检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Fu, Zezheng Yang, Degang Lin, Wenting Liu, Kangming School of Computer and Information Science Chongqing Normal University Chongqing401331 China Chongqing Engineering Research Center of Educational Big Data Intelligent Perception and Application Chongqing401331 China

Reducing carbon emissions in energy systems remains a critical concern, giving rise to a variety of low-carbon initiatives. Current research largely focuses on the application of individual or dual low-carbon technologies (such as carbon capture, carbon trading, renewable energy, etc.), with limited exploration of the synergistic effects of integrating multiple technologies. To address this, we propose a low-carbon economic dispatch model for an electricity-gas system designed to maintain system stability under extreme conditions in renewable energy scenarios. This study integrates several low-carbon technologies—including carbon capture systems, carbon trading mechanisms, demand response strategies, power-to-gas technology, and renewable energy generation—and examines their collective impact on the system. To address uncertainties in renewable energy output, a two-stage robust optimization framework with a min-max-min structure is developed, aiming to determine optimal renewable energy scheduling under extreme scenarios. By employing a column-and-constraint generation algorithm and the KKT conditions, the problem is decomposed into a primary mixed-integer linear programming problem and a series of subproblems, which are solved iteratively to achieve the optimal solution. Simulation results verify the proposed model's effectiveness. © 2025, The Authors. All rights reserved.

关键词： Carbon capture and utilization

来源：评论

学校读者我要写书评

暂无评论

Leveraging the Strengths of Long Short-Term Memory and Gated Recurrent Unit Architectures for Indian Stock Market Prediction

Leveraging the Strengths of Long Short-Term Memory and Gated...

引用

Emerging Systems and Intelligent Computing (ESIC), International Conference on

作者： Prem Purusottam Jena Kaberi Das Debahuti Mishra Arundhati Lenka Sashikala Mishra Pradeep Kumar Mallick Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to be University Bhubaneswar India Department of Computer Application Siksha ‘O’ Anusandhan (Deemed to be University Bhubaneswar India Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune India School of Computer Engineering KIIT Deemed to be University Bhubaneswar India

The study recognizes the multifaceted nature of the stock market and the challenges inherent in predicting market movements accurately. Focused on the Indian stock market, the research harnesses the capabilities of deep learning, specifically the long short-term memory (LSTM) and gated recurrent unit (GRU) architectures, known for their prowess in processing sequential data with predictions over a 10-day horizon. The models are systematically evaluated, considering parameters such as root mean square error (RMSE), mean absolute error (MAE), regression variance, and R2-score, with a comparative analysis highlighting the effectiveness of the proposed hybrid models—LSTM-GRU and GRU-LSTM. The experimental analysis reveals that the GRU-LSTM model demonstrates superior performance on the HDFC bank Ltd. dataset, while the LSTM-GRU model excels on the TATA Motors Ltd. dataset, aligning with the predictive performance and accuracy metrics observed in earlier experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cold-Start Link Prediction via Weighted Symmetric Nonnegative Matrix Factorization with Graph Regularization

引用

computer Systems science & engineering 2022年第12期43卷 1069-1084页

作者： Minghu Tang Wei Yu Xiaoming Li Xue Chen Wenjun Wang Zhen Liu key Laboratory of Artificial Intelligence Application Technology State Ethnic Affairs Commission Qinghai Minzu UniversityXining810007China School of Computer Science Qinghai Minzu UniversityXining810007China College of Intelligence and Computing Tianjin UniversityTianjin300350China School of International Business Zhejiang Yuexiu UniversityShaoxing312069China Law School Tianjin UniversityTianjin300072China Graduate School of Engineering Nagasaki Institute of Applied ScienceNagasaki851-0193Japan

