检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Sengar, Sandeep Singh Bin Hasan, Affan Kumar, Sanjay Carroll, Fiona Cardiff School of Technologies Cardiff Metropolitan University CardiffCF5 2YB United Kingdom Department of Computer Science and Engineering Delhi Technological University New Delhi110042 India

In recent years, the study of artificial intelligence (AI) has undergone a paradigm shift. This has been propelled by the groundbreaking capabilities of generative models both in supervised and unsupervised learning scenarios. Generative AI has shown state-of-the-art performance in solving perplexing real-world conundrums in fields such as image translation, medical diagnostics, textual imagery fusion, natural language processing, and beyond. This paper documents the systematic review and analysis of recent advancements and techniques in Generative AI with a detailed discussion of their applications including application-specific models. Indeed, the major impact that generative AI has made to date, has been in language generation with the development of large language models, in the field of image translation and several other interdisciplinary applications of generative AI. Moreover, the primary contribution of this paper lies in its coherent synthesis of the latest advancements in these areas, seamlessly weaving together contemporary breakthroughs in the field. Particularly, how it shares an exploration of the future trajectory for generative AI. In conclusion, the paper ends with a discussion of Responsible AI principles, and the necessary ethical considerations for the sustainability and growth of these generative models. © 2024, CC BY-NC-ND.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Networks for Handwritten Bangla Character Recognition

引用

IAENG International Journal of Applied Mathematics 2023年第4期53卷 1页

作者： Begum, H. Islam, M.M. Eva, H.S. Emon, N.H. Siddique, F.A. Department of Electrical and Electronic Engineering East West University A/2 Aftabnagar Dhaka Bangladesh Department of Electrical Engineering and Computer Science South Dakota State University United States Engineering and Design Department Reverie Power and Automation Engineering Limited Bangladesh Program in Smart System Integrated Solutions Aalto University Finland

In recent years, deep convolutional networks (DCNN) have gained popularity for different classification (or recognition) tasks. In this paper, three well known DCNN structures were used, i.e., AlexNet, SqueezeNet and GoogLeNet, and their classification performances in recognizing handwritten Bangla isolated characters were compared. These networks have simpler structures compared to the recent DCNNs. Experiments on a standard Bangla database revealed that the overall performance of GoogLeNet is slightly better than the other two networks. Further analysis using saliency maps of the test samples revealed the important features that are learned by the networks for classifying characters. This information led us to understand why classification of some samples fail and how to rectify these. © (2023), (International Association of Engineers). All Rights Reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Universal scaling hypothesis of quantum spatial search in complex networks

arXiv

引用

arXiv 2024年

作者： Sato, Rei Nikuni, Tetsuro Nohara, Kayoko Salani, Giorgio Watabe, Shohei Department of Physics Tokyo University of Science Shinjuku Tokyo162-8601 Japan Department of Transdisciplinary Science and Engineering School of Environment and Society Tokyo Institute of Technology 2-12-1 O-okayama Meguro-ku Tokyo152-8550 Japan Faculty of Engineering Computer Science and Engineering Shibaura Institute of Technology Toyosu Tokyo135-8548 Japan

Since quantum spatial searches on networks have a strong network dependence, the question arises whether the universal perspective exists in this quantum algorithm for various networks. Here, we propose a universal scaling hypothesis of the quantum spatial search on complex networks such as small-world and scale-free networks. The average path length, a key quantity in the complex network science, is useful to expose this universal feature, where the collapse plot can be generated for the optimal time, the maximal finding probability and the optimal hopping parameter. Based on the path integral method, we also clarify that the probability amplitude in the continuous-time quantum walk can be determined by the path length distribution. Copyright © 2024, The Authors. All rights reserved.

关键词： Small-world networks

来源：评论

学校读者我要写书评

暂无评论

A Survey of Graph-Based Resource Management in Wireless Networks -Part I: Optimization Approaches

引用

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Dai, Yanpeng Lyu, Ling Cheng, Nan Sheng, Min Liu, Junyu Wang, Xiucheng Cui, Shuguang Cai, Lin Shen, Xuemin Dalian Maritime University School of Information Science and Technology Dalian116026 China Xidian University State Key Laboratory of ISN School of Telecommunications Engineering Xian710071 China Guangdong Provincial Key Laboratory of Future Networks of Intelligence Shenzhen518066 China University of Victoria Department of Electrical and Computer Engineering VictoriaBCV8P 5C2 Canada University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

The evolution of wireless communications and networking technologies has led significantly expansion of the dimensionality of network resources, which compels innovations in resource management. Graphs, a classic discrete mathematical tool, have long been widely used for resource management thanks to their capabilities to model complex relationships and interactions among elements in wireless networks. Recently, resource management over graphs embraces various advanced approaches of graph optimization and graph learning, aligned with evolving demands in future wireless networks. To better learn recent research landscape and explore important trends, this twopart survey provides a comprehensive overview for resource management via graph optimization and learning. Part I presents the fundamentals of graph optimization and provides a recent literature review of graph optimization for resource management in various wireless communication scenarios, including cellular networks, device-to-device communications, multi-hop networks, multi-antenna systems, edge caching and computing, and nonterrestrial networks. Part II gives the basics of graph learning and provides a state-of-the-art literature review of graph learning in wireless networks for addressing various resource management issues, covering power control, spectrum management, beamforming design, task scheduling, and aerial coverage planning. A discussion of technical challenges and future research directions is covered in Part II. © 2015 IEEE.

