检索结果-内蒙古大学图书馆

Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lin, Shaohui Huang, Wenxuan Xie, Jiao Zhang, Baochang Shen, Yunhang Yu, Zhou Han, Jungong Doermann, David The School of Computer Science and Technology East China Normal University Shanghai China The Key Laboratory of Advanced Theory and Application in Statistics and Data Science Ministry of Education China The Department of Automation School of Aerospace Engineering Xiamen University Xiamen China The Institute of Artificial Intelligence Beihang University Beijing China Zhongguancun Laboratory Beijing China The Youtu Lab Tencent Shanghai China The School of Statistics East China Normal University Shanghai China The Department of Computer Science University of Sheffield United Kingdom The University at Buffalo BuffaloNY United States

Filter pruning simultaneously accelerates the computation and reduces the memory overhead of CNNs, which can be effectively applied to edge devices and cloud services. In this paper, we propose a novel Knowledge-driven Differential Filter Sampler (KDFS) with Masked Filter Modeling (MFM) framework for filter pruning, which globally prunes the redundant filters based on the prior knowledge of a pre-trained model in a differential and non-alternative optimization. Specifically, we design a differential sampler with learnable sampling parameters to build a binary mask vector for each layer, determining whether the corresponding filters are redundant. To learn the mask, we introduce masked filter modeling to construct PCA-like knowledge by aligning the intermediate features from the pre-trained teacher model and the outputs of the student decoder taking sampling features as the input. The mask and sampler are directly optimized by the Gumbel-Softmax Straight-Through Gradient Estimator in an end-to-end manner in combination with global pruning constraint, MFM reconstruction error, and dark knowledge. Extensive experiments demonstrate the proposed KDFS’s effectiveness in compressing the base models on various datasets. For instance, the pruned ResNet-50 on ImageNet achieves 55.36% computation reduction, and 42.86% parameter reduction, while only dropping 0.35% Top-1 accuracy, significantly outperforming the state-of-the-art methods. The code is available at https://***/Osilly/KDFS. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Compact stereo waveguide display using a polarization-multiplexed Incoupling Metagrating

学校读者我要写书评

暂无评论

Compact stereo waveguide display using a polarization-multip...

International Conference on Display Technology, ICDT 2021

作者： Liu, Zeyang Zhang, Cheng Huang, Zhanhua Guo, Lingjie Jay Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States Key Laboratory of Optoelectronics Information Technology Ministry of Education Tianjin University Tianjin300072 China School of Optical and Electronic Information and Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan430074 China

Three-dimensional (3D) vision in augmented reality (AR) displays can enable highly immersive and realistic viewer experience, hence attracts much attention. Most current approaches create 3D visions by projecting stereoscopic images to different eyes using two separate projection systems, which are inevitably bulky for wearable devices. Here, we propose a compact stereo waveguide AR display system using a single piece of thin flat glass integrated with a polarization-multiplexed metagrating in-coupler and two diffractive grating out-couplers. Incident light of opposite circular polarization states carrying stereoscopic images are first steered by the metagrating to opposite propagation directions in the flat glass waveguide, subsequently extracted by the diffractive gratings and finally received by different eyes, forming 3D stereo vision. Experimentally we fabricated a display prototype and demonstrated independent projection of two polarizationmultiplexed stereoscopic images. This work paves a novel path towards the implementation of high-performance stereo displays with compact size, light weight, and multi-color compatibility. © 2021, John Wiley and Sons Inc. All rights reserved.

关键词： Augmented reality

Enabling End-to-End Secure Federated Learning in Biomedical Research on Heterogeneous Computing Environments with APPFLx

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hoang, Trung-Hieu Fuhrman, Jordan Madduri, Ravi Li, Miao Chaturvedi, Pranshu Li, Zilinghan Kim, Kibaek Ryu, Minseok Chard, Ryan Huerta, E.A. Giger, Maryellen Department of Electrical and Computer Engineering Coordinated Science Laboratory University of Illinois at Urbana-Champaign Street UrbanaIL61801 United States University of Chicago ChicagoIL United States Data Science and Learning Division Argonne National Laboratory LemontIL United States Department of Computer Science University of Illinois at Urbana-Champaign Street UrbanaIL61801 United States School of Industrial and Systems Engineering Georgia Institute of Technology AtlantaGA United States School of Computing Augmented Intelligence Arizona State University TempeAZ United States

