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

1,195 篇 会议
36 篇 期刊文献

馆藏范围

1,231 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

642 篇 工学
- 551 篇 计算机科学与技术...
- 456 篇 软件工程
- 225 篇 信息与通信工程
- 126 篇 控制科学与工程
- 96 篇 电气工程
- 94 篇 生物工程
- 90 篇 生物医学工程（可授...
- 73 篇 电子科学与技术（可...
- 69 篇 网络空间安全
- 53 篇 光学工程
- 46 篇 安全科学与工程
- 34 篇 仪器科学与技术
- 32 篇 机械工程
- 30 篇 动力工程及工程热...
- 29 篇 化学工程与技术
- 27 篇 交通运输工程
368 篇 理学
- 226 篇 数学
- 114 篇 统计学（可授理学、...
- 102 篇 生物学
- 54 篇 物理学
- 33 篇 化学
- 29 篇 系统科学
242 篇 管理学
- 167 篇 管理科学与工程(可...
- 97 篇 图书情报与档案管...
- 55 篇 工商管理
85 篇 医学
- 80 篇 基础医学(可授医学...
- 79 篇 临床医学
- 43 篇 公共卫生与预防医...
- 43 篇 药学(可授医学、理...
39 篇 法学
- 36 篇 社会学
25 篇 经济学
21 篇 农学
7 篇 教育学
3 篇 军事学

主题

165 篇 feature extracti...
157 篇 accuracy
108 篇 convolutional ne...
79 篇 deep learning
54 篇 optimization
51 篇 support vector m...
50 篇 predictive model...
49 篇 internet of thin...
42 篇 computational mo...
35 篇 training
34 篇 long short term ...
33 篇 real-time system...
33 篇 machine learning
33 篇 data models
31 篇 classification a...
25 篇 security
25 篇 prediction algor...
25 篇 measurement
24 篇 visualization
24 篇 network security

机构

194 篇 department of co...
135 篇 department of el...
117 篇 the islamic univ...
98 篇 nitte meenakshi ...
87 篇 school of comput...
82 篇 the islamic univ...
58 篇 sr university sc...
53 篇 college of techn...
44 篇 school of comput...
37 篇 department of co...
36 篇 department of ec...
33 篇 nitte meenakshi ...
33 篇 nitte meenakshi ...
31 篇 nitte meenakshi ...
28 篇 department of ar...
28 篇 school of comput...
26 篇 east west instit...
26 篇 department of co...
26 篇 sr university sc...
25 篇 department of co...

作者

73 篇 pareek piyush ku...
73 篇 piyush kumar par...
24 篇 ramachandra a.c.
23 篇 muntather almusa...
23 篇 almusawi muntath...
21 篇 ramachandra a c
21 篇 parameshachari b...
20 篇 myasar mundher a...
20 篇 srinivas aluvala
20 篇 aluvala srinivas
19 篇 al-jawahry hassa...
18 篇 alabdeli haider
18 篇 hassan m. al-jaw...
18 篇 adnan myasar mun...
18 篇 haider alabdeli
16 篇 mohammed al-faro...
16 篇 nalini n.
15 篇 sundaram s. meen...
15 篇 alzubaidi laith ...
15 篇 mohammed i. habe...

语言

1,053 篇 英文
177 篇 其他
2 篇 中文

检索条件"机构=Computer Science and Engineering Nitte Meenakshi Intitute of Technology"

共 1231 条记录，以下是721-730 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：

Wide-Deep Neural Networks with Randomized Sparse Backpropagation Simplify Demand-Side Load Event Detection

Wide-Deep Neural Networks with Randomized Sparse Backpropaga...

