检索结果-内蒙古大学图书馆

Iterative Algorithm Induced Deep-Unfolding Neural Networks: Precoding Design for Multiuser MIMO Systems

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hu, Qiyu Cai, Yunlong Shi, Qingjiang Xu, Kaidi Yu, Guanding Ding, Zhi College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China School of Software Engineering Tongji University Shanghai China Department of Electrical and Computer Engineering University of California DavisCA95616 United States

Optimization theory assisted algorithms have received great attention for precoding design in multiuser multiple-input multiple-output (MU-MIMO) systems. Although the resultant optimization algorithms are able to provide excellent performance, they generally require considerable computational complexity, which gets in the way of their practical application in real-time systems. In this work, in order to address this issue, we first propose a framework for deep-unfolding, where a general form of iterative algorithm induced deep-unfolding neural network (IAIDNN) is developed in matrix form to better solve the problems in communication systems. Then, we implement the proposed deep-unfolding framework to solve the sum-rate maximization problem for precoding design in MU-MIMO systems. An efficient IAIDNN based on the structure of the classic weighted minimum mean-square error (WMMSE) iterative algorithm is developed. Specifically, the iterative WMMSE algorithm is unfolded into a layer-wise structure, where a number of trainable parameters are introduced to replace the high-complexity operations in the forward propagation. To train the network, a generalized chain rule of the IAIDNN is proposed to depict the recurrence relation of gradients between two adjacent layers in the back propagation. Moreover, we discuss the computational complexity and generalization ability of the proposed scheme. Simulation results show that the proposed IAIDNN efficiently achieves the performance of the iterative WMMSE algorithm with reduced computational complexity. Copyright © 2020, The Authors. All rights reserved.

关键词： Iterative methods

An ANTLR-based flattening framework for AltaRica 3.0 model

学校读者我要写书评

暂无评论

International Journal of Performability engineering 2019年第9期15卷 2462-2475页

作者： Hu, Jun Chen, Shuo Chen, Defeng Kang, Jiexiang Wang, Hui College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China Department of Software China National Aeronautic Radio Electronics Research Institute Shanghai200233 China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing210007 China School of Mechanical Engineering Hefei University of Technology Hefei230601 China

AltaRica is a modeling language that is capable of hierarchical modelling and fault behavior description for industrial safety-critical system design. AltaRica 3.0 is the latest version, and its semantics are based on a formal GTS (Guarded Transition Systems) model. One of the key steps in the process of safety analysis toward AltaRica 3.0 models is that how to flatten a hierarchical AltaRica 3.0 model into a semantically equivalent GTS semantic model. This paper proposes an AltaRica 3.0 model flattening algorithm framework based on ANTLR (Another Tool for Language Recognition). Firstly, considering the different structural features of Block and Class, the AltaRica 3.0 model is sliced carefully in order to obtain the corresponding AST (Abstract Syntax Tree). Secondly, a set of recursive transformation algorithms are designed to extract and transform the AltaRica model elements, which are stored in the AST nodes based on the traversal technique of the AST. Then, a semantically equivalent flattened GTS model can be obtained. Lastly, several case studies show that the algorithms designed in this paper can effectively implement the flattening process of AltaRica 3.0 models. © 2019 Totem Publisher, Inc. All rights reserved.

关键词： Modeling languages

3D shape generation via functionality-aware model evolution

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Guan, Yanran Liu, Han Liu, Kun Yin, Kangxue Hu, Ruizhen van Kaick, Oliver Zhang, Yan Yumer, Ersin Carr, Nathan Mech, Radomir Zhang, Hao School of Computer Science Carleton University Canada Electronic Arts United States Department of Computer Science and Technology Nanjing University China College of Computer Science and Software Engineering Shenzhen University China Uber ATG United States Adobe Systems United States School of Computing Science Simon Fraser University Canada

