检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhao, Yuze Pang, Shijie Wang, Zhuoyao He, Wen Wang, Yingwen Zhao, Rui-Wei Feng, Rui Zhang, Xiaobo Fudan University Academy for Engineering and Technology China Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing China Children's Hospital Fudan University National Children's Medical Center China

ISBN: (纸本)9798350386226

Pediatric chest X-rays (CXRs) are crucial for diagnosing respiratory diseases in children. However, most deep learning models perform poorly on pediatric data due to domain gaps, as they are primarily trained on adult datasets with limited pediatric samples. Recent large models, though effective, still struggle with domain-specific terminology and specialized medical reasoning essential for pediatric diagnoses. To address these challenges, we propose PRIDE: a two-stage Pediatric Radiological Image Diagnosis Engine guided by medical knowledge. PRIDE works consistently with real clinical workflows by first gathering medical evidence from patient data, followed by applying clinical knowledge to enhance diagnostic accuracy. In the Multi-source Radiological Findings Recognition Stage, PRIDE integrates insights from generalized medical models and fine-tuned adult and pediatric radiological models to provide comprehensive findings results. In the Knowledge and Evidence-guided Diagnosis Stage, a Multimodal Large Language Model (MLLM) acts as a pediatric clinician, making diagnostic decisions using CXRs, radiological findings, demographic data, and clinical knowledge. Our evaluation on the VinDr-PCXR pediatric dataset demonstrates that PRIDE outperforms existing methods. Ablation studies further confirm the importance and effectiveness of its key components. © 2024 IEEE.

关键词： Pediatrics

来源：评论

学校读者我要写书评

暂无评论

MFCM-DTI model of multimodal feature fusion: Prediction of drug-target interaction

MFCM-DTI model of multimodal feature fusion: Prediction of d...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Li, Wenjun Ma, Wanjun Yang, Mengyun Tang, Xiwei Changsha University of Science and Technology Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha China Hunan First Normal University School of Computer Science Changsha China Hunan First Normal University School of Intelligent Manufacturing Changsha China

ISBN: (纸本)9798350386226

Drug repositioning is a vital area of biomedicine, where confirming interactions between drugs and specific targets is essential for establishing the efficacy of pharmaceutical agents. Traditional in vitro screening methods have limitations, prompting the use of computer simulations as an effective alternative for predicting drug-target interactions (DTI). This approach has gained significant attention in the scientific community. In this study, we introduce MFCM-DTI, a DTI prediction model that employs multimodal features to accurately capture the intricate interactions between drug molecular structures and key amino acids of target proteins. Our results demonstrate that MFCM-DTI outperforms existing models in prediction accuracy and robustness. Furthermore, MFCM-DTI has been successfully used to predict interactions between key SARS-CoV-2 proteins and existing drugs, providing a solid foundation for developing therapeutic agents against SARS-CoV-2 infection. This study underscores the broad applicability and strong predictive capabilities of MFCM-DTI in drug-protein interaction prediction, opening new avenues for research. The predicted drug targets and interaction data offer valuable insights for future experimental validation and clinical trials, potentially driving innovation in the biomedical field. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

MOL-AE: Auto-Encoder Based Molecular Representation Learning With 3D Cloze Test Objective 41

MOL-AE: Auto-Encoder Based Molecular Representation Learning...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Junwei Zheng, Kangjie Long, Siyu Nie, Zaiqing Zhang, Ming Dai, Xinyu Ma, Wei-Ying Zhou, Hao School of Computer Science National Key Laboratory for Multimedia Information Processing Peking University-Anker Embodied AI Lab Peking University China School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University China Tsinghua University China PharMolix Inc. China

3D molecular representation learning has gained tremendous interest and achieved promising performance in various downstream tasks. A series of recent approaches follow a prevalent framework: an encoder-only model coupled with a coordinate denoising objective. However, through a series of analytical experiments, we prove that the encoder-only model with coordinate denoising objective exhibits inconsistency between pre-training and downstream objectives, as well as issues with disrupted atomic identifiers. To address these two issues, we propose MOL-AE for molecular representation learning, an auto-encoder model using positional encoding as atomic identifiers. We also propose a new training objective named 3D Cloze Test to make the model learn better atom spatial relationships from real molecular substructures. Empirical results demonstrate that MOL-AE achieves a large margin performance gain compared to the current state-of-the-art 3D molecular modeling approach. The source codes of MOL-AE are publicly available at https://***/yjwtheonly/MolAE. Copyright 2024 by the author(s)

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

A Compact Magnetic-Electric CP Element and Its Design in Pattern Reconfigurable Antenna with Full Coverage in Azimuth Plane and Wide Coverage in Elevation Plane