引用

2023 International Conference on Data science and Network Security, ICDSNS 2023

作者： Adusumilli, Manasa Ramesh, G.P. Katkam, Vijayrani Bhargavi Pareek, Piyush Kumar Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaadeswaram India St. Peter's Institute for Higher Education and Research Department of Electronics and Communication Engineering Chennai India Ballari Institute of Technology and Management Department of e and Ce Bellary India Hyderabad Institute of Technology and Management Department of Cse Hyderabad India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350301595

Identifying demand-side load events is a critical step in lowering energy use in a number of situations. Using wide-deep neural networks and randomised sparse backpropagation algorithms, this study presents a unique way to identify demand-side load events. To detect subtleties in the input data, we employ randomised sparse backpropagation and both shallow and deep network topologies. We also use the ReLU and sigmoid activation functions to improve the performance of our model. We use the Adam optimizer to train the proposed model, using a learning rate of 0.001 per batch and a batch size of 64. The results were compared to those of other popular technologies, such as support vector machines. According to the findings of our studies, the technique we utilised is more precise and efficient than any other option we investigated. The proposed approach combines wide-deep neural networks with randomised sparse backpropagation to simplify demand-side load event identification. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Advanced Machine Learning Frameworks for Multimodal Image and Speech Signal Processing 3

Advanced Machine Learning Frameworks for Multimodal Image an...

引用

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Ramesh Naidu, P. Shandilya, Saurabh Srividya, C.N. Gujar, Shantanu Sudhir Devi, Supriya Dankan Gowda, V. Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Karnataka Bangalore560064 India Poornima College of Engineering Department of Advance Computing Rajasthan Jaipur India BGSIT Adichunchanagiri University Faculty of Engineering Management & Technology Dept. of ECE B G Nagara571448 India Rochester Institute of Technology Golisano College of Computing and Information Sciences Department of CyberSecurity RochesterNY14623 United States Alliance University Department of Mathematics Karnataka Bangalore562106 India BMS Institute of Technology and Management Department of Electronics and Communication Engineering Karnataka Bangalore India

ISBN: (纸本)9798350354171

Multimodal data processing, especially the fusion of image and speech modality, is important for future human computer interface, medical applications and security surveillance. This research proposes the new machine learning approach for the efficient handling of multimodal data in which feature extraction from images and from the speech signal is obtained by employing CNN and LSTM networks, respectively. These features are combined by a hybrid fusion approach so that the resulting algorithm would be both accurate and fast. CIFAR-10 and LibriSpeech were used to assess the framework;the highest accuracy was 92% whilst the conventional methods like MDNN and EFMS could only reach 86%. Moreover, the analysis showed that the proposed method can take a processing time of 0.15 seconds to taxonomy and 0.45 seconds for speech data, thus making it preferable for real time data. These results illustrate the framework's efficiency in predicting the multimodal input and demonstrate superiority over the prior methods. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Cocky Search Algorithm with Hill Climb Approach for solving the Quality-of-Service Multicast Routing in MANET

Hybrid Cocky Search Algorithm with Hill Climb Approach for s...

引用

Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE), International Conference on

作者： P. Revathi V S Anusuya Vijilius Helena Raj Piyush Kumar Pareek Department of Computer Science Holy Cross College (Autonomous) Tiruchirappalli New Horizon College of Engineering Bengaluru Dept of AIML Nitte Meenakshi Institute of Technology Bengaluru

Multicast QoS routing is a significant research subject in networks. In so many research has intensive on the low-cost multicast routing tree that fulfills the limits of bandwidth and delay of jitter. Because of its complete problem, many procedures have been agreed to solve this type of difficult. The study offered a novel hybrid algorithm, namely Cocky Search Algorithm, and the Hill Climb (CSAHC), to resolve the issue. The most important ground-breaking task is to association the process of generating the CSAHC procedure solution with the cloud model (CM). In addition, as part of the CSAHC framework, we have integrated the cloud model into the CSAHC algorithm to improve the performance of the CSAHC procedure by optimizing the pheromone trace at the edges. While the high intensity of the pheromone trail can fall into an optimal space on some edges, the CM-based pheromone search strategy is areas. To neglect the option of forming a cycle, we develop integrate it into the path creation procedure. Lastly, the calculation results show that the hybrid procedure has the compensations of effective and superior presentation for the excellence of the solution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Internet of Things Based Tired Detection using Deep Learning Techniques

Internet of Things Based Tired Detection using Deep Learning...

