检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2021年第4期6卷 688-703页

作者： He, Xiankang Chu, Shu-Chuan Liu, Shi-Jian Pan, Jeng-Shyang Yan, Lijun College of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Shenzhen Institute of Information Technology Shenzhen518000 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China College of Science and Engineering Flinders University Adelaide Australia Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China

The localization of wireless sensor network (WSN) is an increasingly promi-nent problem. The goal of this problem is to use the anchor nodes in WSN to esti-mate the geographical location of the unknown nodes. This paper proposes a novel al-gorithm, named dynamic parallel Harris Hawks optimization (DPHHO). It contains the dynamic control strategy of the escaping energy and the parallel communication mecha-nism. DPHHO algorithm significantly improves the global search ability of the original Harris Hawks optimization (HHO) algorithm. Also, a novel localization algorithm based on hop distance correction and DPHHO is proposed. The proposed DPHHO algorithm was tested on the 23 classical test functions and the DPHHO-DV-Hop algorithm is applied to the localization of WSN. The experimental results show that, compared with HHO and other optimization algorithms, the proposed DPHHO algorithm is more effective and efficient. Compared with DV-Hop and other localization algorithms, the proposed DPHHO-DV-Hop is an effective algorithm for the localization of WSN. © 2021, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Closer through commonality: Enhancing hypergraph contrastive learning with shared groups

arXiv

引用

arXiv 2025年

作者： Roh, Daeyoung Han, Donghee Kim, Daehee Han, Keejun Yi, Mun Graduate School of Data Science KAIST Korea Republic of School of Computer Engineering Hansung University Korea Republic of Department of Industrial and Systems Engineering KAIST Korea Republic of

Hypergraphs provide a superior modeling framework for representing complex multidimensional relationships in the context of real-world interactions that often occur in groups, overcoming the limitations of traditional homogeneous graphs. However, there have been few studies on hypergraph-based contrastive learning, and existing graph-based contrastive learning methods have not been able to fully exploit the high-order correlation information in hypergraphs. Here, we propose a Hypergraph Fine-grained contrastive learning (HyFi) method designed to exploit the complex high-dimensional information inherent in hypergraphs. While avoiding traditional graph augmentation methods that corrupt the hypergraph topology, the proposed method provides a simple and efficient learning augmentation function by adding noise to node features. Furthermore, we expands beyond the traditional dichotomous relationship between positive and negative samples in contrastive learning by introducing a new relationship of weak positives. It demonstrates the importance of fine-graining positive samples in contrastive learning. Therefore, HyFi is able to produce high-quality embeddings, and outperforms both supervised and unsupervised baselines in average rank on node classification across 10 datasets. Our approach effectively exploits high-dimensional hypergraph information, shows significant improvement over existing graph-based contrastive learning methods, and is efficient in terms of training speed and GPU memory cost. The source code is available at https://***/Noverse0/***. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

FREEZE THE BACKBONES: A PARAMETER-EFFICIENT CONTRASTIVE APPROACH TO ROBUST MEDICAL VISION-LANGUAGE PRE-TRAINING

arXiv

引用

arXiv 2024年

作者： Qin, Jiuming Liu, Che Cheng, Sibo Guo, Yike Arcucci, Rossella Department of Computing Imperial College London United Kingdom Data Science Institute Imperial College London United Kingdom Department of Earth Science and Engineering Imperial College London United Kingdom Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Modern healthcare often utilises radiographic images alongside textual reports for diagnostics, encouraging the use of Vision-Language Self-Supervised Learning (VL-SSL) with large pre-trained models to learn versatile medical vision representations. However, most existing VL-SSL frameworks are trained end-to-end, which is computation-heavy and can lose vital prior information embedded in pre-trained encoders. To address both issues, we introduce the backbone-agnostic Adaptor framework, which preserves medical knowledge in pre-trained image and text encoders by keeping them frozen, and employs a lightweight Adaptor module for cross-modal learning. Experiments on medical image classification and segmentation tasks across three datasets reveal that our framework delivers competitive performance while cutting trainable parameters by over 90% compared to current pre-training approaches. Notably, when fine-tuned with just 1% of data, Adaptor outperforms several Transformer-based methods trained on full datasets in medical image segmentation. © 2024, CC BY.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Decomposed linear dynamical systems (dLDS) for learning the latent components of neural dynamics

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 2962-2973页

作者： Noga Mudrik Yenho Chen Eva Yezerets Christopher J. Rozell Adam S. Charles Department of Biomedical Engineering Center for Imaging Science Kavli NDI Johns Hopkins University Baltimore MD Department of Biomedical Engineering Georgia Institute of Technology Atlanta GA Department of Biomedical Engineering Center for Imaging Science Johns Hopkins University Baltimore MD School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA Department of Biomedical Engineering Center for Imaging Science Mathematical Institute for Data Science Kavli NDI Johns Hopkins University Baltimore MD