引用

IEEE Transactions on Antennas and Propagation 2025年

作者： Zhang, Minghui Liu, Juhua Sun Yat-sen University Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems the School of Electronics and Information Technology Guangzhou510006 China

A compact magnetic-electric circularly polarized (MECP) element is proposed and employed in the design of a pattern reconfigurable antenna that provides full coverage in the azimuth plane and wide coverage in the elevation plane. The MECP element, working in the zeroth-order resonant (ZOR) mode, inherently has a compact size of 0.17λ0 × 0.32λ0 × 0.06λ0 (λ0 denotes the free space wavelength at 920 MHz). The MECP element achieves a fan beam with wide azimuthal and elevational 3-dB axial ratio (AR) beamwidths of 192° and 110°, respectively. By integrating four such sequentially rotated MECP elements, a pattern reconfigurable antenna is designed and fabricated. The antenna has the advantage of compact size of 0.58λ0 × 0.58λ0 × 0.04λ0. By switching the excited elements through the feeding ports, the antenna provides four reconfigurable beams for full coverage in the azimuth plane (one effective beamwidth covering an angle larger than 90°) and wide coverage in the elevation plane (effective beamwidths covering angles within the range of θ ≤ 75°). © 1963-2012 IEEE.

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

Adaptive Monitoring Optimization Based on Deep-Q-Network for Energy Harvesting Wireless Sensor Networks 12th

Adaptive Monitoring Optimization Based on Deep-Q-Network for...

引用

12th International Conference on Mobile Networks and Management, MONAMI 2022

作者： Bao, Xuecai Bian, Peilun Tan, Wenqun Xu, Xiaohua Nie, Jugen Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang Institute of Technology Nanchang Jiangxi330099 China Jiangxi Provincial Technology Innovation Center for Ecological Water Engineering in Poyang Lake Basin Jiangxi330029 China

ISBN: (纸本)9783031324420

In order to improve the energy efficiency of environmental monitoring for energy harvesting wireless sensor networks (EH-WSNs) in remote areas and achieve energy-neutral operation, an adaptive monitoring and energy management optimization method of EH-WSNs based on deep Q network (DQN) algorithm is proposed. In this paper, aiming at EH-WSNs with single-hop cluster structure, we first present a more realistic energy model established by combining different climate characteristics. Then, the optimization model of maximizing long-term monitoring utility is formulated based on harvested energy constraints. We use deep Q network (DQN) to learn random and dynamic solar energy harvesting process on solar-powered sensor nodes and optimize the monitored performance of EH-WSNs through the replay memory mechanism and freezing parameter mechanism. Finally, we present an adaptive monitoring optimization method based DQN to achieve the long-term utility. Through simulation verification and comparative analysis, in different rainy weather environments, the proposed optimization algorithm has greatly improved in terms of average monitoring reward, monitoring interruption rate and energy overflow rate. Moreover, it also indicates that the proposed algorithm has effective adaptation to the random and dynamic solar energy arrival. © 2023, ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

KAC-Unet: A Medical Image Segmentation With the Adaptive Group Strategy and Kolmogorov-Arnold Network

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Lin, Shiying Hu, Rong Li, Zuoyong Lin, Qinghua Zeng, Kun Wu, Xiang Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fuzhou350118 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Fuzhou350121 China Fuzhou University Affiliated Provincial Hospital Provincial Clinical Medical College Fujian Medical University Department of Urology Fuzhou350001 China

In the field of deep learning-based medical image segmentation, convolutional neural networks (CNNs) extract image features by combining linear convolutional layers with nonlinear activation functions. However, excessive stacking of linear layers in the network limits the model’s ability to capture fine-grained details. In addition, the feature distribution imbalance caused by the traditional fixed grouping strategy (FGS) can affect the deep model’s capacity to perceive the overall structure of the image. To address these challenges, we propose a medical image segmentation framework, called Kolmogorov-Arnold Network with the adaptive group strategy and contextual Transformer based on Unet (KAC-Unet). First, we propose the adaptive group strategy (AGS) to balance the grouping of different input channels, alleviating the performance degradation caused by differences in group information. Then, we propose the Shift Tokenized Kolmogorov-Arnold Network (KAN) Block to capture complex features in medical images through flexible nonlinear transformations and shift operations. Extensive experiments are conducted on three medical image segmentation datasets. The results demonstrate the effectiveness and superiority of our proposed method compared with state-of-the-art algorithms. © 1963-2012 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Tunable bound states in the continuum with high Q factors

