检索结果-内蒙古大学图书馆

International Conference on Signal Processing Proceedings (ICSP)

作者： Guohui Yu Lihui Wang Qijian Chen Li Wang Kun Tang Xinyu Cheng Yuemin Zhu State Key Laboratory of Public Big Data College of Computer Science and Technology Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Guizhou University Guiyang China INSA Lyon CNRS Inserm CREATIS UMR 5220 U1206 Univ Lyon Lyon France

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

Accurate brain tumor segmentation of magnetic resonance imaging (MRI) images requires the integration of multimodal data in effective collaborative learning. However, clinical scenarios often face missing modalities, significantly impacting segmentation performance. In this paper, we propose the penta-encoder with medical transformer (Penta-MedTrans) for incomplete multimodal learning, which consists of four main components: a modality-specific encoder (MSE), a modality-dynamic encoder (MDE), a multimodal fusion module (MMFM) and a convolutional decoder. The MSE extracts unique features for each modality, while the MDE captures inter-modal semantics to address missing modalities. The MMFM establishes and aligns long-range correlations between modal-invariant features and global semantics of tumor regions. The convolutional decoder generates robust segmentation results by progressively upsampling and fusing modality-invariant features. We extensively validated our method on the BraTS 2020 and BraTS 2021 datasets for brain tumor segmentation. Results showed that our method outperforms SOTA for incomplete multimodal brain tumor segmentation across most subsets.

关键词： Image segmentation Correlation Convolution Magnetic resonance imaging Semantics Brain tumors Transformers Feature extraction Decoding Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

引用

Neuroscience Bulletin 2022年第10期38卷 1215-1228页

作者： Liwei Sun Wenjing Zhang Mengyue Wang Songjian Wang Zhen Li Cui Zhao Meng Lin Qian Si Xia Li Ying Liang Jing Wei Xu Zhang Renji Chen Chunlin Li School of Biomedical Engineering Capital Medical UniversityBeijing100069China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Capital Medical UniversityBeijing100069China Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application School of Biomedical EngineeringCapital Medical UniversityBeijing100069China Beijing Stomatological Hospital Capital Medical UniversityBeijing100050China School of Life Science Beijing Institute of TechnologyBeijing100081China Beijing Institute of Otolaryngology-Head and Neck Surgery Beijing100005China Key Laboratory of Otolaryngology-Head and Neck Surgery(Capital Medical University) Ministry of EducationBeijing100005China Beijing Tongren Hospital Capital Medical UniversityBeijing100005China Department of Ultrasound Beijing Obstetrics and Gynecology HospitalCapital Medical UniversityBeijing100026China Peking University First Hospital Beijing100034China

Cleft lip and/or palate(CLP)are the most common craniofacial malformations in *** problems often persist even after cleft repair,such that follow-up articulation training is usually ***,the neural mechanism behind effective articulation training remains largely *** used fMRI to investigate the differences in brain activation,functional connectivity,and effective connectivity across CLP patients with and without articulation training and matched normal *** found that training promoted task-related brain activation among the articulation-related brain networks,as well as the global attributes and nodal efficiency in the functional-connectivity-based graph of the *** results reveal the neural correlates of effective articulation training in CLP patients,and this could contribute to the future improvement of the post-repair articulation training program.

关键词： Non-syndromic cleft lip and palate Articulation training fMRI Functional connectivity Graph-based network analysis

来源：评论

学校读者我要写书评

暂无评论

Detecting JVM JIT Compiler Bugs via Exploring Two-Dimensional Input Spaces

Detecting JVM JIT Compiler Bugs via Exploring Two-Dimensiona...