引用

2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023

作者： Nijaguna, S.G. Kumar, Sharan Sv, Devika Lal, Bechoo Pradeep Kumar, S. S.E.A. College of Engineering and Technology Department of Information Science and Engineering Bangalore India H. K. E. Society's S. L. N. College of Engineering Dept of Electronics & Communication Engg Raichur India Hyderabad Institute of Technology and Management Dept of Electronics and Communication Engineering Telangana India K L University Vadeeshwaram Dept of Computer Science & Engineering Vijayawada India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350398465

Sleep is essential for human survival since it helps to restore and maintain our bodies' immune systems and other essential processes. One-third of a person's life is devoted to sleeping, although few are aware of the many positive aspects of this activity. Two distinct types of sleep, REM and NREM, have been identified. A good night's rest is achieved when REM and NREM sleep alternate in a regular pattern. Disruptions to this cycle, whether they originate physiologically or psychologically, have been linked to a variety of health problems. Polysomnography (PSG) equipment is often used in sleep labs inside hospitals to perform sleep studies. A polysomnogram is an in-depth medical technique that records a patient's vital signs while they sleep and necessitates a hospital stay. Clinically, sleep apnea is defined as a breathing disease in which there are periodic pauses in breathing lasting 10 seconds or more that occur more than five times during the night. Sleep apnea may be classified as either Obstructive, Central, or Mixed. The prevalent sleep problem known as obstructive sleep apnea (OSA) is caused by the relaxation of muscles in the upper airway during sleep. The purpose of this study is to provide a technique for screening for Obstructive Sleep Apnea by analysing Heart Rate Variability of Electrocardiogram (ECG) data while the subject is asleep. The goals of this study are to create computational approaches for identifying OSA based on characteristics extracted from Heart Rate Variability (HRV) signals derived from sleep electrocardiograms (ECGs). Physio Net's Apnea-ECG recordings serve as the source for the ECG data. © 2023 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning with TSOA Model for Predicting the Parkinson Disease using Speech Features

Hybrid Deep Learning with TSOA Model for Predicting the Park...

引用

Data science and Information System (ICDSIS), IEEE International Conference on

作者： Piyush Kumar Pareek Pankaj Zanke Anoop N Prasad Mohan B R Artificial Intelligence and Machine Learning Nitte Meenakshi Institute of Technology Bengaluru India Senior Technical Business Analyst Sapiens International Corporation Department of Computer Science and Engineering East West Institute of Technology Bengaluru India

ISBN: (数字)9798350381665

ISBN: (纸本)9798350381672

True early identification of Parkinson’s illness (PD) is absolutely fundamental to stopping the ill health course and planning affected role with access to disease-modifying medications. To do this, significant attention should be paid to the premotor stage of PD. Based on premotor characteristics, a unique deep-learning algorithm is provided to swiftly detect whether or not a person has PD. By identifying and assessing indicators that indicate speech attribute and degree of worsening, a voiced numerical biomarker may supplement the laborious traditional physical test. The project attempts to develop a revolutionary end-to-end deep learning model using speech data for Parkinson’s disease identification. The current study employs a mixed deep learning model to evaluate and identify PD. The study’s objectives were to identify vocal anomalies in PD patients and create an automatic test technique that can distinguish concerning PD patients’ voices and those of fit informs while also grading voice quality. his study investigates the effectiveness of utilizing deep learning architectures for speech data analysis in the context of [insert context]. Specifically, we employ a convolutional neural network (CNN) architecture with recurrent layers (e.g., Long Short-Term Memory, LSTM) to extract hierarchical features from raw speech signals. Our methodology involves preprocessing the raw audio data to extract relevant acoustic features, such as mel-frequency cepstral coefficients (MFCCs) and spectrograms. These features are then fed into the CNN-LSTM model, which learns discriminative representations for various speech tasks, including [mention specific tasks, e.g., speech recognition, emotion recognition, etc.].The category accurateness was evaluated using the Italian PVS speaking quantities and the Lithuanian PD voice dataset. With values of 0.92 showing that the results are medically adequate, the findings demonstrated that the suggested model is highly generalizable.

