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

17,168 篇 会议
2,555 篇 期刊文献
141 册 图书

馆藏范围

19,864 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

11,635 篇 工学
- 7,838 篇 计算机科学与技术...
- 6,564 篇 软件工程
- 3,354 篇 信息与通信工程
- 1,984 篇 控制科学与工程
- 1,795 篇 电子科学与技术（可...
- 1,758 篇 电气工程
- 1,230 篇 生物工程
- 1,060 篇 生物医学工程（可授...
- 897 篇 光学工程
- 808 篇 机械工程
- 767 篇 动力工程及工程热...
- 732 篇 仪器科学与技术
- 596 篇 化学工程与技术
- 522 篇 安全科学与工程
- 455 篇 交通运输工程
- 393 篇 材料科学与工程（可...
5,935 篇 理学
- 3,007 篇 数学
- 1,841 篇 物理学
- 1,357 篇 生物学
- 998 篇 统计学（可授理学、...
- 703 篇 系统科学
- 599 篇 化学
2,903 篇 管理学
- 1,826 篇 管理科学与工程(可...
- 1,241 篇 图书情报与档案管...
- 938 篇 工商管理
943 篇 医学
- 810 篇 临床医学
- 756 篇 基础医学(可授医学...
- 464 篇 药学(可授医学、理...
- 428 篇 公共卫生与预防医...
569 篇 法学
- 461 篇 社会学
354 篇 经济学
259 篇 农学
208 篇 教育学
88 篇 文学
48 篇 军事学
12 篇 艺术学
1 篇 历史学

主题

693 篇 accuracy
501 篇 deep learning
453 篇 feature extracti...
413 篇 computational mo...
354 篇 support vector m...
352 篇 real-time system...
310 篇 training
305 篇 internet of thin...
273 篇 machine learning
245 篇 predictive model...
240 篇 convolutional ne...
219 篇 reliability
215 篇 optimization
209 篇 computer science
208 篇 computer archite...
193 篇 neural networks
185 篇 wireless communi...
176 篇 routing
172 篇 throughput
163 篇 data mining

机构

84 篇 institut univers...
82 篇 north-west unive...
82 篇 national centre ...
81 篇 tno technical sc...
80 篇 nikhef national ...
79 篇 infn sezione di ...
76 篇 infn sezione di ...
75 篇 université de st...
73 篇 university würzb...
70 篇 university of jo...
66 篇 università di ca...
58 篇 university moham...
57 篇 ncsr demokritos ...
52 篇 leiden universit...
51 篇 dept. of compute...
50 篇 school of automa...
50 篇 university moham...
43 篇 in2p3 lpc campus...
42 篇 infn lnf via enr...
41 篇 université de ha...

作者

85 篇 ferrara g.
85 篇 ardid m.
84 篇 calvo d.
83 篇 gal t.
83 篇 bozza c.
81 篇 chen a.
81 篇 kalekin o.
81 篇 díaz a.f.
81 篇 boumaaza j.
80 篇 coleiro a.
80 篇 gozzini s.r.
80 篇 dallier r.
77 篇 anguita m.
75 篇 boettcher m.
72 篇 aly z.
72 篇 enzenhöfer a.
71 篇 huang f.
67 篇 celli s.
60 篇 dornic d.
55 篇 carretero v.

语言

17,320 篇 英文
2,286 篇 其他
193 篇 中文
45 篇 日文
21 篇 朝鲜文
2 篇 斯洛文尼亚文
1 篇 阿拉伯文
1 篇 德文
1 篇 法文
1 篇 土耳其文

检索条件"机构=Dept Computer Engineering and Technology"

共 19864 条记录，以下是741-750 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：

Footwear 3D Model Generation from Smartphone 2D Images Utilizing Photogrammetry 3

Footwear 3D Model Generation from Smartphone 2D Images Utili...

