检索结果-内蒙古大学图书馆

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Konkathi Preethi Xiaojun Li Roberto Fernandez-Moran Xiangzhuo Liu Zanpin Xing F. Frappart Maria Piles Karthikeyan Lanka Jean-Pierre Wigneron Centre of Studies in Resources Engineering Indian Institute of Technology Bombay India INRAE UMR1391 ISPA Villenave d'Ornon France Image Processing Lab (IPL) University of Valencia Valencia Spain Cryosphere Research Station on the Qinghai-Tibet Plateau State Key Laboratory of Cryospheric Science Northwest Institute of Eco-Environment and Resource Chinese Academy of Sciences Lanzhou China IDP in Climate Studies Indian Institute of Technology Bombay India

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Soil Moisture Ocean Salinity (SMOS) mission was the first L-band radiometer launched in 2010 and is operational for retrieving global scale soil moisture and Vegetation Optical Depth (VOD). SMOS-INRA-CESBIO (SMOS-IC) version-2 is the latest retrieval algorithm for SMOS radiometers that outperforms existing SMOS retrieval algorithms. Research is underway to enhance the SMOS-IC product by improving surface roughness information that influences soil moisture and VOD retrievals. In the present study, we developed a new global parameterization of soil roughness using SMOS-IC retrievals. For this purpose, we retrieved the soil moisture and surface roughness (through the Hr parameter) values over bare soils using the SMOS-IC algorithm. A Random Forest (RF) model was trained with soil textural and terrain properties as inputs (explanatory variables) to model Hr over bare soils. Later, we extrapolated the Hr values obtained over bare soils to a global scale using the RF model. The newly calibrated Hr values were further used in the SMOS-IC algorithm for soil moisture and VOD retrievals (SMOS-IC v2.1). The SMOS-IC v2.1, the soil moisture product, is wetter than the original SMOS-IC v2 product and has improved performance compared to in situ ISMN soil moisture and modeled ECMWF soil moisture data sets. Regarding VOD, the SMOS-IC v2.1 VOD product showed improved spatial correlation with the reference aboveground biomass product. In addition, SMOS-IC v2.1 VOD product showed improved temporal correlation with MODIS NDVI over low-to-moderate vegetated regions.

关键词： Radio frequency Sea surface Correlation Soil moisture Vegetation mapping Surface roughness Rough surfaces

来源：评论

学校读者我要写书评

暂无评论

MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical image Segmentation

arXiv

引用

arXiv 2024年

作者： Tang, Fenghe Nian, Bingkun Li, Yingtai Jiang, Zihang Yang, Jie Liu, Wei Zhou, S. Kevin School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Jiangsu Suzhou215123 China Suzhou Institute for Advanced Research USTC Suzhou China Department of Automation Shanghai Jiao Tong University China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Institute of Medical Robotics Shanghai Jiao Tong University China State Key Laboratory of Precision and Intelligent Chemistry University of Science and Technology of China Anhui Hefei230026 China

Recently, the state space model Mamba has demonstrated efficient long-sequence modeling capabilities, particularly for addressing long-sequence visual tasks in 3D medical imaging. However, existing generative self-supervised learning methods have not yet fully unleashed Mamba’s potential for handling long-range dependencies because they overlook the inherent causal properties of state space sequences in masked modeling. To address this challenge, we propose a general-purpose pre-training framework called MambaMIM, a masked image modeling method based on a novel TOKen-Interpolation strategy (TOKI) for the selective structure state space sequence, which learns causal relationships of state space within the masked sequence. Further, MambaMIM introduces a bottom-up 3D hybrid masking strategy to maintain a masking consistency across different architectures and can be used on any single or hybrid Mamba architecture to enhance its multi-scale and long-range representation capability. We pre-train MambaMIM on a large-scale dataset of 6.8K CT scans and evaluate its performance across eight public medical segmentation benchmarks. Extensive downstream experiments reveal the feasibility and advancement of using Mamba for medical image pre-training. In particular, when we apply the MambaMIM to a customized architecture that hybridizes MedNeXt and Vision Mamba, we consistently obtain the state-of-the-art segmentation performance. The code is available at: https://***/FengheTan9/MambaMIM. Copyright © 2024, The Authors. All rights reserved.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Continuous Distributed processing of Software Defined Radar

