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

3,259 篇 会议
56 册 图书
24 篇 期刊文献

馆藏范围

3,339 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,736 篇 工学
- 1,337 篇 计算机科学与技术...
- 1,225 篇 软件工程
- 212 篇 控制科学与工程
- 210 篇 信息与通信工程
- 197 篇 电气工程
- 153 篇 机械工程
- 135 篇 材料科学与工程（可...
- 132 篇 安全科学与工程
- 127 篇 生物工程
- 126 篇 生物医学工程（可授...
- 94 篇 土木工程
- 93 篇 交通运输工程
- 85 篇 建筑学
- 79 篇 动力工程及工程热...
- 75 篇 电子科学与技术（可...
- 70 篇 化学工程与技术
- 62 篇 力学（可授工学、理...
709 篇 理学
- 498 篇 数学
- 173 篇 统计学（可授理学、...
- 131 篇 生物学
- 115 篇 物理学
- 113 篇 系统科学
- 60 篇 化学
390 篇 管理学
- 281 篇 管理科学与工程(可...
- 172 篇 图书情报与档案管...
- 128 篇 工商管理
94 篇 医学
- 86 篇 基础医学(可授医学...
- 81 篇 临床医学
56 篇 经济学
- 56 篇 应用经济学
52 篇 教育学
- 51 篇 教育学
43 篇 法学
32 篇 农学
6 篇 文学
5 篇 军事学
1 篇 艺术学

主题

971 篇 predictive model...
282 篇 accuracy
268 篇 data models
240 篇 computational mo...
208 篇 analytical model...
182 篇 prediction algor...
149 篇 training
138 篇 software enginee...
136 篇 feature extracti...
121 篇 software
120 篇 machine learning
118 篇 deep learning
108 篇 forecasting
105 篇 neural networks
103 篇 adaptation model...
84 篇 optimization
83 篇 machine learning...
82 篇 mathematical mod...
75 篇 real-time system...
62 篇 support vector m...

机构

10 篇 school of inform...
7 篇 national enginee...
7 篇 hubei key labora...
7 篇 school of electr...
7 篇 school of automa...
6 篇 school of comput...
6 篇 school of softwa...
6 篇 school of electr...
6 篇 engineering rese...
5 篇 school of comput...
5 篇 school of transp...
5 篇 nanjing univ sta...
5 篇 chitkara univers...
5 篇 school of softwa...
4 篇 school of inform...
4 篇 naval university...
4 篇 school of manage...
4 篇 school of softwa...
4 篇 software enginee...
4 篇 school of electr...

作者

8 篇 labiche yvan
7 篇 hassan ahmed e.
7 篇 menzies tim
5 篇 yang yang
5 篇 mcintosh shane
5 篇 chen li
5 篇 ziadi tewfik
5 篇 yan wang
4 篇 yu wang
4 篇 ming li
4 篇 liu yang
4 篇 hall tracy
4 篇 xintian liu
4 篇 bowes david
4 篇 monden akito
4 篇 min wu
4 篇 matsumoto ken-ic...
4 篇 yu zhang
4 篇 lei zhang
4 篇 briand lionel c.

语言

3,043 篇 英文
285 篇 其他
25 篇 中文
1 篇 俄文

检索条件"任意字段=Proceedings of the 6th International Conference on Predictive Models in Software Engineering"

共 3339 条记录，以下是841-850 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：

Prediction of SOC Values for Sodium Batteries by Using the GRU and BiGRU Network models

Prediction of SOC Values for Sodium Batteries by Using the G...

引用

Energy Systems and Electrical Power (ICESEP), international conference on

作者： Fuliang Cheng Xuan Wu Peng Li Liqian Qi Guangxi University of Science and Technology School of Mechanical and Automotive Engineering Liuzhou China

ISBN: (数字)9798350353563

ISBN: (纸本)9798350353570

To enhance the predicted accuracy of state of charge (SOC) values, this paper proposes the gated recurrent unit (GRU) network model and bidirectional gated recirculation unit (BiGRU) network model to predict the SOC values of sodium batteries. the dynamic characteristics of sodium batteries were measured under two operation conditions (DST and FUDS) to collecting the training data and test data. Here, the values of voltage and current are the input parameters and the SOC values are the output results. the comparison results indicate that the BiGRU network model is more accurate than the GRU network model. the RMSE value and MAE value can be decreased to 32.28% and 17.77% by using the BiGRU network model. therefore, the BiGRU network model can improve the prediction accuracy of SOC values for sodium batteries.

