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

2,820 篇 会议
2,259 篇 期刊文献
24 册 图书

馆藏范围

5,103 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,954 篇 工学
- 2,294 篇 计算机科学与技术...
- 1,975 篇 软件工程
- 642 篇 信息与通信工程
- 491 篇 生物工程
- 467 篇 控制科学与工程
- 344 篇 电气工程
- 341 篇 生物医学工程（可授...
- 300 篇 光学工程
- 242 篇 电子科学与技术（可...
- 155 篇 化学工程与技术
- 152 篇 机械工程
- 151 篇 网络空间安全
- 139 篇 安全科学与工程
- 123 篇 动力工程及工程热...
- 102 篇 交通运输工程
- 92 篇 仪器科学与技术
1,692 篇 理学
- 765 篇 数学
- 564 篇 生物学
- 504 篇 物理学
- 310 篇 统计学（可授理学、...
- 196 篇 化学
- 142 篇 系统科学
834 篇 管理学
- 487 篇 管理科学与工程(可...
- 389 篇 图书情报与档案管...
- 235 篇 工商管理
340 篇 医学
- 301 篇 临床医学
- 268 篇 基础医学(可授医学...
- 154 篇 公共卫生与预防医...
- 147 篇 药学(可授医学、理...
157 篇 法学
- 143 篇 社会学
72 篇 经济学
52 篇 农学
49 篇 教育学
21 篇 文学
3 篇 军事学
1 篇 艺术学

主题

352 篇 accuracy
264 篇 deep learning
206 篇 training
202 篇 machine learning
183 篇 feature extracti...
181 篇 convolutional ne...
180 篇 real-time system...
164 篇 computational mo...
150 篇 predictive model...
124 篇 data models
103 篇 internet of thin...
102 篇 artificial intel...
98 篇 reinforcement le...
93 篇 support vector m...
92 篇 optimization
87 篇 security
86 篇 semantics
82 篇 machine learning...
76 篇 measurement
73 篇 adaptation model...

机构

177 篇 department of co...
141 篇 moe key lab of a...
81 篇 tencent ai lab
76 篇 department of co...
66 篇 lovely professio...
51 篇 moe key lab of a...
43 篇 key laboratory o...
41 篇 the islamic univ...
39 篇 department of co...
39 篇 the islamic univ...
38 篇 shanghai ai labo...
36 篇 department of co...
32 篇 department of co...
30 篇 university of ch...
30 篇 school of comput...
30 篇 school of comput...
29 篇 department of cs...
28 篇 department of el...
26 篇 peng cheng labor...
24 篇 department of co...

作者

106 篇 yu kai
98 篇 zhao hai
57 篇 qian yanmin
56 篇 yan junchi
41 篇 zhang zhuosheng
36 篇 chen xie
33 篇 li zuchao
33 篇 chen lu
31 篇 yanmin qian
30 篇 al-turjman fadi
27 篇 lyu michael r.
25 篇 fadi al-turjman
23 篇 zhu su
22 篇 zhu jun
21 篇 guo yiwei
21 篇 junchi yan
21 篇 liu tongliang
20 篇 ramiz salama
19 篇 han bo
18 篇 pareek piyush ku...

语言

4,446 篇 英文
650 篇 其他
8 篇 中文
2 篇 德文
2 篇 朝鲜文

检索条件"机构=Department of Computer Science and Engineering-AI and ML"

共 5103 条记录，以下是781-790 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：

IoT-Edge Computing for Efficient and Effective Information Process on Industrial Automation 1

IoT-Edge Computing for Efficient and Effective Information P...

引用

1st IEEE International Conference on Networking and Communications, ICNWC 2023

作者： Rudra Kumar, M. Rupa Devi, B. Rangaswamy, K. Sangeetha, M. Kumar, Korupalli V Rajesh GPCET Department of Computer Science Engineerin Kurnool India Annamacharya Institute of Technology and Sciences Department of Computer Science Engineering Tirupati India Nandyal India Fatima Michael College of Engineering and Technology Department of CSE Madurai India Woxsen University AI Research Centre School of Business Telangana India

ISBN: (纸本)9798350336009

The Internet of Things (IoT) has transformed the way industrial systems operate by allowing physical devices, machines, and systems to be connected and monitored over a network. The Internet of Things has facilitated the development of smart factories and industrial automation systems, in which data from various sources is collected and analyzed in real-time to make informed decisions. IoT-enabled industrial automation systems can perform a variety of tasks, including predictive maintenance, process control, and energy management, among others. The main advantages of IoT in industrial automation are increased efficiency, increased safety, and cost savings. The generation of massive amounts of data from numerous sources or sensors is common in the IIoT world, but there are numerous challenges. The goal of this study is to demonstrate how the Internet of Things and ai enable Industrial Automation to develop in response to real-world issues. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Multi-Speaker Multi-Lingual VQTTS System for LIMMITS 2023 Challenge 48

