检索结果-内蒙古大学图书馆

Emerging theory and phenomena in thermal conduction: A selective review

science China(Physics,Mechanics & Astronomy) 2022年第11期65卷 2-17页

作者： Jie Chen Jia He Dongkai Pan Xiaotian Wang Nuo Yang Jiaojiao Zhu Shengyuan A.Yang Gang Zhang Center for Phononics and Thermal Energy Science China-EU Joint Lab for NanophononicsMOE Key Laboratory of Advanced Microstructured MaterialsSchool of Physics Science and EngineeringTongji UniversityShanghai 200092China School of Energy and Power Engineering Huazhong University of Science and Technology(HUST)Wuhan 430074China School of Physical Science and Technology Southwest UniversityChongqing 400715China Research Laboratory for Quantum Materials Singapore University of Technology and DesignSingapore 487372Singapore Institute of High Performance Computing Agency for ScienceTechnology and Research(A*STAR)Singapore 138632Singapore

Recently, emerging phonon phenomena have been discovered and rapidly developed, which have become an active hot research topic. In this review article, we present state-of-the-art advances in several fascinating phonon transport phenomena. First, we summarize the recent progress on the wave nature of phonons, including phonon coherence and its effects on thermal conductivity and the topological properties of phonons. Then, we discuss the particle nature of phonons, including the weak coupling of phonons and the high-order phonon anharmonicity. Finally, we present the summary and a brief outlook. This review presents the advanced understanding of some emerging phonon phenomena in solid materials, which provides new opportunities for further advancement in a wide variety of applications.

关键词： phonon transport coherence topological phonon high-order phonon interaction

来源：评论

学校读者我要写书评

暂无评论

Comparison of deep learning classification based methods with hyper parameter tuning on hyperspectral imagery 2

Comparison of deep learning classification based methods wit...

引用

2nd International Conference on Range Technology, ICORT 2021

作者： Bidari, Indira Chickerur, Satyadhyan Soumya, G S Sushmita, H T Talikoti, Rekha Smita, S K KLE Technological University School of Computer Science and Engineering Hubballi India KLE Technological University Centre for High Performance Computing School of Computer Science and Engineering Hubballi India

ISBN: (纸本)9781665449564

Hyperspectral Imagery (HSI) with classification is the most significant and dominant area in remote sensing. The HSI's profuse information is used for various applications in mineralogy, agriculture, physics, astronomy, chemical imaging, surveillance, and environmental sciences. In this paper, a comparison of classification approaches on the hyperspectral image dataset of Indian Pines is carried out. The three methods considered for the study. First one is CNN-Convolutional Neural Network is used for encoding pixel's spectral and spatial information and conducted the classification. Second is the MLP-Multi-Layer Perceptron is a typical kind of neural network with several layers for classification and third is HybridSN is a spectral-spatial 3D-CNN along with spatial2D-CNN. A comparison of these deep learning classification-based methods is piloted. Hyperparameter tuning is performed to increase the model accuracy for the ideal model architecture. © 2021 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Change detection and classification using hyperspectral imagery 2

Change detection and classification using hyperspectral imag...

引用

2nd International Conference on Range Technology, ICORT 2021

作者： Bidari, Indira Chickerur, Satyadhyan Kulkarni, Akshay Mahajan, Anish Nikkam, Amogh Akella, Sumanth KLE Technological University School of Computer Science and Engineering Hubballi India KLE Technological University Centre for High Performance Computing School of Computer Science and Engineering Hubballi India

ISBN: (纸本)9781665449564

Hyperspectral Imagery is a field with various applications in the present world. Classification and Change Detection (CD) have been fields of great importance over the years. Powerful tools are built by combining these two approaches, HSI with classification and with change detection. Deep learning-based land-cover classification and change detection algorithms have made significant advancements during recent times. In this paper, a band-specific feature extraction and classification method using 2D and 3D CNN (Hybrid Spectral Net) is being projected, which is computationally more accessible. Also, a change detection algorithm uses the Slow Feature Analysis (SFA) technique and fully connected layers of a neural network to give a binary classification. So initially, we aimed to do the multiclass classification by combining classification and change detection in one module. But a dataset with the ground truth value and bitemporal was required, which was not available, so both classification and change detection have been implemented on different datasets. © 2021 IEEE.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Health Care and Management based on Block chain and Machine Learning

Health Care and Management based on Block chain and Machine ...