Learning interpretable representations of neural dynamics at a population level is a crucial first step to understanding how observed neural activity relates to perception and behavior. Models of neural dynamics often focus on either low-dimensional projections of neural activity or on learning dynamical systems that explicitly relate to the neural state over time. We discuss how these two approaches are interrelated by considering dynamical systems as representative of flows on a low-dimensional manifold. Building on this concept, we propose a new decomposed dynamical system model that represents complex non-stationary and nonlinear dynamics of time series data as a sparse combination of simpler, more interpretable components. Our model is trained through a dictionary learning procedure, where we leverage recent results in tracking sparse vectors over time. The decomposed nature of the dynamics is more expressive than previous switched approaches for a given number of parameters and enables modeling of overlapping and non-stationary dynamics. In both continuous-time and discrete-time instructional examples, we demonstrate that our model effectively approximates the original system, learns efficient representations, and captures smooth transitions between dynamical modes. Furthermore, we highlight our model's ability to efficiently capture and demix population dynamics generated from multiple independent subnetworks, a task that is computationally impractical for switched models. Finally, we apply our model to neural "full brain" recordings of C. elegans data, illustrating a diversity of dynamics that is obscured when classified into discrete states.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantum-Improved Weather Forecasting: Integrating Quantum Machine Learning for Precise Prediction and Disaster Mitigation

Quantum-Improved Weather Forecasting: Integrating Quantum Ma...

引用

Quantum Technologies, Communications, Computing, Hardware and Embedded Systems Security (iQ-CCHESS), International Conference on

作者： S Suhas S Divya School of Computer Science and Engineering Vellore Institute of Technology Chennai India Centre for Advanced Data Science Vellore Institute of Technology Chennai India

In numerous industries, weather forecasting is essential for making informed decisions and mitigating the effects of extreme weather events. The complexity and chaos of weather systems, however, place restrictions on standard procedures, leading to errors and significant threats. We suggest the Quantum Improved Weather Forecast framework, which combines quantum machine learning methods with conventional methodologies, to solve these issues. By using quantum algorithms including quantum support vector machines, quantum neural networks, and quantum clustering, the QWF framework seeks to improve accuracy. Despite a few drawbacks, the QWF framework provides a method to revolutionize weather forecasting by enhancing prediction accuracy and facilitating improved catastrophe preparedness. It may prevent fatalities, safeguard critical infrastructure, and promote sustainable growth.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GeoAI in Resource-Constrained Environments

GeoAI in Resource-Constrained Environments

引用

AI, science, engineering, and Technology (AIxSET), Conference on

作者： Gede Sughiarta Atiek Kurnianingsih Srikar Reddy Gopaladinne Sujay Shrivastava Hemanth Kumar Reddy Gorla Marc Böhlen Wisnu foundation Denpasar Indonesia Department of Computer Science and Engineering University at Buffalo Buffalo USA Department of Art Institute for Artificial Intelligence and Data Science University at Buffalo Buffalo USA

ISBN: (数字)9798350390995

ISBN: (纸本)9798350391008

This paper describes spatially aware Artificial Intelligence, GeoAI, tailored for small organizations such as NGOs in resource constrained contexts where access to large datasets, expensive compute infrastructure and AI expertise may be restricted. We furthermore consider future scenarios in which resource-intensive, large geospatial models may homogenize the representation of complex landscapes, and suggest strategies to prepare for this condition.

关键词： Computational modeling Organizations Geospatial analysis Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Simulating cyber security management: A gamified approach to executive decision making 22

Simulating cyber security management: A gamified approach to...

引用

Proceedings of the 37th IEEE/ACM International Conference on Automated Software engineering

作者： Adam Tonkin William Kosasih Marthie Grobler Mehwish Nasim Fivecast Australia School of Computer Science The University of Adelaide Australia CSIRO's Data61 Australia Department of Computer Science and Software Engineering The University of Western Australia Australia and College of Science and Engineering Flinders University Australia

ISBN: (纸本)9781450394758

Executive managers are not all equipped with the cyber security expertise necessary to enable them to make business decisions that accurately represent the status and needs of the cyber security side of the business. Unfortunately, the lack of understanding between the business and cyber security domains contribute to structurally endorsed vulnerabilities within a business context, where either the business needs were considered without understanding the impact on cyber security, or alternatively, the cyber security needs were considered without fully understanding the impact this would have on the business strategy and financial stability. To combat this dilemma, a gamified approach to cyber security training for executives is proposed as a solution to not only minimise the realisation of cyber vulnerabilities within a business context, but also to improve business outcomes that are supported by cyber security measures. We developed a serious game software platform, Aurelius, to simulate an executive decision maker’s role in managing the everyday cyber security investment decisions, and linking that to business metrics to incorporate the business and cyber security understanding. Our game includes simulated cyber security attacks that would require the executive decision maker (the player) to respond appropriately. The algorithms underpinning our simulated cyber security game are a product of a complex systems approach, as this most accurately models an executive’s experience. In our design, we set up Aurelius to fulfil eight of the nine criteria specified for a state of the art serious game in the cyber security domain.