Multi-Speaker Multi-Lingual VQTTS System for LIMMITS 2023 Ch...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Du, Chenpeng Guo, Yiwei Shen, Feiyu Yu, Kai Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence AI Institute X-LANCE Lab Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9781728163277

In this paper, we describe the systems developed by the SJTU X-LANCE team for LIMMITS 2023 Challenge, and we mainly focus on the winning system on naturalness for track 1. The aim of this challenge is to build a multi-speaker multi-lingual text-to-speech (TTS) system for Marathi, Hindi and Telugu. Each of the languages has a male and a female speaker in the given dataset. In track 1, only 5 hours data from each speaker can be selected to train the TTS model. Our system is based on the recently proposed VQTTS that utilizes VQ acoustic feature rather than mel-spectrogram. We introduce additional speaker embeddings and language embeddings to VQTTS for controlling the speaker and language information. In the cross-lingual evaluations where we need to synthesize speech in a cross-lingual speaker's voice, we provide a native speaker's embedding to the acoustic model and the target speaker's embedding to the vocoder. In the subjective MOS listening test on naturalness, our system achieves 4.77 which ranks first. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Adaptive Large Margin Fine-Tuning For Robust Speaker Verification 48

Adaptive Large Margin Fine-Tuning For Robust Speaker Verific...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Zhang, Leying Chen, Zhengyang Qian, Yanmin Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Ai Institute X-LANCE Lab Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9781728163277

Large margin fine-tuning (LMFT) is an effective strategy to improve the speaker verification system's performance and is widely used in speaker verification challenge systems. Because the large margin in the loss function could make the training task too difficult, people usually use longer training segments to alleviate this problem in LMFT. However, the LMFT model could have a duration mismatch with the real scenario verification, where the verification speech may be very short. In our experiments, we also find that LMFT fails in short duration and other verification scenarios. To solve this problem, we propose the duration-based and similarity-based adaptive large margin fine-tuning (ALMFT) strategy. To verify its effectiveness, we constructed fixed, variable length, and asymmetric verification trials based on VoxCeleb1. Experimental results demonstrate that ALMFT algorithms are very effective and robust, which not only achieve comparable improvement with LMFT in official VoxCeleb evaluation trials but also overcome performance degradation problems in short-duration and asymmetric scenarios respectively. © 2023 IEEE.

关键词： asymmetric scenario duration mismatch large margin fine-tuning speaker verification

来源：评论

学校读者我要写书评

暂无评论

A Novel Energy-Efficient Hybrid Optimization Algorithm for Load Balancing in Cloud Computing 1

A Novel Energy-Efficient Hybrid Optimization Algorithm for L...

引用

1st IEEE International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics, aiKIIE 2023

作者： Prasanna Kumar, K.R. Gm, Siddesh Yamsani, Nagendar Kiran Kumar, T.M. Pani, Alok Kumar Msrit Department of Cse Bangalore India Msrit Department of Ai&ds Bangalore India School of Computer Science and Artificial Intelligence Sr University Warangal India Siddaganga Institute of Technology Department of Cse Tumkur India Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350316469

In the field of Cloud Computing (CC), load balancing is a method applied to distribute workloads and computing resources appropriately. It enables organizations to effectively manage the needs of their applications or workloads by spreading resources across numerous PCs, networks, or servers. This research paper offers a unique load balancing method named FFBSO, which combines Firefly algorithm (FF) which reduces the search space and Bird Swarm Optimization (BSO). BSO takes inspiration from the collective behavior of birds, exhibiting tasks as birds and VMs as destination food patches. In the cloud environment, tasks are regarded as autonomous and non-preemptive. On the other hand, the BSO algorithm maps tasks onto suitable VMs by identifying the possible best positions. Simulation findings reveal that the FFBSO algorithm beat other approaches, obtaining the lowest average reaction time of 13ms, maximum resource usage of 99%, all while attaining a makespan of 35s. © 2023 IEEE.

