检索结果-内蒙古大学图书馆

Decision Making: Applications in Management and Engineering 2023年第1期6卷 303-320页

作者： Mukherjee, Anupam Barma, Partha Sarathi Dutta, Joydeep Das, Sujit Pamucar, Dragan School of Applied Science and Humanities Haldia Institute of Technology Haldia India Center for Distance and Online Education The University of Burdwan Burdwan India Dept. of Computer Science Kazi Nazrul University Asansol India National Institute of Technology Warangal India Department of Operations Research and Statistics Faculty of Organizational Sciences University of Belgrade Belgrade Serbia

In this paper, we formulate and solve an Imprecise Covering Ring Star Problem (ICRSP), a generalization of the Ring Star Problem (RSP). For a given network, the objective of this problem is to find a subset of nodes that forms a cycle, and other nodes are left-out nodes. This problem minimizes the total routing cost due to the cycle itself and assignment costs from the left-out nodes assigned to their nearest concentrators (i.e., nodes on the cycle). No assigned node exceeds a predetermined covering distance from its concentrator. The covering distance and the routing and assignment costs are considered fuzzy in the proposed ICRSP. A Modified Genetic Algorithm (MGA) has been developed and used to solve this model for different confidence levels depending on the corresponding imprecise parameters, reducing it to a deterministic form with fuzzy possibility and necessity approaches. Some comparisons with TSP benchmark problems are presented to justify the algorithm's performance. As individual cases, some practical ICRSPs are also solved and presented numerically. © 2023 by the authors.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Adaptive Federated Learning for EEG Emotion Recognition

Adaptive Federated Learning for EEG Emotion Recognition

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Calvin Chan Qingqing Zheng Chengjian Xu Qiong Wang Pheng Ann Heng Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Department of Computer Science and Engineering The Chinese University of Hong Kong

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Emotion classification based on electroencephalogram (EEG) signals has drawn huge attention in affective brain computer interface (BCI). Recently, plenty of deep learning approaches have been proposed to improve the performance of EEG emotion recognition, especially the application of domain adaptation methods to tackle the challenge of large individual differences of EEG signals from subject to subject. However, these conventional transfer learning methods would result in information leakage during the sharing of domain data to enhance the accuracy of the target tasks. Therefore, in this paper, we proposed a distributed deep learning method, named adaptive federated learning (AdaFL) for EEG emotion recognition. In AdaFL, a server collaboratively learns a global model by adaptively aggregating the local models according to their importance in several communication rounds. In particular, an importance function is developed to evaluate each client, which would determine to select a subset of optimal clients for subsequent global model aggregation. The function is a simple transformation of the training loss and the sample size of the local models. Then, the resulting importance scores of selected clients are further converted into aggregation coefficients to measure the weights of the local models for global model aggregation. The distinct advantage of AdaFL is that the cross-subject information could be well utilized and the information leakage risk could be significantly reduced. To validate the efficacy of the proposed AdaFL, we conduct extensive experiments on two real EEG emotion datasets, i.e., SEED and DEAP. The experimental results show that the proposed AdaFL has achieved 94.95 ± 0.40% and 91.06 ± 0.29% average classification accuracy on the SEED and DEAP datasets, respectively, which reflects the superiority of our method over the state-of-the-art approaches.

关键词： Training Deep learning Adaptation models Emotion recognition Accuracy Federated learning Brain modeling

来源：评论

学校读者我要写书评

暂无评论

Towards Depth-continuous Scene Representation with Displacement Field for Robust Light Field Depth Estimation

引用

IEEE Transactions on Multimedia 2025年 27卷 3637-3649页

作者： Chen, Rongshan Sheng, Hao Yang, Da Cong, Ruixuan Cui, Zhenglong Wang, Sizhe Wang, Tun Zhao, Mingyuan Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Key Laboratory of Data Science and Intelligent Computing International Innovation Institute 166 Shuanghongqiao Street Pingyao Town Yuhang District Hangzhou31 1115 China Macao Polytechnic University Faculty of Applied Sciences Macao999078 China