Link prediction has attracted wide attention among interdisciplinaryresearchers as an important issue in complex network. It aims to predict the missing links in current networks and new links that will appear in future *** the presence of missing links in the target network of link prediction studies, the network it processes remains macroscopically as a large connectedgraph. However, the complexity of the real world makes the complex networksabstracted from real systems often contain many isolated nodes. This phenomenon leads to existing link prediction methods not to efficiently implement the prediction of missing edges on isolated nodes. Therefore, the cold-start linkprediction is favored as one of the most valuable subproblems of traditional linkprediction. However, due to the loss of many links in the observation network, thetopological information available for completing the link prediction task is extremely scarce. This presents a severe challenge for the study of cold-start link prediction. Therefore, how to mine and fuse more available non-topologicalinformation from observed network becomes the key point to solve the problemof cold-start link prediction. In this paper, we propose a framework for solving thecold-start link prediction problem, a joint-weighted symmetric nonnegative matrixfactorization model fusing graph regularization information, based on low-rankapproximation algorithms in the field of machine learning. First, the nonlinear features in high-dimensional space of node attributes are captured by the designedgraph regularization term. Second, using a weighted matrix, we associate the attribute similarity and first order structure information of nodes and constrain eachother. Finally, a unified framework for implementing cold-start link prediction isconstructed by using a symmetric nonnegative matrix factorization model to integrate the multiple information extracted together. Extensive experimental validationon five rea

关键词： Link prediction cold-start nonnegative matrix factorization graph regularization

来源：评论

学校读者我要写书评

暂无评论

Explore Unsupervised Exposure Correction Via Illumination Component Divided Guidance

SSRN

引用

SSRN 2023年

作者： Wei, Sun Linyang, Tian Ruijia, Cui Xiaobao, Yang Yanning, Zhang School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology China

Capturing images with poor exposures remains a major source of errors in camera-based photography. Under- or over-exposure problems greatly reduce contrast and naturalness, and the disappearance of detailed content affects the understanding of an image. While recent works have built a great deal of learning frameworks to address the problem, they mainly focus on low-light or general image enhancement. Towards this end, we explore an unsupervised exposure correction framework. Our model disentangles the exposure correction into two easier sub-tasks. Different branches focus on different missions, making the network easy to solve coupling correction problems. Additionally, a novel attention-based pixel-wise brightness estimation makes it possible for coarse-to-fine mapping adjustment and correction. Experiments on various widely used benchmark datasets show that, relying on illumination perception and components divided guidance, the proposed network can outperform previous state-of-the-art methods, especially for recovering fine detailed contents. © 2023, The Authors. All rights reserved.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

Design of Deep Learning Models for the Identification of Harmful Attack Activities in the Industrial Internet of Things (IIOT)

Design of Deep Learning Models for the Identification of Har...

引用

IEEE UP Section Conference on Electrical computer and Electronics (UPCON)

作者： Rajesh M Rajiv Vincent Sakshi Kathuria Bhavana Jamalpur Thirupathi Durgam Tarun Jaiswal School of Computer Science and Engineering Vellore Institute of Technology Chennai Computer Science and Engineering K. R. Mangalam University University Gurugram Haryana School of Computer Science and Artificial Intelligence SR University Warangal Telangana ECE St. Martins Engineering College JNTUH University (Hyderabad) Department. of Computer Application National Institute of Technology Raipur C.G.

Traditional industrial processes benefit greatly from the Industrial Internet of Things (IIoT), which increases efficiency as well as productivity. However, as IIoT becomes more connected, critical infrastructure is exposed to a variety of cyber risks. In order to accurately identify dangerous attack behaviors within IIoT systems, the present research focuses on the development and execution of deep learning models, combining recurrent neural networks (RNNs) including artificial neural networks (ANNs). The approach uses Python-based visualization techniques, model creation, and data pretreatment. By proactively identifying and mitigating cyber risks, our research seeks to strengthen IIoT security and ensure the resilience and honesty of industrial operations in a world that is becoming more linked.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SBA: A Swift and Stealthy Backdoor Attack Framework for Federated Learning

SBA: A Swift and Stealthy Backdoor Attack Framework for Fede...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Junhan Wang Zhangming Wu Zhuoyue Wang Lu Dong School of Cyber Science and Engineering Southeast University Nanjing China Engineering Research Center of Blockchain Application Supervision and Management Southeast University Ministry of Education Department of Electrical Engineering and Computer Sciences University of California Berkeley USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Federated Learning (FL) enables collaborative model training while protecting the privacy of individual participants. However, this decentralized framework is vulnerable to certain risks, particularly backdoor attacks. In such attacks, malicious actors embed triggers into the global model, causing incorrect classifications for inputs with specific features. Traditional backdoor attacks typically use uniform triggers, which makes them more likely to be detected. Furthermore, These methods tend to overlook the fact that poisoned samples may cause abnormal confidence levels in non-target classes. These methods also require an extended attack window to achieve the desired success rate, which reduces their efficiency and increases the chances of detection. This paper introduces a novel backdoor attack method called Swift Backdoor Attack (SBA), designed to overcome these challenges. SBA improves both the stealth and success rate of backdoor attacks by generating adaptive triggers tailored to specific inputs. It also incorporates Non-Target Class Suppression (NTCS) loss and an entropy gain mechanism to enhance the attack’s effectiveness. Our approach suppresses unnecessary activations in the neural network when encountering poisoned samples, making the attack harder to be detected. Experimental results demonstrate that this method significantly increases the success rate of backdoor attacks within a shorter attack window, while evading existing detection mechanisms. This provides a more efficient and covert strategy for executing backdoor attacks in FL. Our code is available at https://***/bigcheeses/SBA.