We introduce a modeling tool which can evolve a set of 3D objects in a functionality-aware manner. Our goal is for the evolution to generate large and diverse sets of plausible 3D objects for data augmentation, constrained modeling, as well as open-ended exploration to possibly inspire new designs. Starting with an initial population of 3D objects belonging to one or more functional categories, we evolve the shapes through part recombination to produce generations of hybrids or crossbreeds between parents from the heterogeneous shape collection. Evolutionary selection of offsprings is guided both by a functional plausibility score derived from functionality analysis of shapes in the initial population and user preference, as in a design gallery. Since cross-category hybridization may result in offsprings not belonging to any of the known functional categories, we develop a means for functionality partial matching to evaluate functional plausibility on partial shapes. We show a variety of plausible hybrid shapes generated by our functionality-aware model evolution, which can complement existing datasets as training data and boost the performance of contemporary data-driven segmentation schemes, especially in challenging cases. Our tool supports constrained modeling, allowing users to restrict or steer the model evolution with functionality labels. At the same time, unexpected yet functional object prototypes can emerge during open-ended exploration owing to structure breaking when evolving a heterogeneous collection. Copyright © 2020, The Authors. All rights reserved.

关键词： 3D modeling

Efficient Multi-Grained Wear Leveling for Inodes of Persistent Memory File Systems

学校读者我要写书评

暂无评论

Efficient Multi-Grained Wear Leveling for Inodes of Persiste...

Design Automation Conference

作者： Chaoshu Yang Duo Liu Runyu Zhang Xianzhang Chen Shun Nie Fengshun Wang Qingfeng Zhuge Edwin H.-M. Sha Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education China College of Computer Science Chongqing University Chongqing China School of Computer Science and Software Engineering East China Normal University Shanghai China

ISBN: (数字)9781728110851

ISBN: (纸本)9781728158020

Existing persistent memory file systems usually store inodes in fixed locations, which ignores the external and internal imbalanced wears of inodes on the persistent memory (PM). Therefore, the PM for storing inodes can be easily damaged. Existing solutions achieve low accuracy of wear-leveling with high-overhead data migrations. In this paper, we propose a Lightweight and Multi-grained Wear-leveling Mechanism, called LMWM, to solve these problems. We implement the proposed LMWM in Linux kernel based on NOVA, a typical persistent memory file system. Compared with MARCH, the state-of-theart wear-leveling mechanism for inode table, experimental results show that LMWM can improve 2.5× lifetime of PM and 1.12× performance, respectively.

关键词： Silicon Metadata Indexes Linux Kernel File systems

WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Han, Chu Pan, Xipeng Yan, Lixu Lin, Huan Li, Bingbing Yao, Su Lv, Shanshan Shi, Zhenwei Mai, Jinhai Lin, Jiatai Zhao, Bingchao Xu, Zeyan Wang, Zhizhen Wang, Yumeng Zhang, Yuan Wang, Huihui Zhu, Chao Lin, Chunhui Mao, Lijian Wu, Min Duan, Luwen Zhu, Jingsong Hu, Dong Fang, Zijie Chen, Yang Zhang, Yongbing Li, Yi Zou, Yiwen Yu, Yiduo Li, Xiaomeng Li, Haiming Cui, Yanfen Han, Guoqiang Xu, Yan Xu, Jun Yang, Huihua Li, Chunming Liu, Zhenbing Lu, Cheng Chen, Xin Liang, Changhong Zhang, Qingling Liu, Zaiyi The Department of Radiology Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou510080 China Guangdong Prov. Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou510080 China The Department of Pathology Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou510080 China The School of Computer Science and Information Security Guilin University of Electronic Technology Guangxi541004 China The Department of Pathology Guangdong Provicial People's Hospital Ganzhou Hospital Ganzhou China The College of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The School of Computer Science and Engineering South China University of Technology Guangzhou510640 China The Institute for AI in Medicine School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing210044 China The School of Biological Science and Medical Engineering State Key Laboratory of Software Development Environment Key Laboratory of Biomechanics and Mechanobiology of Ministry of Education Research Institute of Beihang University in Shenzhen Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing100191 China The Department of Radiology Guangzhou First People's Hospital Hospital of South China University of Technology Guangzhou510180 China The Zhejiang Dahua Technology Co. Ltd Zhejiang310053 China The School of Biomedical Engineering University of Science and Technology of China Hefei230022 China The Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China Electronic and Computer Engineering & Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong The School of Automation Science and Engineering Xi'An Jiaotong University Xian710049 Chi

