检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Ma, Yu Wang, Xingya Gu, Xin Zhao, Zhihong College of Computer and Information Engineering College of Artificial Intelligence Nanjing Tech University Jiangsu Nanjing211816 China College of Command and Control Engineering Army Engineering University of PLA Jiangsu Nanjing210001 China College of Computing Science and Artificial Intelligence Suzhou City University Jiangsu Suzhou215104 China

In Ethereum, a game-theoretic relationship exists among transactions competing to be included in blocks. Miners prioritize transactions in the memory pool by their gasPrice, and select higher-ranked transactions for confirmation in blocks firstly. Consequently, from the perspective of transactions, this process of selection and packaging can be likened to a queuing system. To assist users in saving transaction fees and reducing waiting time, this paper utilizes a queuing game model to describe the transaction confirmation competition process and proposes an optimal pricing strategy for Ethereum transaction gasPrice that satisfies the Nash equilibrium. Specifically, the paper first models the queuing competition for transaction confirmation as a non-preemptive queuing model with priority. Then, it analyzes the impact of gasPrice on waiting time, deducing a functional relationship between waiting time and gasPrice, thereby deriving the users’ Nash equilibrium payment strategy. Experimental results demonstrate that compared to two state of the art machine learning-based pricing strategies and one based on Poisson regression, applying the pricing strategy proposed in this paper increases the Packing Rates of transactions being included in the next block by 56.21%, 50.95%, and 39.15%, respectively, and achieves cost savings of 21 times, 297 times, and 3 times for users. The results indicate that the gasPrice optimal pricing strategy proposed in this paper helps users effectively balance waiting time and cost. © 2023, The Authors. All rights reserved.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

LDNet-RUL: Lightweight Deformable Neural Network for Remaining Useful Life Prognostics of Lithium-ion Batteries

引用

IEEE Transactions on Power Electronics 2025年

作者： Wu, Xiankui Li, Penghua Deng, Zhongwei Liu, Zhitao Kurboniyon, Mekhrdod S. Xiang, Sheng Yin, Gang Chongqing University of Posts and Telecommunications School of Computer Science and Technology Chongqing400065 China Chongqing University of Posts and Telecommunications School of Automation Chongqing400065 China Chongqing University of Science and Technology School of Computer Science and Engineering Chongqing401331 China University of Electronic Science and Technology School of Mechanical and Electrical Engineering Chengdu611731 China Zhejiang University Institute of Cyber-Systems and Control Zhejiang 310058 China National Academy of Sciences of Tajikistan Center of Innovative Development of Science and New Technologies Dushanbe734025 Tajikistan Chongqing University College of Resource and Safety Engineering Chongqing400044 China

Deep neural networks (DNNs)-based battery remaining useful life (RUL) prognostics models suffer from high computational costs, long inference times, and a tendency to overfit, posing significant challenges for deployment on memory-constrained edge devices. To address this, LDNet-RUL, a lightweight yet high-performance model, is proposed for lithiumion battery lifetime prognostics. Specifically, a deformable depthwise convolution unit is designed that efficiently adapts to variations in input features with relatively low computational cost, which leverages fewer parameters and an adaptive receptive field to capture battery degradation dynamics. A multi-scale feature extraction method is introduced to extract degradation features from both short-term and long-term data during the battery charging process, which makes the method applicable to various battery charging protocols. To address overfitting and accelerate model inference, an adaptive channel selector, an adaptive residual connector, and a progressive dimensionalitygrouped bottleneck filter are incorporated to refine feature selection and reduce the model's complexity, boosting the model's overall performance. Experiments on vehicle lithium-ion battery datasets demonstrate that LDNet-RUL achieves state-of-the-art (SOTA) performance, with average RMSE of 0.23 and Score of 0.49. The model is lightweight, with only 7.92K parameters, achieves inference times of 3.94ms on GPU and CPU, and 5.39ms on the NVIDIA Jetson TX2. © 1986-2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Amplitude-frequency-aware deep fusion network for optimal contact selection on STN-DBS electrodes

引用

science China(Information sciences) 2022年第4期65卷 48-63页

作者： Linxia XIAO Caizi LI Yanjiang WANG Weixin SI Hai LIN Doudou ZHANG Xiaodong CAI Pheng-Ann HENG College of Control Science and Engineering China University of Petroleum (East China) Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Department of Neurosurgery Shenzhen Second People's Hospital School of Medicine Shenzhen University Department of Computer Science and Engineering The Chinese University of Hong Kong

