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

6,385 篇 会议
161 册 图书
46 篇 期刊文献

馆藏范围

6,592 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,754 篇 工学
- 4,179 篇 计算机科学与技术...
- 3,373 篇 软件工程
- 1,160 篇 信息与通信工程
- 761 篇 生物工程
- 562 篇 生物医学工程（可授...
- 496 篇 控制科学与工程
- 422 篇 电气工程
- 327 篇 动力工程及工程热...
- 267 篇 机械工程
- 254 篇 光学工程
- 251 篇 电子科学与技术（可...
- 242 篇 安全科学与工程
- 220 篇 化学工程与技术
- 214 篇 环境科学与工程（可...
2,078 篇 理学
- 943 篇 数学
- 830 篇 生物学
- 413 篇 物理学
- 399 篇 统计学（可授理学、...
- 278 篇 系统科学
- 223 篇 化学
1,417 篇 管理学
- 785 篇 管理科学与工程(可...
- 775 篇 图书情报与档案管...
- 514 篇 工商管理
614 篇 医学
- 580 篇 临床医学
- 554 篇 基础医学(可授医学...
- 331 篇 药学(可授医学、理...
- 302 篇 公共卫生与预防医...
359 篇 法学
- 266 篇 社会学
209 篇 农学
- 199 篇 作物学
197 篇 经济学
- 196 篇 应用经济学
133 篇 教育学
23 篇 军事学
13 篇 文学

主题

279 篇 internet of thin...
263 篇 machine learning
253 篇 cloud computing
230 篇 big data
219 篇 computational mo...
207 篇 deep learning
182 篇 data mining
157 篇 data models
138 篇 predictive model...
136 篇 artificial intel...
133 篇 training
130 篇 feature extracti...
122 篇 real-time system...
119 篇 blockchain
109 篇 support vector m...
108 篇 accuracy
107 篇 machine learning...
102 篇 convolutional ne...
100 篇 forecasting
97 篇 medical services

机构

54 篇 graphic era deem...
44 篇 chitkara univers...
24 篇 department of co...
24 篇 department of co...
21 篇 department of en...
19 篇 school of comput...
19 篇 teerthanker maha...
18 篇 university of ch...
18 篇 school of inform...
17 篇 jaipur national ...
16 篇 uttaranchal inst...
15 篇 fujian provincia...
14 篇 srm institute of...
14 篇 department of co...
14 篇 uttaranchal inst...
13 篇 computer science...
13 篇 school of comput...
11 篇 uttaranchal inst...
10 篇 college of compu...
10 篇 school of manage...

作者

21 篇 pant bhasker
20 篇 chang kuo-chi
13 篇 tripathi vikas
12 篇 kukreja vinay
12 篇 vinay kukreja
11 篇 jacob lija
11 篇 joshi kapil
11 篇 gangodkar durgap...
10 篇 iwendi celestine
10 篇 lourens melanie
10 篇 chu kai-chun
10 篇 sujithra m.
10 篇 alanya-beltran j...
9 篇 rajeswari d.
9 篇 chang fu-hsiang
9 篇 singh rajesh
8 篇 kapil joshi
8 篇 kapila dhiraj
8 篇 pavithra g.
8 篇 sanjay misra

语言

6,256 篇 英文
330 篇 其他
15 篇 中文

检索条件"任意字段=International Conference on Advances in Data Science and Computing Technologies, ASDC 2022"

共 6592 条记录，以下是4631-4640 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：

Post-hoc Explainable Reinforcement Learning Using Probabilistic Graphical Models 1

引用

11th international Advanced computing conference, IACC 2021

作者： Deshpande, Saurabh Walambe, Rahee Kotecha, Ketan Jakovljević, Marina Marjanović Symbiosis Centre for Applied Artificial Intelligence Symbiosis Institute of Technology Symbiosis International University Pune412 115 India Faculty of Technical Sciences Singidunum University Belgrade Serbia

ISBN: (数字)9783030955021

ISBN: (纸本)9783030955014

Reinforcement learning (RL) has recently enjoyed significant success in games, robotics, bioinformatics, etc. Soon, it will not be uncommon to see AI models employing RL agents integrated with various hardware and software solutions. Due to its generality and robustness, RL is applied in several disciplines such as game theory, control theory, multi-agent systems, swarm intelligence, robotics, and NLP. Despite these advances and successes, reinforcement learning faces many challenges for real-world adoption. Some of the major difficulties being, operator’s trust and ability of an agent to explain the actions taken in a human-understandable manner. Traditionally the AI systems are black-box models. With the advent of various legal regulations worldwide, notably the European General data Protection Regulation (GDPR) [29], it has started becoming mandatory that the AI models be transparent, interpretable, and secure. If an RL agent can effectively and accurately explain the actions carried out by the RL system to the observers/operators, it will be a tangible step towards developing the ART (accountable, reliable and trustworthy) RL agent. This can effectively facilitate the adoption of RL systems in real-world domains. Various explainable AI (XAI) methods have been reported in the literature. However, there is a considerable lacuna in the availability of Explainable RL (XRL) methods. This paper introduces a novel RL algorithm agnostic approach of generating human-understandable explanations using the probabilistic graphical model. This method is based on Probabilistic Graphical Models (PGM) [36]. It is algorithm agnostic in that it is not dependent on any specific RL method and can be integrated with any RL algorithm. We also introduce a PGM model, which is learned along with an agent’s training via classic methods and used for generating explanations at run time. Specific case studies are considered, and results are presented which demonstrate our approach. Our exper