引用

International Conference on Software engineering (ICSE)

作者： Haoxiang Jia Ming Wen Zifan Xie Xiaochen Guo Rongxin Wu Maolin Sun Kang Chen Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology China Hubei Key Laboratory of Distributed System Security Services Computing Technology and System Lab Cluster and Grid Computing Lab. Hubei Engineering Research Center on Big Data Security National Engineering Research Center for Big Data Technology and System School of Informatics Xiamen University China School of Computer Science and Technology Huazhong University of Science and Technology China

Java Virtual Machine (JVM) is the fundamental software system that supports the interpretation and execution of Java bytecode. To support the surging performance demands for the increasingly complex and large-scale Java programs, Just-In-Time (JIT) compiler was proposed to perform sophisticated runtime optimization. However, this inevitably induces various bugs, which are becoming more pervasive over the decades and can often cause significant consequences. To facilitate the design of effective and efficient testing techniques to detect JIT compiler bugs. This study first performs a preliminary study aiming to understand the characteristics of JIT compiler bugs and the corresponding triggering test cases. Inspired by the empirical findings, we propose JOpFuzzer, a new JVM testing approach with a specific focus on JIT compiler bugs. The main novelty of JOpFuzzer is embodied in three aspects. First, besides generating new seeds, JOpFuzzer also searches for diverse configurations along the new dimension of optimization options. Second, JOpFuzzer learns the correlations between various code features and different optimization options to guide the process of seed mutation and option exploration. Third, it leverages the profile data, which can reveal the program execution information, to guide the fuzzing process. Such nov-elties enable JOpFuzzer to effectively and efficiently explore the two-dimensional input spaces. Extensive evaluation shows that JOpFuzzer outperforms the state-of-the-art approaches in terms of the achieved code coverages. More importantly, it has detected 41 bugs in OpenJDK, and 25 of them have already been confirmed or fixed by the corresponding developers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optical generation of UWB pulses utilizing Fano resonance modulation

引用

Frontiers of Optoelectronics 2021年第4期14卷 426-437页

作者： Zhe XU Yanyang ZHOU Shuhuang CHEN Liangjun LU Gangqiang ZHOU Jianping CHEN Linjie ZHOU State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Key Laboratory of Navigation and Location ServicesShanghai Institute for Advanced Communication and Data ScienceDepartment of Electronic EngineeringShanghai Jiao Tong UniversityShanghai 200240China

In this paper,we reported an integrated method to generate ultra-wideband(UWB)pulses of different orders based on a reconfigurable silicon micro-ring resonator-coupled Mach–Zehnder *** proper operating conditions,the device can produce Fano resonances with a peak-to-valley extinction ratio of above 20 *** monocycle and doublet signals with picosecond pulse widths are produced when the microring resonator is modulated by square and Gaussian electrical pulses,*** our Fano resonance modulator on silicon photonics,it is promising to foresee versatile on-chip microwave signal generation.

关键词： ultra-wideband(UWB)generation Fano resonance intensity modulation integrated silicon modulator

来源：评论

学校读者我要写书评

暂无评论

引用

2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes, SAFEPROCESS 2021

作者： Ma, Liang Zhang, Xueyi Peng, Kaixiang Dong, Jie Shunde Graduate School of University of Science and Technology Foshan Beijing528399 China University of Science and Technology Beijing Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering Beijing100083 China

ISBN: (纸本)9781665401159

Quality-related fault detection technology is an important mean to ensure safe operation and stable quality for nonlinear industrial processes, which, thus, have recently become hotspots in the process industrial control domain. In this paper, a mixed kernel partial least squares-based quality-related fault detection method is developed, which has fully considered the nonlinear characteristics of industrial processes. Under that framework, mixed kernel functions and monitoring statistics are reasonably designed, aiming at enhancing the performance of fault detection. Moreover, a case study on Tennessee Eastman process is finally given to compare with other methods to demonstrate the advantages of the new approach. © 2021 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

China's current forest age structure will lead to weakened carbon sinks in the near future