Tunable bound states in the continuum with high Q factors

引用

CLEO: QELS_Fundamental Science, QELS 2022

作者： Hu, Guiying Li, Zhixin Yang, Shuixian Xia, Di Wu, Jiayue Huang, Jianteng Zhang, Bin Xu, Yi Li, Zhaohui Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems School of Electrical and Information Technology Sun Yat-sen University Guangzhou510275 China Key Laboratory of Optoelectronic Materials and Technologies Sun Yat-sen University Guangzhou510275 China Zhuhai519000 China Guangdong Provincial Key Laboratory of Information Photonics Technology Advanced Institute of Photonics Technology School of Information Engineering Guangdong University of Technology Guangzhou510006 China

We realized a chalcogenide glass (ChG) photonic crystal supporting bound states in the continuum (BIC) with a Q-factor of ca. 105. With large photosensitivity of ChG, a non-volatile and high precision resonant-wavelen... 详细信息

ISBN: (纸本)9781557528209

关键词： Q factor measurement

来源：评论

学校读者我要写书评

暂无评论

A Wideband Dielectric Resonator Antenna for Millimeter Wave Applications

A Wideband Dielectric Resonator Antenna for Millimeter Wave ...

引用

2023 Photonics and Electromagnetics Research Symposium, PIERS 2023

作者： Yang, Zhaofang Yang, Wenwen Tong, Mei Song Guo, Lei Dalian University of Technology Dalian China Nantong University Nantong China Tongji University Shanghai China Sun Yat-Sen University Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Guangzhou China

ISBN: (纸本)9798350312843

A wideband millimeter-wave dielectric resonator (DR) antenna (DRA) is proposed for 5G applications. It consists of a rectangular DR with surrounding metallized holes. The simulated results show that the antenna can achieve a bandwidth of 50.2% (24.22-40.46 GHz). The DRA shows an average gain of 6.87 dBi with a maximum value of up to 11.78 dBi over the impedance bandwidth. It is also found that the broadside radiation patterns are very stable in the designed frequency band. © 2023 IEEE.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

Dynamic Mask Curriculum Learning for Non-Autoregressive Neural Machine Translation 1

引用

18th China Conference on Machine Translation, CCMT 2022

作者： Wang, Yisong Hou, Hongxu Sun, Shuo Wu, Nier Jian, Weichen Yang, Zongheng Wang, Pengcong National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology College of Computer Science Inner Mongolia University Hohhot China

ISBN: (数字)9789811979606

ISBN: (纸本)9789811979590

Non-autoregressive neural machine translation is gradually becoming a research hotspot due to its advantages of fast decoding. However, the increase of decoding speed is often accompanied by the loss of model performance. The main reason is that the target language information obtained at the decoder side is insufficient, and the mandatory parallel decoding leads to a large number of mistranslation and missing translation problems. In order to solve the problem of insufficient target language information, this paper proposes a dynamic mask curriculum learning approach to provide target side language information to the model. The target side self-attention layer is added in the pre-training phase to capture the target side information and adjust the amount of information input at any time by way of curriculum learning. The fine-tuning and inference phases disable the module in the same way as the normal NAT model. In this paper, we experiment on two translation datasets of WMT16, and the BLEU improvement reaches 4.4 without speed reduction. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Functional Connectivity Patterns Learning for EEG-based Emotion Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年第3期17卷 480-494页

作者： Shi, Chongxing Chen, C. L. Philip Li, Shuzhen Zhang, Tong South China University of Technology Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information School of Computer Science and Engineering Guangzhou510006 China Pazhou Lab Guangzhou510335 China Eng. Res. Ctr. of the Min. of Educ. on Health Intelligent Perception and Paralleled Digital-Human Guangzhou China

Neuroscience research reveals that different emotions are associated with different functional connectivity structures of brain regions. However, many existing EEG-based emotion recognition methods use these connectivity patterns broadly without distinguishing between specific emotions. Additionally, the non-stationarity of EEG signals often results in high variations across different periods, leading models to extract time-specific features instead of emotional features. This paper proposes a Functional Connectivity Patterns Learning network (FCPL) for EEG-based emotion recognition to address these challenges. FCPL includes a coefficient branch, a graph construction module, and a period domain adversarial module. These components capture individual characteristics and specific emotional connectivity patterns and reduce period-related variations, respectively. FCPL achieves state-of-the-art results: 42.04%/28.81% for seven-class subject-dependent/independent experiments on the MPED dataset, 97.45%/89.88% for subject-dependent/independent experiments on the SEED dataset, and 95.98%/96.19% for valence/arousal subject-dependent experiments and 67.90%/65.60% for valence/arousal subject-independent experiments on the DREAMER dataset. This work advances the exploration of functional connectivity structures in EEG signals from coarse-grained emotion-related patterns to fine-grained emotional distinctions, promoting neuroscience and EEG-based emotion recognition technologies. © 2016 IEEE.

关键词： Emotion Recognition

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：