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

1,327 篇 会议
11 篇 期刊文献
9 册 图书

馆藏范围

1,347 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

915 篇 工学
- 757 篇 计算机科学与技术...
- 498 篇 软件工程
- 303 篇 信息与通信工程
- 204 篇 电气工程
- 175 篇 生物工程
- 127 篇 生物医学工程（可授...
- 107 篇 光学工程
- 90 篇 控制科学与工程
- 80 篇 电子科学与技术（可...
- 58 篇 仪器科学与技术
- 48 篇 机械工程
- 35 篇 化学工程与技术
- 28 篇 安全科学与工程
- 26 篇 交通运输工程
425 篇 理学
- 189 篇 生物学
- 187 篇 数学
- 151 篇 物理学
- 76 篇 统计学（可授理学、...
- 54 篇 系统科学
- 40 篇 化学
169 篇 管理学
- 106 篇 图书情报与档案管...
- 72 篇 管理科学与工程(可...
- 40 篇 工商管理
146 篇 医学
- 130 篇 临床医学
- 88 篇 基础医学(可授医学...
- 65 篇 药学(可授医学、理...
- 24 篇 公共卫生与预防医...
28 篇 教育学
- 28 篇 教育学
27 篇 法学
- 21 篇 社会学
18 篇 经济学
- 17 篇 应用经济学
16 篇 农学
5 篇 军事学
1 篇 文学
1 篇 历史学

主题

210 篇 machine learning
134 篇 deep learning
78 篇 signal processin...
71 篇 accuracy
70 篇 feature extracti...
68 篇 signal processin...
61 篇 support vector m...
56 篇 machine learning...
45 篇 predictive model...
33 篇 neural networks
32 篇 convolutional ne...
31 篇 random forests
29 篇 computational mo...
29 篇 training
26 篇 natural language...
25 篇 prediction algor...
21 篇 technological in...
20 篇 real-time system...
19 篇 adversarial mach...
18 篇 image processing

机构

16 篇 chitkara centre ...
14 篇 centre of resear...
12 篇 shenyang ligong ...
6 篇 chitkara univers...
6 篇 ai & ds vishwaka...
6 篇 school of inform...
5 篇 department of me...
5 篇 khulna universit...
5 篇 department of co...
4 篇 delhi technologi...
4 篇 heilongjiang uni...
4 篇 department of s&...
4 篇 beijing univ pos...
4 篇 it vishwakarma i...
4 篇 chitkara univers...
4 篇 sri lanka instit...
4 篇 advanced telecom...
4 篇 shenyang ligong ...
4 篇 graduate school ...
3 篇 karunya institut...

作者

6 篇 mehta shiva
5 篇 rasmita panigrah...
4 篇 neelamadhab padh...
4 篇 wang xin
3 篇 m. vigenesh
3 篇 baydeti nagaraju
3 篇 sinambela marzuk...
3 篇 santosh kumar sh...
3 篇 ganapati panda
3 篇 debendra muduli
3 篇 abujar sheikh
3 篇 a. sivanantham
3 篇 li yajie
3 篇 li aihua
3 篇 zhou feng
3 篇 islam md. sanzid...
2 篇 aira kharvel par...
2 篇 nokshangthemba
2 篇 maheswara rao v ...
2 篇 lee tzong-ru

语言

1,187 篇 英文
151 篇 其他
11 篇 中文

检索条件"任意字段=Proceedings of the 2019 2nd International Conference on Signal Processing and Machine Learning"

共 1347 条记录，以下是561-570 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：

Parkinson’s Disease Detection Based on Gait Analysis of Vertical Ground Reaction Force Using signal processing with machine learning 2nd

Parkinson’s Disease Detection Based on Gait Analysis of Ver...