引用

2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent engineering, ICECONF 2023

作者： Bakh, Ruhi Sarkar, VeenaNair Auguskani, Jerlin Priya Lovelin Poornima, Galiveeti Shetty, Monali N. Raj, Meerjumla Govind Dr. Ambedkar Institute of Management Studies and Research India Iihmr University India Department of Nursing College Aldrab Jazan University Saudi Arabia High Performance Computing Lab School of Computer Science and Information Science Presidency University Bengaluru India Computer Science Engineering Fr. Crce India St. Martin and #39 s Engineering College Survey No. 563 Dulapally Kompally Telangana Secunderabad500100 India

ISBN: (纸本)9798350334357

With the coming of technology, we currently have an immense measure of information accessible in each field, making it conceivable to offer responses to many issues. We will utilize machine learning and block chain technology to resolve issues with healthcare information the executives in this review. With the guide of machine learning, separating just the relevant information from the data is plausible. Using prepared calculations, this is finished. The reliability of information trade turns into a test after this information has been put away. This is where block chain technology is valuable. Block chain technology's agreement guarantees that information is credible and exchanges are secure. By putting the patient at the focal point of the healthcare framework and upgrading the security and interoperability of health information, block chain technology can possibly further develop health care organization. This article fundamentally centres around settling issues with healthcare information the board using Block chain technology and including a few urgent highlights utilizing Machine Learning. The freshest technology, block chain, offers a strong and secure groundwork. With these offices, block chain has gotten some momentum in an assortment of use areas, including the food business, store network the board, energy, government support offices, and healthcare. © 2023 IEEE.

关键词： Health care

来源：评论

学校读者我要写书评

暂无评论

An Efficient Sparse LSTM Accelerator on Embedded FPGAs with Bandwidth-Oriented Pruning

An Efficient Sparse LSTM Accelerator on Embedded FPGAs with ...

引用

International Conference on Field Programmable Logic and Applications

作者： Shiqing Li Shien Zhu Xiangzhong Luo Tao Luo Weichen Liu School of Computer Science and Engineering Nanyang Technological University Singapore Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore

Long short-term memory (LSTM) networks have been widely used in natural language processing applications. Although over 80% weights can be pruned to reduce the memory requirement with little accuracy loss, the pruned model still cannot be buffered on-chip for small embedded FPGAs. Considering that weights are stored in the off-chip DDR, the performance of LSTM is bounded by the available memory bandwidth. However, current pruning strategies did not consider bandwidth utilization and thus lead to bad performance in this situation. In this work, we propose an efficient sparse LSTM accelerator on embedded FPGAs with bandwidth-oriented pruning. The key idea is that data sequences can be compressed if items can be represented by a linear function of their indices in the sequences. Inspired by this idea, we first propose a column-wise pruning strategy that removes all the column indices and around 75% row indices of the remaining weights. Based on the strategy, we design a dedicated compressed format to fill the bandwidth. Further, we propose a fully pipelined hardware accelerator, which achieves the workload balance and shortens the critical path. Finally, we train the LSTM model using the TIMIT dataset and implement the accelerator on the Xilinx PYNQ-Z1 platform. The experimental result shows that our design achieves around 0.3% accuracy improvement, a 2.18x performance speedup, and a 1.96x power efficiency compared to the state-of-the-art work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identification of Key Genes as Potential Drug Targets for Gastric Cancer

引用

Tsinghua science and Technology 2023年第4期28卷 649-664页

作者： Md.Tofazzal Hossain Md.Selim Reza Yin Peng Shengzhong Feng Yanjie Wei Center for High Performance Computing Joint Engineering Research Center for Health Big Data Intelligent Analysis TechnologyShenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China Department of Statistics Bangabandhu Sheikh Mujibur Rahman Science and Technology UniversityGopalganj 8100Bangladesh Guangdong Provincial Key Laboratory for Genome Stability and Disease Prevention and Regional Immunity and Diseases Department of PathologyShenzhen UniversityShenzhen 518060China

