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

554 篇 会议
8 册 图书
2 篇 期刊文献

馆藏范围

564 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

386 篇 工学
- 370 篇 计算机科学与技术...
- 246 篇 软件工程
- 61 篇 信息与通信工程
- 58 篇 生物工程
- 43 篇 生物医学工程（可授...
- 28 篇 电气工程
- 25 篇 控制科学与工程
- 18 篇 化学工程与技术
- 13 篇 机械工程
- 13 篇 光学工程
- 13 篇 农业工程
- 13 篇 安全科学与工程
161 篇 理学
- 106 篇 数学
- 61 篇 生物学
- 57 篇 系统科学
- 39 篇 统计学（可授理学、...
- 20 篇 物理学
- 13 篇 化学
- 9 篇 大气科学
95 篇 管理学
- 52 篇 图书情报与档案管...
- 47 篇 管理科学与工程(可...
- 24 篇 工商管理
42 篇 医学
- 42 篇 临床医学
- 41 篇 基础医学(可授医学...
- 29 篇 药学(可授医学、理...
- 15 篇 公共卫生与预防医...
18 篇 农学
- 18 篇 作物学
15 篇 法学
- 11 篇 社会学
10 篇 教育学
- 10 篇 教育学
9 篇 经济学
- 9 篇 应用经济学

主题

116 篇 machine learning
50 篇 deep learning
44 篇 machine learning...
38 篇 accuracy
35 篇 support vector m...
21 篇 predictive model...
20 篇 security
18 篇 data models
15 篇 adversarial mach...
15 篇 feature extracti...
15 篇 random forests
15 篇 prediction algor...
15 篇 training
14 篇 decision trees
14 篇 classification a...
14 篇 forecasting
13 篇 computational mo...
12 篇 internet of thin...
12 篇 information tech...
11 篇 real-time system...

机构

3 篇 faculty of compu...
2 篇 faculty of compu...
2 篇 infologia techno...
2 篇 kindi center for...
2 篇 centre of resear...
2 篇 department of co...
2 篇 graphic era hill...
2 篇 greater bay area...
2 篇 vellore institut...
2 篇 department of ar...
2 篇 school of comput...
2 篇 department of ma...
2 篇 chitkara centre ...
2 篇 fraunhofer cente...
2 篇 department of co...
2 篇 sreyas institute...
2 篇 school of comput...
2 篇 ipmi internation...
2 篇 al-farabi kazakh...
2 篇 department of ma...

作者

6 篇 azar ahmad taher
3 篇 bhatnagar roheet
3 篇 foozy cik feresa...
3 篇 ammar hossam has...
2 篇 valeeva elvira
2 篇 khan ayub
2 篇 santos igor
2 篇 varun ojha
2 篇 shreya
2 篇 bringas pablo ga...
2 篇 kurniawan r.
2 篇 maragatharajan m...
2 篇 usha g.
2 篇 singh shikha
2 篇 xiao kai
2 篇 cao peng
2 篇 shyamala devi m.
2 篇 nazri m.z.a.
2 篇 m. maragatharaja...
2 篇 swathi p.

语言

544 篇 英文
18 篇 其他
2 篇 中文

检索条件"任意字段=4th International Conference on Machine Learning and Soft Computing, ICMLSC 2020"

共 564 条记录，以下是31-40 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：

Optimizing Speed and Accuracy Trade-off in machine learning Models via Stochastic Gradient Descent Approximation 9

Optimizing Speed and Accuracy Trade-off in Machine Learning ...

引用

9th international conference on soft computing and machine Intelligence (ISCMI)

作者： Catapang, Jasper Kyle Univ Birmingham Dept English Language & Linguist Birmingham England

ISBN: (纸本)9798350320886

Stochastic gradient descent (SGD) is a widely used optimization algorithm for training machine learning models. However, due to its slow convergence and high variance, SGD can be difficult to use in practice. In this paper, the author proposes the use of the 4th order RungeKutta-Nystrom (RKN) method to approximate the gradient function in SGD and replace the Newton boosting and SGD found in XGBoost and multilayer perceptrons (MLPs), respectively. the new variants are called ASTRA-Boost and ASTRA perceptron, where ASTRA stands for "AccuracySpeed Trade-off Reduction via Approximation". Specifically, the ASTRA models, through the 4th order RungeKutta-Nystrom, converge faster than MLP with SGD and they also produce lower variance outputs, all without compromising model accuracy and overall performance.