Continuous Distributed Processing of Software Defined Radar

引用

2021 CIE International Conference on Radar, Radar 2021

作者： Li, Bing Qiu, Qiang Gong, Shiqi Liu, Yongjun Lei, Yu Institute of Computing Technology CAS Key Lab of Network Data Science and Technology Chinese Academy of Sciences Beijing China State Key Laboratory of Internet of Things for Smart City University of Macau Macau China Xidian University National Laboratory of Radar Signal Processing Xi'an China Golaxy Data Technology Co. Ltd. Beijing China

ISBN: (纸本)9781665498142

Software-defined radar has been an active research field for more than ten years. However, the low performance and low scalability of the traditional processing techniques of SDR make it hard to deal with complex radar tasks. The stream processing engine is a software that supports low latency and high scalability distributed data processing. It is widely used in log, image, and video processing scenarios but rarely used in radar applications. This paper reviews processing software-defined radar data by using the stream processing engine, and we illustrate the differences between processing log data and radar data. Furthermore, we discuss some optimizations for stream processing engines to get better performance in the radar data processing. © 2021 IEEE.

关键词： distributed processing Software-defined radar stream processing engine

来源：评论

学校读者我要写书评

暂无评论

Tablet Identification Using Ensemble Convolutional Neural Networks and Vibrational Spectroscopy

SSRN

引用

SSRN 2023年

作者： Sun, Penghui Wang, Jiajia Liu, Pei Dong, Zhilin School of Computer Science and Technology Xinjiang University Urumqi China The Key Laboratory of Signal Detection and Processing Xinjiang Uygur Autonomous Region Xinjiang University China Post-doctoral workstation of Xinjiang Xinjiang Uygur Autonomous Region Product Quality Supervision and Inspection Institute Urumqi China

Vibrational spectroscopy reflects molecular vibrational data, facilitating tablet identification. This paper introduces the DCNN-EL model, which integrates vibrational spectroscopy to accurately discern tablet categories. The DCNN-EL model is built upon the Alexnet framework, starting with the proposal of the Alexnet-BN model, enhancing model training speed and robustness by iteratively applying the BN layer in lieu of the pooling layer. Subsequently, by adjusting the parameters of Alexnet-BN, five deep convolutional neural network (DCNN) models are established and combined using an integrated machine learning approach to form the DCNN-EL model. Evaluating the DCNN-EL model with two public datasets (Tablets_Nir and Tablets_Raman) demonstrates its 100% and 91.67% accuracy, affirming its efficacy and generalizability in tablet identification. Consequently, the amalgamation of convolutional neural networks and vibrational spectroscopy bears significant practical relevance in the qualitative detection of tablets. © 2023, 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

High Information Density and Low Coverage Data Storage in DNA with Efficient Channel Coding Schemes

arXiv

引用

arXiv 2024年

作者： Ding, Yi He, Xuan Nguyen, Tuan Thanh Song, Wentu Yakhini, Zohar Yaakobi, Eitan Pan, Linqiang Tang, Xiaohu Cai, Kui Information Coding and Transmission Key Lab of Sichuan Province Southwest Jiaotong University Sichuan Chengdu611756 China Cluster Singapore University of Technology and Design 487372 Singapore Faculty of Computer Science Technion - Israel Institute of Technology Haifa3200003 Israel School of Computer Science RUNI Herzliya4615200 Israel Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China

DNA-based data storage has been attracting significant attention due to its extremely high data storage density, low power consumption, and long duration compared to conventional data storage media. Despite the recent advancements in DNA data storage technology, significant challenges remain. In particular, various types of errors can occur during the processes of DNA synthesis, storage, and sequencing, including substitution errors, insertion errors, and deletion errors. Furthermore, the entire oligo may be lost. In this work, we report a DNA-based data storage architecture that incorporates efficient channel coding schemes, including different types of error-correcting codes (ECCs) and constrained codes, for both the inner coding and outer coding for the DNA data storage channel. We also carried out large scale experiments to validate our proposed DNA-based data storage architecture. Specifically, 1.61 and 1.69 MB data were encoded into 30,000 oligos each, with information densities of 1.731 and 1.815, respectively. It has been found that the stored information can be fully recovered without any error at average coverages of 4.5 and 6.0, respectively. This experiment achieved the highest net information density and lowest coverage among existing DNA-based data storage experiments (with standard DNA), with data recovery rates and coverage approaching theoretical optima. Copyright © 2024, The Authors. All rights reserved.