关键词： Accuracy Fluctuations Sodium Neural networks Estimation predictive models Logic gates

来源：评论

学校读者我要写书评

暂无评论

Traffic Flow Prediction Based on Delayed Attention Neural Ordinary Differential Equation

Traffic Flow Prediction Based on Delayed Attention Neural Or...

引用

Frontiers Technology of Information and Computer (ICFTIC), IEEE international conference on

作者： Xin Zhao Li Lan School of Electronic and Information Engineering Lanzhou Jiaotong University Lanzhou China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

To address the issues of delayed effects and insufficient exploration of spatiotemporal correlation characteristics in traffic flow prediction, a dynamic graph neural delay differential equation model is proposed to improve prediction accuracy. First, traffic flow features across different periods are extracted. Next, the delay time between upstream and downstream roads is calculated, and a delay differential equation is introduced to capture the time-lagged characteristics among nodes in the road network. Finally, validation on real-world public traffic flow datasets, including PEMS04 and PEMS08, demonstrates that the proposed model achieves an average reduction of approximately 35% in mean absolute error (MAE) and 27% in root mean square error (RMSE).

关键词： Accuracy Roads predictive models Ordinary differential equations Feature extraction Mathematical models Delays Trajectory Spatiotemporal phenomena Root mean square

来源：评论

学校读者我要写书评

暂无评论

the Impact of Temporal Contrastive Learning on Self-Supervised Action Recognition

The Impact of Temporal Contrastive Learning on Self-Supervis...

引用

international conference on Computational Intelligence and Networks (CINE)

作者： Vaidehi Gupta Vaibhav Sahay Rajat Kumar Behera School of Computer Engineering Kalinga Institute of Industrial Technology Odisha India

ISBN: (数字)9798331516796

ISBN: (纸本)9798331516802

Action recognition in videos is a crucial task in computer vision with applications in video surveillance, humancomputer interaction, and robotics. Traditional supervised learning methods often require extensive label data, which can be a major obstacle in practice due to their expense and timeconsuming tendencies. Self-supervised learning (SSL) can serve as a promising method for action recognition in video data and thus be an efficient cure to this issue. Self-supervised learning is built upon the concept of unsupervised learning but it instead tries to understand the unlabelled data fed to it on the very first iteration to generate signals that it can understand as supervisory signals. this work thus explores various SSL techniques to train models that can efficiently capture the temporal evolution of actions in video without relying on the sedated recorded data. this research contributes to the field by improving the performance of SSL and opening the way to develop more efficient and scalable models for video understanding tasks for future studies in the said area.

关键词： Training Analytical models Computer vision Statistical analysis Supervised learning Contrastive learning predictive models Video surveillance Unsupervised learning Videos

来源：评论

学校读者我要写书评

暂无评论

An Optimization Method for Short-Term Power Load Forecasting Based on IPSO-SVM

An Optimization Method for Short-Term Power Load Forecasting...

引用

Energy Systems and Electrical Power (ICESEP), international conference on

作者： Yaguang Shi Shaopeng Wang Haoran Huang Yingchun Yang Lijun Zhang China Electrical Equipment Xuji Electric Zhengzhou R&D Zhengzhou China China Electrical Equipment Xuji Electrical Software Company Xuchang China China Mobile Online Marketing Service Center Zhengzhou China

ISBN: (数字)9798350353563

ISBN: (纸本)9798350353570

To improve the accuracy of short-term power load forecasting, this paper presents an optimization method for short-term power load forecasting, which is based on Improved Particle Swarm Optimization algorithm and Support Vector Machine(IPSO-SVM) combined forecasting model to forecast power load, and constructs a complete short-term power load forecasting model. Compared with traditional PSO-SVM, the optimized IPSO-SVM prediction model has higher prediction accuracy, which has important practical reference value in the research of power load prediction, and provides a new method path for the field of power load forecasting.

关键词： Accuracy Load forecasting predictive models Prediction algorithms Search problems Vectors Space exploration

来源：评论

学校读者我要写书评

暂无评论

Application of Logic Control and predictive PID Control in Smart Grid Dispatching and Decision Making

Application of Logic Control and Predictive PID Control in S...