关键词： stochastic gradient descent Runge-KuttaNystrom Runge-Kutta XGBoost gradient approximation

来源：评论

学校读者我要写书评

暂无评论

Investigation on Leveraging Optimal machine learning Models for Air Quality Assessment to Promote Environmental Health and Sustainability 4

Investigation on Leveraging Optimal Machine Learning Models ...

引用

4th international conference on soft computing for Security Applications, ICSCSA 2024

作者： Silpa, N. Sravanthi, Potuluri Maheswara Rao, V.V.R. Swain, Sangram Keshari Reddy, Shiva Shankar Kurada, Ramachandra Rao Shri Vishnu Engineering College for Women Department of C.S.E. Bhimavaram India Centurion University of Technology and Management Department of C.S.E. Bhubaneswar India S.R.K.R. Engineering College Department of C.S.E. Bhimavaram India

ISBN: (纸本)9798331515720

Air Quality is of paramount importance since it directly impact on the welfare of individuals, environmental sustainability, along with their general wellness. Poor air quality, characterized by high levels of pollutants, contributes to respiratory diseases, cardiovascular issues, and other health concerns. Additionally, it impacts ecosystems, climate patterns, and visibility. Monitoring and maintaining good air quality are crucial for safeguarding public health, preserving the environment, and fostering sustainable living conditions for present and future generations. machine learning models are crucial for finding air quality as they offer advanced tools to analyze complex datasets, model intricate relationships, and enhance prediction accuracy with a specific emphasis on Extreme Gradient Boosting (XGBoost) an efficient gradient algorithm renowned for handling complex datasets. Additionally, the research investigates attribute selection methods to identify influential features impacting air quality. the proposed approach ensures the identification of key attributes that significantly contribute to the accuracy of air quality predictions, thereby enhancing the sophistication and focus of the modelling process. the proposed methodology involves obtaining and preparing data from an open-source dataset, followed by meticulous curation, classification, and analysis using machine learning models. the robust capability of XGBoost to capture intricate relationships within air quality data, evidenced by its high accuracy, underscores its reliability as a predictive model for real-world air quality forecasting. © 2024 IEEE.

关键词： Air Quality Assessment Environmental Health Extreme Gradient Boosting Feature Engineering Feature Selection machine learning

来源：评论

学校读者我要写书评

暂无评论

Power Efficiency Enhancement in 5G HetNets Using Adaptive BPSO and Classification Trees 4

Power Efficiency Enhancement in 5G HetNets Using Adaptive BP...

引用

4th international Mobile, Intelligent, and Ubiquitous computing conference

作者： Osama, Mayada Misr Int Univ Fac Engn Sci & Arts Elect & Commun Dept Cairo Egypt

ISBN: (纸本)9798350367782;9798350367775

the exponential demand for multimedia services is one contributing factor to the significant increase in mobile data traffic. Consequently, the overloaded Macro Cells (MCs) are incapable of guaranteeing high Quality of Service (QoS) for every User Equipment (UE). Heterogeneous Networks (HetNets) comprised of Small Cells (SCs) and MCs is an auspicious solution to overcome this problem. Unfortunately, a critical challenge of the dense deployment of SCs in 5G HetNets is the co-tier interference between them. To enhance the power-efficiency in 5G HetNets, exploiting machine learning (ML) approaches is proposed in this paper. Adaptive Binary Particle Swarm Optimization (A-BPSO) algorithm is presented in this paper for turning the SCs on&off to alleviate the power consumption of the system. Additionally, a soft Frequency Reuse (SFR) scheme is proposed exploiting Classification Trees (CTs) in order to mitigate the interference and ameliorate the overall network throughput. the results demonstrate that the proposed scheme surpasses the other conventional schemes in terms of the overall throughput and the power-efficiency of the network.