引用

2nd international conference on Electronics, Biomedical Engineering, and Health Informatics, ICEBEHI 2021

作者： Fuadah, Yunendah Nur Taliningsih, Fauzi Frahma Wijayanto, Inung Pratiwi, Nor Kumalasari Caecar Rizal, Syamsul School of Electrical Engineering Telkom University Bandung Indonesia

ISBN: (纸本)9789811918032

Parkinson’s Disease (PD) is a type of brain disorder caused by dopaminergic neuron loss. People with Parkinson's disease have symptoms such as tremors and stiffness which caused the affected people difficulty to control their movement. The diagnosis of PD is usually based on measures neurologist analyses of medical history, review of the symptoms, neurological and physical examination. Therefore, it requires along procedure to identify Parkinson's disease and considerable risk of misdiagnosis. This study proposes automatic detection of Parkinson’s disease formed on gait analysis of Vertical Ground Reaction Force (VGRF) signals. The raw data of VGRF signals obtained from the Physionet database is filtered using a Butterworth high-pass filter with a cut-off frequency of 0.8 Hz. Afterward, the features were used based on the maximum amplitude value, the minimum amplitude value, and the maximum power value of VGRF signals after filtering. K-Nearest Neighbor was performed as a classifier to classify PD and healthy subjects. The total data used are 165 data that consists of 93 PD and 72 healthy subjects. The proposed model was evaluated using 42 test datasets and obtained a 77% AUC score by using the most optimal parameter of K-NN with K = 7 and Chebyshev as a distance matrix. The performance of accuracy and AUC score obtained in classification was acceptable even though only used 3 features as input for the KNN classifier model. In addition, the proposed method simplifies the previous algorithm in detecting Parkinson's disease. Early detection of Parkinson's disease is very important;hence it can provide the proper treatments that can delay the disease progression. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Seizure Prediction Using XGBoost and EEG Data: A machine learning Approach with increasing Model Metrics

Enhanced Seizure Prediction Using XGBoost and EEG Data: A Ma...

引用

international conference on signal processing, Communication, Power and Embedded System (SCOPES)

作者： Sanghamitra Panda Sushree Sasmita Dash Rakesh Pandey Swapnajit Sahoo Annimesh Sasmal Debasish Swapnesh Kumar Nayak Department of Computer Science and Engineering Centurion University of Technology and management Bhubaneswar Odisha India Deparment of CSE KIIT University Bhubaneswar India Department of AI & DS IIMT College of Engineering Greater Noida India School of Computer Science and Engineering IILM University Greater Noida Uttar Pradesh INDIA

ISBN: (数字)9798331506452

ISBN: (纸本)9798331506469

Epilepsy is a neurological disorder marked by abnormal brain activity. Normally, brain cells (neurons) communicate with each other through electrical signals. In epilepsy, these signals become disrupted, leading to excessive and synchronized firing, resulting in seizures. But, if it can be predicted early, then it may be prevented or made to progress slowly. For prediction, machine learning has played a great role nowadays. In this study, we have used models like Random Forest, Decision Tree, Extra-trees classifier, Gradient Boost (XGBoost) has given better result for prediction. In this paper we have taken total 500 individuals EEG data with each has 4097 data points. The EEG scans provided detailed images of brain structures, allowing for precise analysis of epileptic activity using EEG data. The prediction of seizures has proven to be a formidable challenge, with existing studies failing to yield consistently accurate results. Our methodology involved a 60/40 train-test split and again 20/20 for test-validation split ensuring the model was trained on the majority of the data. By utilizing the XGBoost, we achieved an accuracy of 98%, demonstrating its effectiveness in handling complex spatial data inherent in EEG scans. Besides, we have presented roc-auc curve, f1-score, recall, support, precision and confusion matrix to show the execution of the model. This localization capability represents a significant advancement in epilepsy research, enabling more targeted treatment strategies. The researches already performed on prediction of Epilepsy disease has given poor performance of 95% classification accuracy in comparison to our model.

关键词： Location awareness Surveys Accuracy Epilepsy Predictive models Brain modeling Electroencephalography Data models Spatial databases Synchronization

来源：评论

学校读者我要写书评

暂无评论

Application of multi-classification method of skin cancer based on dermoscopic image 21

Application of multi-classification method of skin cancer ba...