Parkinson's disease(PD) is treated effectively by deep brain stimulation(DBS) of the subthalamic nucleus(STN), using an electrode inserted into the head of a PD patient. The electrode has multiple electrical contacts along its length, so the best may be chosen for selectively stimulating the STN. Neurosurgeons usually determine the optimal stimulated contact via the clinical experience of the neurosurgeon and the motor improvement of PD patients. This is a time-consuming and labor-intensive trial-and-error process. The selection of optimal stimulated contact highly depends on the locations of sweet spots, which are manually identified by the characteristic features of microelectrode recordings(MERs). This paper presents an amplitude-frequency-aware deep fusion network for optimal contact selection on STN-DBS *** method first obtains the amplitude-frequency fusion features by combining the MERs time sequence features and the amplitude sequence features, and then uses the convolutional neural network(CNN) with convolutional block attention module(CBAM) to identify both the border of the STN and the sweet spots to implant the electrode. The optimal stimulated contact can be selected according to the distribution of the sweet spots. Experimental results indicate that, for successful surgeries, neurosurgeons and the proposed AI solution selected the same optimal contacts. Furthermore, the proposed method outperforms the state-of-the-art methods for STN and sweet spot identification. The proposed method shows great potential for optimal contact selection to improve the efficiency of STN-DBS surgery and reduce the dependence on clinicians' experience.

关键词： optimal contact selection sweet spots microelectrode recordings amplitude-frequency feature deep fusion network

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Speech Emotion Recognition via Feature Distribution Adaptation Network

arXiv

引用

arXiv 2024年

作者： Li, Shaokai Ji, Yixuan Song, Peng Sun, Haoqin Zheng, Wenming School of Computer and Control Engineering Yantai University Yantai264005 China Business School Xuzhou University of Technology Xuzhou221018 China College of Computer Science Nankai University Tianjin300350 China Key Laboratory of Child Development and Learning Science of Ministry of Education Southeast University Nanjing210096 China

In this paper, we propose a novel deep inductive transfer learning framework, named feature distribution adaptation network, to tackle the challenging multi-modal speech emotion recognition problem. Our method aims to use deep transfer learning strategies to align visual and audio feature distributions to obtain consistent representation of emotion, thereby improving the performance of speech emotion recognition. In our model, the pre-trained ResNet-34 is utilized for feature extraction for facial expression images and acoustic Mel spectrograms, respectively. Then, the cross-attention mechanism is introduced to model the intrinsic similarity relationships of multi-modal features. Finally, the multi-modal feature distribution adaptation is performed efficiently with feed-forward network, which is extended using the local maximum mean discrepancy loss. Experiments are carried out on two benchmark datasets, and the results demonstrate that our model can achieve excellent performance compared with existing ones. Our code is available at https://***/shaokai1209/FDAN. Copyright © 2024, 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

LanCOPE: Language-Guided Category-Level Object Pose Estimation from a Single RGB Image

引用

IEEE Robotics and Automation Letters 2025年第7期10卷 7555-7562页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Dai, Zhenqi Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha 410082 China Central South University School of Architecture and Art Changsha 410082 China The University of Western Australia Department of Computer Science and Software Engineering 6009 WA Australia

Monocular RGB-based category-level object pose estimation is more practical and cost-effective for robotics. However, existing methods do not fully exploit the rich semantic and contextual information in multimodal data (e.g. language) that provides additional object attributes to guide the model in extracting category features more reliably. We propose a language-guided category-level object pose estimation method (LanCOPE), taking a single RGB image as input. Our method uses DINOv2 to recover depth from a single RGB image and converts it into point cloud to perceive the object's geometry. We then introduce language descriptions for the RGB image, estimated point cloud and overall scene to better guide the point cloud encoder and image encoder in learning category features. We develop a cross-modal differential perception feature fusion network to fuse multimodal features. This network employs a differential perception module to eliminate redundant information across different modalities, highlighting signifcant semantic differences and similarities. Furthermore, it uses a cross-attention mechanism to fuse the semantic information of the language and vision features, improving the overall perception. Finally, we design a denoising network based on the skip fusion transformer to recover the object pose accurately. Extensive experiments on REAL275 and Wild6D datasets show that LanCOPE achieves state-of-the-art performance. Our code is available at LanCOPE. © 2016 IEEE.