关键词： Training Privacy Codes Federated learning Neural networks Collaboration Signal processing Entropy Robustness Speech processing

来源：评论

学校读者我要写书评

暂无评论

Adaptive Beamforming in MIMO Systems Using Deep Learning

Adaptive Beamforming in MIMO Systems Using Deep Learning

引用

2024 IEEE International Conference on Communication, Computing and Signal Processing, IICCCS 2024

作者： Vinithra Banu, T. Hussein, Layth Grover, Varsha Kumar, T. Arun Sharma, Rupesh Sudha, I. Prince Shri Venkateshwara Padmavathy Engineering College Chennai India The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq The Islamic University Of Al Diwaniyah College Of Technical Engineering Department Of Computers Techniques Engineering Al Diwaniyah Iraq Chandigarh Group of Colleges Chandigarh Engineering College Department of Computer Application Punjab Jhanjeri Mohali140307 India Kongu Engineering College Department of Cse India Ies University Ies Institute of Technology and Management Department of Electronics & Communication Engineering M.P. Bhopal India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350390759

One of the most significant procedures in MIMO system is the adaptive beamforming which is the technique of adjusting the direction of signal transmission for better wireless communication. This paper aims to investigate the application of deep learning in combination with adaptive beamforming for the improvement of the existing technologies and techniques having some limitations which prove efficient when working in certain applications and scenarios only. Utilizing the CNNs and RNNs, the proposed approach then determines ideal beamforming patterns from various datasets, synthetic simulations, as well as measured ones. In this paper, various approaches are employed which include the Super & Reinforcement learning techniques, which makes the deep learning-based models capable of learning in real-time the change of channel characteristics. Simulations and practical adaptations of changing protocols have illustrated substantial enhancements on SINR, BER, and system capacity. The conclusion indicates that the proposed DL based technique is better than the existing standards providing more considerably higher data rates with reasonable less error rates and possessing highly adaptive capability. From the literature, it is clear that deep learning has a significant use in adaptive beam forming;although it has significantly increased the computational load. For future wireless communication technologies such as 5G and beyond MIMO systems this work has demonstrated the promises of deep learning to improve such systems. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Real-time Monitoring and Control Systems Using IoT-Integrated Wireless Sensor Networks - Leveraging Machine Learning Algorithms for Enhanced Performance and Efficiency

Real-time Monitoring and Control Systems Using IoT-Integrate...

引用

Cybernation and Computation (CYBERCOM), International Conference on

作者： Subbiah Swaminathan N. Poongavanam M. Arun S. Pushparani A. Muthukrishnan Prashant Johri Department of Information Technology Rajalakshmi Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Saveetha University Chennai Department of Electronics and Communication Engineering Panimalar Engineering College Chennai Tamil Nadu Department of Computer Science and Engineering Meenakshi College of Engineering Chennai Tamil Nadu Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai Tamil Nadu India School of Computer Application and Technology Galgotias University