关键词： Bird Swarm Optimization Cloud Computing Firefly Algorithm Load Balancing Makespan

来源：评论

学校读者我要写书评

暂无评论

Exploring the Effects of Block Chain-Based Security Systems on Cyber Security

Exploring the Effects of Block Chain-Based Security Systems ...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Reeta Mishra Kapil Kumar Shruti Nagpal Mehta Neelu Chadhuary Department of Computer Science & Engineering Delhi Technical Campus Greater Noida India Manav Rachna University Department of Computer Science & Engineering (AI) IIMT College of Engineering Department of Computer Science & Engineering Sharda University Department of Computer Science & Engineering Manav Rachna University

Due to the rapid advancement of cyber technology, virtual property is becoming more susceptible to hostile activity. Security structures that are mostly built on block chains (BCSSs) have gained traction. Disbursed ledger structures protected by encryption and consensus procedures are checked by BCSSs to protect industries against cyber attacks, data loss, and unwanted access. They provide users with a distributed ledger machine that is encrypted, shared, and may be used to manage virtual risks and digital property. It follows objectives to investigate how BCSSs affect cyber security. One way to perform a qualitative synthesis of the literature is to examine and analyze relevant academic materials and publications that discuss the challenges and advantages faced by BCSSs in the field of cyber security. The evaluation's findings will help determine the overall effect of BCSS on cyber security and offer recommendations for BCSS setups that will improve cyber security defense. To identify gaps in current cyber security measures, all findings will be compared with existing studies. It will provide invaluable analysis and insights into how best to use BCSSs for increased cyber security in comparison to traditional security architectures. When enforcing BCSSs, it will also recognize remarkable practices and tactics for businesses and professional clients.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimized Residual Attention U-Net-Based Lung Cancer Detection

Optimized Residual Attention U-Net-Based Lung Cancer Detecti...

引用

International Conference on Computational Intelligence and Communication Networks (CICN)

作者： Jyoti Kumari Sapna Sinha Laxman Singh Department of Information Technology Amity Institute of Information Technology Amity University Noida Uttar Pradesh Department of Computer Science and Engineering (AI-ML) KIET Group of Institutions Ghaziabad Uttar Pradesh

ISBN: (数字)9798331505264

ISBN: (纸本)9798331505271

Lung cancer detection using CT pictures is critical for early detection. Deep learning methods can learn hierarchical representations of image characteristics, but detecting subtle patterns and anomalies is difficult. This study proposed an optimized residual attention U-Net for lung tumor detection using a Gaussian filter and the Binary Grasshopper Optimisation Algorithm (BGOA). The U-Net enhances feature extraction using multi-attention-gated modules and residual layers, broadening the receptive field while avoiding overfitting. The suggested Optimised Residual Attention U-Net increases classification accuracy by 96.66%, the F1-score by 87.98%, precision by 83.53%, AUC by 98.65%, specificity by 97.22%, and recall by 92.94%. This technique overcomes the issues of detecting subtle patterns and anomalies in CT images and improves the outcomes of lung cancer identification.

关键词： Accuracy Computed tomography Lungs Computational modeling Lung cancer Filtering algorithms Feature extraction Classification algorithms Optimization Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Flying Fox Optimization with Deep Belief Network for Resource Allocation and Offloading Task in IoT Environment 2

Flying Fox Optimization with Deep Belief Network for Resourc...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Jaisharma, K. Al-Fatlawy, Ramy Riad Anu, D. Kumar, K Sudheer Soni, Mukesh Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India The Islamic University College Of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Ai & Ds Bengaluru India School of Computer Science & Artificial Intelligence Sr University Warangal India Graphic Era Hill University Graphic Era Deemed to be University Department of Cse Dehradun India

ISBN: (纸本)9798350372892

In the recent days, mobile edge computing is a booming technology by using the advanced trend technology as Internet of Things (IoT) based devices of mobile. Offloading computation used to maintain the consistence of mobile devices and tasks of application to redirect the data center of cloud system. The mobile edge computing has many regions of devices and access points so in each edge has consists of different resource allocation. Large amount of regions process leads to mobile edge server down. To resolve this issue, we implemented a new approach of flying fox optimization (FFO) with deep learning technique for offloading task and resource allocation. The Deep Belief Network (DBN) used for to find the finest offloading values and optimization algorithm employed for fine tune the parameters of DBN model. Additionally, objective function is defined based on consumption of energy in reducing way. This implemented method (DBN-FFO) enables the finest offloading decision to reduce system cost and significantly works on huge tasks of offloading. Effectiveness of the optimization algorithm tested on single and double models of node. Moreover, it fine-tunes the model parameters in appropriate way. Compared to the other existing methods like deep learning with seagull optimization (DLSGO), Deterministic Policy Gradient (DPG), the proposed DBN-FFO achieved maximum rate of 93.50 %. © 2024 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Skill-Based Edge-Brain Smart Manufacturing: A Case of Grasp Pose Selection Skill 6

Skill-Based Edge-Brain Smart Manufacturing: A Case of Grasp ...

