检索结果-内蒙古大学图书馆

Cleaner Engineering and technology 2025年 27卷

作者： Shuaiyin Ma Yichun Cao Yang Liu School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an 710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Xi'an 710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an 710121 China Shaanxi Union Research Centre of University and Enterprise for 5G+ Industrial Internet Communication Terminal Technology Xi'an University of Posts and Telecommunications Xi'an 710121 China Department of Management and Engineering Linköping University SE-581 83 Linköping Sweden Industrial Engineering and Management University of Oulu 90570 Oulu Finland

Within the context of cleaner production, enhancing energy efficiency and sustainability has emerged as a central focus in supercomputing center development. To address the challenges in predicting energy consumption, this study proposes an architecture of edge computing-enabled energy efficiency prediction of immersion cooling system for supercomputing centers. This architecture combines time-series generative adversarial network (TimeGAN) for data augmentation with the neural basis expansion analysis for time series (N-BEATS) for prediction, providing a robust solution for accurate energy consumption prediction. TimeGAN enhances the training dataset by generating high-quality synthetic time-series data, effectively mitigating issues of data sparsity and imbalance. N-BEATS, with its modular architecture and strong adaptability to temporal data, ensures precise predictions by capturing both global trends and local variations in energy usage. Experimental results demonstrate the effectiveness of the proposed architecture, exhibiting superior performance across key metrics when compared to traditional models. Specifically, the RMSE of TimeGAN-N-BEATS reduced by more than 8 %, the MSE decreased by over 18 %, and the R 2 reached 97.31 %, outperforming baseline models such as long short-term memory and gated recurrent unit, and their attention-enhanced variants. This study highlights the potential of integrating generative and predictive models to optimize energy efficiency in liquid cooling systems, offering valuable insights for sustainable supercomputing operations.

关键词： Edge computing Liquid cooling system N-BEATS Supercomputing centers TimeGAN

来源：评论

学校读者我要写书评

暂无评论

Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax

Overcoming Classifier Imbalance for Long-Tail Object Detecti...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yu Li Tao Wang Bingyi Kang Sheng Tang Chunfeng Wang Jintao Li Jiashi Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Electrical and Computer Engineering National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored. In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution. We find existing detection methods are unable to model few-shot classes when the dataset is extremely skewed, which can result in classifier imbalance in terms of parameter magnitude. Directly adapting long-tail classification models to detection frameworks can not solve this problem due to the intrinsic difference between detection and classification. In this work, we propose a novel balanced group softmax (BAGS) module for balancing the classifiers within the detection frameworks through group-wise training. It implicitly modulates the training process for the head and tail classes and ensures they are both sufficiently trained, without requiring any extra sampling for the instances from the tail classes. Extensive experiments on the very recent long-tail large vocabulary object recognition benchmark LVIS show that our proposed BAGS significantly improves the performance of detectors with various backbones and frameworks on both object detection and instance segmentation. It beats all state-of-the-art methods transferred from long-tail image classification and establishes new state-of-the-art. Code is available at https://***/FishYuLi/BalancedGroupSoftmax.

关键词： Training Object detection Proposals Adaptation models Feature extraction Computational modeling Detectors

来源：评论

学校读者我要写书评

暂无评论

Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

arXiv

引用

arXiv 2020年

作者： Li, Yu Wang, Tao Kang, Bingyi Tang, Sheng Wang, Chunfeng Li, Jintao Feng, Jiashi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Electrical and Computer Engineering National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Real-time Ship Track Association: a Benchmark and a Network-Based Method

Real-time Ship Track Association: a Benchmark and a Network-...