关键词： Deep learning Speech recognition Feature extraction Data models Numerical models Object recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Deep Reinforcement Learning-Based Task Offloading Framework for Edge-Cloud Computing

A Deep Reinforcement Learning-Based Task Offloading Framewor...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Ponugoti Kalpana Muntather Almusawi Yerrolla Chanti V Sunil Kumar M Varaprasad Rao Department of Computer Science and Engineering AVN Institute of Engineering & Technology Telangana India The Islamic University Najaf Iraq School of Computer Science & Artificial Intelligence SR University Warangal India Department of AI and ML Nitte Meenakshi Institute of Technology Bengaluru India Department of Data Science CVR College of Engineering Hyderabad India

By introducing the processing and resources storage to the network edge, edge computing is a new, promising computing paradigm that drastically decreases network traffic and service latency. Many edge computing applications consist of interdependent tasks, wherein the results of one task are the inputs of another. The important and difficult problem of where to position each running task to optimise Quality-of-Service (QoS) is how to offload these tasks to edge of network. In this work, implemented a novel Deep Reinforcement Learning based Task Offloading (DRLTO) method utilized as the intelligent task offloading that uses a Directed Acyclic Graph (DAG) to represent the dependent tasks and off-policy reinforcement learning powered by a Sequence-to-Sequence (S2S) neural network. This research outcomes show that the DRLTO achieved less cloud processing time, and number of single terminal tasks, and percentage of failed task when compared to Deep reinforcement learning-based cloud-edge collaborative mobile computation offloading (DRL-CCMCO) and DeepEdge.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Peer-to-Peer Network Security using 3D Convolutional Autoencoder based Anomaly Detection

Enhancing Peer-to-Peer Network Security using 3D Convolution...

引用

Intelligent Systems and Computational Networks (ICISCN), International Conference on

作者： Rana Veer Samara Sihman Bharattej R Zaid Ajznblasm E. G. Satish Adlin Sylvia A M. Devi Department of Computer Science Saint Leo University FL USA Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology Bengaluru India Department of Computer Science and Engineering Dhanalakshmi Srinivasan College of Engineering and Technology India Department of Electrical and Electronics Engineering New Prince Shri Bhavani College of Engineering and Technology Chennai India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

In this era, Peer-to-Peer (P2P) networks have developed as a revolutionized network for data distribution and alternate to traditional client-server network. The features of P2P networks allow a distributed group of users to stake resources in the form of digital content or information. However, P2P networks lack in controlling access and it has limited security. In this research, Three Dimensional-Convolutional Autoencoder (3D-CA) is proposed to improve the security in P2P network. Initially, the data is obtained from University of New South Wales Network Behavior 2015 (UNSW-NB15) dataset and then preprocessed with data cleaning to ensure data quality. After that, the P2P autoencoder architecture is employed to learn the normal patterns which employs the detection in P2P network. Finally, the proposed 3D-CA is trained to detect the anomalies based on reconstruction error between input node and reconstructed pattern. From the results, the proposed 3D-CA model attained better outcomes compared to existing K-means algorithm in terms of accuracy, precision as well as F1-score by achieving 0.764, 0.90 and 0.80 respectively.

关键词： Accuracy Three-dimensional displays Scalability Autoencoders Telecommunication traffic Reinforcement learning Probabilistic logic Cleaning Peer-to-peer computing Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Task Scheduling Approach for Optimizing 5G Edge Network Performance Through Cloud-Edge Collaborative Computing

A Task Scheduling Approach for Optimizing 5G Edge Network Pe...