The light field (LF) captures both the spatial and angular information of scenes, enabling accurate depth estimation. However, previous deep learning methods typically model surface depth only while ignoring the continuous nature of depth in 3D scenes. In this paper, we use the displacement field (DF) to describe this continuous property, and propose a novel depth-continuous scene representation for robust LF depth estimation. Experiments demonstrate that our representation enables the network to generate highly detailed depth maps with fewer parameters and faster speeds. Specifically, inspired by the signed distance field in 3D object descriptions, we aim to exploit the intrinsic depth-continuous property of 3D scenes via DF and define a novel depth-continuous scene representation. Then, we introduce a simple, yet general, learning framework for depth-continuous scene embedding, and the proposed network, DepthDF, achieves state-of-the-art performance on both synthetic and real-world LF datasets, ranking 1st on the HCI 4D light field benchmark. Furthermore, previous LF depth estimation methods can also be seamlessly integrated into this framework. Finally, we extend this framework beyond LF depth estimation to various tasks, including multiview stereo depth inference, LF superresolution, and LF salient object detection. Our experiments demonstrate an improved performance when continuous scene representation is applied, suggesting that our framework can potentially provide insights for more fields. © 1999-2012 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

3L-AODV: Three Layer Security Protocol for Grayhole Attack Mitigation in MANET 8th

3L-AODV: Three Layer Security Protocol for Grayhole Attack ...

引用

8th International Congress on Information and Communication Technology, ICICT 2023

作者： Kamel, Mohammed B. M. Abdullah, Wisam Dawood Hamoud, Alaa Khalaf Valadares, Dalton C. G. Shareiyat, Ammar Ligeti, Peter Department of Computer Algebra Eotvos Lorand University Budapest Hungary Institute for Data Science Cloud Computing and IT Security Furtwangen University of Applied Sciences Furtwangen im Schwarzwald Germany Department of Computer Science University of Kufa Najaf Iraq Department of Computer Science University of Tikrit Tikrit Iraq Department of Computer Information Systems University of Basrah Basrah Iraq Virtus RDI Center Federal University of Campina Grande Campina Grande Brazil Federal Institute of Pernambuco Pernambuco Caruaru Brazil Department of CSS University of Stockholm Stockholm Sweden Department of Vulnerability Operations Center Orange Cyberdefense Stockholm Sweden

ISBN: (纸本)9789819930425

As the mobile ad hoc networks infrastructure has no centralized points of connections, the traffic from a source to a destination passes through number of intermediate nodes. When more than one neighbor node is available, the traffic passes through one of them based on some criteria. If a node behaves maliciously in all of the connections and drops the traffic, it creates a security blackhole, while a malicious node that behaves normally is some of the connections creates a security grayhole. Since the malicious node behaves normally in some connections, mitigating this attack is challenging. In this paper, we proposed 3L-AODV, a security protocol that uses three layers of protection and detection to mitigate the grayhole attack. As it does not require any modification on the AODV protocol, it can be implemented on any network that its routing is based on AODV. The analysis of our results shows that 3L-AODV could mitigate the grayhole attack without affecting the performance of the network. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Robust Detection of Tables in Documents Using Scores from Table Cell Cores

引用

SN computer Science 2022年第2期3卷 161页

作者： Ajij, Md. Pratihar, Sanjoy Roy, Diptendu Sinha Hanne, Thomas Department of Computer Science and Engineering National Institute of Technology Meghalaya Shillong India Department of Computer Science and Engineering Indian Institute of Information Technology Kalyani India FHNW University of Applied Sciences and Arts Northwestern Switzerland School of Business Riggenbachstrasse 16 Olten 4600 Switzerland

Table detection is an essential step in many document analysis systems. Tabular data are a pivotal form of information representation that can organize data in a conventional structure for comfortable and quick information retrieval and comparison. Detection of table structures in PDF files or images is a challenging task because of the variability of table layouts, and sometimes the tabular structures’ similarities with non-tabular elements like charts, plots, etc. In this work, we have presented a table detection method using a geometric analysis of the table cell cores that represents the table cell texts. The proposed method works by analyzing the text gap information, and hence it can detect the table cell cores, irrespective of the presence of the table boundary lines and cell-separating rule-lines. Experimentations have been done on various document images of complex structures from well-known datasets. The detection accuracies obtained by us corroborate the usefulness of the proposed method. © The Author(s) 2022.