关键词： Channel coding

来源：评论

学校读者我要写书评

暂无评论

Unified-modal Salient Object Detection via Adaptive Prompt Learning

arXiv

引用

arXiv 2023年

作者： Wang, Kunpeng Li, Chenglong Tu, Zhengzheng Liu, Zhengyi Luo, Bin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China The Institute of Physical Science and Information Technology Anhui University Hefei230601 China

Existing single-modal and multi-modal salient object detection (SOD) methods focus on designing specific architectures tailored for their respective tasks. However, developing completely different models for different tasks leads to labor and time consumption, as well as high computational and practical deployment costs. In this paper, we attempt to address both single-modal and multi-modal SOD in a unified framework called UniSOD, which fully exploits the overlapping prior knowledge between different tasks. Nevertheless, assigning appropriate strategies to modality variable inputs is challenging. To this end, UniSOD learns modality-aware prompts with task-specific hints through adaptive prompt learning, which are plugged into the proposed pre-trained baseline SOD model to handle corresponding tasks, while only requiring few learnable parameters compared to training the entire model. Each modality-aware prompt is generated from a switchable prompt generation block, which adaptively performs structural switching based on single-modal and multi-modal inputs without human intervention. Through end-to-end joint training, UniSOD achieves overall performance improvement on 14 benchmark datasets for RGB, RGB-D, and RGB-T SOD, which demonstrates that our method effectively and efficiently unifies single-modal and multi-modal SOD tasks. The code and results are available at https://***/Angknpng/UniSOD. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Isomer Engineering for Red Thermally Activated Delayed Fluorescence Molecules: Luminescence Mechanism Study and Rational Molecular Design

SSRN

引用

SSRN 2023年

作者： Zhao, Xin Liu, Huanling Mu, Qingfang Xie, Zhen Song, Yuzhi Lin, Lili Xu, Yuanyuan Fan, Jianzhong Shandong Province Key Laboratory of Medical Physics and Image Processing Technology Institute of Materials and Clean Energy School of Physics and Electronics Shandong Normal University Jinan250014 China School of Science Qilu University of Technology Shandong Academy of Sciences Jinan250353 China Guangdong Provincial Key Laboratory of Luminescence from Molecular Aggregates South China University of Technology Guangzhou510640 China

Through urgently needed, red thermally activated delayed fluorescence (TADF) molecules are still rare due to the energy-gap law, developing efficient red TADF molecules remains a great challenge and it is extremely urgent to reveal the luminescence mechanisms through theoretical perspectives. Herein, based on density functional theory (DFT) and time-dependent density functional theory (TD-DFT) methods coupled with the thermal vibration correlation function (TVCF) method, the photophysical properties of two pairs of red TADF isomers (PDCN-DPAC, PDCN-DPAC-2, PPDCN-DPAC and PPDCN-DPAC-2) in toluene and solid phase have been theoretically studied by the polarizable continuum model (PCM) and the combined quantum mechanics and molecular mechanics (QM/MM) method, respectively. Detailed parameters such as the adiabatic singlet-triplet energy gaps, natural transition orbital properties, reorganization energies, the rate constants of radiative, non-radiative, intersystem crossing (ISC) and reverse intersystem crossing (RISC) processes are studied, and excited state energy consumption processes are analyzed. Results indicate that, compared with trans-isomers (PDCN-DPAC and PPDCN-DPAC) in toluene, cis-isomers PDCN-DPAC-2 and PPDCN-DPAC-2 possess smaller energy gaps which bring fast RISC processes. While for molecules in solid phase, decreased energy gaps and increased spin orbit coupling (SOC) constants are determined, all these factors contribute to the remarkable RISC processes. Furthermore, based on the PPDCN-DPAC configuration, three new red TADF molecules (PPDCN-PAS, PPDCN-TPA and PPDCN-DMAC) are theoretically designed by linking different donor fragments phenazasiline (PAS), triphenylamine (TPA), dimethylacridine (DMAC) with acceptor unit PPDCN. Notably, small energy gaps and large SOC constants are obtained, remarkable triplet excitons harvest abilities and fast up-conversion processes are revealed. Moreover, oscillator strengths are significantly improved and promising

关键词： Isomers

来源：评论

学校读者我要写书评

暂无评论

EWT: Efficient Wavelet-Transformer for Single image Denoising

arXiv

引用

arXiv 2023年

作者： Li, Juncheng Cheng, Bodong Chen, Ying Gao, Guangwei Zeng, Tieyong The School of Communication & Information Engineering Shanghai University Shanghai China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing China The School of Computer Science and Technology Xidian University Xian China The Department of Cyberspace Security Beijing Electronic Science & Technology Institute Beijing China The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China The Department of Mathematics The Chinese University of Hong Kong New Territories Hong Kong