ISBN: (数字)9798331542344

ISBN: (纸本)9798331542351

This paper introduces a developed real-time monitoring and control system using Internet of Things (IoT) incorporated Wireless Sensor Networks (WSNs) supported by machines learning algorithms. The system focuses at meeting core issues and questions in terms of productivity, reliability and timeliness within evolving settings. The current paper contributes to the ongoing research and development in the area of IoT and WSN to enable, always-on real-time data gathering from a variety of discrete sensors which is invaluable for various applications including industrial, environmental and smart city applications. The heart of the system is based on the idea of utilising machine learning methods to acquire and elaborate sensor signals. More specifically, the deep learning models that are used include Long Short-Term Memory (LSTM) networks as well as Reinforcement Learning (RL) algorithms for predictive analytics, as well as anomaly detection. The work also entails a comparison of the system performance based on energy consumption and other factors such as latency, packet delivery ratio and even the accuracy of the predictions made by the system. The findings suggest improved utilisation within substantial ranges; decreased energy use by 30 per cent or more. 7%, latency decrease by 33. Although achieving this was accompanied by an increased data packet loss rate to 3%, the overall packet delivery ratio was boosted to 98%. Additionally, the system established overall accuracy rate of 95% with negligible error percentage. In conclusion, this research proves the applicability of incorporating the IoT and the advanced machine learning methods in the real-time monitoring and control systems development to overcome cases of low efficiency and reduced performance in numerous real-world applications..

关键词： Wireless sensor networks Energy consumption Machine learning algorithms Accuracy Smart cities Predictive models Control systems Real-time systems Reliability Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Spectral-Spatial Fusion Hypergraph Convolutional Network for Multispectral Point Cloud Classification 11

Spectral-Spatial Fusion Hypergraph Convolutional Network for...

引用

11th International Conference on Information Systems and Computing Technology, ISCTech 2023

作者： Huang, Jiangbo Wang, Qingwang Zhang, Zifeng Liu, Sivang Wang, Zhifeng Shen, Tao Kunming University of Science and Technology Yunnan Key Laboratory of Computer Technologies Application Kunming China Kunming University of Science and Technology School of Information Engineering and Automation Kunming China Real Estate Resource Management Center General Logistics Department of Pla Beijing China Beijing Anlu International Technology Co Beijing China

ISBN: (纸本)9798350342406

Graph Neural Networks (GNNs) based on simple graph can directly model 3D multispectral point clouds, thus avoiding the problem of 3D spatial information loss when converting 3D point clouds to 2D feature images. However, considering the dense distribution of objects in remote sensing scenes, GNNs only consider the association between pairs of vertices, which is insufficient for exploring high-order correlations and long-term dependence correlations. Hypergraph neural network (HGNN) is a more generalized framework that overcomes the limitations of traditional simple graph. In this paper, we propose a spectral-spatial fusion hypergraph convolutional network (S2FHGCN) for 3D multispectral point cloud classification. S2FHGCN first generates two hypergraphs from multidimensional features including spectral feature and spatial feature, respectively. The hypergraph structure can better handle complex high-order correlations for representation learning. Then the two hypergraphs are fused to obtain global representation information. Finally, the multidimensional features and the fused hypergraph are input to the hypergraph convolution network. The experimental results on real multispectral point clouds demonstrate the effectiveness of our proposed S2FHGCN for multispectral point cloud classification. © 2023 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level

arXiv

引用

arXiv 2023年

作者： Luo, Haoran Haihong, E. Yang, Yuhao Guo, Yikai Sun, Mingzhi Yao, Tianyu Tang, Zichen Wan, Kaiyang Song, Meina Lin, Wei School of Computer Science Beijing University of Posts and Telecommunications China School of Automation Science and Electrical Engineering Beihang University China Beijing Institute of Computer Technology and Application China Inspur Group Co. Ltd. China

Link Prediction on Hyper-relational Knowledge Graphs (HKG) is a worthwhile endeavor. HKG consists of hyper-relational facts (H-Facts), composed of a main triple and several auxiliary attribute-value qualifiers, which can effectively represent factually comprehensive information. The internal structure of HKG can be represented as a hypergraph-based representation globally and a semantic sequence-based representation locally. However, existing research seldom simultaneously models the graphical and sequential structure of HKGs, limiting HKGs' representation. To overcome this limitation, we propose a novel Hierarchical Attention model for HKG Embedding (HAHE), including global-level and local-level attention. The global-level attention can model the graphical structure of HKG using hypergraph dual-attention layers, while the local-level attention can learn the sequential structure inside H-Facts via heterogeneous self-attention layers. Experiment results indicate that HAHE achieves state-of-the-art performance in link prediction tasks on HKG standard datasets. In addition, HAHE addresses the issue of HKG multi-position prediction for the first time, increasing the applicability of the HKG link prediction task. Our code is publicly available. © 2023, CC BY-NC-SA.

关键词： Forecasting

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：