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

8,730 篇 会议
439 篇 期刊文献
19 篇 学位论文
3 篇 科技报告
1 册 图书
1 篇 专利

馆藏范围

9,193 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

5,626 篇 工学
- 2,389 篇 信息与通信工程
- 2,338 篇 电气工程
- 2,203 篇 计算机科学与技术...
- 1,244 篇 软件工程
- 627 篇 控制科学与工程
- 608 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...
- 212 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
- 83 篇 材料科学与工程（可...
- 76 篇 建筑学
- 76 篇 交通运输工程
2,781 篇 理学
- 1,658 篇 物理学
- 775 篇 数学
- 299 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
815 篇 医学
- 746 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

1,268 篇 signal processin...
583 篇 signal processin...
462 篇 signal to noise ...
351 篇 target tracking
318 篇 object detection
306 篇 feature extracti...
275 篇 training data
231 篇 data mining
220 篇 radar
212 篇 training
203 篇 data processing
200 篇 array signal pro...
191 篇 neural networks
190 篇 sensors
165 篇 signal resolutio...
159 篇 radar tracking
154 篇 signal detection
152 篇 synthetic apertu...
152 篇 data models
150 篇 speech processin...

机构

59 篇 national laborat...
34 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

8,944 篇 英文
155 篇 中文
57 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 9193 条记录，以下是91-100 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：

Targeted data Poisoning for Black-Box Audio datasets Ownership Verification

Targeted Data Poisoning for Black-Box Audio Datasets Ownersh...

引用

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

作者： Wassim Wes Bouaziz El-Mahdi El-Mhamdi Nicolas Usunier Meta FAIR Labs CMAP École Polytechnique Paris France CMAP École Polytechnique Palaiseau France Meta FAIR Labs Paris France

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Protecting the use of audio datasets is a major concern for data owners, particularly with the recent rise of audio deep learning models. While watermarks can be used to protect the data itself, they do not allow to identify a deep learning model trained on a protected dataset. In this paper, we adapt to audio data the recently introduced data taggants approach. data taggants is a method to verify if a neural network was trained on a protected image dataset with top-k predictions access to the model only. This method relies on a targeted data poisoning scheme by discreetly altering a small fraction (1%) of the dataset as to induce a harmless behavior on out-of-distribution data called keys. We evaluate our method on the Speechcommands and the ESC50 datasets and state of the art transformer models, and show that we can detect the use of the dataset with high confidence without loss of performance. We also show the robustness of our method against common data augmentation techniques, making it a practical method to protect audio datasets.

关键词： Deep learning Adaptation models Closed box Watermarking data augmentation Transformers data models Robustness Speech processing signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A study of image recognition intelligent small car system 16

A study of image recognition intelligent small car system

引用

16th International conference on signal processing Systems, ICSPS 2024

作者： Zhang, Zhixi Wang, Zhilei Advanced Perception and Intelligent Equipment Engineering Research Center of Jiangsu Province Suzhou City University Jiangsu China Yi Jin Luo power supply branch of Ordos power supply company Inner Mongolia Ordos China

ISBN: (纸本)9781510689251

With the rapid development of modern science and technology, control technology and theory have made great progress, the development of industrial automation is more and more rapid, the degree of automation is also higher and higher, and the scope of use has also been greatly expanded. Under the influence of the rapidly developing microcontroller technology, the technology covers many disciplines including sensor technology. This design is under the background of hardware selection and software design to realize the image recognition intelligent car system. The intelligent car system designed by the design can realize a variety of functions, including image recognition, Bluetooth remote control, voice broadcast, ultrasonic obstacle avoidance, speech recognition, autonomous tracking, gesture recognition, ultrasonic speed measurement, OLED screen display and other functions. The design of the camera on the OpenMV module are used to collect images, and identify and process them. If the target image is identified, send data to the microcontroller through the established serial port communication protocol, and the microcontroller performs the next *** car has added a LD3320 voice recognition module, which can distinguish the sound of people, and can control the car driving through the sound. The car can be remotely controlled through the HC-05 Bluetooth module, and each module can be selected through the *** the ATK-PAJ7620 gesture recognition module, the car can recognize our gestures and realize the corresponding functions. The TCRT5000L tracking sensor can detect the black track on the ground, and the ultrasonic HC-SR 04 sensor is added in the front position for distance detection. The module transmits the collected relevant data to the main control, so as to realize the autonomous tracking of the car and the function of of avoiding obstacles. Speed measurement can also be performed by the ultrasonic module, and the speed results can be display