Lung cancer is the leading cause of cancer death worldwide, and adenocarcinoma (LUAD) is the most common subtype. Exploiting the potential value of the histopathology images can promote precision medicine in oncology. Tissue segmentation is the basic upstream task of histopathology image analysis. Existing deep learning models have achieved superior segmentation performance but require sufficient pixel-level annotations, which is time-consuming and expensive. To enrich the label resources of LUAD and to alleviate the annotation efforts, we organize this challenge WSSS4LUAD to call for the outstanding weakly-supervised semantic segmentation (WSSS) techniques for histopathology images of LUAD. Participants have to design the algorithm to segment tumor epithelial, tumor-associated stroma and normal tissue with only patch-level labels. This challenge includes 10,091 patch-level annotations (the training set) and over 130 million labeled pixels (the validation and test sets), from 87 WSIs (67 from GDPH, 20 from TCGA). All the labels were generated by a pathologist-in-the-loop pipeline with the help of AI models and checked by the label review board. Among 532 registrations, 28 teams submitted the results in the test phase with over 1,000 submissions. Finally, the first place team achieved mIoU of 0.8413 (tumor: 0.8389, stroma: 0.7931, normal: 0.8919). According to the technical reports of the top-tier teams, CAM is still the most popular approach in WSSS. Cutmix data augmentation has been widely adopted to generate more reliable samples. With the success of this challenge, we believe that WSSS approaches with patch-level annotations can be a complement to the traditional pixel annotations while reducing the annotation efforts. The entire dataset has been released to encourage more researches on computational pathology in LUAD and more novel WSSS techniques. © 2022, CC BY.

关键词： Semantic Segmentation

Usability Evaluation of Pandemic Health Care Mobile Applications

学校读者我要写书评

暂无评论

IOP Conference Series: Earth and Environmental science 2021年第1期704卷

作者： M Mubeen M W Iqbal M Junaid M H Sajjad M R Naqvi B A Khan M M Saeed M U Tahir Department of Software Engineering The Superior College Lahore 54700 Pakistan Department of Computer Science The Superior College Lahore 54700 Pakistan

This study was conducted to evaluate the usability of health care apps and its significance in the field of health care. As health care centers are the settings working 24/7 for providing health services to patients. For this study a systematic review, comparison and functionality assessment of selected COVID19 mobile apps was performed. The assessment was performed on two digital platforms, App store on Apple iPhone and Google play store on Android smartphones. Further online search of keywords on Google was also conducted in order to ensure the reliability and validity of apps on these stores. And only those apps were selected which were in English because of the language proficiency of authors. The mobile apps selected were having five features of assessment, a questionnaire, Privacy statement, Precautionary measures if test positive for COVID19, after plans of Pandemic and Region based. The sample was a blend of participants from different fields including students, doctors, patients and software developers. This is quantitative study; a questionnaire was distributed among the selected participants who were familiar with the use of health care mobile apps. The data was analyzed on the basis of gender and age. The results were made on the basis of responses towards effectiveness, efficiency and satisfaction of users towards mobile phone apps. The results show that apps were found 64.5% informative for participants as they helped in fast communication of doctors and patients while sitting at the other corner of world.