引用

3rd International Conference on Electrical, computer and Communication engineering, ECCE 2023

作者： Abrar, Raiyan Islam, Md. Tariquel Naim, Mahapara Tabassum, Nuzhat Military Institute of Science and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350345360

3D modeling in the shoe industry is growing as the technology becomes more widely available. 3D modeling lets companies customize shoes for individual customers, making manufacturing more flexible and efficient. In the shoe industry of Bangladesh, using smartphone images for 3D modeling is a fairly new idea. This allows designers and manufacturers to collaborate and quickly share designs with customers for feedback. A photogrammetry pipeline is a cost-effective and efficient way to create 3D models. This study proposes a potential and affordable method for using photogrammetry to create 3D representations of footwear. The major goal was to determine whether photogrammetry, as opposed to RGB depth camera photos, can more conveniently construct 3D models of footwear from a small number of smartphone images. In order to assure correct reconstruction, the pipeline required taking a collection of photos from 6-9 distinct perspectives and augmenting the dataset. Then, from these images, point clouds are produced, and from these aligned point clouds, the 3D mesh is produced. The mesh is then textured and smoothed to give color. In Bangladesh's shoe industry, this 3D modeling pipeline can be used for AR shoe try-on. © 2023 IEEE.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Political Party Twitter Data using Ensemble Learning Classifier 14

Sentiment Analysis of Political Party Twitter Data using Ens...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Kumar, Sunny Uddin Haider, Md. Tanwir National Institute of Technology Patna Dept. of Computer Science & Engineering Patna India

ISBN: (纸本)9798350335095

Sentiment analysis is a field that has gained a lot of popularity in the last decade. We can identify the sentiment of a user in various fields like 'Movie Reviews', 'Hotel reviews', 'Online Product reviews' etc. Analysis of sentiment helps the other user in decision-making. Nowadays, sentiment analysis is also being used in the political scenario to select appropriate candidates/parties. Seeing this fact, we have performed a sentiment analysis on the political Twitter dataset to find out which Indian political party is getting positive/negative reviews. Generally, researchers use Textblob which is a lexicon-based sentiment analyzer to predict sentiment. The lexicon-based technique does not provide good accuracy to predict sentiment therefore in this paper we have applied ensemble learning using boosting techniques along with basic machine learning and deep learning techniques like SVM and LSTM. The result in terms of accuracy and ROC-AUC shows that ensemble learning *** with SVM outperform as compared to other ML technique. The accuracy is 87% and the ROC-AUC score is 93%. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

An Incremental Algorithm for (2-ϵ)-Approximate Steiner Tree Requiring O(n) Update Time 11

An Incremental Algorithm for (2-ϵ)-Approximate Steiner Tree...

引用

11th International Symposium on Computing and Networking, CANDAR 2023

作者： Raikwar, Hemraj Karmakar, Sushanta Indian Institute of Technology Guwahati Dept. of Computer Science and Engineering Guwahati India

ISBN: (纸本)9798350306705

Given an undirected connected weighted graph with non-negative edge weights and a subset of vertices called terminals, the goal of the Steiner tree problem is to find a tree that spans the terminals such that the weight of the tree is minimized. A dynamic graph is a graph where the edge set or the vertex set or both may change with time. In this paper, first, we give a lower bound on the worst case update time for maintaining a(2-\epsilon)-Approximate Steiner tree (\epsilon being a small fraction) based on MST heuristic in a general dynamic graph with edge insertions and deletions. Then we propose an incremental algorithm for the Steiner tree problem in general dynamic graphs with edge insertions. We consider a weighted undirected connected graph with positive real edge weights and each update inserts an edge with a specific weight in the graph. The goal is to maintain a Steiner tree of the terminals. The algorithm maintains a(2-\epsilon)-Approximate Steiner tree in O(n) update time where n is the number of vertices in the graph. © 2023 IEEE.

关键词： Undirected graphs

来源：评论

学校读者我要写书评

暂无评论

DC Microgrid Energy Optimization

DC Microgrid Energy Optimization

引用

2023 IEEE International Conference on Electrical, computer and Energy Technologies, ICECET 2023

作者： Jiyane, Muziwenkosi Pillay, Nelendran Sewsunker, Rathilall Durban University of Technology Dept. of Electronic & Computer Engineering Durban South Africa