关键词： serious game decision making human centric cyber security situational awareness. socio-technical systems simulation

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Assessment and Evaluation: Enhancing Sustainability in Educational Practices

AI-Driven Assessment and Evaluation: Enhancing Sustainabilit...

引用

Automation, Computing and Renewable Systems (ICACRS), International Conference on

作者： P. Chinnasamy M. Pushpalatha V. Nirmala Vidhya V Ramesh Kumar Ayyasamy Divya Priya Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Tamilnadu India Department of Computer Science and Technology Karpagam College of Engineering Coimbatore India Department of MCA Annamacharya PG College of Computer Studies Kadapa Artificial Intelligence and Data Science Kongunadu College of Engineering and Technology (Autonomous) Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman (UTAR) Kampar Perak Malaysia Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

ISBN: (数字)9798331532420

ISBN: (纸本)9798331532437

AI-powered educational technologies are emerging as transformative forces in the quickly changing field of education, where innovation is essential to keeping ahead of the competition. Assessments are one area that is undergoing revolutionary transformation. Artificial Intelligence (AI) is redefining the way we evaluate learning outcomes as traditional evaluation approaches struggle to keep up with the demands of the digital age. The field of artificial intelligence-powered learning assessments has a lot of promising future developments ahead of it. This research proposes novel technique in assessment and evaluation based on online education system using Artificial intelligence in machine learning techniques. Here, the input has been analysed as student performance data based on online education and processed for removing of missing values with noise removal. Then this data has been analysed using spatio LSTM convolutional fuzzy neural network for classification of evaluation and assessment model. the experimental analysis has been carried out for various student performance analysis dataset in terms of training accuracy, average precision, specificity, F-measure and recall. Proposed method training accuracy 97%, Average precision 94%, F-measure 90%, RECALL 93%, SPECIFICITY 96%.

关键词： Training Technological innovation Renewable energy sources Accuracy Education Learning (artificial intelligence) Machine learning Fuzzy neural networks Sustainable development Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Joint Service Placement and Request Scheduling in Mobile Edge Computing Networks 28

Deep Reinforcement Learning for Joint Service Placement and ...

引用

28th IEEE Symposium on computers and Communications, ISCC 2023

作者： Deng, Yuxuan Li, Xiuhua Sun, Chuan Hao, Jinlong Wang, Xiaofei Leung, Victor C. M. School of Big Data and Software Engineering Chongqing University Chongqing China Chongqing Changan Automobile Software Technology Co. Ltd Chongqing China TKLAN College of Intelligence and Computing Tianjin University Tianjin China College of Computer Science and Software Engineering Shenzhen University Shenzhen China The University of British Columbia Department of Electrical and Computer Engineering Vancouver Canada

ISBN: (纸本)9798350300482

Mobile edge computing aims to provide cloud-like services on edge servers located near Mobile Devices (MDs) with higher Quality of Service (QoS). However, the mobility of MDs makes it difficult to find a global optimal solution for the coupled service placement and request scheduling problem. To address these issues, we consider a three-Tier MEC network with vertical and horizontal cooperation. Then we formulate the joint service placement and request scheduling problem in a mobile scenario with heterogeneous services and resource limits, and convert it into two Markov decision processes to decouple decisions across successive time slots. We propose a Cyclic Deep Q-network-based Service placement and Request scheduling (CDSR) framework to find a long-Term optimal solution despite future information unavailability. Specifically, to solve the issue of enormous action space, we decompose the system agent and train them cyclically. Evaluation results demonstrates the effectiveness of our proposed CDSR on user-perceived QoS. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities

arXiv

引用

arXiv 2024年

作者： Narayanaswami, Sai Kiran Srinivasan, Gopalakrishnan Ravindran, Balaraman Centre for Responsible AI Indian Institute of Technology Madras India Robert Bosch Centre for Data Science and AI Dept. of Computer Science and Engineering Indian Institute of Technology Madras India Wadhwani School of Data Science and AI Indian Institute of Technology Madras India

As machine learning gets deployed more and more widely, and model sizes continue to grow, improving computational efficiency during model inference has become a key challenge. In many commonly used model architectures, including Transformers, a significant portion of the inference computation is comprised of exponential non-linearities such as Softmax. In this work, we develop QuAKE, a collection of novel operators that leverage certain properties of IEEE-754 floating point representations to quickly approximate the exponential function without requiring specialized hardware, extra memory, or precomputation. We propose optimizations that enhance the efficiency of QuAKE in commonly used exponential non-linearities such as Softmax, GELU, and the Logistic function. Our benchmarks demonstrate substantial inference speed improvements between 10% and 35% on server CPUs, and 5% and 45% on embedded and mobile-scale CPUs for a variety of model architectures and sizes. Evaluations of model performance on standard datasets and tasks from various domains show that QuAKE operators are able to provide sizable speed benefits with little to no loss of performance on downstream tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Exponential functions

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：