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection using EfficientNet: Working Towards Dense Sampling and Frames Selection

Deepfake Detection using EfficientNet: Working Towards Dense...

引用

IEEE international conference on Research, Innovation and Vision for the Future

作者： Tuan-An To Hoang-Chau Luong Nham-Tan Nguyen Trong-Tin Nguyen Minh-Triet Tran Trong-Le Do Faculty of Information Technology and Software Engineering Laboratory University of Science VNUHCM Ho Chi Minh City Vietnam Viet Nam National University Ho Chi Minh City Vietnam

ISBN: (纸本)9781665461672

Deepfake is a controversial technology that allows the automatic generation of video content through generative adversarial networks. The emergence of Deepfake technology is problematic and sophisticated, making it more difficult to detect. In our paper, we contribute a deep-learning method to resolve that problem. We use the MTCNN face detector to extract facial images and apply data augmentation and EfficientNet for real-fake classification. We apply frame selection with the raw label prediction to tackle the fault cases and receive the final label. With the approach above applied, we utilize training and evaluation datasets from FaceForensics++ and achieve an accuracy of 62.5%.

关键词： Deep learning Training Learning systems Deepfakes Image resolution Social networking (online) Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Cloud computing Methods Based on IoT for Better Patient data Planning: A Research

Cloud Computing Methods Based on IoT for Better Patient Data...

引用

international conference on System Modeling & Advancement in Research Trends (SMART)

作者： Arvind Kumar Pandey Sumitra Maneria Department of Computer Science ARKA JAIN University Jamshedpur Jharkhand India Department of CSE PIT Parul University Vadodara Gujarat India

ISBN: (纸本)9781665487351

Clinics all across the world are implementing more recent, extremely sophisticated technologies. Information and communication technology improvements are to blame for the emergence of the Internet of Things (IoT). In recent years, new opportunities for data collection and wiser judgments have emerged with the integration of the Internet of Things with patient-accessible medical devices, as well as with patients and their surroundings. IoT technologies aid patients and doctors in today's healthcare environment since they are applied in a range of medical sectors (like real-time monitoring, patient information and healthcare management). In the future of IoT for healthcare, various and distributed devices will collect, analyses, and transmit real-time medical data to open clouds, enabling the accumulation, piling, and analysis of crucial data streams in numerous new procedures as well as the activation of context-dependent intimations. IoT paradigm can advance the current development of traditional healthcare model toward engaged medicine by using sensors (environmental, wearable, and implanted) dispersed across local surroundings with the purpose of monitoring patient's health and launching remotely care. The development of new technology for storing vast amounts of clinical data has become increasingly important in recent years. The management of the massive amount of cloud storage is done by fusing edge computing with the Internet of Things. Recent studies have shown that the cloud and IoT integration significantly affect remote healthcare. This survey study focuses on the various applications of edge computing IoT devices to improve people's health while ensuring the accuracy of medications and medication delivery. Healthcare practitioners, researchers, and others interested in learning more about IoT with edge computing-based health care applications will be able to use the research's goal as a source and reference for information about smart healthcare.

关键词： Cloud computing data privacy Smart healthcare data integration Distributed databases Medical services Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Research on Document Level Machine Translation Method Based on Human Like Translation Model

Research on Document Level Machine Translation Method Based ...

引用

Advanced technologies in Intelligent Control, Environment, computing & Communication Engineering (ICATIECE), international conference on

作者： Shoujin Wang Xin Meng Chengyu Duan School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9781665493970

The existing document level machine translation methods do not clearly represent the reasoning process between sentences. Therefore, there is “exposure bias”, and the development trend of document-level translation tasks of machine will expand the translation object from translating a string of words to translating lots of strings of words. But research demonstrates once machine translate the whole document as a whole, the existing model cannot complete the task well. After research, we find that this phenomenon is not caused by over fitting, but by local minimum. Analytical studies we conducted show that increase of attention's difficulty from target side to source side leads to the convergence of the model at the local minimum rather than the global minimum, which leads to failure. In order to solve this problem, we introduce a local hypothesis mechanism into the existing model to reduce the attention's assumption roomage from the side after translation through the side before translation. Our numerous studies have shown this method will converge not only more stable but also faster than the existing models, and achieves good Bleu scores on the three basic data sets. Based on this method, in order to better characterize the sentence reasoning process, alleviate exposure bias and effectively deal with discourse phenomena, we propose a new human-like-translation model by imitating the drafting revision process in the process of human translation.