ISBN: (纸本)9798350327816

DC microgrids, which utilize PV arrays and batteries or wind turbines and batteries, offer a viable solution for meeting the low to medium-power needs of rural, remote, and informal settlements. However, these solutions have limitations since they rely on the availability of the sun or wind. To address these limitations, researchers have identified that hybrid systems that combine multiple power sources may be more effective than a battery-only PV/wind system. These hybrid systems use dynamic energy dispatch to optimize the overall cost and operation of the microgrid. Energy management systems are used to achieve this dynamic energy dispatch, which involves load profiling and intelligent decision-making on energy dispatch. While numerous energy management systems have been implemented worldwide to optimize microgrids, less work has been done in Africa and South Africa, specifically on the demand side energy management system. This paper focuses on a hybrid PV-driven battery and fuel cell backup system, with the initial aim of dimensioning the PV/battery and fuel cell. The work then shifted towards developing an energy management system. The proposed system was a low-power provision in a +48 VDC format, which covered lighting and powered computing, entertainment, and communication modules. Seven households were selected with a total energy consumption of 8640 W/h daily. The results compared the efficiency of microgrid with demand-side management versus without demand-side management, as well as the effect of load scheduling. The simulation was conducted using MATLAB/Simulink. © 2023 IEEE.

关键词： dc-dc converter energy management system microgrid

来源：评论

学校读者我要写书评

暂无评论

Hybrid Feature Selection Techniques in Intrusion Detection System 10

Hybrid Feature Selection Techniques in Intrusion Detection S...

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2023

作者： Singh, Harvinder Beniwal, Sunita Kumar, Dharminder Guru Jambheshwar University of Science and Technology Dept of Computer Science and Engineering Hisar India

ISBN: (纸本)9798350382471

Network and information security have become difficult problems as a result of the network's phenomenal expansion. The main aim of intrusion detection is to detect and prevent security flaws in information systems. Intrusion detection system works with a vast volume of data. The processing time required by intrusion detection systems is high and detection rate is poor if all the features are used. Therefore, these unnecessary and redundant elements must be removed in order to improve intrusion detection system effectiveness. Three hybrid feature selection strategies are utilized in this study to choose features. K-Nearest Neighbor, Support Vector Machines, and Genetic Programming are used to analyze and evaluate the performance of selected features. © 2023 IEEE.

关键词： detection Genetic Programming K-Nearest Neighbor Support Vector Machines

来源：评论

学校读者我要写书评

暂无评论

Mood -Enhancing Music Recommendation System based on Audio Signals and Emotions 6

Mood -Enhancing Music Recommendation System based on Audio S...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Mounika, V. Charitha, Y. Dept.Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9798350398496

The identity of emotional speech is a significant topic within the discipline of interactions between humans and computers. Many strategies of figuring out emotions in human speech had been introduced and installed through diverse researchers. To identify noises in audio documents is the purpose of one of these versions. Together with gender recognition and YouTube video will be played depending on mood, this suggested computer also features speech emotion detection, which listens for sentiments like happiness, rage, and sadness in audio cues. This output is sent as input to YouTube, which plays song within the user's mind, resulting in the person's temper to stabilize fast. Using the CNN characteristic extraction approach, the function sizes vector become processed with NumPy, and the audio class became carried out in MFCC. This research study mainly uses two programs: RAVDESS and SAVEE. Using the acquired datasets, a new version of the look was produced in-depth. The device area is the platform where the Google Colab is used to perform code execution. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Explainability to Business: Demystify Transformer Models with Attention-based Explanations 2

Explainability to Business: Demystify Transformer Models wit...

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

作者： Thiruthuvaraj, Rajasekhar Jo, Ashly Ann Raj, Ebin Deni Indian Institute of Information Technology Dept. of Computer Science & Engineering Kottayam India

ISBN: (纸本)9781665456302

Recently, many companies are relying on Natural Language Processing (NLP) techniques to understand the text data generated daily. It has become very critical to deal with this data because finding the sentiments of text and summarizing them will help the company understand the pain points of the customers posting reviews on social media or understand the experience of the customer. These requirements have increasingly demanded many advanced algorithms to deal the text data. The introduction of Transformers led to businesses adopting NLP methods more and more to keep up with their needs. Models like Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformers (GPT), state-of-the-art results were achieved with billions of parameters learned. Although these advancements improved the accuracy and expanded the use of algorithms to a wide range of NLP tasks like language translation, text summarization, and language modeling. Businesses are more interested in the Explainability of the model compared to its accuracy. Explainable Artificial Intelligence (XAI) plays an important role to comprehend the complexities of the model as well as the influence of weights on predictions. In this paper, the complexities of the transformer model are unraveled by presenting a straightforward method for computing explainable predictions. The DistilBERT model is chosen as an example to implement the explainable system due to its lighter nature. Combining the strengths of a Posthoc expla-nation with those of a self-learning neural network, the method makes it simple to scale it to other algorithms to implement. With technologies like python, PyTorch, and Hugging Face, a detailed step-by-step algorithmic computation is demonstrated to explain the predictions from the attention-based explanations. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Adaptive Contour Noise Generation Network for Semi-supervised Medical Data Segmentation 6

