检索结果-内蒙古大学图书馆

3rd International Symposium on Semiconductor and Electronic Technology, ISSET 2024

作者： Xiang, Tianzi Xu, Quanyuan Liu, Haorui Lu, Ying Southwest Forestry University College of Big Data and Intelligent Engineering Yunnan Kunming China Southwest Forestry University Key Laboratory of Forestry and Ecological Big Data State Forestry Administration Yunnan Kunming China Changchun University of Science and Technology School of Physics Jilin Changchun China

ISBN: (纸本)9798350390285

In this work, an Enhanced-Precision Bandgap Reference Incorporating Temperature-Compensation was proposed. Unlike traditional bandgap references, the reference voltage output of 0.701 V is realized by combining reference current and resistor. Meanwhile, an innovative Linear-piecewise current compensation was proposed, which aimed at optimizing the temperature drift of the bandgap reference. The simulation results shows that the proposed curvature-compensation technique improves the TC from 24.96 to 2.14 ppm°C in the temperature range of -40 °C to 120 °C;the PSRR of Enhanced-Precision Bandgap Reference at low frequency is 72.40 dB;the line regulation is about 0.08 %/V for input voltages between 3.2 and 3.7 V in standard 0.18 μm 1P6M CMOS process. The proposal of this new circuit provides a new idea for the realization of high- performance integrated circuits in the future. © 2024 IEEE.

关键词： Piecewise linear techniques

来源：评论

学校读者我要写书评

暂无评论

Label-guided heterogeneous domain adaptation

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第14期81卷 20105-20126页

作者： Zhou, Zhiheng Wang, Yifan Niu, Chang Shang, Junyuan South China Univ Technol Sch Elect & Informat Engn Guangzhou Peoples R China South China Univ Technol Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou Peoples R China

Heterogeneous domain adaptation(HDA) mainly considers how to solve the target domain task with the help of the relevant knowledge of the source domain when both data distribution and feature space of the target domain are different from the source domain. In this paper, we propose Label-guided Heterogeneous Domain Adaptation method, which focuses on how to enhances the application of a small amount of labeled target domain data. In our algorithm, we consider learning a mapping matrix to map the data of two domains into a shared subspace and make predictions accordingly. Firstly, we match the marginal and conditional distribution of the source and target domain data. Secondly, considering the guidance of labeled data in the target domain, we combine all labeled data and adapted it to the unlabeled part of the target domain. Finally, we introduce F-norm to reduce the parameter complexity of the mapping matrix. We conduct extensive experiments on text-to-text and image-to-image transfer tasks, and the experimental results demonstrated that our algorithm is significantly superior to several state-of-the-art algorithms.

关键词： Heterogeneous domain adaptation data distribution Distribution adaptation

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Sarcasm Generation: dataset and Solution 61

Multi-modal Sarcasm Generation: Dataset and Solution

引用

61st Annual Meeting of the the Association-for-Computational-Linguistics (ACL)

作者： Zhao, Wenye Huang, Qingbao Xu, Dongsheng Zhao, Peizhi Guangxi Univ Sch Elect Engn Nanning Guangxi Peoples R China Guangxi Key Lab Multimedia Commun & Network Techn Nanning Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot SCUT Beijing Peoples R China

ISBN: (纸本)9781959429623

As an interesting and challenging task, sarcasm generation has attracted widespread attention. Although very recent studies have made promising progress, none of them considers generating a sarcastic description for a given image - as what people usually do on Twitter. In this paper, we present a Multi-modal Sarcasm Generation (MSG) task: Given an image with hashtags that provide the sarcastic target, MSG aims to generate sarcastic descriptions like humans. Compared with textual sarcasm generation, MSG is more challenging as it is difficult to accurately capture the key information from images, hashtags, and OCR tokens and exploit multi-modal incongruity to generate sarcastic descriptions. To support the research on MSG, we develop MuSG, a new dataset with 5000 images and related Twitter text. We also propose a multi-modal Transformer-based method as a solution to this MSG task. The input features are embedded in the common space and passed through the multi-modal Transformer layers to generate the sarcastic descriptions by the auto-regressive paradigm. Both automatic and manual evaluations demonstrate the superiority of our method. The dataset and code will be available at ***/lukakupolida/MSG.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Visual question generation for explicit questioning purposes based on target objects

引用

NEURAL NETWORKS 2023年 167卷 638-647页

作者： Xie, Jiayuan Chen, Jiali Fang, Wenhao Cai, Yi Li, Qing South China Univ Technol Sch Software Engn Guangzhou Peoples R China South China Univ Technol Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China