关键词： Training Semantics Fitting Big data Market research data models Cognition

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Recent advances in Big data Analytics in Vehicular Ad Hoc Networks

A Comparative Study of Recent Advances in Big Data Analytics...

引用

international Wireless Communications and Mobile computing conference, IWCMC

作者： Kawthar Zaraket Ismail Bennis Hassan Harb Ali Jaber Abedalhafid Abouaissa MERCEL Lab Doctoral School of Science and Technology Lebanese University Beirut Lebanon IRIMAS Universit&#x00E9 de Haute Alsace Mulhouse France

Big data is becoming a research focus in Intelligent Transportation Systems (ITS), which can be seen in many projects worldwide. Intelligent transportation systems will produce a large amount of data. The produced big data will profoundly impact the design and application of the ITS, which makes them safer, more efficient, and profitable. Studying big data analytics in ITS is a flourishing field. This paper aims to provide a comparative study of some recent works in Big data analytics for Vehicular Ad Hoc Networks. The study includes reviewing some frameworks that conduct big data analytics in ITS while discussing the data source and collection methods, data analytics methods, platforms and big data analytics application categories. The comparison and implementation of five recent works, with a focus on the data collection and application layers, are followed to pick up the best approach based on the Friedman test results.

关键词： Wireless communication Measurement data analysis Soft sensors Vehicular ad hoc networks Computer architecture Big data

来源：评论

学校读者我要写书评

暂无评论

Multi Disease Diagnosis Model for Chest X-ray Images with Explainable AI – Grad-Cam Feature Map Visualization

Multi Disease Diagnosis Model for Chest X-ray Images with Ex...

引用

international conference on Futuristic technologies (INCOFT)

作者： N Shobha Rani C H Nachappa Arun Sri Krishna B J Bipin Nair Department of Computer Science Amrita School of Computing Mysuru Campus Amrita Vishwa Vidyapeetham India

In this work, we have proposed a deep convolutional neural network model with the background of a network as ResNet and a classification block as a faster RCNN model to predict multiple lung cancer abnormalities from X-ray images. Experimentations are conducted on Kaggle image dataset repositories with X-ray images of about 55000 images comprising of 15 different classes. We have proposed a region proposal network capable of autonomously learning from the pre-trained data specifications and applying a bounding box to cancer-affected regions to detect the affected areas. About 80% of samples were considered to conduct training from each class, and 20% were used for testing. The results obtained have an accuracy of about 96% for classification.

关键词： Training Lung Lung cancer Predictive models Feature extraction Proposals Medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

An Efficient Approach for Track data Simplification in Geographic Information System

An Efficient Approach for Track Data Simplification in Geogr...

引用

Recent advances and Innovations in Engineering (ICRAIE)

作者： Rajesh Kumar Dilip Kumar Dalei Rakesh Kp Rajesh M A Narayan Panigrahi CAIR Defence Research & Development Organisation (DRDO) Bengaluru India

There is a phenomenal growth in geospatial data due to rapid advancement in remote sensing technologies. Geospatial data has become ubiquitous in many applications such as disaster management, town planning, environmental observations, military systems, etc. The demand for geospatial data and related technologies is increasing continuously due to easy access to high resolution geospatial data at an affordable cost. Furthermore, modern computing systems enables to store and process these high-resolution data within a tolerable time limit. Track datasets are geospatial data that represents the information about geospatial movements of objects or events sensed from moving sensors. A track is a spatio-temporal data measured in land, sea and air through a sensor such as RADAR, SONAR or LiDAR. A track data can be modelled as position, speed, time etc. of an object or event. During the capture and monitoring of track data, the volume of data generated is very large and depends on time and space resolution of the measuring sensor. Track data are very much useful in analyzing and planning of land, water and air path *** track data is being recorded in a very high volume, thus processing and displaying it in real time becomes a challenging task. It is very much necessary to reduce the track dataset without affecting the track shape and size significantly. i.e the route is being simplified with few numbers of joining points or polygons, which makes the visualisation process easy and interactive. In this paper, we propose an efficient approach for implementation of Douglas-Peucker algorithm for Map simplification of track data. Douglas-Peucker algorithm is one of the classic and popular algorithms that is generally applied for line simplification. The current work modifies this existing algorithm and adapt it for simplifying the history of a track for efficient map rendering. This reduces the track size significantly while preserving its original shape and size.