引用

Evolutionary Algorithms and Soft Computing Techniques (EASCT), International Conference on

作者： Shanthi M. B. Vaishali Rao K. P. Sudhakar K. N. Parameshachari B. D Department of Computer Science and Engineering CMR Institute of Technology Bengaluru India Department of Information Science and Engineering CMR Institute of Technology Bengaluru India Department of Computer Science and Engineering RV University Bengaluru India Department of Electronics and Communication Engineering Nitte Meenakshi Institute of Technology Bengaluru India

This document discusses various techniques that are crucial for 5G mobile communication. These techniques include high-frequency transmission, direct communication, device-to-device (D2D) communication and massive multiple input and multiple-output (MIMO) technologies. The document provides an overview of each technology, including its benefits and limitations. In addition to these techniques, the document also covers mobile edge computing (MEC), which involves distributing computer resources over mobile communication networks. The document outlines eight potential uses of MEC. Lastly, the document proposes a cloud-edge collaborative computing job scheduling system. The proposed technique aims to dynamically assign computer resources to edge devices based on network conditions and current workloads while considering network latency, computation capability, and energy use. Performance scores for the Cloud Only plan range from 4.0 to 4.5, which shows that the plan is very effective. Lower scores from 1.8 to 3.0 obtained by the Edge Only approach imply that its performance is constrained.

关键词：

来源：评论

学校读者我要写书评

暂无评论

African Vultures Based Feature Selection with Multi-modal Deep Learning for Automatic Seizure Prediction

African Vultures Based Feature Selection with Multi-modal De...

引用

Distributed Computing and Optimization Techniques (ICDCOT), International Conference on

作者： Mounika Nallur Sandhya M Zabiha Khan Mohan B R C P Nayana S A Rajashekhar Software Engineer Masters in Computer Information Systems Murray State University USA Department of Computer Science and Engineering East West Institute of Technology Bengaluru India Department of Artificial Intelligence & Machine Learning Nitte Meenakshi Institute of Technology Bengaluru India

The superiority of life for people with epilepsy can be greatly improved with the assistance of accurate seizure prediction and early warning. An automatic prediction model is required to procedure the EEG signals and account for the leads optimization problematic, as opposed to the majority of hand-designed prediction approaches. In this research, we put forth a fully automated model for seizure prediction using Channel and Spatial attention (CASA). The first step in the feature extraction practice is to pre-process the raw EEG signals. Large amounts of computation can be saved by adding more features to the system, but finding the right ones can be tricky. The African vulture optimization algorithm's (AVOA) strong capacity to break out of local optima is what makes this procedure possible. CASA saved the raw EEG data's temporal and geographical details. Automatic optimization of EEG full-lead data was completed with channel attention (CA), leading to an increase in the accuracy of predictions. The aforementioned adaptive learning of feature parameters was accomplished via spatial attention (SA). When all else fails, a fully associated layer is used to make the seizure forecast. The suggested algorithm is tested on the Freiburg EEG database, and the results reveal that the AVOA-based system performs admirably when it comes to predicting seizures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Fingerprint Based Novel Cancelable Biometric Authentication Technique

A Fingerprint Based Novel Cancelable Biometric Authenticatio...

引用

Innovation in technology (ASIANCON), Asian Conference on

作者： Aruna Ravi K R Karthik S Vineeth B V Yogesh T Kavitha Sooda Karunakara Rai B Computer Science and Engineering B.M.S. College of Engineerig Bangalore India Electronics and Communication Engg Nitte Meenakshi Institute of Technology Bangalore India

In recent years, the usage of diverse biometric technologies for reliable automatic human recognition has grown at an exponential rate. There is rising concern that, with the widespread use of biometric technologies, people's privacy and anonymity may be in risk. In contrast to passwords and credit cards, biometrics are linked to a person forever and cannot be altered if they are stolen. Biometric patterns should be altered using non-invertible and revocable transformations to create cancelable biometric templates in order to avoid theft. A summary of latest advancement in different cancelable biometric systems for biometric template protection is provided. The shortcomings and benefits of current cancelable biometric systems are explored and point out promising research areas for development in this rapidly evolving domain. Also present a model of generating cancelable fingerprint template using Reed Solomon error corrections, which can be used to authenticate a distorted biometric image. This approach provides an accuracy of 95%.

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124页 << < 69 70 71 72 73 74 75 76 77 78 > >>

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：