Visual question generation aims to focus on some target objects in an image to generate questions with certain questioning purposes. Existing studies mainly utilize an answer to extract the target object corresponding to the questioning purpose for questioning. However, answers fail to accurately and completely map to every target object, such as the objects corresponding to the answer are ambiguous or the answers are the relationship between multiple objects. To address this problem, we propose a content-controlled question generation model, which generates questions based on a given target object set specified from an image. Considering that the target objects have different contributions during the generation process, we design a recurrent generative architecture to explicitly control attention to different objects and their corresponding image information at each generative stage. Extensive experiments on the VQA v2.0 dataset and the Visual7w dataset show that the proposed model outperforms the state-of-the-art models and can controllably generate questions with specified content.(c) 2023 Elsevier Ltd. All rights reserved.

关键词： Visual question generation Questioning purposes Target object

来源：评论

学校读者我要写书评

暂无评论

LogADCH: Hyperspheric-Based Log Message Anomaly Detection And Classification

LogADCH: Hyperspheric-Based Log Message Anomaly Detection An...

引用

2023 International Conference on Frontiers of robotics and Software Engineering, FRSE 2023

作者： He, Shiming Xiao, Jinpan Chen, Bowen Lei, Ying Changsha University of Science & Technology School of Computer and Communication Engineering The Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha China

ISBN: (纸本)9798350301113

Web services have been integrated with all walks of life in society. Abnormalities in the network and services seriously affect user experience and company revenue. The system log records various information of the system, and the information-rich log messages usually show different anomalies. It is particularly important to accurately and timely identify the anomalies of the log messages and classify the anomalies. In addition, most of the current existing work only detects anomalies and does not classify them, and a few existing works require anomaly labels to classify anomalies. Based on these potential challenges, we propose an unsupervised hypersphere-based log message anomaly detection and classification method, LogADCH. We use the hypersphere loss function to let the BERT model learn compact representations of log messages and perform anomaly detection. Finally, K-Means clustering is performed on the semantic feature vectors detected as anomalies to form clusters of different types of anomalies. Compared with other works, LogADCH further classifies the abnormal types after detecting the abnormal logs, helping the operation and maintenance personnel to quickly locate the fault. We compare our method with other methods on two public datasets, and the experimental results show that LogADCH has superior performance in anomaly detection as well as anomaly classification. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

DFGR: Deep Feature Graph Representation for Predicting Knee Osteoarthritis 4

DFGR: Deep Feature Graph Representation for Predicting Knee ...

引用

4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024

作者： Xu, Tao Dai, Dawei Wang, Yuqi Li, Gen Chongqing University of Posts and Telecommunications Key Laboratory of Big Data Intelligent Computing Chongqing China Shanghai Jiaotong University School of Medicine Department of Orthopedics Ruijin Hospital Shanghai China

ISBN: (纸本)9798350394375

Knee osteoarthritis (KOA) is a common joint disease that severely affects the normal lives of patients. In clinical practice, the severity of KOA is evaluated by observing the X-ray images of the knee joint, which is highly dependent on the subjective experience of the doctor. In this study, we developed a novel deep CNN model that integrates structural information processing to predict KOA severity automatically. Specifically, (1) The knee joint regions of the original X-ray images are segmented using automatic detection;(2) We employed a pre-trained deep CNN models to extract deep features of key regions, and construct their corresponding graph representations;(3) A graph attention network (GAT) was designed as a fine-tuning module to build a KOA prediction model. Experiments demonstrate that our method significantly improves the performance in multiple aspects. In addition, our method demonstrates good interpretability. Codes are available at https://***/ddw2AIGROUP2CQUPT/DFGR © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Improved EDVR Model for Robust and Efficient Video Super-Resolution

Improved EDVR Model for Robust and Efficient Video Super-Res...

引用

22nd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Huang, Yulin Chen, Junying South China Univ Technol Sch Software Engn Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou Peoples R China

ISBN: (纸本)9781665458245

Computer vision technologies are increasingly commonly used in daily life, and video super-resolution is gradually drawing more attention in the computer vision community. In this work, we propose an improved EDVR model to tackle the robustness and efficiency problems of the original EDVR model in video super-resolution. First, to handle the blurring situations and emphasize the effective features, we devise a preprocessing module consisting of rigid convolution sub-modules and feature enhancement sub-modules, which are flexible and effective. Second, we devise a temporal 3D convolutional fusion module, which can extract information in image frames more accurately and rapidly. Third, to better utilize the information in feature maps, we design a new reconstruction block by introducing a new channel attention approach. Moreover, we use multiple programmatic methods to accelerate the model training and inference process, making the model useful for practical applications.