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

Generative Expansion of small datasets: An Expansive Graph Approach

Generative Expansion of Small Datasets: An Expansive Graph A...

引用

2025 IEEE International conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Jebraeeli, Vahid Jiang, Bo Krim, Hamid Cansever, Derya ECE Department NC State University Raleigh United States Neuroscience Department Washington University St. Louis United States

ISBN: (纸本)9798350368741

Limited data availability in machine learning significantly impacts performance and generalization. Traditional augmentation methods enhance moderately sufficient datasets. GANs struggle with convergence when generating diverse samples. Diffusion models, while effective, have high computational costs. We introduce an Expansive Synthesis model generating large-scale, information-rich datasets from minimal samples. It uses expander graph mappings and feature interpolation to preserve data distribution and feature relationships. The model leverages neural networks' non-linear latent space, captured by a Koopman operator, to create a linear feature space for dataset expansion. An autoencoder with self-attention layers and optimal transport refines distributional consistency. We validate by comparing classifiers trained on generated data to those trained on original datasets. Results show comparable performance, demonstrating the model's potential to augment training data effectively. This work advances data generation, addressing scarcity in machine learning applications. © 2025 IEEE.

关键词： Dimension Expansion Expander Graph Mapping Koopman Operator Theory Optimal Transport

来源：评论

学校读者我要写书评

暂无评论

Tensor Decomposition-Based Feature Transfer Learning for BCI Applications

Tensor Decomposition-Based Feature Transfer Learning for BCI...

引用

International conference on Intelligent Control and Information processing (ICICIP)

作者： Zahra Sohrabi Bonab Mohammad Bagher Shamsollahi Department of Electrical Engineering Sharif University of Technology Tehran Iran

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

Event-Related Potential (ERP) detection and enhancement remain significant challenges in EEG signal processing due to the complex and multidimensional nature of ERP signals. This paper addresses these challenges by proposing a novel framework that combines low-rank tensor representation with heuristic feature transfer learning for efficient ERP processing. By leveraging tensor decomposition, we capture intricate multidimensional patterns in ERP data, facilitating the extraction of informative features. These features greatly reduce processing time, making the method particularly suitable for online Brain-Computer Interface (BCI) applications. We also present a feature transfer learning mechanism utilizing tensor decomposition, which facilitates the efficient adaptation of features trained on multiple subjects to new subjects, requiring only a small amount of calibration data. This approach leverages shared classification structures across subjects, allowing for rapid deployment and minimizing the need for extensive retraining. Our results demonstrate that the proposed method achieves reasonable ERP detection accuracy while drastically reducing computational overhead, presenting a robust solution for real-time BCI systems.

关键词： Training Tensors Accuracy Transfer learning Training data signal processing Feature extraction Real-time systems Neurorehabilitation data mining

来源：评论

学校读者我要写书评

暂无评论

Domain-Specific Adaptation in Speech Emotion Recognition Using Emotional Distribution Alignment

Domain-Specific Adaptation in Speech Emotion Recognition Usi...