关键词： Document analysis Information retrieval Table recognition

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic-Based Deep Learning for Human-Machine Interaction and Gesture Recognition in Uncertain and Noisy Environments 1

Fuzzy Logic-Based Deep Learning for Human-Machine Interactio...

引用

1st International Conference on Advances in computer Science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Anand, John Thamilarasi, V. Rayal, Ashish Gupta, Himanshu Kumar Jyothi, Kamboji Vishwakarma, Pramatma Greater Noida201310 India Department of Computer Science & Engineering Tamilnadu Salem-16 India School of Applied and Life Sciences Uttaranchal University Department of Mathematics Dehradun248007 India Bipin Tripathi Kumaon Institute of Technology Department of Electrical Engineering Almora Dwarahat India Chaitanya Bharathi Institute of Technology Department of Mathematics AP Proddatur India Lovely Professional University Department of Computer Aplication Punjab 144411 India

ISBN: (纸本)9798331518578

Conventional deep learning methods have considerable hurdles when it comes to Human-Machine Interaction (HMI) and gesture identification in noisy and uncertain situations. A Fuzzy Logic-Based Deep Learning (Fuzzy DL) method is presented in this work to improve the resilience, accuracy, and adaptability of human gesture recognition in a variety of scenarios. We test several algorithms on various datasets, lighting situations, and noise levels, such as CNN, LSTM, Transformer, and Fuzzy DL. The outcomes show that Fuzzy DL functions better than other systems, retaining 91.0% accuracy at high noise levels and reaching 97.5% accuracy under typical circumstances. In comparison to traditional structures, it also shows faster inference times and a lower mean squared error. Its superiority is further demonstrated by comparative analysis on precision, recall, and F1-score. This study presents a robust and noise-resilient solution for real-world HMI applications, including as assistive systems and virtual interfaces. The outcomes indicate that incorporating fuzzy logic with DL substantially enhances gesture recognition in difficult environments. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-based AI approach towards smart home organization security

A Blockchain-based AI approach towards smart home organizati...

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Khan, Sarfraz Fayaz Priya, S. Sharon Soni, Mukesh Keshta, Ismail Khan, Ihtiram Raza SAT – Algonquin College Ottawa Canada Abdur Rahman Crescent Institute of Science and Technology Tamil Nadu India Department of CSE University Centre for Research and Development Chandigarh University Punjab Mohali India Computer Science and Information Systems Department College of Applied Sciences AlMaarefa University Riyadh Saudi Arabia Computer Science Department Jamia Hamdard Delhi India

ISBN: (纸本)9781032669663

The Internet of Things’ (IoT) predicted enormous breadth and extensive organization make it challenging to acknowledge safe and secret communications. Investigations on the application of BC technology for decentralized assurance as well as protection are still ongoing. However, these arrangements are quite difficult to implement in terms of computation requirements and time constraints, preventing them from being used in most IoT applications. This study describes a blockchain-based asset-productive explanationwith regard to safe as well aspersonal Internet-of-Thing. The arrangement has beenfacilitated by the unique use of double-dealing of computing sources within a typical Internet-of-Things surrounding (such as intelligent houses), as well as the use of a Deep Outrageous Learning Machine event (DOLME). The Brilliant Home Engineering located in Blockchain gets protected in this suggested method by carefully evaluating its unshakable quality about the essential security elements of protection, trustworthiness, and availability. The overheads incurred with this approach (in regards to propagation, handling stage, along withpower use) have been peripherally linkedwith their assurance as well as protection advantages, which is why we also give reproduction findings. © 2024 The Author(s).