关键词： Training Computer vision Solid modeling Three-dimensional displays Convolution Computational modeling Superresolution

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Current Control for Asymmetric Six-phase Permanent Magnet Motors with Less Computation and Optimized Voltage Vector Magnitude

Model Predictive Current Control for Asymmetric Six-phase Pe...

引用

2022 International Conference on Smart Energy and Electrical Engineering, SEEE 2022

作者： Sun, Jinyu Chen, Fubing Huai'An Key Laboratory of Big Data Intelligent Computing and Analysis China The School of Computer Science and Technology Huaiyin Normal University Huaian223001 China

For the sake of the fixed magnitude of candidate control sets, the conventional model predictive current control (MPCC) for asymmetric six-phase permanent magnet motors suffers from huge harmonic currents. This article designs a novel MPCC that aims to improve operational performance. First, virtual-voltage vector (VV) sets are synthesized as the new candidate vectors to restrain harmonic currents. Then, a simplified method for evaluating voltage vectors is used to alleviate the computation in the enumeration process. Moreover, the duty cycle modulation with the deadbeat solution is introduced to optimize the magnitude of the VV. The modulation range can be expanded by utilizing null vectors, which will significantly reduce the torque fluctuations and flux ripples. The experiments are conducted to verify the designed control strategy. © Published under licence by IOP Publishing Ltd.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Fast Multivariate Time Series Anomaly Detection Based on Matrix Completion

Fast Multivariate Time Series Anomaly Detection Based on Mat...

引用

2023 International Conference on Frontiers of robotics and Software Engineering, FRSE 2023

作者： He, Shiming Yi, Tongzhijian Yang, Bo Guo, Chenxi Changsha University of Science & Technology School of Computer and Communication Engineering The Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha China

ISBN: (纸本)9798350301113

Increasingly complex systems contain large numbers of devices that generate great number of multivariate time series that are monitored and recorded. For anomaly detection of these complex time series, deep learning technology is often used to build a learning model for anomaly detection. The method based on deep learning usually takes a long time to train data in practice, and the online service system is deployed or changed very frequently, which makes the online service system need to frequently spend a lot of time updating the anomaly detection model. To overcome this challenge, this paper proposes a fast multivariate time series anomaly detection (FMAD) approach based on matrix completion. After sampling the primitive low-rank matrix, FMAD uses matrix completion to reconstruct the original low-rank matrix to detect anomalies in multivariate time series. We conducted related experimental analysis and discussion. The experimental results on three real data sets show that FMAD has improved the problem of too long model training time and improved the detection efficiency. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerators 31

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerato...

引用

31st IEEE International Symposium on High Performance Computer Architecture, HPCA 2025

作者： Yang, Siling He, Shuibing Wang, Wenjiong Yin, Yanlong Wu, Tong Chen, Weijian Zhang, Xuechen Sun, Xian-He Feng, Dan The State Key Laboratory of Blockchain and Data Security Zhejiang University China Zhejiang Lab China Institute of Blockchain and Data Security China Zhejiang Key Laboratory of Big Data Intelligent Computing China Washington State University Vancouver United States Illinois Institute of Technology United States Huazhong University of Science and Technology China Wuhan National Laboratory for Optoelectronics China

ISBN: (纸本)9798331506476

Graph convolutional networks (GCNs) are popular for a variety of graph learning tasks. ReRAM-based processing-in-memory (PIM) accelerators are promising to expedite GCN training owing to their in-situ computing capability. However, existing accelerators can be severely underutilized even with pipelines, due to the oversight of the skewed execution times of various GCN stages and the ignorance of skewed degrees of graph vertices. In this work, we propose GOPIM, a GCN-oriented pipeline optimization for PIM accelerators to expedite GCN training. First, GOPIM proposes an ML-based scheme that allocates crossbar resources to the most needed stages to streamline the overall pipeline. Second, GOPIM utilizes a selective vertex updating technique that evenly distributes vertices on crossbars by interleaved mapping. These techniques collectively reduce the overall execution time without losing much accuracy. We also provide a practical architecture design for GOPIM. Our experimental results show that, GoPIM achieves up to 191 × speedup and 16.1 × energy saving, compared to the state-of-the-art work. © 2025 IEEE.

关键词： Graph neural networks

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：