OPF solutions. Traditional studies have typically focused on either complete topological structures or modifications within small bus system test sets. In contrast, the proposed method applies topology labels as inputs and employs one-hot encoding to represent the topology change, allowing for effective computation across networks with varying topological structures. Experiments were conducted using the IEEE 30-bus system and 118-bus system, incorporating N-1 topology changes within the bus system. Compared to recent studies, the errors for P G and V G are reduced by 57.73% and 45.12% on the IEEE 30-bus system, and by 36.26% and 38.41% on the IEEE 118-bus system, respectively.

关键词： Network topology Energy conservation signal processing Transformers Feature extraction Real-time systems Topology Convolutional neural networks Speech processing Load flow

来源：评论

学校读者我要写书评

暂无评论

A Prompt Learning Framework with Large Language Model Augmentation for Few-shot Multi-label Intent Detection

A Prompt Learning Framework with Large Language Model Augmen...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Ning Zhuang Xiao Wei Junlei Li Xiaobao Wang Chenyang Wang Longbiao Wang Jianwu Dang Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China Huiyan Technology (Tianjin) Co. Ltd Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Intent detection (ID) is essential in spoken language understanding, especially in multi-label settings where intent labels are interdependent and diverse. Existing methods like SE-MLP and QA-FT struggle in few-shot settings, due to limited data availability and efficiency concerns. To address this, we introduce a Prompt Learning framework with large language Model Augmentation (PLMA) for few-shot multi-label ID. In this study, we make three contributions. First, PLMA integrates large language models (LLMs) with small language models (SLMs), using LLMs to enhance SLMs, with prompt learning as the core framework. Second, it leverages LLMs to improve the model’s understanding of both queries and labels by intent spans extraction and answer space expansion. Third, PLMA refines the QA-FT. A novel QA format template is designed to allow single-step training and inference for each input, improving efficiency. Experiments on NLU++ show that PLMA significantly outperforms other baselines in both in-domain and cross-domain settings, demonstrating its effectiveness in combining the strengths of both small and large models.

关键词： Training Adaptation models Accuracy Large language models signal processing Natural language processing Acoustics Multilingual Speech processing

来源：评论

学校读者我要写书评

暂无评论

Personalizing Keyword Spotting with Speaker Information

Personalizing Keyword Spotting with Speaker Information

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Beltrán Labrador Pai Zhu Guanlong Zhao Angelo Scorza Scarpati Quan Wang Alicia Lozano-Diez Ignacio Lopez-Moreno Google Zurich Switzerland Google New York USA Audias Escuela Politécnica Superior Universidad Autónoma de Madrid Madrid Spain

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Keyword spotting systems often struggle to generalize to a diverse population with various accents and age groups. To address this challenge, we propose a novel approach that integrates speaker information into keyword spotting using Feature-wise Linear Modulation (FiLM), a recent method that allows models to learn from different data inputs and features. We explore both Text-Dependent and Text-Independent speaker recognition systems to extract speaker information, and we experiment on extracting this information from both the input audio and pre-enrolled user audio. Evaluating our systems on a diverse dataset, our primary approach yields a notable 2.6% relative improvement on Equal Error Rate overall, particularly improving performance by 5.9% for children under 12 years old and up to 24% for underrepresented speaker groups. Moreover, our proposed approach only requires a small 1% increase in the number of parameters, with a minimum impact on latency and computational cost, which makes it a practical solution for real-world applications.

关键词： Error analysis Modulation Feature extraction data models Acoustics Speaker recognition Computational efficiency data mining Speech processing

来源：评论

学校读者我要写书评

暂无评论

Proceedings of SPIE: signal and data processing of small targets 1997

Proceedings of SPIE: Signal and data processing of small tar...

引用

signal and data processing of small targets 1997

The proceedings contains 53 papers from the Proceedings of SPIE : signal and data processing of small targets 1997. Topics discussed include: detection of small targets in clutter modeled as a Gaussian mixture or a hidden Markov process;performance analysis of a velocity filter bank;Kalman-filter-aided correlation for parameter estimation;random sets in data fusion problems;data association performance model;monopulse tracking of two unresolved Rayleigh targets;and tracklets and hybrid fusion with process noise.