关键词： 5G HetNets Adaptive BPSO (A-BPSO) Classification Trees (CTs) soft Frequency Reuse (SFR) Small Cells (SCs)

来源：评论

学校读者我要写书评

暂无评论

Differential diagnosis of radiation encephalopathy and post-radiation brain tumor recurrence by machine learning models based on contrast-enhanced MRI 4

Differential diagnosis of radiation encephalopathy and post-...

引用

4th international conference on Bioinformatics and Intelligent computing (BIC)

作者： Li, Te Wang, Lingfei Wang, Xi Sun, Hong Zhejiang Police Vocat Acad Dept Secur & Precaut Hangzhou Peoples R China Hangzhou Med Coll Dept Oncol 903 Hosp PLA Joint Logist Support Force Xi Hu Affiliated Hosp Hangzhou Peoples R China

ISBN: (纸本)9798400716645

Purpose: Discriminating radiation encephalopathy (REP) from brain tumor recurrence is often difficult. this study aims to develop and validate an approach to distinguish REP from post-radiation brain tumor recurrence using machine learning. Methods: this study involved 102 patients diagnosed and treated in our institution between 2020 and 2023. A total of 2153 radiomics features were extracted from contrast-enhanced MRI by using 3D-Slicer software and Pycharm platform. Nine diagnostic models were built and compared based on three selection methods and three classification algorithms. the sensitivity, specificity, accuracy, and area under curve (AUC) of each model were calculated, and based on these the optimal model was chosen. Results: the least absolute shrinkage and selection operator with correlation (LASSO+corr) was chosen as the optimal selection method, which selected 17 important radiomics features. the most promising model was a combination of LASSO+corr as the selection method and logistic regression (LR) as the classification algorithm. the combination models of LASSO+corr with LR, random forest (RF) and support vector machine (SVM) showed sensitivities of 0.88, 0.86 and 0.97, and specificities of 0.98, 0.93 and 0.90 with AUC of 0.9805, 0.9452 and 0.9743, respectively. Conclusion: Radiomics-based machine learning has potential to be utilized in differentiating REP from recurrent brain tumor after radiotherapy accurately.

关键词： Radiation encephalopathy (REP) brain tumor radiomics machine learning differential diagnosis

来源：评论

学校读者我要写书评

暂无评论

Risk Analysis of Enterprise Cross-network Data via DAE-BiLSTM and Fuzzy Bayesian Network 4

Risk Analysis of Enterprise Cross-network Data via DAE-BiLST...

引用

4th international conference on Intelligent Communications and computing

作者： Li, Wei Li, Jianjun Shan, Yuxiang Li, Junjie Nie, Guibing China Tobacco Zhejiang Ind Co Ltd Informat Ctr Hangzhou Peoples R China Zhejiang Univ Sch Engn Hangzhou Peoples R China Hangzhou DBAPPSecur Co Ltd Hangzhou Peoples R China

ISBN: (纸本)9798331530372;9798331530365

With the increasing severity of enterprise information security issues, the identification and evaluation of cross-network data risk has become one of the essential technologies to safeguard enterprise data and network security. However, traditional rule-based or signature-based anomaly detection methods are increasingly unable to cope with the complex and evolving forms of attacks, necessitating more intelligent and flexible detection mechanisms to counter these constantly changing threats. To address this, a method integrating denoising autoencoder (DAE) and bidirectional long short-term memory network (BiLSTM) is first proposed for monitoring the enterprise cross-network data traffic and identify the occurring abnormal risks. On this basis, we use a fuzzy Bayesian network to effectively measure these known abnormal risks. In the end, experimental results demonstrate that the proposed method outperforms traditional machine learning algorithms and other deep learning models across various evaluation metrics, exhibiting high accuracy and efficiency.

关键词： network security cross-network data risk analysis deep learning

来源：评论

学校读者我要写书评

暂无评论

DGE-GSIM: A multi-task dual graph embedding learning for graph similarity computation 2022

DGE-GSIM: A multi-task dual graph embedding learning for gra...