引用

The Innovation 2023年第6期4卷 38-47页

作者： Rong Shang Jing M.Chen Mingzhu Xu Xudong Lin Peng Li Guirui Yu Nianpeng He Li Xu Peng Gong Liangyun Liu Han Liu Wenzhe Jiao Key Laboratory for Humid Subtropical Eco-Geogr aphical Processes of the Ministy of Education School of Geographical SciencesFujian Normal UniversityFuzhou 350117China Department of Geography and Planning University of TorontoTorontoOntario M5S 3G3Canada Key Laboratory of Ecosystem Network Observation and Modeling Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBejing 100101China Institute for Climate and Carbon Neutrality Department of Geography and Department of Earth SciencesUniversity of Hong KongHong Kong 999077China International Research Center of Big Data for Sustainable Development Goals Beijing 100094China Land Consolidation and Rehabilitation Center Ministry of Natural ResourcesBeijing 100035China Department of Civil and Environmental Engineering Massachusetts Institute of TechnologyCambridgeMA 02139USA

Forests are chiefly responsible for the terrestrial carbon sink that greatly re duces the buildup of CO_(2)concentrations in the atmosphere and alleviates climate *** predictions of terrestrial carbon sinks in the future have so far ignored the variation of forest carbon uptake with forest ***,we predict the role of China's current forest age in future carbon sink capacity by generating a high-resolution(30 m)forest age map in 2019 over China's landmass using satellite and forest inventory data and deriving forest growth curves using measurements of forest biomass and age in 3,121 *** China's forests currently have large proportions of young and middle-age stands,we project that China's forests will maintain high growth rates for about 15 ***,as the forests grow older,their net primary productivity will decline by 5.0%±1.4%in 2050,8.4%±1.6%in 2060,and 16.6%±2.8%in 2100,indicating weakened carbon sinks in the near *** weakening of forest carbon sinks can be potentially mitigated by optimizing forest age structure through selective logging and implementing new or improved *** finding is important not only for the global carbon cycle and climate projections but also for developing forest management strategies to enhance land sinks by alleviating the age effect.

关键词： forest carbon structure

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Lumbar Spondylolisthesis and Instability Using Supine Magnetic Resonance Images

SSRN

引用

SSRN 2023年

作者： Liu, Zewen Zhang, Han Zhao, Hang Liu, Yuwu Zhang, Chi Shi, Xiaohu College of Software Jilin University Changchun130021 China Guangyuan Central Hospital China College of Computer Science and Technology Jilin University Changchun130021 China Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Changchun130021 China

Background and Objective: Lumbar spondylolisthesis is a condition in which one vertebra is displaced relative to the vertebra below it. Lumbar instability can be divided into static and dynamic spondylolisthesis depending on whether the degree of slippage changes significantly in images taken in different postures. Usually, the degree of slippage of lumbar instability is not obvious on magnetic resonance (MR) images taken in the supine position;therefore, it is easy to miss the detection of spondylolisthesis with lumbar instability based on slippage. This feature of lumbar instability also poses a challenge for the automatic detection of dynamic spondylolisthesis, particularly in supine MR images. This study aimed to develop a two-stage model for the automatic detection of spondylolisthesis and lumbar instability using supine MR ***: Specifically, we used You Only Look Once (YOLO) to detect and crop consecutive images near the intervertebral discs (IVDs) on both sagittal and transverse axis magnetic resonance images, and then classified the cropped images using weight-sharing convolutional neural networks (CNNs). Consistency regularization and a new contrast loss function ware also developed to improve the robustness. The MR data we used includes 108 mixed samples of lumbar instability and spondylolisthesis (39 cases of lumbar instability and 69 cases of spondylolisthesis) and 182 normal ***: We found that YOLO could detect the complete image sequence between L1 and S1 with 97.24% accuracy (ACC). Compared with the ground truth labels, the mean of intersection over union (mIOU) is 84.58%. In addition, the ACC and mIoU for transverse axis image are 98.62% and 85.71% respectively. In the classification stage, CNN achieved a maximum ACC of 97.9% with transverse axis image as inputs and using consistency ***: While MR images offer a wider range of applications in disease detection compared to X-rays, the identification of con

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Marine Fish Object Detection Based on YOLOv5 and Attention Mechanism