关键词： signal processing

来源：评论

学校读者我要写书评

暂无评论

A Self-supervised UAV Detection Method Based on Channel State Information

A Self-supervised UAV Detection Method Based on Channel Stat...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Pengxuan Gao Disheng Xiao Ruiheng Zou Kai Ying School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Department of Computer Science and Technology Nanjing University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Due to the widespread applications and potential security risks, unmanned aerial vehicle (UAV) detection has received increasing attention in recent years. Among the various methods, one promising method is wireless sensing with channel state information (CSI). However, most CSI-based approaches are supervised and cannot fully utilize unlabeled data. To address this issue, this paper proposes a self-supervised learning method based on CSI. Utilizing a Transformer architecture, the method employs two decoders for prediction and reconstruction tasks to learn the features of the CSI. The pretrained model can be fine-tuned for UAV detection tasks with a small number of training samples to leverage unlabeled data. In experiments across multiple task scenarios, the pretrained model has achieved up to 100% accuracy when fine-tuned with the entire dataset, and approximately 80% accuracy when fine-tuned with only 1% of the data, which has surpassed those models without pretrained parameters. These results demonstrate that our pretraining method can enhance the accuracy of UAV detection while reducing dependency on labeled data.

关键词： Wireless communication Training Wireless sensor networks Accuracy Speech recognition Autonomous aerial vehicles Feature extraction Transformers data models Channel state information

来源：评论

学校读者我要写书评

暂无评论

Guitar-TECHS: An Electric Guitar dataset Covering Techniques, Musical Excerpts, Chords and Scales Using a Diverse Array of Hardware

Guitar-TECHS: An Electric Guitar Dataset Covering Techniques...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Hegel Pedroza Wallace Abreu Ryan M. Corey Iran R. Roman Dept. of Art & Humanities UAM Lerma Estado de México México Signals Media & Telecom. Lab UFRJ Rio de Janeiro Brasil Discovery Partners Institute UIC Chicago United States School of EECS QMUL London United Kingdom

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Guitar-related machine listening research involves tasks like timbre transfer, performance generation, and automatic transcription. However, small datasets often limit model robustness due to insufficient acoustic diversity and musical content. To address these issues, we introduce Guitar-TECHS, a comprehensive dataset featuring a variety of guitar techniques, musical excerpts, chords, and scales. These elements are performed by diverse musicians across various recording settings. Guitar-TECHS incorporates recordings from two stereo microphones: an egocentric microphone positioned on the performer’s head and an exocentric microphone placed in front of the performer. It also includes direct input recordings and microphoned amplifier outputs, offering a wide spectrum of audio inputs and recording qualities. All signals and MIDI labels are properly synchronized. Its multi-perspective and multi-modal content makes Guitar-TECHS a valuable resource for advancing data-driven guitar research, and to develop robust guitar listening algorithms. We provide empirical data to demonstrate the dataset’s effectiveness in training robust models for Guitar Tablature Transcription.

关键词： Training signal processing algorithms Acoustics Robustness Magnetic heads Machine listening Timbre Synchronization Speech processing Microphones

来源：评论

学校读者我要写书评

暂无评论

Detecting Deceptive Narratives in Social Media Using Advanced Natural Language and signal processing Techniques

Detecting Deceptive Narratives in Social Media Using Advance...

引用

2025 International conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Manjunatha Nijhawan, Ginni Reddy, B. Veerasekhar Najm, Rusul Upadhya, Maneesh Harika, Karibandi Venkata Sai Lakshmi New Horizon College of Engineering Department of Mechanical Engineering Bangalore India Lovely Professional University Phagwara India Mlr Institute of Technology Department of Information Technology Telangana Hyderabad India College of Medical Technology The Islamic University Radiology Techniques Department Najaf Iraq Galgotias university Department of Electrical Electronics & Communication Engineering Uttar Pradesh Gerater Noida203201 India Griet Department of Cse Bachupally Telangana Hyderabad India

ISBN: (纸本)9798331527495

The recent spread of fake news through social media has raised very crucial issues of information credibility. The current study presents an employ of signal processing methodology., natural language processing (NLP) for the scheduling of the fake news detection system. The Kaggle Fake News Challenge dataset is used in this research;it provides a rich set of news articles labeled as fake and real. The proposed technique has been called NLP-SignaIFusion., and it applies TF-IDF and wordPEDES for the extraction of textual features from the opinion and sentiment data. Sentiment analysis is used as feature extraction method in this context in order to detect the affective content which fulfils the aim to suggest markers of deception. Logistic regression and neural networks classifiers are applied to categorize the news articles. The targets I employed to perform the model assessment include accuracy., the receiver operating characteristic- area under curve., and the confusion matrix. The integration of signal processing with NLP optimizes the fake news detection and provides new avenues for understanding the differences between anything fake news in social medial. © 2025 IEEE.

关键词： Emotion Recognition

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500页 << < 12 13 14 15 16 17 18 19 20 21 > >>

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：