Transformer-based image denoising methods have achieved encouraging results in the past year. However, it must uses linear operations to model long-range dependencies, which greatly increases model inference time and consumes GPU storage space. Compared with convolutional neural network-based methods, current Transformer-based image denoising methods cannot achieve a balance between performance improvement and resource consumption. In this paper, we propose an Efficient Wavelet Transformer (EWT) for image denoising. Specifically, we use Discrete Wavelet Transform (DWT) and Inverse Wavelet Transform (IWT) for downsampling and upsampling, respectively. This method can fully preserve the image features while reducing the image resolution, thereby greatly reducing the device resource consumption of the Transformer model. Furthermore, we propose a novel Dual-stream Feature Extraction Block (DFEB) to extract image features at different levels, which can further reduce model inference time and GPU memory usage. Experiments show that our method speeds up the original Transformer by more than 80%, reduces GPU memory usage by more than 60%, and achieves excellent denoising results. All code will be public. © 2023, CC BY.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

Prediction of Drug-Disease Associations Based on Long Short-Term Memory Network and Gaussian Interaction Profile Kernel 15th

Prediction of Drug-Disease Associations Based on Long Short-...

引用

15th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2020

作者： Jiang, Han-Jing Wang, Yan-Bin Huang, Yabing Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China College of Computer Science and Technology Zhejiang University Hangzhou315000 China Department of Pathology Renmin Hospital of Wuhan University Wuhan430060 China

ISBN: (纸本)9789811613531

Drug-disease association depicts the accessibility landscape of the association at the molecular level, thereby revealing the intermolecular reaction in the process of drug reposition. However, the scarcity of drug-disease association data often complicates the drug reposition. In this work, we present a method for predicting drug-disease association, which is called drug-disease association prediction via Gaussian interaction profile kernel and long short-term memory network (G-LSTM). G-LSTM combines a recurrent network framework with a Gaussian interaction profile kernel to learn underlying features that accurately characterize drug-disease-association data. We have verified G-LSTM models on the two benchmark datasets Fdataset and Cdataset, respectively. The experimental results show that the predictive performance was significantly improved, with AUC of 0.9527 and 0.9705, respectively. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Novel YJQR-LSTM Model for Nonparametric Probabilistic Sustainable Agriculture Wind Power Forecasting Based on Intelligent IoT

引用

IEEE Internet of Things Journal 2024年

作者： Wang, Jie Jiang, Junhui Chen, Xinlong Cai, Defu Wu, Yue Lu, Renzhi School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Harbin Engineering University College of Computer Science and Technology Harbin150001 China State Grid Hubei Electric Power Research Institute Hubei Wuhan430079 China School of Technology State Key Laboratory of Efficient Production of Forest Resources Key Laboratory of National Forestry and Grassland Administration on Forestry Equipment and Automation Beijing Forestry University Beijing100083 China Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Industrial Internet of Things and Networked Control Ministry of Education Chongqing400065 China State Key Laboratory of Mechanical Transmission for Advanced Equipment Chongqing University Chongqing400044 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China

Energy costs associated with the consumption of non-renewable energy sources have become an important issue in improving the international competitiveness of agriculture. Wind power, as a renewable energy source, can replace non-renewable energy sources to reduce energy costs and improve the sustainability of agricultural. However, the inherent intermittency, randomness, and volatility within weather conditions and wind speed presents a substantial challenge in accurately predicting wind power generation. This work proposes a novel YJQR-LSTM algorithm that leverages Yeo-Johnson quantile regression (YJQR) with a long short-term memory (LSTM) network for nonparametric probabilistic forecasting of wind power generation via the Intelligent Internet of Things. First, an improved YJQR model based on the YJ transformation is designed to obtain a more precise characterization of wind uncertainty, providing a more flexible probability density function for wind power generation. Then, utilizing the unique structure of the LSTM network to learn the parameters of the YJQR model, temporal features can be extracted from time series data. To mitigate the impact of outliers in the raw data on accuracy and improve computational efficiency, a novel logarithmic likelihood function is developed as the loss function utilized in the training phase. The effectiveness of the proposed algorithm is validated using a real-world dataset from five wind farms from the Global Energy Forecasting Competition. Numerical results demonstrate that the algorithm provides more accurate wind power prediction results in complex wind power data environments, which is important for making full use of wind energy and thus reducing the consumption of non-renewable energy in agriculture. © 2024 IEEE.

关键词： Wind 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：