引用

2nd international Symposium on Artificial Intelligence for Medicine Sciences, ISAIMS 2021

作者： Chen, Qian Li, Min Chen, Cheng Chen, Chen Lv, Xiaoyi College of Software Key Laboratory of Software Engineering Technology Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China College of Information Science and Engineering Xinjiang University Urumqi China

ISBN: (纸本)9781450395588

As a kind of cancer with high incidence, skin cancer seriously threatens people's life and health. Early detection, early diagnosis, and early treatment are one of the effective ways to increase the survival rate of patients with skin diseases. Therefore, this paper used the ResNet50 model as a feature extractor based on deep learning, and combined machine learning algorithms to explore the heterogeneity among multi-type of skin cancer, and tried to construct the best performance computer-aided diagnosis model. The research first used preprocessing techniques such as hair noise removal and data enhancement, and then achieved a classification accuracy of 90.497% on the public data set of ISIC2019. The proposed model effectively relieves the huge work pressure of dermatologists, and provides a reference for the better use of dermoscopic images for intelligent diagnosis and classification of skin cancer. © 2021 ACM.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

machine learning Based Approach to Selective Measurements of Hydrogen for Catalytic Gas Sensors

Machine Learning Based Approach to Selective Measurements of...

引用

IEEE international conference on Computation, Communication and Engineering (ICCCE)

作者： Denis Spirjakin Alexander Baranov Ivan Ivanov Cù Thanh Phong Nguyen Ngoc Tuan Moscow Aviation Institute Moscow Russia Air Defense - Airforce Academy Son Tay Vietnam

ISBN: (纸本)9781665482493

The results of research to improve hydrogen measurement selectivity of catalytic gas sensors are presented. The method uses temperature modulation to obtain the multidimensional signal, which includes a temperature-dependent sensor response to the presence of different gases in the environment: hydrogen, methane, ethylene, propane, butane, and hexane. The signal processing was performed using machine learning methods. Two models were trained: the linear regression and the neural network. The neural network model showed substantially better accuracy in comparison to the linear one. The absolute mean error for this model is 0.0095 %vol. The level of error is consistent for all gases. The results show that the presented method allows the selective measurements of target gases, hydrogen in particular, and minimize the interference of other gases. In comparison to other methods, the method does not need any changes in the sensor construction and allows selective results even when gases have a strong response to similar temperatures.

关键词： Temperature measurement Temperature sensors Methane Atmospheric measurements Hydrogen Neural networks Modulation

来源：评论

学校读者我要写书评

暂无评论

Features Domains and Classification Algorithms in Motor Imagery Brain Computer Interface

Features Domains and Classification Algorithms in Motor Imag...

引用

Electronic Information Engineering and Computer Technology (EIECT), international conference on

作者： Weizheng Yuan Department of Computational Biology Carnegie Mellon University Pittsburgh PA USA

Motor imagery brain-computer interface (MI-BCI) is well approved to help people with movement impairments due to neural disorders. The procedure for MI-BCI to translate MI brain signals to understandable instructions for external devices involves extracting features from recorded signals and predicting desired movements. This paper summarizes and compares feature extraction methods and classification algorithms and their modifications that are commonly used for MI EEG signals. Feature extraction techniques are discussed based on their feature domains: time, frequency, and spatial. Classification algorithms are divided into classical machine learning and deep learning. This paper aims to provide a straightforward view of common ways to extract features and classifying movements in MI-BCI and show difficulties in MI-BCI signal processing. The nature of MI EEG signals and MI-BCI applications points to several promising field such as transfer learning and deep learning neural networks.

关键词： Deep learning Time-frequency analysis Computational modeling Transfer learning Feature extraction Brain modeling Brain-computer interfaces

来源：评论

学校读者我要写书评

暂无评论

Integration Design of Motion Capture and Sensor Technology in Home Fitness

Integration Design of Motion Capture and Sensor Technology i...