Adaptive Contour Noise Generation Network for Semi-supervise...

引用

6th International Conference on Artificial Intelligence and Big Data, ICAIBD 2023

作者： Ye, Shunlong Nanjing University of Science and Technology Dept. of Computer Science and Engineering Nanjing China

ISBN: (纸本)9781665491259

When training convolutional neural networks, noise distribution in data can affect segmentation accuracy. Therefore, many neural networks will strengthen the segmentation ability of the model by artificially adding noise. However, because the noise distribution of the input data is not known, the model training process can only generate random noise, e.g., gaussian noise, but cannot simulate real-world noise. In the medical imaging domain, more attention is paid to the image contours, which can also be used for noising simulation. Meanwhile, considering the existence of rich unlabeled data sets in medical images, this paper proposes a semi-supervised framework for uncertainty estimation by using Monte Carlo Dropout and generates adaptive noise using the uncertainty map. Specifically, the framework consists of three parts, including a noise generation model, a teacher model, and a student model. The noise generation part processes the data input to the other two parts and uses the contour feature identified by the posteriori uncertainty map to simulate priori noise to guide the process of training segmentation model. Meanwhile, the student model updates its parameters based on the teacher model output and the ground truth annotations by minimizing a joint loss. Segmentation experiments on left atrium 3D data show that our method has competitive results with other SOTA semi-supervised methods. © 2023 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

All-fiber real-time ultrafast ranging Lidar for motion management of patients during stereotactic radiotherapy 13

All-fiber real-time ultrafast ranging Lidar for motion manag...

引用

Biomedical Applications of Light Scattering XIII 2023

作者： Boroomandisorkhabi, Behzad Esmaeelpour, Mina Electrical and Computer Engineering Dept Missouri University of Science and Technology 65409 United States

ISBN: (纸本)9781510658912

We report a fiber-optic-based ultrafast time-stretch laser detection and ranging (Lidar) sensor with 10 MHz speed and 10 μm accuracy with 30 mm dynamic range for head motion detection under the thermoplastic mask during image-guided radiotherapy procedures. The sensor (1) is miniaturized and fits under the mask, (2) is small enough not to cause attenuation in radiation beams, (3) has a spatial resolution of a tenth of a millimeter, (4) is real-time, and (5) is immune to electromagnetic radiation. © 2023 SPIE.

关键词： Electromagnetic waves

来源：评论

学校读者我要写书评

暂无评论

Smart Roads: U-Turn Accident Prevention System 4

Smart Roads: U-Turn Accident Prevention System

引用

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Johnson, Neena Ancy Jenifer, J. Khan, Aanya Jyothi, Akhila Karunya Institute of Technology and Sciences Dept. of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350300093

When discussing statistics of everyday road accidents in India, a very large contributing factor is accidents in hilly areas due to hairpin bends. These blind turns are highly dangerous and may more often than not result in fatal accidents. The low visibility results in the driver being extremely vulnerable to head-on collisions. Coming up with a preventive measure to this perilous situation is the prime focus of this paper. The proposed system in this paper is to, warn drivers of other vehicles at hairpin curves to avoid accidents involving human lives. This system is designed to allow residents and tourists to drive safely by warning them of blind corners and u-turns and reducing the possibility of accidents. This paper intends to reduce the chances of head-on collisions by implementing an accident prevention system. A prevention system, although new, should be comprehensible for a new user, to solve this issue, an existing system has been integrated with the proposed idea. © 2023 IEEE.

关键词： Light emitting diodes

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 << < 71 72 73 74 75 76 77 78 79 80 > >>

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：