引用

International Conference on Information Fusion

作者： Lin Wu Yongjun Xu Fei Wang Qiang Lu Miao Hu Institute of Computing Technology Chinese Academy of Sciences Beijing China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

ISBN: (数字)9780996452786

ISBN: (纸本)9781728118406

Multiple systems are tracking ships independently, including cooperative as well as non-cooperative ones. Most track association works focused on association cost functions and optimal track matching matrix was determined by solving a multidimensional assignment problem, assuming synchronous detections of fixed number of targets received periodically from an ideal communication channel, which is not satisfied when tracking targets in a large scale by heterogeneous methods. We put forward an evolving target network-based association approach to create, update, merge, separate and destroy targets over time, which centers on targets rather than tracks. In the network, nodes are fused ships corresponding to tracks from one or more sources and weights of directed edges pointing to each node are association beliefs constituting its basic probability assignment (BPA) function in Dempster-Shafer theory (DST). Once a new message is received, this network evolves by combining the corresponding node's BPA with a new one calculated according to the message. This method is evaluated by an extensible benchmark consisting of an open source track simulator ICTShips and a free visualization software ICTShipVisual. The benchmark consists of four scenes with 32 to 102,231 targets observed by 3 sources at present, having GERs (Gap Error Ratio) from 0.787 to 1,412. Error ratios of our track association method under these scenes range from 0% to 0.539%.

关键词： Target tracking Radar tracking Real-time systems Marine vehicles Sensors Benchmark testing Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Controlled-source electromagnetic signal detection using a hybrid deep learning model: Convolutional and long short-term memory neural networks

引用

Computers & Geosciences 2025年 204卷

作者： Yecheng Liu Diquan Li Jin Li Yanfang Hu Zijie Liu Xian Zhang School of Geosciences and Info-Physics Central South University Changsha 410083 China Key Laboratory of Metallogenic Prediction of Non-Ferrous Metals and Geological Environment Monitor Ministry of Education Central South University Changsha 410083 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Normal University Changsha 410081 China Hunan Provincial Key Laboratory of Finance & Economics Big Data Science and Technology School of Information Technology and Management Hunan University of Finance and Economics Changsha 410205 China

Controlled-source electromagnetic (CSEM) method using a periodic transmitted signal source suppresses random noise by superimposing and averaging the recorded signal over multiple periods. However, it still faces great challenges in strong interference environments. Here we present a CSEM signal detection method based on a hybrid architecture of convolutional neural network (CNN) and long short-term memory neural network (LSTM). Our method improves the quality of the recorded signal by filtering out all the noise periods and retaining the useful signal periods. The core lies in combining the spatial feature extraction capability of CNN with the time series modeling capability of LSTM, which can deeply excavate the feature differences between noise and CSEM useful signal. Meanwhile, a classification model of signal and noise is constructed using a large-scale training dataset. This hybrid model exhibits superior performance compared to other deep learning models such as CNN or LSTM. Also, we propose a novel signal detection mechanism that not only maintains the periodicity of CSEM signal, but also greatly enhances processing efficiency. The results of synthetic and measured data demonstrate that our method can obtain useful signals from CSEM data containing different noise types and significantly improve the quality of sounding curves. In particular, our method is useful for CSEM signal detection in strong interference.

关键词： Controlled-source electromagnetic method Deep learning Noise Signal detection

来源：评论

学校读者我要写书评

暂无评论

Multispectral Pan-sharpening via Dual-Channel Convolutional Network with Convolutional LSTM Based Hierarchical Spatial-Spectral Feature Fusion

arXiv

引用

arXiv 2020年

作者： Wang, Dong Bai, Yunpeng Li, Ying School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing Northwestern Polytechnical University Xian China School of Computing and Information Systems University of Melbourne VIC3010 Australia

Multispectral pan-sharpening aims at producing a high resolution (HR) multispectral (MS) image in both spatial and spectral domains by fusing a panchromatic (PAN) image and a corresponding MS image. In this paper, we propose a novel dual-channel network (DCNet) framework for MS pan-sharpening. In our DCNet, the dual-channel backbone involves a spatial channel to capture spatial information with a 2D CNN, and a spectral channel to extract spectral information with a 3D CNN. This heterogeneous 2D/3D CNN architecture can minimize causing spectral information distortion, which typically happens in conventional 2D CNN models. In order to fully integrate the spatial and spectral features captured from different levels, we introduce a multi-level fusion strategy. Specifically, a spatial-spectral CLSTM (S2-CLSTM) module is proposed for fusing the hierarchical spatial and spectral features, which can effectively capture correlations among multi-level features. The S2-CLSTM module attaches two fusion ways: the intra-level fusion via bi-directional lateral connections and inter-level fusion via the cell state in the S2-CLSTM. Finally, the ideal HR-MS image is recovered by a reconstruction module. Extensive experiments have been conducted at both simulated lower scale and the original scale of real-world datasets. Compared with the state-of-the-art methods, the proposed DCNet achieves superior or competitive performance. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A discovery of Two Slow Pulsars with FAST: "Ronin" from the Globular Cluster M15