关键词： category-level object pose estimation languag RGB image

来源：评论

学校读者我要写书评

暂无评论

A Material Identification Approach Based on Wi-Fi Signal

引用

computers, Materials & Continua 2021年第12期69卷 3383-3397页

作者： Chao Li Fan Li Wei Du Lihua Yin Bin Wang Chonghua Wang Tianjie Luo Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhou510700China PCL Research Center of Cyberspace Security Peng Cheng LaboratoryShenzhen518052China Department of Computer Science and Computer Engineering University of ArkansasFayetteville72701USA College of Electrical Engineering Zhejiang UniversityHangzhou310058China China Industrial Control Systems Cyber Emergency Response Team Beijing100040China

Material identification is a technology that can help to identify the type of target *** approaches depend on expensive instruments,complicated pre-treatments and professional *** is difficult to find a substantial yet effective material identification method to meet the daily use *** this paper,we introduce a Wi-Fi-signal based material identification approach by measuring the amplitude ratio and phase difference as the key features in the material classifier,which can significantly reduce the cost and guarantee a high level *** practical measurement of WiFi based material identification,these two features are commonly interrupted by the software/hardware noise of the channel state information(CSI).To eliminate the inherent noise of CSI,we design a denoising method based on the antenna array of the commercial off-the-shelf(COTS)Wi-Fi *** that,the amplitude ratios and phase differences can be more stably utilized to classify the *** implement our system and evaluate its ability to identify materials in indoor *** result shows that our system can identify 10 commonly seen liquids with an average accuracy of 98.8%.It can also identify similar liquids with an overall accuracy higher than 95%,such as various concentrations of salt water.

关键词： Internet of Things Wi-Fi signal channel state information material identification noise elimination

来源：评论

学校读者我要写书评

暂无评论

Empirical Analysis of Vulnerabilities Life Cycle in Golang Ecosystem

arXiv

引用

arXiv 2023年

作者： Hu, Jinchang Yang, Sen Zhang, Lyuye Liu, Chengwei Huang, Song Liu, Yang College of Command and Control Engineering Army Engineering University of PLA Nanjing China Continental-NTU Corporate Lab Nanyang Technological University Singapore Singapore School of Computer Science and Engineering Nanyang Technological University Singapore Singapore

Open-source software (OSS) greatly facilitates program development for developers. However, the high number of vulnerabilities in open-source software is a major concern, including in Golang, a relatively new programming language. In contrast to other commonly used OSS package managers, Golang presents a distinctive feature whereby commits are prevalently used as dependency versions prior to their integration into official releases. This attribute can prove advantageous to users, as patch commits can be implemented in a timely manner before the releases. However, Golang employs a decentralized mechanism for managing dependencies, whereby dependencies are upheld and distributed in separate repositories. This approach can result in delays in the dissemination of patches and unresolved vulnerabilities. To tackle the aforementioned concern, a comprehensive investigation was undertaken to examine the life cycle of vulnerability in Golang, commencing from its introduction and culminating with its rectification. To this end, a framework was established by gathering data from diverse sources and systematically amalgamating them with an algorithm to compute the lags in vulnerability patching. It turned out that 66.10% of modules in the Golang ecosystem were affected by vulnerabilities. Within the vulnerability life cycle, we found two kinds of lag impeding the propagation of vulnerability fixing. By analyzing reasons behind non-lagged and lagged vulnerabilities, timely releasing and indexing patch versions could significantly enhance ecosystem security. © 2023, CC BY.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Dynamic Optimization of Electric Vehicle Charging for Sustainable Power Grids using Sine Hunter-Prey Optimization with GRUs

Dynamic Optimization of Electric Vehicle Charging for Sustai...

引用

International Conference on Electrical Power and Energy Systems (ICEPES)

作者： Mohd Khizar Syed Prakash Chandra Behera P Joel Josephson Shamim Ahmad Khan Timur Kholmukhamedov Ponni Valavan M Department of Physics Kohinoor college Maharashtra India Department of Science St. Claret College Bangalore India Department of ECE Malla Reddy Engineering College Medchal Malkajgiri Telangana India Glocal School of Science & Technology Glocal University Uttar Pradesh India Automatic Control and Computer Engineering Department Turin Polytechnic University Tashkent Uzbekistan Department of AI & DS K.Ramakrishnan College of Engineering Trichy Tamil Nadu India

ISBN: (数字)9798350390728

ISBN: (纸本)9798350390735

The integration of electric vehicles (EVs) into power grids presents a significant challenge for sustainability due to their dynamic charging demands and the need to accommodate renewable energy sources. Existing optimization methods often fail to adequately address the complexity of this problem. In this study, propose a novel approach that combines Sine Hunter-Prey Optimization (SHPO) with Gated Recurrent Units (GRUs) to dynamically optimize EV charging for sustainable power grid operation. Traditional optimization methods struggle to capture the nonlinear and time-varying nature of EV charging demands and renewable energy availability. To overcome this limitation, SHPO's ability to efficiently explore complex solution spaces and GRUs' capability to model temporal dependencies in sequential data. This proposed method optimizes EV charging schedules by considering grid stability, renewable energy utilization, and cost minimization. Validating the approach using historical data on EV charging patterns, renewable energy generation, and grid conditions. Performance metrics include grid stability indices, renewable energy integration rates, and cost savings compared to baseline strategies. Experimental results demonstrate that the method outperforms traditional optimization techniques, leading to more sustainable and resilient power grid operation with 92% stability. Overall, this study contributes to advancing the modern methods in dynamic optimization of EV charging, paving the way for more sustainable transportation and energy systems.