引用

Internet of things, Automation and Artificial Intelligence (IoTAAI), international conference on

作者： Zhixin Ou Department of Urban Rail Transit and Information Engineering Anhui Communications Vocational & Technical College Hefei China

ISBN: (数字)9798350386974

ISBN: (纸本)9798350386981

the smart grid dispatching and decision-making system has the characteristics of smart power detection, data cloud storage, and information fusion. the disadvantage is that the difficulty of model estimation is high, significant fluctuations in energy storage and transmission, algorithm update iteration delay, and low accuracy of data fusion technology. First, models and algorithms for smart grids, improve the multiple domain value delay problem of output stability. Second, the nine-point logic control strategy is based on partitioning deviation and deviation variation based on pan Boolean dispatching, effectively solving the frequency and band amplitude issues of power grid transmission load fluctuations. When the integral variable or input signals change, compared with traditional PID control, it is concluded that, just adjusting according to the nine-point logic control strategy, can obtain ideal control and output results. Finally, establishing a simulation model, the results indicate that its control curve performs well in model matching, satisfactory dispatching in case of model mismatch, and ensures that the fluctuation amplitude and error accuracy meet the requirements. the control strategy has the characteristics of a fast output response, high stability and robustness, and a small overshoot for changing power grid models.

关键词： Analytical models Fluctuations PI control predictive models Dispatching Stability analysis Smart grids Logic PD control Load modeling

来源：评论

学校读者我要写书评

暂无评论

Analysis of Clinical Intelligent Diagnosis and Treatment of Hemorrhagic Stroke

Analysis of Clinical Intelligent Diagnosis and Treatment of ...

引用

international conference on Electronic engineering and Informatics (EEI)

作者： Lele Wang Tangju Yuan School of Chongqing Three Gorges University Chongqing China

ISBN: (数字)9798350353594

ISBN: (纸本)9798350353600

Among hemorrhagic stroke cases, acute cerebral hemorrhage conditions account for 10-15% of stroke cases. Its complex etiology is usually triggered by ruptured cerebral aneurysms, abnormalities of cerebral arteries, and other factors that cause blood to enter the brain tissue, resulting in mechanical damage and physiopathological reactions. this disease has an acute onset and rapid progression, the prognosis is usually poor, the mortality rate is high, and patients often suffer from neurological deficits that place a heavy burden on the patient and his/her socio-economy. Extension of the hematoma is one of the risk factors for poor prognosis and can be acutely life threatening. therefore, early identification and prediction of hematoma expansion and edema development are crucial for improving prognosis. Medical imaging and artificial intelligence provide powerful tools for monitoring brain injury [1]. Intelligent diagnostic models can predict poor prognostic risk factors and support personalized treatment.

关键词： predictive models Brain modeling Hemorrhaging Prognostics and health management Informatics Monitoring Brain injuries Blood Diseases Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Research on Factors Affecting Weight Based on Machine Learning Algorithm

Research on Factors Affecting Weight Based on Machine Learni...

引用

Robotics, Intelligent Control and Artificial Intelligence (RICAI), international conference on

作者： Rujuan Huang Qunqiang Chen Mei Qian Hao Zheng Chen Chen Shixiao Wu School of Information Engineering Wuhan Business University Wuhan China School of Mechanical and Electrical Engineering Wuhan Business University Wuhan China

ISBN: (数字)9798331541699

ISBN: (纸本)9798331541705

In view of the increasing prevalence of overweight and obesity in Chinese residents, in order to explore the factors affecting weight, three machine learning models based on logical regression algorithm, decision tree algorithm and random forest algorithm are constructed to explore the factors affecting weight. the model is continuously optimized by parameters and cross-validation, and the performance of the model is evaluated by using four indicators: accuracy, precision, recall and the harmonic average of the two. the results show that the accuracy of logistic regression algorithm, decision tree algorithm and random forest algorithm are 0.65, 0.75 and 0.8 respectively, which shows that the decision tree algorithm and random forest algorithm can better complete the classification and prediction of weight influencing factors, and the random forest algorithm has the best classification and prediction effect, which can be used for researchers and practitioners in the field of nutrition and health reference.

关键词： Logistic regression Visualization Machine learning algorithms Accuracy predictive models Prediction algorithms Harmonic analysis Classification algorithms Random forests Robots

来源：评论

学校读者我要写书评

暂无评论

Detection of Contradictions and Inconsistencies in German Regulatory Documents

Detection of Contradictions and Inconsistencies in German Re...