arXiv

引用

arXiv 2023年

作者： Zhou, Dengke Wang, Pei Li, Di Fang, Jianhua Miao, Chenchen Freire, Paulo C.C. Zhang, Lei Zhang, Dandan Chen, Huaxi Feng, Yi Xiao, Yifan Xie, Jintao Zhang, Xu Jin, Chenwu Wang, Han Ke, Yinan Guo, Xuerong Zhao, Rushuang Niu, Chenhui Zhu, Weiwei Xue, Mengyao Wang, Yabiao Wu, Jiafu Gan, Zhenye Sun, Zhongyi Wang, Chengjie Zhang, Junshuo Cao, Jinhuang Lu, Wanjin Zhang, Jie Research Center for Astronomical Computing Zhejiang Laboratory Hangzhou311121 China National Astronomical Observatories Chinese Academy of Sciences Beijing100101 China Institute for Frontiers in Astronomy and Astrophysics Beijing Normal University Beijing102206 China University of Chinese Academy of Sciences Beijing100049 China New Cornerstone Science Laboratory Shenzhen518054 China Max Planck Institut für Radioastronomie Bonn53121 Germany Centre for Astrophysics and Supercomputing Swinburne University of Technology Hawthorn3122 Australia School of Mathematical Sciences School of Physics and Electronic Sciences Guizhou Normal University Guiyang550001 China Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guiyang550001 China School of Physics and Electronic Engineering Qilu Normal University Jinan250200 China School of Physics and Electronic Science Guizhou Normal University Guiyang550001 China College of Physical Science and Technology Central China Normal University Wuhan430079 China Tencent Youtu Lab Shanghai201103 China

Globular clusters harbor numerous millisecond pulsars, but long-period pulsars (P 100 ms) are rarely found. In this study, we employed a fast folding algorithm to analyze observational data from multiple globular clusters obtained by the Five-hundred-meter Aperture Spherical radio Telescope (FAST), aiming to detect the existence of long-period pulsars. We estimated the impact of the median filtering algorithm in eliminating red noise on the minimum detectable flux density (Smin) of pulsars. Subsequently, we successfully discovered two isolated long-period pulsars in M15 with periods approximately equal to 1.928451 seconds and 3.960716 seconds, respectively. On the P − P diagram, both pulsars are positioned below the spin-up line, suggesting a possible history of partial recycling in X-ray binary systems disrupted by dynamical encounters later on. According to timing results, these two pulsars exhibit remarkably strong magnetic fields. If the magnetic fields were weakened during the accretion process, then a short duration of accretion might explain the strong magnetic fields of these pulsars. © 2023, CC BY.

关键词： Magnetic fields

来源：评论

学校读者我要写书评

暂无评论

Syntax-enhanced Pre-trained model

arXiv

引用

arXiv 2020年

作者： Xu, Zenan Guo, Daya Tang, Duyu Su, Qinliang Shou, Linjun Gong, Ming Zhong, Wanjun Quan, Xiaojun Jiang, Daxin Duan, Nan School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Microsoft Research Asia Beijing China Microsoft Search Technology Center Asia Beijing China Guangdong Key Laboratory Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. Such a problem would lead to the necessity of having human-annotated syntactic information, which limits the application of existing methods to broader scenarios. To address this, we present a model that utilizes the syntax of text in both pre-training and fine-tuning stages. Our model is based on Transformer with a syntax-aware attention layer that considers the dependency tree of the text. We further introduce a new pre-training task of predicting the syntactic distance among tokens in the dependency tree. We evaluate the model on three downstream tasks, including relation classification, entity typing, and question answering. Results show that our model achieves state-of-the-art performance on six public benchmark datasets. We have two major findings. First, we demonstrate that infusing automatically produced syntax of text improves pre-trained models. Second, global syntactic distances among tokens bring larger performance gains compared to local head relations between contiguous tokens. Copyright © 2020, The Authors. All rights reserved.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Non-structured Pruning for Deep-learning based Steganalytic Frameworks

Non-structured Pruning for Deep-learning based Steganalytic ...