关键词： Renewable energy sources Costs Stability criteria Power system dynamics Optimization methods Power system stability Electric vehicle charging

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline 39

Zero-Shot Learning in Industrial Scenarios: New Large-Scale ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Zekai Chen, Qinghui Xiong, Maomao Ding, Shijiao Su, Zhanzhi Yao, Xinjie Sun, Yiming Bai, Cong Zhang, Jinglin School of Control Science and Engineering Shandong University Jinan China National Supercomputing Center in Jinan Qilu University of Technology Jinan China College of Intelligence and Computing Tianjin University Tianjin China School of Automation Southeast University Nanjing China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China

ISBN: (纸本)157735897X

Large Visual Language Models (LVLMs) have achieved remarkable success in vision tasks. However, the significant differences between industrial and natural scenes make applying LVLMs challenging. Existing LVLMs rely on user-provided prompts to segment objects. This often leads to suboptimal performance due to the inclusion of irrelevant pixels. In addition, the scarcity of data also makes the application of LVLMs in industrial scenarios remain unexplored. To fill this gap, this paper proposes an open industrial dataset and a Refined Text-Visual Prompt (RTVP) for zero-shot industrial defect detection. First, this paper constructs the Multi-Modal Industrial Open Dataset (MMIO) containing 80K+ samples. MMIO contains diverse industrial categories, including 6 super categories and 18 subcategories. MMIO is the first large-scale multi-scenes pre-training dataset for industrial zero-shot learning, and provides valuable training data for open models in future industrial scenarios. Based on MMIO, this paper provides a RTVP specifically for industrial zero-shot tasks. RTVP has two significant advantages: First, this paper designs an expert-guided large model domain adaptation mechanism and designs an industrial zero-shot method based on Mobile-SAM, which enhances the generalization ability of large models in industrial scenarios. Second, RTVP automatically generates visual prompts directly from images and considers text-visual prompt interactions ignored by previous LVLM, improving visual and textual content understanding. RTVP achieves SOTA with 42.2% and 24.7% AP in zero-shot and closed scenes of MMIO. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Predicting Off-Design Performance of Axial Compressors Using Multilayer Neural Network Model for Surge control

SSRN

引用

SSRN 2023年

作者： Elmelegy, Mohamed Ali Elhosseini, Mostafa A. Ali, Hesham Arafat Haikal, Amira Y. Instrument Maintenance support Engineer DLNG Damietta LNG Egypt College of Computer Science and Engineering Taibah University Yanbu Saudi Arabia Department of Computers and Control Systems Engineering Faculty of Engineering Mansoura University Mansoura Egypt

The incidence of surge within axial compressors profoundly influences the efficacy and reliability of aero-engines. Conventional methodologies in engine design have predominantly concentrated on the precise and efficient forecasting of critical characteristics during such occurrences. This paper presents a novel approach for predicting the surge phenomenon in axial compressors. Surge is a major issue in the operation of axial compressors, causing reduced performance, increased wear and tear, and in some cases, complete machine failure. The proposed approach utilizes a neural network model based on the compressor's design data to forecast the behavior of the compressor's working map under off-design conditions. The model is verified using real data collected over five years during compressor operation, including the opening angle of the Inlet Guided Van (IGV), an important parameter often ignored or assumed to be fixed in previous studies. The results show that the neural network-based approach effectively predicts the compressor's behavior under different operating conditions, providing valuable insights into the onset of surge and offering a real-time surge prediction and control tool. The ability to predict the compressor's working map enables optimizing its performance and controlling instability. This model was validated by comparing its predictions with real operating conditions observed over five years across various compressor operating modes. As a result, this predictive model enables the safe operation of axial compressors by mitigating instability risks during operation. This study's findings highlight the model's effectiveness, as evidenced by the minimal error observed between the predicted and actual data collected across various compressor operating modes. The model exhibits a strong performance, characterized by a high regression factor of 0.92667 and a low mean squared error of 3.04465 x 10^-3. These numerical values underscore the reliability and pr

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：