引用

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

作者： Abinay Reddy Naini Donita Robinson Elizabeth Richerson Carlos Busso The University of Texas at Dallas Richardson TX USA North Carolina State University Raleigh NC USA Language Technologies Institute Carnegie Mellon University Pittsburgh PA USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

This work addresses the challenge of building speech emotion recognition models that generalize effectively across different domains, particularly when only limited target domain data is available with or without emotional label information. Traditional models often struggle with cross-domain performance due to the variability in emotional expressions and the lack of alignment between the training and target domains. We propose a novel approach that prioritizes aligning the emotional label distribution of the training data with that of the target domain by undersampling the source domain. Even though we intentionally reduce the size of the training set from the source domain, the emotional content alignment leads to clear performance improvements, outperforming models trained with the complete training set. This strategy highlights the importance of aligning emotional attributes during training, helping to create robust emotion recognition models across diverse applications. Our findings also reveal that performance significantly improves when even a small amount of labeled target domain data is available, allowing for a more accurate assessment of the emotional distribution in the target domain.

关键词： Training Emotion recognition Adaptation models Training data Speech recognition signal processing Predictive models data models Iterative methods Speech processing

来源：评论

学校读者我要写书评

暂无评论

FDR-Controlled Portfolio Optimization for Sparse Financial Index Tracking

FDR-Controlled Portfolio Optimization for Sparse Financial I...

引用

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

作者： Jasin Machkour Daniel P. Palomar Michael Muma Robust Data Science Group Technische Universität Darmstadt Germany Convex Optimization Group The Hong Kong University of Science and Technology China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In high-dimensional data analysis, such as financial index tracking or biomedical applications, it is crucial to select the few relevant variables while maintaining control over the false discovery rate (FDR). In these applications, strong dependencies often exist among the variables (e.g., stock returns), which can undermine the FDR control property of existing methods like the model-X knockoff method or the T-Rex selector. To address this issue, we have expanded the T-Rex framework to accommodate overlapping groups of highly correlated variables. This is achieved by integrating a nearest neighbors penalization mechanism into the framework, which provably controls the FDR at the user-defined target level. A real-world example of sparse index tracking demonstrates the proposed method’s ability to accurately track the S&P 500 index over the past 20 years based on a small number of stocks. An open-source implementation is provided within the R package TRexSelector on CRAN.

关键词： Target tracking High dimensional data Biological system modeling signal processing Acoustics Indexes Speech processing Tuning Portfolios Optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing data Security Through Double Steganography Approaches

Enhancing Data Security Through Double Steganography Approac...

引用

International conference on signal processing and Communication (ICSC)

作者： Irfan Mirda Adifa Widyadhani Chanda D'Layla Ntivuguruzwa Jean De La Croix Tohari Ahmad Department of Informatics Institut Teknologi Sepuluh Nopember Surabaya Indonesia University of Rwanda Kigali Rwanda

ISBN: (数字)9798331511890

ISBN: (纸本)9798331511906

The growth of internet users aligns closely with population growth, with more people going online each year. As internet usage expands, both individuals and companies increasingly prioritize privacy in their digital activities, making data security a key concern. In the field of steganography, double steganography plays a significant role by offering enhanced data security through the combination of multiple embedding techniques. This study focuses on double steganography in the spatial domain, utilizing the LSB, ISB, and MSB methods. The MSB-LSB technique emerges as the optimal choice for small data sizes (10 kb), achieving SAW scores ranging from 1.073 to 1.240, PSNR values between 51.93 and 53.92 dB, and a near-perfect SSIM of 1.00. Additionally, the method demonstrates a low BER of 0.03-0.05 and an efficient processing time of approximately 1.94-1.95 seconds, ensuring excellent embedding quality with minimal distortion for small data sizes. For larger data sizes (30 kb, 50 kb, and 90 kb), the LSB-LSB and ISB-LSB approaches alternate as the most effective techniques. These methods deliver reliable embedding quality with SAW scores ranging from 0.787 to 0.954, PSNR values between 51.14 and 51.21 dB, and a consistent SSIM of 1.00. processing times increase with data size, ranging from 2.79 to 6.38 seconds, while the BER remains stable at 0.06 for larger loads. Due to their ability to balance quality and performance, the LSB-LSB and ISB-LSB methods are better suited for embedding larger datasets.