关键词： Target tracking Shape Navigation Sea measurements Radar tracking Geospatial analysis Sensors

来源：评论

学校读者我要写书评

暂无评论

Information Storage and Retrieval System for a Molecular Dynamics Based Digital Twin of Materials

Information Storage and Retrieval System for a Molecular Dyn...

引用

IEEE Region 8 international conference on Computational technologies in Electrical and Electronics Engineering, SIBIRCON

作者： Dmitry Topolsky Alexander Belyakov Veronica Pochinskaia Irina Topolskaya Nikolay Yumagulov Dmitry Fedorov Dept. of Electronic Computing Machines South Ural State University Chelyabinsk Russia Dept. of Energy and Power Engineering South Ural State University Chelyabinsk Russia Dept. for Education in Physics and Mathematics Name of Organization Nizhnevartovsk State University Nizhnevartovsk Russia Dept. of Informatics and Computer Engineering Surgut State University Surgut Russia

ISBN: (纸本)9781665464819

Digital twin technology becomes an appropriate respond to the new challenge of rapid development in science and industry. Chemical data include the information about structure and properties of materials and compounds. Machine learning technology can help to predict properties of innovative compounds and material, but it takes enormous amount of raw data. The implementation of digital twin technology in spectral and molecular dynamics helps to reduce risks introducing the innovations. Large systems technologies are used in multiscale modeling of materials with computer programs. The world experience of chemical data aggregation and storage is based on specialized databases creation. Disunity of data sources demands a single multiscale data model to operate raw data and amend the accuracy of prediction. To collect and analyze unstructured data full-text search and distributed computing were applied. In respond to perpetual raw data expansion a data Lake technology is used to store, analyze and search for information of atomic and molecular systems.

关键词： Technological innovation Systematics Computational modeling Biological system modeling Soft sensors Big data applications data models

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection System using ML

Network Intrusion Detection System using ML

引用

advances in computing, Communication Control and Networking (ICAC3N), international conference on

作者： Raghav Kumar Abdul Haq Nalband School of Multidisciplinary Studies REVA University Bangalore

technologies are making our life easier and simple, but it has both positive and negative effect. Many new methods of cybercrimes are coming which cannot be solved using earlier conventional method like using firewalls, antivirus, old ML algorithms. In recent years every device whether it’s hardware or software is being connected with IOT. Hence, there is huge growth in data also their privacy is huge concern for industries. In this model, we are implementing Network Intrusion detection system using Machine learning algorithms which would resolve security problems using KNN, SVM, LR, RF, DT and Gaussian NB with greater efficiency. Our system uses both supervised and unsupervised machine learning techniques. Both misuse and Anomaly based detection to detect malware and viruses, our system is capable to detect both known and unknown attacks. In case of misuse detection system known attacks are being easily identified using a database where list of all known attacks is available. If any attack happens on network system, then NIDS checks whether the attack is listed in dataset or not. If attack is known, then system administrator gets notified. If attack is unknown, then NIDS uses outlier detection to identify attack using several machine learning algorithms like clustering and other techniques. So, with the help of above-mentioned techniques attack is being detected. Our model improves the attack detection mechanism with high accuracy and less prediction time. It is better than previous conventional machine learning algorithms. Our model is broadly accepted in companies and organization. it is fulfilling the cyber security issue also threat prediction time of our model is quite improved and the prediction time is reduced as compared to previous model.

关键词： Support vector machines Radio frequency Machine learning algorithms Firewalls (computing) Computational modeling Software algorithms Network intrusion detection

来源：评论

学校读者我要写书评

暂无评论

SIEM integration with SOAR

SIEM integration with SOAR

引用

international conference on Futuristic technologies (INCOFT)

作者： Anish Sridharan V Kanchana Department of Computer Science Amrita School of Arts and Sciences Amrita Vishwa Vidyapeetham Mysuru Campus Mysuru India

The reliance on basic perimeter controls is coming to an end, as it is no longer reliable to rely solely on the firewall, intrusion detection system, or antivirus. Sophisticated cyber threats have emerged as a significant adversary in the cyber space. These advanced cyber threats include ”zero-day,” social engineering tactics, or advanced evasion techniques to avoid detection. As of now, today’s technology has accumulated a large amount of data, which necessitates the use of an effective tool for ”control, monitoring, and defense against potential *** a result, enterprises have resorted to building SOCs to combat these advanced threats, and as an add-on to the SOC, enterprises implement SOAR as well, as it has its own benefit of reducing SOC Alert volume by identifying duplicate cases. The SOAR playbook aims to reduce the amount of manual work required, potentially reducing threat and vulnerability response times.

关键词： Automation Firewalls (computing) Intrusion detection Manuals Market research Pattern recognition Time factors

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 << < 460 461 462 463 464 465 466 467 468 469 > >>

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：