引用

Natural Language Processing (ICNLP), international conference on

作者： Gerrit Schumann Jorge Marx Gómez Dept. of Business Informatics University of Oldenburg Oldenburg Germany

ISBN: (数字)9798350349115

ISBN: (纸本)9798350349122

Companies create regulatory documents, such as policies, guidelines, or instructions, to define their processes and structures. these documents are used by employees to ensure the proper execution of processes and by auditors to assess the conformity of processes. Nowadays, companies are constantly updating these documents due to various internal and external factors, which can lead to inconsistencies and contradictions. the detection of such cases is difficult, especially in German regulatory documents with a non-controlled natural language, as these have a high lexical and syntactic complexity. To address this challenge, this paper aims to develop a classifier for the detection of contradictions and inconsistencies specifically for German regulatory documents covering different topics. To this end, the paper describes several rules for the annotation of a corresponding dataset, its resulting characteristic properties and the classification quality that can be achieved when using the dataset for fine-tuning different Bert models (up to an accuracy of 0.8473).

关键词： Accuracy Annotations Semantics Companies predictive models Syntactics Natural language processing Prompt engineering Tuning Guidelines

来源：评论

学校读者我要写书评

暂无评论

Detection of Alzheimer's Disease using Deep Learning: An Optimized Approach

Detection of Alzheimer's Disease using Deep Learning: An Opt...

引用

international conference on Intelligent Autonomous Systems (ICoIAS)

作者： Gulnaz Ahmed Meng Joo Er Shahid Zikria Muhammad Sadiq Fareed Institute of Artificial Intelligence and Marine Robotics Dalian Maritime University Dalian China Department of Software Engineering Software Engineering Institute of Guangzhou Guangzhou China

this paper suggests a new CNN that requires just a few parameters to diagnose AD and is perfect for training on smaller datasets. Compared to existing state-of-the-art models, the proposed model uses a more optimized technique to identify the early stages of Alzheimer's disease. the image is sharpened and normalized as part of the preparation phase to help the model learn more quickly and succinctly. We used a bespoke CNN model that makes precise predictions with minimum parameters. Five Convolutional layers and three fully connected layers, which have equally learned samples from each class, make up the proposed model. the approach was compared using a variety of accuracy metrics, such as accuracy, AUC, precision, recall, and Fl-Score, as well as categorical cross-entropy loss, self, and other comparisons. To accurately forecast the method, several trials were carried out. the values for the evaluation measures are as follows: accuracy, AUC, precision, recall, fl-score, and loss are 99.95%, 99.99%, 99.97%, 99.95%, and 0.0016 respectively. According to simulation results, the proposed model performs better than existing cutting-edge models in all evaluation metrics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vehicle and Pedestrian Fast Detection based on YOLO-FPN

Vehicle and Pedestrian Fast Detection based on YOLO-FPN

引用

software engineering and Computer Science (CSECS), international conference on

作者： Juan Du Cunqian Feng Wenxiong Cheng Wei Tan Jia Li Qian Cheng Xiuyi Zhang Department of Basic Air Force Engineering University Xi'an China Air Defense and Missile Defense College Air Force Engineering University Xi'an China Beijing Mechano-Electronic Engineering Institute Beijing China

An unbalanced accuracy and computational cost exist within the YOLO series object detection algorithms, as well as a lack of generalization in the models. To address these issues, we propose YOLO-Day Night and Fast, a highly accurate and fast vehicle and pedestrian detection model based on YOLO that is capable of detecting both vehicles and pedestrians across a wide range of lighting conditions. the purpose of this paper is to investigate the effects of convolutional structure and network depth on the ability of the Backbone to extract features and its calculation cost in comparison to mainstream detection models that use convolutional neural networks. In this paper, we propose a low-cost ACNet network that has a high feature extraction capability. We select Arrow-Blocks and CSP-Blocks to represent different levels of the network, and determine network depth by quantifying the computational cost of stacked units. A data enhancement strategy of HSV domain perturbation and luminance processing has also been developed to improve the detection accuracy of the model and to alleviate the problem of insufficient generalization of the model. Furthermore, differences in luminosity between daytime and nighttime images are taken into account in the experiments. the experimental results indicate that the proposed model achieves 32.8% detection accuracy of full time mAP at 24.36 frames per second after training using the SODA10M dataset containing only daytime images, which is higher than the current mainstream detection models in terms of detection accuracy and speed. the nighttime accuracy reached 27.7%, which improved the nighttime detection capability of the model and extended the detection application scenarios of the model.

关键词：

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334页 << < 81 82 83 84 85 86 87 88 89 90 > >>

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：