Marine Fish Object Detection Based on YOLOv5 and Attention M...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Lulu Chen Zhaoxiang Zang Tianxing Huang Zhao Li Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges University Yichang Hubei China Nanhai Resources Big Data Center Southern Marine Science and Engineering Guangdong Laboratory (Zhanjiang) Zhanjiang Guangdong China

Automatic fish object detection methods based on computer vision have been widely used in recent years. In this paper, a YOLOv5s marine fish detection method that integrates attention mechanisms is proposed, which has alleviated the issue of misdetections and omissions caused by the shape, color, and size of the marine fish object. First, the multi-scale clustering method is used to recalculate the anchor box for matching the dataset. Then, the channel attention module is added to the feature extraction network of YOLOv5s by using the lightweight attention ECA-Net to obtain important feature information. Meanwhile, the spatial attention module SSA is used to enhance the edge feature information and improve detection accuracy. To further increase the generalization of the detection model, the DropBlock regularization method is added to sparse the features extracted from the backbone network to lessen the overfitting problem. The network is trained and tested using a combination of two publicly available datasets and a self-built dataset with rich samples covering complex living environments of marine fishes. Experiments demonstrate that our method can effectively increase the accuracy of fish object detection while also maintaining the speed of object detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meteorology-Assisted Spatio-Temporal Graph Network for Uncivilized Urban Event Prediction

Meteorology-Assisted Spatio-Temporal Graph Network for Unciv...

引用

IEEE International Conference on data Mining (ICDM)

作者： Yang Luo Zehao Gu Shiyang Zhou Yun Xiong Xiaofeng Gao Shanghai Jiao Tong University Shanghai China Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University Fudan University Shanghai China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University

Uncivilized urban events disrupt urban order and have a detrimental impact on daily life. Recognizing the significant implications of these events, urban managers strive to proactively prevent them by accurately predicting their future occurrence. However, existing methods overlook crucial contextual information within urban scenarios while mining spatio-temporal dependencies in single event series. Fortunately, we discovered a connection between meteorological conditions and uncivilized events. To leverage this relationship, we propose a novel approach named the Meteorology-Assisted Spatio-Temporal Graph Neural Network (MAST) which integrates meteorological information into the spatio-temporal dependency modeling for predicting urban uncivilized events. Additionally, our approach captures latent regularities in human behavior by explicitly modeling individuals’ psychological states based on meteorological information. We also adopt cross-view contrastive learning between urban regions to dynamically capture the informative components of meteorological information for precise prediction of urban uncivilized events. Experimental evaluations on a real-world dataset demonstrate the superiority of MAST over state-of-theart baselines in terms of predictive performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Fault Assessment Method Integrating Global and Local Information for Industrial Processes

A Novel Fault Assessment Method Integrating Global and Local...

引用

2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes, SAFEPROCESS 2021

作者： Guo, Yingxin Zhang, Xueyi Ma, Liang Peng, Kaixiang School of Automation and Electrical Engineering University of Science and Technology Beijing Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education Beijing100083 China Shunde Graduate School of University of Science and Technology Foshan Beijing528399 China

ISBN: (纸本)9781665401159

Feature extraction methods in the industrial process may affect the performance of process monitoring and fault assessment. In order to reduce the influence of model preference, a novel fault assessment method integrating global and local structure information is proposed by using the strategy of parallel extraction and weighted combination. First, kernel sparse locally linear embedding and kernel principal component analysis models are constructed to handle nonlinear system states and describe the local and global information in parallel. Second, the fault assessment indicators are obtained through support vector data description models. Then, a comprehensive fault assessment index is established by the weighted fusion method, which can keep the global and local neighbor information of the original sample space, and thus more feature information is included. Finally, the feasibility and effectiveness of the proposed assessment method are illustrated by the application in the simulation process of Tennessee Eastman Process, and the results show that the fusion of two basic models can bring a model with better generalization performance than a single model. © 2021 IEEE.

关键词： Process monitoring

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：