引用

6th international conference on machine learning and soft computing (icmlsc)

作者： Tan, Wenhui Cao, Peng Jin, Zhiyong Luo, Futao Wen, Guangqi Li, Weiping Northeastern Univ Comp Sci & Engn Key Lab Intelligent Comp Med Image Minist Educ Shenyang Peoples R China Northeastern Univ Comp Sci & Engn Shenyang Peoples R China Peking Univ Sch Software & Microelect Beijing Peoples R China

ISBN: (纸本)9781450387477

Graph similarity estimation is a challenging task due to the complex graph structure. To achieve an exact similarity estimation for input graphs, two critical factors are how to learn an appropriate graph embedding and how to compute the similarity between a pair of graphs. Graph neural networks (GNN) generalize convolutional neural networks (CNN) to graph data for learning graph embeddings. However, the GNN models ignore the edge information when earning graph embeddings. To solve it, we propose a graph similarity estimation framework by taking into consideration the edge feature learning during the graph embedding learning. We name our approach as DGE-GSIM, i.e., Dual Graph Embedding for Graph SIMilarity learning. More specifically, we firstly construct an edge graph with node-edge switching, and then we propose a multi-task learning framework for learning a dual graph embedding with simultaneously considering the node and edge features with GNN. Finally, with the obtained dual graph embedding, we develop a three-way graph similarity computation from the perspectives of the graph-graph interaction, node-node interaction and node-graph interaction. It can model a comprehensive similarity for input graphs. We conduct extensive experiments on a very popular graph similarity/distance metric, GED, based on Linux dataset to demonstrate the effectiveness of the proposed method.

关键词： Graph similarity Graph convolution networks Multi-task learning Attention

来源：评论

学校读者我要写书评

暂无评论

A Traffic Sign Recognition Method Based on YOLOv5 Deep learning Algorithm 23

A Traffic Sign Recognition Method Based on YOLOv5 Deep Learn...

引用

7th international conference on machine learning and soft computing, icmlsc 2023

作者： Tang, Yinqing Yu, Benguo Wang, Anran Liu, Fengning Hainan Medical University China

ISBN: (纸本)9781450398633

Aiming at the problems of low accuracy and slow recognition efficiency of the traditional traffic sign recognition algorithm in complex environment, a deep learning traffic sign recognition method based on YOLOv5 is proposed. Firstly, the Chinese traffic sign data set TT100K is randomly divided into training set and test set. Convolutional neural network YOLOv4 and convolutional neural network YOLOv5 are used to train respectively on the training set, so as to build the prediction model of traffic signs. then the trained model is validated on the test set. through the evaluation of the experimental, it is found that compared with YOLOv4 model, YOLOv5 model has higher recognition accuracy and faster recognition speed. © 2023 ACM.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Scheme of Reducing Read Latency in NAND Flash by Integrating Duplications and soft Decoding 2022

A Hybrid Scheme of Reducing Read Latency in NAND Flash by In...

引用

6th international conference on machine learning and soft computing (icmlsc)

作者： Zhang, Yaofang Li, Peixuan Xie, Ping Normal Univ Coll Comp Qinghai Xining 810016 Peoples R China State Key Lab Tibetan Intelligent Informat Proc & Xining 810016 Peoples R China Key Lab Internet Things Qinghai Prov Xining 810016 Peoples R China Acad Plateau Sci & Sustainabil Xining 810016 Peoples R China

ISBN: (纸本)9781450387477

the continuous development of the technology scale has made the storage density of NAND flash memory larger and larger, and its reliability has become lower and lower. therefore, reliability has become an issue of concern to everyone. In order to alleviate reliability problems caused by technological expansion, LDPC codes are widely used in flash memory to provide high error correction capabilities. However, the decoding methods of LDPC codes are divided into hard decoding and soft decoding. the LDPC code is directly used and as the quantization level of soft decoding increases, the delay caused to the Solid-State Drive is also increasing. Taking into account the characteristics of the quantization level of LDPC soft decoding, this paper proposes a new method IDSD, which combines duplications and LDPC soft decoding. this scheme is mainly for hot data. While reading the data, it needs to be based on the quantization level of the record. Use the duplications or soft decoding method to correct the erroneous data. When the quantization level of LDPC soft decoding reaches one, it needs to read the data in the duplications at this time. this method reduces the reading of the Solid-State Drive. Take the delay and improve the average response time. Experimental results show that compared with the original scheme, the average response delay time of the IDSD scheme is increased by 5%-30%, and compared with the traditional refresh scheme, it is increased by 1%-30%.