关键词：

Research on cancer rapid diagnosis technology based on adaptive channel attention mechanism and two-dimensional spectral fusion

学校读者我要写书评

暂无评论

Microchemical Journal 2025年 213卷

作者： Liu, Wei Chang, Chenjie Li, Jiahe Lv, Xiaoyi Liu, Yang Chen, Chen Chen, Cheng College of Software Xinjiang University Urumqi 830046 China School of Computer Science and Technology Xinjiang University Urumqi 830046 China Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi 830046 China Xinjiang Cloud Computing Application Laboratory Xinjiang Cloud Computing Engineering Technology Research Center Karamay 834000 China

With the widespread use of Artificial Intelligence (AI) in biomedicine, integrating infrared and Raman spectra with biological information offers new prospects for enhanced disease diagnosis. For these two types of data, more information can be extracted using multimodal data fusion compared to single modality, but existing studies tend to only fuse one-dimensional spectral data, ignoring the richer information of the spectra when they are converted to two-dimensional images. In this study, we propose a rapid diagnostic method for cancer, which first converts one-dimensional (1D) Raman and Infrared spectra into two-dimensional (2D) spectral images using Short-Time Fourier Transform (STFT), respectively. Then the features are fused by our designed Adaptive Graph Channel Attention Spacial Cross-Attention Fusion Module (ASCFM). This fusion module innovatively uses the adaptive graph channel attention mechanism to strengthen the model's ability to capture the key information of different spectral features, and utilizes the spatial attention fusion module and the cross-attention module for spatial information extraction and fusion. The output fused features effectively avoid feature information loss through this multimodal feature extraction and fusion, which greatly improves the performance of the model. In this study, Gradient-weighted Class Activation Mapping is also used to make the decision-making process of the neural network more interpretable. The results show that the accuracy of 2D Raman spectral images fused with 2D infrared spectral images by ASCFM followed by ResidualNetwork (ResNet) for diagnosis of lung cancer and glioma datasets is 98.88 % and 96.38 %, which suggests that it is a highly promising adjunctive technique for cancer diagnosis. © 2025

关键词： Auxiliary diagnostic technology Deep learning Infrared spectroscopy Lung cancer Multimodal fusion Raman spectroscopy

Uplink Throughput Maximization for Low Latency in Wireless Powered Communication Networks

学校读者我要写书评

暂无评论

Uplink Throughput Maximization for Low Latency in Wireless P...

International Conference on Communication Technology (ICCT)

作者： M.S. Syam Yue Ling Che Sheng Luo Kaishun Wu College of Information Engineering Shenzhen University College of Computer Science and Software Engineering Shenzhen University

With the coming of 5G era, wireless transmissions of high data rates in the uplink (UL) are intensely demanded, for supporting low-latency wireless transmissions in various applications. In this paper, a joint downlink (DL) and UL optimization to maximize the sum of UL throughput of devices for a given sum of DL throughput in a wireless powered communication network (WPCN) with two devices is considered. The time frame is divided into two phases: a DL phase followed by a UL phase. In the DL, a hybrid access point (H-AP) first conducts wireless energy transfer (WET) to both devices, and then conducts wireless information transfer (WIT) to each device respectively. In the UL, each device conducts WIT to the H-AP in its allocated time. Each device exploits the total harvested energy from the H-AP in the DL to support its DL information reception and decoding as well as WIT in the UL. We optimize the time allocation for WET and WIT in the DL, WIT for each device in the UL, as well as transmit power of H-AP and devices, so as to maximize total UL throughput of the network for a given DL throughput, subject to energy causality constraints for each device, H-AP's and each device's transmit power constraint and time allocation constraint. However, this problem is non-convex and thus is difficult to be solved. To address this difficulty, we transform this problem into a convex optimization problem, and solve it efficiently. Simulation results are also conducted to show the performance of the proposed system.

关键词： Throughput Resource management Wireless communication Uplink Convex functions Transforms Time factors

Unsupervised Domain Adaptation through Transferring both the Source-Knowledge and Target-Relatedness Simultaneously

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tian, Qing Zhu, Yanan Ma, Chuang Cao, Meng School of Computer and Software Nanjing University of Information Science and Technology Nanjing China Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautic Nanjing China

Unsupervised domain adaptation (UDA) is an emerging research topic in the field of machine learning and pattern recognition, which aims to help the learning of unlabeled target domain by transferring knowledge from th... 详细信息

关键词： Pattern recognition