引用

6th International Conference on Industry 4.0 and Smart Manufacturing, ISM 2024

作者： Lee, Sukhan Jang, Byungwoo Hyeon, Seokjong Lee, Soojin Lee, Jaesun Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of Department of Artificial Intelligence Sungkyunkwan University Suwon16419 Korea Republic of Department of Computer Science and Engineering Sungkyunkwan University Suwon16419 Korea Republic of Department of AI System Engineering Sungkyunkwan University Suwon16419 Korea Republic of Department of Regional Industry Innovation Korea Institute of Industrial Technology Ulsan44413 Korea Republic of

The edge-brain framework (EBF) is a S/W framework that allows manufacturers to easily integrate ai-empowered robot work skills into a legacy production system in an edge computing environment with minimal time and effort. For EBF-based smart manufacturing, is a skill-based task-level robot programming environment that plays a key role. In this paper, we present the grasp pose selection skill as a case study to demonstrate the proposed skill-based edge-brain smart manufacturing. The proposed grasp-pose selection skill determines the optimal 6D grasp pose associated with the target object in a cluttered workspace by taking into consideration grasp stability, object manipulability, and collision-free path efficacy. To achieve a real-time operation of optimal grasp pose selection skill, deep learning networks are designed to compute, in particular, the manipulability and collision-free path efficacy indices. Experiments demonstrate the effectiveness of the proposed real-time grasp pose selection skill developed for EBF-based smart manufacturing. © 2024 The Authors. Published by Elsevier B.V.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

ECAPA++: Fine-grained Deep Embedding Learning for TDNN Based Speaker Verification 24

ECAPA++: Fine-grained Deep Embedding Learning for TDNN Based...

引用

24th International Speech Communication Association, Interspeech 2023

作者： Liu, Bei Qian, Yanmin MoE Key Lab of Artificial Intelligence AI Institute X-LANCE Lab Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

In this paper, we aim to bridge the performance gap between TDNN and 2D CNN based speaker verification systems. Specifically, three types of architectural enhancements to ECAPA-TDNN are proposed: 1) follow depth-first design to significantly increase network depth while maintaining its complexity. 2) introduce recursive convolution to better capture fine-grained speaker information. 3) propose pyramid-based multi-path feature enhancement module to yield more discriminative speaker representation. Experiments on Voxceleb show that our final model, named ECAPA++, achieves 25%, 23% and 24% relative improvements on Vox1-O, E and H respectively, while with 2.4x fewer parameters and 2.3x fewer FLOPs over the previous best TDNN-based system. Meanwhile, it is comparable to the state-of-the-art ResNet-based systems with higher computational efficiency. In addition, further performance gains can be achieved by fusing ECAPA++ and ResNet-based systems. © 2023 International Speech Communication Association. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

HuBERT-AGG: Aggregated Representation Distillation of Hidden-Unit Bert for Robust Speech Recognition 48

HuBERT-AGG: Aggregated Representation Distillation of Hidden...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wang, Wei Qian, Yanmin Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Ai Institute X-LANCE Lab Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9781728163277

Self-supervised learning (SSL) has attracted widespread research interest since many successful SSL approaches such as wav2vec 2.0 and Hidden-unit BERT (HuBERT) have achieved promising results on speech-related tasks such as automatic speech recognition (ASR). However, few works have been conducted to improve the noise robustness of SSL models. In this paper, we propose HuBERT-AGG, a novel method that learns noise-invariant SSL representations for robust speech recognition by distilling aggregated layer-wise representations. Specifically, we learn an aggregator that computes the weighted sum of all hidden states of a pretrained vanilla Hu-BERT by fine-tuning it on a small portion of labeled data. Then a noise-robust HuBERT is trained on the simulated noisy speech by distilling from the aggregated representations and layer-wise hidden states produced by a pretrained vanilla HuBERT with parallel original speech as input. Experiments on libriSpeech simulated noisy test sets show 13.1%-17.0% relative word error rate (WER) reduction with very slight degradation on the original test sets. On CHiME-4 1-channel real speech test sets, we have surpassed the best results achieved by all published fully supervised ASR models as well as other SSL approaches adopting the same data usage as ours. © 2023 IEEE.

关键词： Distillation

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 << < 75 76 77 78 79 80 81 82 83 84 > >>

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：