引用

Sensors, Electronics and Computer Engineering (ICSECE), IEEE international conference on

作者： He Chen Xu Hong Kaiwen Xiao Sujie Mao Sangmyung University Seoul South Korea Jiangsu Second Normal University Nanjing China Nanjing Institute of Physical Education Nanjing China

ISBN: (数字)9798350373646

ISBN: (纸本)9798350373653

Background and Purpose: This study aims to design an integrated home fitness system combining motion capture (Mocap) and sensor technology (Sensing Tech). With remote work and home-based lifestyles becoming the norm, traditional home fitness methods face challenges in personalized guidance and real-time feedback. This system aims to provide personalized fitness advice and instant corrections by monitoring users' movement quality and physiological state in real time, thereby enhancing the safety, effectiveness, and overall health level of home fitness. Technical Overview: Mocap captures human motion data through devices such as cameras and sensors, generating precise three-dimensional data models, primarily divided into optical, inertial, and hybrid systems. Sensing Tech utilizes accelerometers, gyroscopes, heart rate sensors, etc., to detect and respond to physical, chemical, or biological changes in the environment, providing real-time data for monitoring health conditions. System Design: The system comprises four parts: architecture, data acquisition, data processing, and user interface. It adopts a hierarchical architecture including the data acquisition layer, data processing layer, and user interface layer. User actions and physiological data are collected using IMU sensors, heart rate monitors, and camera systems. Integrated signal processing, feature extraction, behavior recognition algorithms run on microprocessors or cloud servers. Real-time feedback and personalized training advice are provided through a graphical user interface (GUI). Technical Implementation and Simulation: Software such as MATLAB/Simulink is used for system modeling and simulation to validate feasibility. machine learning algorithms are developed for action recognition and health monitoring, optimizing model parameters and conducting validation. Performance Evaluation: Model performance is evaluated using metrics like confusion matrices, accuracy, recall rate, and F1 scores. User feedba

关键词： Heart rate Accuracy System performance signal processing algorithms Computer architecture Cameras Real-time systems Motion capture Biomedical monitoring Monitoring

来源：评论

学校读者我要写书评

暂无评论

Morphological Segmentation with Modified Otsu’s Method and Multi-Scale Morphological processing for Shape Recognition

Morphological Segmentation with Modified Otsu’s Method and ...

引用

Innovations in High Speed Communication and signal processing (IHCSP), international conference on

作者： Manish Nagpal N.T. Velusudha Deepak Minhas Supriya Rai Ashwini Ranjit Nawadkar D. Bhanu Centre of Research Impact and Outcome Chitkara University Punjab India Department of ECE Prince Shri Venkateshwara Padmavathy Engineering College Chennai India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India School of Mangement UG ManagementJAIN (Deemed to be University) Bangalore Karnataka India AI & Ds Vishwakarma Institute of Technology Pune India Department of Information Technology Karpagam Institute of Technology Coimbatore India

ISBN: (数字)9798350368949

ISBN: (纸本)9798350368956

Motological segmentation is essential in the domains of medical imaging, object recognition, and remote sensing. Classical approaches, such as Otsu's thresholding, fail miserably in the presence of noise, light, and complex backgrounds. These concerns are addressed by creating Modified Otsu's Method (MOM). Slow and precise segmentation, adaptive thresholding, and morphological processes are two new areas that MOM aims to tackle. The proposed MOM makes both local and global adjustments taking into account the image and text in order to mitigate the impact of variations in light intensity and noise level. Accurate segmentation and less noise artefacts are achieved by the use of dilation and erosion. On datasets including medical, nature, and remote sensing images, the suggested MOM algorithm achieves better results than previous top-tier segmentation approaches as well as Otsu's approach to generic thresholding based on experimental quantities. This study investigates the optimal execution time of the method for image processing in real time in terms of computing cost. Automated safety devices and medical imaging analysis are two examples of applications where MOM stands out for its exceptional performance in picture segmentation. Therefore, in order to make MOM more versatile and effective in a wide range of imaging contexts, future studies will use machine learning methods.

关键词： Image segmentation Accuracy Thresholding (Imaging) Noise Real-time systems Object recognition Method of moments Remote sensing Biomedical imaging Noise level

来源：评论

学校读者我要写书评

暂无评论

Radar signal Modulation Recognition Based on Bispectrum Features and Deep learning 2

Radar Signal Modulation Recognition Based on Bispectrum Feat...