关键词： graph resource management Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Implantable Nanophotonic Neural Probes with 3D-Printed Microfluidics

Implantable Nanophotonic Neural Probes with 3D-Printed Micro...

引用

2023 Conference on Lasers and Electro-Optics Europe and European Quantum Electronics Conference, CLEO/Europe-EQEC 2023

作者： Mu, Xin Chen, Fu-Der Dang, Ka My Brunk, Michael G.K. Li, Jianfeng Wahn, Hannes Stalmashonak, Andrei Ding, Peisheng Luo, Xianshu Lo, Guo-Qiang Poon, Joyce K.S. Sacher, Wesley D. Max Planck Institute of Microstructure Physics Weinberg 2 Halle06120 Germany Department of Electrical and Computer Engineering University of Toronto 10 King's College Rd. TorontoONM5S 3G4 Canada Advanced Micro Foundry Pte. Ltd. 11 Science Park Road Singapore Science Park II 117685 Singapore

ISBN: (纸本)9798350345995

Implantable neural probes with microfluidic channels have been previously demonstrated for multi-drug delivery [1] and neurochemical sampling [2] in brain tissue. We have previously demonstrated foundry-fabricated implantable nanophotonic neural probes for functional imaging, optogenetic stimulation, and electrophysiology recording [3-5]. To further extend our neural probe functionalities, here we present the integration of microfluidic structures onto neural probes with precise and flexible 3D printing. © 2023 IEEE.

关键词： Electrophysiology

来源：评论

学校读者我要写书评

暂无评论

Gradient-Guided Modality Decoupling for Missing-Modality Robustness

arXiv

引用

arXiv 2024年

作者： Wang, Hao Luo, Shengda Hu, Guosheng Zhang, Jianguo Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Oosto BelfastBT1 2BE United Kingdom Peng Cheng Lab Shenzhen China

Multimodal learning with incomplete input data (missing modality) is practical and challenging. In this work, we conduct an in-depth analysis of this challenge and find that modality dominance has a significant negative impact on the model training, greatly degrading the missing modality performance. Motivated by Grad-CAM, we introduce a novel indicator, gradients, to monitor and reduce modality dominance which widely exists in the missing-modality scenario. In aid of this indicator, we present a novel Gradient-guided Modality Decoupling (GMD) method to decouple the dependency on dominating modalities. Specifically, GMD removes the conflicted gradient components from different modalities to achieve this decoupling, significantly improving the performance. In addition, to flexibly handle modal-incomplete data, we design a parameter-efficient Dynamic Sharing (DS) framework which can adaptively switch on/off the network parameters based on whether one modality is available. We conduct extensive experiments on three popular multimodal benchmarks, including BraTS 2018 for medical segmentation, CMU-MOSI, and CMU-MOSEI for sentiment analysis. The results show that our method can significantly outperform the competitors, showing the effectiveness of the proposed solutions. Our code is released here: https://***/HaoWang420/Gradientguided-Modality-Decoupling. Copyright © 2024, The Authors. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Facial Expression Recognition through Dual-Direction Attention Mixed Feature Networks and CLIP: Application to 8th ABAW Challenge

arXiv

引用

arXiv 2025年

作者： Cabacas-Maso, Josep Ortega-Beltrán, Elena Benito-Altamirano, Ismael Ventura, Carles eHealth Center Faculty of Computer Science Multimedia and Telecommunication Universitat Oberta de Catalunya Barcelona08018 Spain MIND IN2UB Department of Electronic and Biomedical Engineering Universitat de Barcelona Barcelona08028 Spain

We present our contribution to the 8th ABAW challenge at CVPR 2025, where we tackle valence-arousal estimation, emotion recognition, and facial action unit detection as three independent challenges. Our approach leverages the well-known Dual-Direction Attention Mixed Feature Network (DDAMFN) for all three tasks, achieving results that surpass the proposed baselines. Additionally, we explore the use of CLIP for the emotion recognition challenge as an additional experiment. We provide insights into the architectural choices that contribute to the strong performance of our methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Mobile crane signalman static hand signals classification framework using deep convolution neural network 34

Mobile crane signalman static hand signals classification fr...