引用

Asia-Pacific Signal and Information processing Association Annual Summit and Conference (APSIPA)

作者： Qiushi Li Zilong Shao Shunquan Tan Jishen Zeng Bin Li Shenzhen Key Laboratory of Media Security Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen China

ISBN: (数字)9781728132488

ISBN: (纸本)9781728132495

Image steganalysis aims to discriminate innocent cover images and those suspected stego images embedded with secret message. Recently, increasing advanced deep neural networks have been proposed and used in image steganalysis. Though those deep learning models can gain superior performance, they also result in redundancy of computational resource and memory storage. In this paper, we apply a non-structured pruning method to prune XuNet2 and SRNet - the two state-of-the-art deep-learning framework in the field of JPEG image steganalysis. We obtain the priorities of the connections among neurons according to a certain criterion, then keep those significant weights and prune those nonsignificant ones in the meantime. We have conducted extensive experiments on BOSSBase and BOWS image dataset. The experimental results demonstrate that our proposed non-structured pruning method can significantly reduce the cost of computation and storage required by the original deep-learning frameworks without affecting their detection accuracy.

关键词： Transform coding Training Convolution Computer architecture Computational modeling Brain modeling Testing

来源：评论

学校读者我要写书评

暂无评论

A New Free-Standing Aqueous Zinc-Ion Capacitor Based on MnO2–CNTs Cathode and MXene Anode

引用

Nano-Micro Letters 2019年第4期11卷 227-238页

作者： Siliang Wang Qiang Wang Wei Zeng Min Wang Limin Ruan Yanan Ma Key Laboratory of Intelligent Computing and Signal Processing Ministry of EducationAnhui UniversityNo.3 Feixi RoadHefei 230039Anhui ProvincePeople’s Republic of China National Engineering Research Center for Agro-Ecological Big Data Analysis and Application School of Electronics and Information EngineeringAnhui UniversityNo.111 Jiulong RoadHefei 230601Anhui ProvincePeople’s Republic of China School of Sciences Hubei University of Automotive TechnologyNo.167 Checheng West RoadShiyan 442002Hubei ProvincePeople’s Republic of China

Restricted by their energy storage mechanism,current energy storage devices have certain drawbacks,such as low power density for batteries and low energy density for ***,the nearest ion capacitors,such as lithium-ion and sodium-ion capacitors containing battery-type and capacitor-type electrodes,may allow achieving both high energy and power *** the inspiration,a new zinc-ion capacitor(ZIC)has been designed and realized by assembling the free-standing manganese dioxide-carbon nanotubes(MnO2-CNTs)battery-type cathode and MXene(Ti3C2Tx)capacitortype anode in an aqueous *** ZIC can avoid the insecurity issues that frequently occurred in lithium-ion and sodium-ion capacitors in organic *** expected,the ZIC in an aqueous liquid electrolyte exhibits excellent electrochemical performance(based on the total weight of cathode and anode),such as a high specific capacitance of 115.1 F g?1(1 mV s?1),high energy density of 98.6 Wh kg?1(77.5 W kg?1),high power density of 2480.6 W kg?1(29.7 Wh kg?1),and high capacitance retention of^83.6%of its initial capacitance(15,000 cycles).Even in an aqueous gel electrolyte,the ZIC also exhibits excellent *** work provides an essential strategy for designing next-generation high-performance energy storage devices.

关键词： Energy storage Zinc-ion capacitor Battery-type and capacitor-type electrodes MXene Electrochemical performance

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：