Gastric cancer(GC)is one of the most common cancers and ranks the third in cancer mortality all over the *** goal of this study was to identify potential hub-genes,highlighting their functions,signaling pathways,and candidate drugs for the treatment of GC *** used publicly available next generation sequencing(NGS)data to identify differentially expressed(DE)*** top DE genes were mapped to STRING database to construct the protein-protein interaction(PPI)network and top hub genes were selected for further *** found a total of 1555 DE genes with 870 upregulated and 685 downregulated genes in *** selected the top 400(200 upregulated and 200 downregulated)genes to construct a PPI network and extracted the top 15 hub *** gene ontology(GO)term and kyoto encyclopedia of genes and genomes(KEGG)pathway enrichment analyses of the 15 hub genes exposed some important functions and signaling pathways that were significantly associated with GC *** survival analysis of the hub genes disclosed that the lower expressions of the three hub genes CDH2,COL4A1,and COL5A2 were associated with better survival of GC *** three genes might be the candidate biomarkers for the diagnosis and treatment of ***,we considered 3 key proteins(genomic biomarkers)(COL4A1,CDH2,and CO5A2)as the drug target proteins(receptors),performed their docking analysis with the 102 meta-drug agents,and found Everolimus,Docetaxel,Lanreotide,Venetoclax,Temsirolimus,and Nilotinib as the top ranked 6 candidate drugs with respect to our proposed target proteins for the treatment against GC ***,the proposed drugs might play vital role for the treatment against GC patients.

关键词： gastric cancer hub genes candidate genes molecular docking candidate drugs

来源：评论

学校读者我要写书评

暂无评论

Theoretically guaranteed bidirectional data rectification for robust sequential recommendation 23

Theoretically guaranteed bidirectional data rectification fo...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yatong Sun Xiaochun Yang Zhu Sun Bin Wang Yan Wang School of Computer Science and Engineering Northeastern University China and School of Computing Macquarie University Australia School of Computer Science and Engineering Northeastern University China Center for Frontier AI Research Institute of High Performance Computing A*STAR Singapore School of Computing Macquarie University Australia

Sequential recommender systems (SRSs) are typically trained to predict the next item as the target given its preceding (and succeeding) items as the input. Such a paradigm assumes that every input-target pair is reliable for training. However, users can be induced to click on items that are inconsistent with their true preferences, resulting in unreliable instances, i.e., mismatched input-target pairs. Current studies on mitigating this issue suffer from two limitations: (i) they discriminate instance reliability according to models trained with unreliable data, yet without theoretical guarantees that such a seemingly contradictory solution can be effective; and (ii) most methods can only tackle either unreliable input or targets but fail to handle both simultaneously. To fill the gap, we theoretically unveil the relationship between SRS predictions and instance reliability, whereby two error-bounded strategies are proposed to rectify unreliable targets and input, respectively. On this basis, we devise a model-agnostic Bidirectional Data Rectification (BirDRec) framework, which can be flexibly implemented with most existing SRSs for robust training against unreliable data. Additionally, a rectification sampling strategy is devised and a self-ensemble mechanism is adopted to reduce the (time and space) complexity of BirDRec. Extensive experiments on four real-world datasets verify the generality, effectiveness, and efficiency of our proposed BirDRec.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Numerical simulations of attachment-line boundary layer in hypersonic flow, Part II: the features of three-dimensional turbulent boundary layer

arXiv

引用

arXiv 2024年

作者： Xi, Youcheng Yan, Bowen Yang, Guangwen Song, Fu School of Aerospace Engineering Tsinghua University Beijing100084 China Institute of High Performance Computing Department of Computer Science and Technology Tsinghua University Beijing100084 China

In this study, we investigate the characteristics of three-dimensional turbulent boundary layers influenced by transverse flow and pressure gradients. Our findings reveal that even without assuming an infinite sweep, a fully developed turbulent boundary layer over the present swept blunt body maintains spanwise homogeneity, consistent with infinite sweep assumptions. We critically examine the law-of-the and temperature-velocity relationships, typically applied two-dimensional turbulent boundary layers, in three-dimensional contexts. Results show that with transverse velocity and pressure gradient, streamwise velocity adheres to classical velocity transformation relationships and the predictive accuracy of classical temperature-velocity relationships diminishes because of pressure gradient. We show that near-wall streak structures persist and correspond with energetic structures in the outer region, though three-dimensional effects redistribute energy to align more with the external flow direction. Analysis of shear Reynolds stress and mean flow shear directions reveals in near-wall regions with low transverse flow velocity, but significant deviations at higher transverse velocities. Introduction of transverse pressure gradients together with the transverse velocities alter the velocity profile and mean flow shear directions, with shear Reynolds stress experiencing similar changes but with a lag increasing with transverse. Consistent directional alignment in outer regions suggests a partitioned relationship between shear Reynolds stress and mean flow shear: nonlinear in the inner region and approximately linear in the outer region. © 2024, CC BY.