引用

2nd international conference on Computer Engineering and Application, ICCEA 2021

作者： Dong, Zeyu Lv, Fengrong Wan, Tao Jiang, Kaili Fang, Xueli Zhang, Lei University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu China Key Laboratory of Complex Aviation Simulation System Beijing China

ISBN: (纸本)9781665426169

signal bispectral transformation can not only suppress the influence of Gaussian white noise on signal modulation recognition, but also retain the signal amplitude and phase information. It is also used to extract the non-linear characteristics. Compared with other high-order spectra, bispectrum has a simple processing flow. However, the direct use of all bispectrum as signal features will lead to two-dimensional template matching, causing lots of calculations. Converting two-dimensional bispectrum into one-dimensional sequence, for example, extracting slice information of bispectrum, or using integral bispectrum apparently reduce the amount of data to be processed while retaining part of the bispectrum information. We input the extracted bispectral transformation of radar signals into the neural network to realize modulation recognition. The simulations validate our conclusions that our proposed methods still have a high recognition probability while SNR is low. © 2021 IEEE.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

Analysis of Urban Social Electricity Consumption Based on Neural Network and SHAP Model

Analysis of Urban Social Electricity Consumption Based on Ne...

引用

signal processing, Communications and Engineering Management conference (ISPCEM), international

作者： Changquan Gu Hongyi Liu Boyang Ou School of Intelligent Systems Science and Engineering Jinan University Zhuhai China School of Computer Science Qufu Normal University Jining China School of Computer and Information Technology Beijing Jiaotong University Beijing China

Neural networks have been applied in analyzing the influencing factors of electricity consumption in residential households nationwide and have achieved good results in electricity consumption prediction. However, the invisibility of the decision-making process of the neural network system leads to its inability to get a good solution in explaining the influencing factors. It was found that the interpretability of BP neural network was 0.902, compared with 0.847 of FEM model, and the SHAP model gave the marginal contribution of each feature. Also, among the features affecting electricity consumption, household water consumption, retail sales of consumer goods, and education expenditure have important values for residential household electricity consumption. In this paper, we discuss the application of neural networks in the factors affecting residential household electricity consumption from the perspective of interpretability, and innovatively introduce the SHAP interpretation method to study the important indicators in the rating, which is important for the research in the field of residential household electricity consumption.

关键词： Support vector machines Water Analytical models Neural networks Education machine learning signal processing

来源：评论

学校读者我要写书评

暂无评论

BootstrapNet: An Contrastive learning Model for Sleep Stage Scoring based on Raw Single-Channel Electroencephalogram 2

BootstrapNet: An Contrastive Learning Model for Sleep Stage ...

引用

2nd international conference on Artificial Intelligence and Computer Engineering, ICAICE 2021

作者： Mai, Xun Yu, Tianyou Coll. of Automation Sci. & Eng. South China University of Technology Guangzhou China

ISBN: (纸本)9781665421867

Sleep plays a critical role in promoting health. Sleep stage scoring is fundamental for sleep assessment and disease diagnosis. However, most of the existing sleep staging methods are require supervised learning to train feature extractors. To avoid the over-fitting problem, these models require a great quantity of manual label data to train. But labeling the recorded signals can be costly in terms of specialized expertise and human processing time. This article proposes a contrastive learning model called BootstrapNet, using convolutional encoders for extracting high-level feature representation from raw single-channel EEGs. Unlike previous contrastive learning methods, BootstrapNet does not require the label of the signal and is an effective and scalable approach to train encoder with a large set of unlabelled data. Specifically, we explored the influence of different data augmentation on this contrastive learning model suitable and valid data augmentation method was found. And we optimized the network architecture, significantly reduces the number of network parameters without losing accuracy. Experiments using all labeled data achieve 85.5% accuracy on the Sleep-EDF-39 dataset, matching the performance of TinySleepNet. When lowering the amount of labeled data to 1%, BootstrapNet still achieves 77.5% accuracy on the Sleep-EDF-39 dataset, matching the performance of a supervised methods SVM. Experimental results demonstrate that the self-supervised model is outperforming the same supervised model. It is noteworthy that in comparison to the existing deep learning models, our model has the least number of parameters(0.35M). © 2021 IEEE.

关键词： Electroencephalography

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135页 << < 53 54 55 56 57 58 59 60 61 62 > >>

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：