关键词： LDPC duplications NAND flash quantization level soft decoding

来源：评论

学校读者我要写书评

暂无评论

A real time video object tracking method for fish 2022

A real time video object tracking method for fish

引用

6th international conference on machine learning and soft computing (icmlsc)

作者： Gong, Longqin Hu, Zhuhua Zhou, Xiaoyi Hainan Univ Sch Comp Sci & Technol Haikou Peoples R China Hainan Univ Sch Informat & Commun Engn Haikou Peoples R China Hainan Univ Sch Cyberspace Secur Sch Cryptol Haikou Peoples R China

ISBN: (纸本)9781450387477

Fish behavior is an important indicator of water quality in smart aquaculture. the change of fish behavior can timely and effectively reflect the change of water quality. However, for the fish behavior tracking, existing tracking methods still face challenges in tracking accuracy, tracking efficiency and self-adaptive tracking. In this paper, by optimizing Yolov4-tiny detector and Sort tracker, a real-time fish behavior tracking scheme based on tracking-by-detection structure is proposed. Firstly, in the detection stage, the RFB (Receptive Field Block) module is added in Yolov4-tiny network. the new detector can integrate the features of different scales and expand the receptive field, which can greatly improve the detection accuracy of large object. Secondly, in the matching stage, according to the characteristics of fish behavior, we optimize the Sort (Simple Online and Realtime Tracking) algorithm by removing the Kalman filter module (named Simple-Sort). Finally, a new fish behavior data set with detection box annotation is constructed and published. the experimental results show that compared with Sort algorithm, the proposed tracking scheme improves the MOTA and MOTP indicators by 0.8% and 3.5% respectively for the large scale object. For the other scale object, the MOTA and MOTP indicators increase by 1.5% and 2.1%, respectively.

关键词： Fish behavior tracking Smart mariculture object tracking YOLO deep learning

来源：评论

学校读者我要写书评

暂无评论

Ensemble Approach for Early Prediction of Malnutrition Level of Children: A Case Study on Children Under Five Years Old 4

Ensemble Approach for Early Prediction of Malnutrition Level...

引用

4th international conference on Advanced Research in computing, ICARC 2024

作者： Nirmani, H.M.C. Kudagamage, U.P. Sabaragamuwa University of Sri Lanka Department of Computing and Information Systems Belihuloya Sri Lanka

ISBN: (纸本)9798350384864

Malnutrition refers to inadequate nutritional intake, nutrient imbalances or impaired nutrient utilization which is a global health issue that has a significant effect on children, leading to short-term and long-term consequences for their growth, development and overall well-being. the critical period for a child's growth and development is 1 to 60 months. the early identification of a child's malnutrition status is a strong foundation for lifelong health and well-being. therefore, the objective here is to develop a model for early detection, and prediction of malnutrition in children. this study draws on a sample of 574 children under the age of five years in the Lunugala area, who were chosen randomly to be involved in the development of a predictive model for malnutrition using ensemble learning techniques. After pre-processing the collected sample, the dataset was partitioned into 70% of training set and 30% of testing set. Nine machine learning algorithms, namely Support Vector machine (SVM), Decision Tree (DT), Guassian Naïve Bayes (GNB), Bernoulli Naïve Bayes (BNB), Complement Naïve Bayes (CNB), Logistic Regression (LR), Random Forest (RF), AdaBoost and Extreme Gradient Boosting (XGBoost) were initially used. And the evaluation metrics including accuracy, precision, recall and F-measure were utilized to access the performance of these individual algorithms. After comparing the nine base learners with each other based on accuracy, the three best performing machine learning algorithms were combined and integrated into an ensemble model using techniques such as soft Voting Classifier, Hard Voting Classifier and Stacking Classifier. the evaluation of these ensemble models, also based on accuracy, precision, recall and F-measure revealed that the Stacking Classifier achieved the highest accuracy of 93%. Consequently, the study concludes that the ensemble learning technique is well-suited for better prediction of malnutrition status. © 2024 IEEE.

关键词： learning systems

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57页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：