关键词： Image quality Steganography data privacy Error analysis data security data integrity Distortion data transfer Distance measurement Reliability

来源：评论

学校读者我要写书评

暂无评论

Low-Rank Transformer Adaptation for Arbitrary Style Transfer

Low-Rank Transformer Adaptation for Arbitrary Style Transfer

引用

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

作者： Wenjie Xu Meichen Liu Bihan Wen School of Electrical and Electronic Eng Nanyang Technological University Singapore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Arbitrary style transfer aims to apply artistic characteristics from a style reference to an image while preserving the image’s original content. Although many methods have achieved remarkable results in style transfer, they typically rely on largescale datasets for training, which increases both the cost and complexity of data collection. To address this issue, we propose a Low-rank Transformer Adaptation method for style transfer which leverages the efficiency of low-rank adaptation to reduce the model’s complexity without compromising performance. It not only accelerates the training process but also delivers high-quality image generation with a small-scale dataset. Additionally, we introduce an edge detection loss to enhance the preservation of content outlines further, ensuring that the fine details of the image are maintained during the style transfer process Experimental results demonstrate that our method achieves competitive performance even with significantly less data, and it exhibits superiority in both visual quality and evaluation metrics.

关键词： Training Measurement Adaptation models Visualization Image synthesis Image edge detection signal processing Transformers Complexity theory 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 2004

Proceedings of SPIE - Signal and Data Processing of Small Ta...

引用

signal and data processing of small targets 2004

The proceedings contain 50 papers from the conference on SPIE- signal and data processing of small targets 2004. The topics discussed include: background modeling and target segmentation via modified Kalman filtering;automatic target selection in video signals;detection of small targets in IR image sequences using VSLMS;multiple model tracking using fuzzy clustering;tracking maneuvering targets using a scale mixture of normals;physics-based computational complexity of nonlinear filters;IMM estimator with out-of-sequence measurements;feature aided tracking (FAT) and tracking ground vehicles on a grid.

关键词： Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

Zero-shot Stance Detection with Logically Consistent data Augmentation

Zero-shot Stance Detection with Logically Consistent Data Au...

引用

2025 IEEE International conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Zhang, Bowen Li, Xu Ma, Jun Zhang, Xi Dai, Genan Ye, Jianhua College of Big Data and Internet Shenzhen Technology University Shenzhen China College of Applied Science Shenzhen University Shenzhen China

ISBN: (纸本)9798350368741

Zero-shot stance detection (ZSSD) is a challenging task that requires classifying stances towards unseen targets without large, well-curated training datasets. Existing data augmentation methods for ZSSD often suffer from semantic inconsistencies, hindering their effectiveness. To address these limitations, we propose a Logically Consistent data Augmentation (LCDA) framework that enhances data quality by maintaining logical coherence. LCDA comprises two key components: data augmentation and logical graph convolutional network. Our data augmentation approach leverages chain-of-thought (CoT) prompting to enable large language models (LLMs) to distill training text into first-order logic (FOL) expressions, which provide a clear and concise representation of the underlying logic for stance prediction. These FOL expressions are then used to generate high-quality augmented samples. Furthermore, we introduce a novel logical graph convolutional network that effectively exploits FOL knowledge and combines it with augmented data samples to train a more accurate stance detection model. Our experiments on benchmark datasets demonstrate that the LCDA framework significantly outperforms existing ZSSD techniques, highlighting the effectiveness of integrating FOL into data augmentation for improving stance detection accuracy. © 2025 IEEE.

关键词： Chain-of-thought data augmentation First-order logic Zero-shot stance detection

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 << < 6 7 8 9 10 11 12 13 14 15 > >>

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：