关键词： Pressure gradient

来源：评论

学校读者我要写书评

暂无评论

SOCA-DOM:A Mobile System-on-Chip Array System for Analyzing Big Data on the Move

引用

Journal of computer science & Technology 2022年第6期37卷 1271-1289页

作者： Le-Le Li Jiang-Yi Liu Jian-Ping Fan Xue-Hai Qian Kai Hwang Yeh-Ching Chung Zhi-Bin Yu Center for Heterogeneous and Intelligent Computing Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen 518055China School of Science and Engineering The Chinese University of Hong KongShenzhenShenzhen 518172China Center for High Performance Computing Shenzhen Institutes of Advanced TechnologyChinese Academy of Sciences Shenzhen 518055China Ming Hsieh Department of Electrical and Computer Engineering University of Southern CaliforniaLos Angeles CA 90089-0001U.S.A. Department of Computer Science University of Southern CaliforniaLos AngelesCA 90089-0001U.S.A. School of Data and Science The Chinese University of Hong KongShenzhenShenzhen 518172China

Recently,analyzing big data on the move is *** requires that the hardware resource should be low volume,low power,light in weight,high-performance,and highly scalable whereas the management software should be flexible and consume little hardware *** meet these requirements,we present a system named SOCA-DOM that encompasses a mobile system-on-chip array architecture and a two-tier“software-defined”resource manager named ***,we design an Ethernet communication board to support an array of mobile ***,we propose a two-tier software architecture for Chameleon to make it ***,we devise data,configuration,and control planes for Chameleon to make it“software-defined”and in turn consume hardware resources on ***,we design an accurate synthetic metric that represents the computational power of a computing *** employ 12 Apache Spark benchmarks to evaluate ***,SOCA-DOM consumes up to 9.4x less CPU resources and 13.5x less memory than Mesos which is an existing resource *** addition,we show that a 16-node SOCA-DOM consumes up to 4x less energy than two standard Xeon *** on the results,we conclude that an array architecture with fine-grained hardware resources and a software-defined resource manager works well for analyzing big data on the move.

关键词： edge computing mobile architecture resource management big data analytics software-defined systems

来源：评论

学校读者我要写书评

暂无评论

Effective Deep Learning Data Augmentation Techniques for Diabetic Retinopathy Classification

Effective Deep Learning Data Augmentation Techniques for Dia...

引用

2022 International Conference on Machine Learning and Data engineering, ICMLDE 2022

作者： Patil, Mahesh S Chickerur, Satyadhyan Abhimalya, C. Naik, Anishma Kumari, Nidhi Maurya, Shashank School of Computer Science and Engineering K L e Technological University Karnataka Hubballi580031 India Center for High Performance Computing K L e Technological University Karnataka Hubballi580031 India

Diabetic retinopathy(DR) is an eye disorder that affects 80-85% of diabetic patients, and there is a need to detect it in earlier stages to take precautions. Currently, testing for DR is a time-consuming task and requires qualified human resources. Automating DR detection is time-saving and cost-effective, benefiting both doctors and patients. The proposed work automates the DR image detection using deep learning(DL) by using transfer learning. The proposed work provides better results with multi-class classification and generalization than the previous works. i.e a ResNet-50 DL model is trained with the APTOS dataset and tested using the EyePACS dataset. The low accuracy in multi-class classification and data imbalance problems are overcome by using appropriate image pre-processing and augmentation techniques, which have been found by conducting several experiments. Further, the performance of the DL model is enhanced using Test Time Augmentation(TTA). Finally, the authors are able to achieve a multi-class accuracy of 97.87% and Quadratic weighted kappa(QWK) score of 0.985. © 2023 The Authors. Published by Elsevier B.V.

关键词： Classification (of information)

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：