引用

34th European Modeling and Simulation Symposium, EMSS 2022

作者： Mansoor, Asif Liu, Shuai Ali, Ghulam Muhammad Bouferguene, Ahmed Al-Hussein, Mohamed Soda Department of Civil and Environmental Engineering University of Alberta 9105 116 street EdmontonT6H 2W2 Canada Campus Saint-Jean University of Alberta EdmontonT6C 4G9 Canada Department of Computer Science University of Turbat Pakistan

Cranes are the need of every construction site as the construction paradigm is shifting from traditional (on-site) methods toward an off-site (modularization) approach. The communication between the crane operator and the crane signalman plays a significant role to complete the construction project safely and efficiently. The communication between crane operator and signalman relies on hand signals and two-way radio communication systems. However, these means of communication are not reliable in modern construction as the construction sites are more congested and noisy. Any miscommunication may lead to a disastrous accident on the construction site. The recent advancement in information technology can assist to add more layers of communication in the crane Industry. This paper presents a framework that uses deep convolutional neural network (DCNN) architecture for static hand signal classification using the crane signalman hand signals dataset. The DCNN model was developed to classify 18 different crane signalman hand signals. The model was trained, validated, and tested using a dataset of 8133 images, and achieved average accuracies of 89.1% and 84.6% for the training dataset and the validation dataset, respectively. The precision, recall, and F1 score in the test dataset were recorded as 81.5%, 81.8%, and 81.7%, respectively. The model is further validated with real-time hand signals classification and an accuracy of 87.9% is achieved. This developed framework can be used as another layer of communication with the current state of practice to reduce the communication error between crane signalman and operator. © 2022 The Authors.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Survey of Graph-Based Resource Management in Wireless Networks -Part II: Learning Approaches

引用

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Dai, Yanpeng Lyu, Ling Cheng, Nan Sheng, Min Liu, Junyu Wang, Xiucheng Cui, Shuguang Cai, Lin Shen, Xuemin Dalian Maritime University School of Information Science and Technology Dalian116026 China Xidian University State Key Laboratory of ISN the School of Telecommunications Engineering Xian710071 China the Guangdong Provincial Key Laboratory of Future Networks of Intelligence Shenzhen518066 China University of Victoria Department of Electrical and Computer Engineering VictoriaBCV8P 5C2 Canada University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

This two-part survey provides a comprehensive review of graph optimization and learning for resource management in wireless networks. In Part I, we introduced the fundamentals of graph optimization and provided a recent literature review of graph optimization for resource management in various wireless communication scenarios. In this part, we first present an overview of graph learning and introduce several modern graph neural network models. Then, a state-of-the-art literature review of graph learning for different resource management issues in wireless networks is provided, which covers power control, spectrum management, beamforming design, task scheduling, and aerial coverage planning. Furthermore, we discuss current technical challenges and future research directions of graph optimization and learning for resource management in future wireless networks. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Reduction of Data Transmission in an IoT Wireless Sensor Network 1

引用

2nd International Conference on Pan-African Intelligence and Smart Systems, PAAISS 2022

作者： Njoya, Arouna Ndam Salifu, Amina Djedouboum, Assidé Christian Tchangmena, Allassan A. Nken Ari, Ado Adamou Abba Adouane, Amine Mohamed Abdou, Wahabou Gueroui, Abdelhak Mourad Department of Computer Engineering University Institute of Technology University of Ngaoundéré P.O. Box 455 Ngaoundéré Cameroon African Institute for Mathematical Sciences South West Region Crystal Gardens P.O. Box 608 Limbe Cameroon Department of Computer Science University of Moundou P.O. Box 206 Moundou Chad DAVID Lab Université Paris-Saclay University of Versailles Saint-Quentin-en-Yvelines 45 Avenue des États-Unis Versailles78000 France Department of Computer Science University of Maroua P.O. Box 814 Maroua Cameroon Department of Computer Science University of Algiers 1 2 Rue Didouche Mourad Alger Ctre16000 Algeria LIB EA7534 University Bourgogne Franche-Comté 9 Avenue Alain Savary Dijon21078 France African Institute for Mathematical Sciences Senegal P.O. Box 1418 Mbour-Sénégal Cameroon

ISBN: (数字)9783031252716

ISBN: (纸本)9783031252709

A Wireless Sensor Network (WSN) is a collection of spatially separated and specialized sensors that work together to monitor, record, and transmit information about the physical state of the environment to an internet-based location. To improve WSN power consumption, this work proposes a classification technique where K nearest neighborhood was applied in those clusters to select the best nodes. The purpose of the classification technique is to divide the network into various node-groupings. We calculated the correlation matrix for one node in each group and cluster, and we also applied the RNN model to get a better prediction within each node in each cluster, so only one node of data will be sent from each cluster to the base station. Furthermore, the experimental results reveal that, based on a suitable choice of nodes, our proposed model performs accurate predictions, with a minimum error of 0.01 measured using the Root Mean Squared Error (RMSE). The radio-energy transmission model used in this work also shows that a suitable choice of cluster head reduces the amount of energy consumed by the entire network, and by so doing improves it’s life-time. This has been proven in our network’s lifetime algorithm. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Machine learning

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：