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Electricity Consumption by ICT: Facts, trends, and measurements

引用

Ubiquity 2023年第8期2023卷 1-15页

作者： Gelenbe, Erol Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice44100 Poland Université Côte d'Azur CNRS I3S Nice06000 France Dept. of Computer Engineering Yaşar University Bornova Izmir Turkey

This paper considers key issues surrounding energy consumption by information and communication technologies (ICT), which has been steadily growing and is now attaining approximately 10% of the worldwide electricity consumption with a significant impact on greenhouse gas emissions. The perimeter of ICT systems is discussed, and the role of the subsystems that compose ICT is considered. Data from recent years is used to understand how each of these sub-systems contribute to ICT's energy consumption. The quantitatively demonstrated positive correlation between the penetration of ICT in the world's different economies and the same economies' contributions to undesirable greenhouse gas emissions is also discussed. The paper also examines how emerging technologies such as 5G, AI, edge computing, and cryptocurrencies are contributing to the worldwide increase in electricity consumption by ICT, despite the increases in ICT efficiency, in terms of energy consumed per bit processed, stored, or transmitted. The measurement of specific ICT systems' electricity consumption is also addressed, and the manner in which this consumption can be minimized in a specific edge computing context is discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Primordial Black Holes from Null Energy Condition Violation during Inflation

引用

Physical Review Letters 2024年第2期133卷 021001-021001页

作者： Yong Cai Mian Zhu Yun-Song Piao Institute for Astrophysics School of Physics Faculty of Physics Astronomy and Applied Computer Science School of Physical Sciences International Centre for Theoretical Physics Asia-Pacific School of Fundamental Physics and Mathematical Sciences Hangzhou Institute for Advanced Study

Primordial black holes (PBHs) and the violation of the null energy condition (NEC) have significant implications for our understanding of the very early Universe. We present a novel approach to generate PBHs via the NEC violation in a single-field inflationary scenario. In our scenario, the Universe transitions from a first slow-roll inflation stage with a Hubble parameter H=Hinf1 to a second slow-roll inflation stage with H=Hinf2≫Hinf1, passing through an intermediate stage of NEC violation. The NEC violation naturally enhances the primordial scalar power spectrum at a certain wavelength, leading to the production of PBHs with masses and abundances of observational interest. We also investigate the phenomenological signatures of scalar-induced gravitational waves resulting from the enhanced density perturbations. Our work highlights the potential of utilizing a combination of PBHs, scalar-induced gravitational waves, and primordial gravitational waves as a valuable probe for studying NEC violation during inflation, opening up new avenues for exploring the early Universe.

关键词： Classical black holes Dark matter Evolution of the Universe Gravitational waves Inflation

来源：评论

学校读者我要写书评

暂无评论

Train in Austria, Race in Montecarlo: Generalized RL for Cross-Track F1tenthLIDAR-Based Races 19

Train in Austria, Race in Montecarlo: Generalized RL for Cro...

引用

19th IEEE Annual Consumer Communications and Networking Conference, CCNC 2022

作者： Bosello, Michael Tse, Rita Pau, Giovanni Università di Bologna DISI: Department of Computer Science and Engineering Cesena Italy School of Applied Sciences Macao Polytechnic Institute China Ucla Samueli Computer Science Department Los Angeles United States

ISBN: (纸本)9781665431620

Autonomous vehicles have received great attention in the last years, promising to impact a market worth billions. Nevertheless, the dream of fully autonomous cars has been delayed with current self-driving systems relying on complex processes coupled with supervised learning techniques. The deep reinforcement learning approach gives us newer possibilities to solve complex control tasks like the ones required by autonomous vehicles. It let the agent learn by interacting with the environment and from its mistakes. Unfortunately, RL is mainly applied in simulated environments, and transferring learning from simulations to the real world is a hard problem. In this paper, we use LIDAR data as input of a Deep Q-Network on a realistic 1/10 scale car prototype capable of performing training in real-time. The robot-driver learns how to run in race tracks by exploiting the experience gained through a mechanism of rewards that allow the agent to learn without human supervision. We provide a comparison of neural networks to find the best one for LIDAR data processing, two approaches to address the sim2real problem, and a detail of the performances of DQN in time-lap tasks for racing robots. © 2022 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：