Facilitating large-scale, cross-institutional collaboration in biomedical machine learning projects requires a trustworthy and resilient federated learning (FL) environment to ensure that sensitive information such as protected health information is kept confidential. In this work, we introduce APPFLx, a low-code FL framework that enables the easy setup, configuration, and running of FL experiments across organizational and administrative boundaries while providing secure end-to-end communication, privacy-preserving functionality, and identity management. APPFLx is completely agnostic to the underlying computational infrastructure of participating clients. We demonstrate the capability of APPFLx as an easy-to-use framework for accelerating biomedical studies across institutions and healthcare systems while maintaining the protection of private medical data in two case studies: (1) predicting participant age from electrocardiogram (ECG) waveforms, and (2) detecting COVID-19 disease from chest radiographs. These experiments were performed securely across heterogeneous compute resources, including a mixture of on-premise high-performance computing and cloud computing, and highlight the role of federated learning in improving model generalizability and performance when aggregating data from multiple healthcare systems. Finally, we demonstrate that APPFLx serves as a convenient and easy-to-use framework for accelerating biomedical studies across institutions and healthcare system while maintaining the protection of private medical data. Copyright © 2023, The Authors. All rights reserved.

关键词： Privacy-preserving techniques

Gravitational wave cosmology in Einstein-scalar-Gauss-Bonnet gravity

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Fier, Jared Han, Henry Li, Bowen Lin, Kai Mukohyama, Shinji Wang, Anzhong GCAP-CASPER Department of Physics Baylor University One Bear Place #97316 WacoTX76798-7316 United States The Laboratory of Data Science and Artificial Intelligence Innovation Department of Computer Science School of Engineering and Computer Science Baylor University WacoTX76798 United States Universidade Federal de Campina Grande PB Campina Grande58429-900 Brazil Center for Gravitational Physics and Quantum Information Yukawa Institute for Theoretical Physics Kyoto University Kyoto606-8502 Japan The University of Tokyo Institutes for Advanced Study The University of Tokyo Chiba Kashiwa277-8583 Japan

In the framework of Einstein-scalar-Gauss-Bonnet (EsGB) gravity, we systematically study gravitational waves (GWs), first produced by remote compact astrophysical sources and then propagating through the flat homogeneous and isotropic Universe at cosmic distances before arriving at detectors. Assuming that the speed cT of the spin-2 graviton is the same as that of photons, we find explicitly the stability conditions of the theory and then obtain the severest observational constraint found so far. In particular, all these conditions and constraints are satisfied, provided that 0 ≤ αḟ(φ0) . 8.97 × 10−24 (km), where αf(φ) denotes the coupling strength between the scalar field φ and the Gauss-Bonnet term, an over-dot represents the derivative with respect to the cosmic time, and φ0 is the present value of φ. The trajectories for both spin-2 and spin-0 gravitons and the amplitudes of GWs along the trajectories are explicitly obtained. The amplitude of a spin-2 GW is practically indistinguishable from that of GR, while the spin-0 GWs remain almost constant during radiation- and matter-dominated epochs, and in the dark energy-dominated epoch it is proportional to the physical distance between the source and the observer. A careful analysis shows that the latter is due to the assumption cT = 1. When cT 6= 1 to the extent that is consistent with the stability conditions and observational constraints, the above behavior disappears. © 2025, CC BY.

关键词： Statistical mechanics

A Novel In-situ Method for Measuring Soil Organic Carbon Using Photoacoustic Sensor

学校读者我要写书评

暂无评论

A Novel In-situ Method for Measuring Soil Organic Carbon Usi...

IEEE SENSORS

作者： Md Faishal Yousuf MD Shaad Mahmud Baikun Li Yu Lei Haiying Tao Department of Electrical and Computer Engineering University of New Hampshire Durham NH USA Department of Civil and Environmental Engineering University of Connecticut Storrs CT USA Department of Chemical and Biomolecular Engineering University of Connecticut Storrs CT USA Department of Plant Science and Landscape Architecture University of Connecticut Storrs CT USA

ISBN: (数字)9781665484640

ISBN: (纸本)9781665484657

Organic and inorganic elements of soil exhibit a wide range of physical and chemical characteristics. Exact soil composition estimates are required for many ecological and soil science studies and global climate change research. The most typical method for estimating soil variables involves collecting and analyzing data in a laboratory, which is time-consuming and expensive. This paper proposes a rapid, in-situ approach for assessing soil organic carbon utilizing the soil combustion method. In the suggested approach, a metal tube with a heating probe heats the soil to approximately 400°C. The heat oxidizes a known-volume soil sample, creating CO 2 • To estimate soil organic carbon, a CO 2 sensor measures the accumulated CO 2 concentration at the tube's top. A laboratory experiment was undertaken to demonstrate the proposed method's potential.

关键词： Heating systems Soil measurements Moisture Metals Soil Combustion Sensors

The Effects of Boron Doping on the Bulk and Surface Acoustic Phonons in Single-Crystal Diamond

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Guzman, Erick Kargar, Fariborz Angeles, Frank Meidanshahi, Reza Vatan Grotjohn, Timothy A. Hardy, Aaron Muehle, Matthias Wilson, Richard B. Goodnik, Stephen Balandin, Alexander A. Nano-Device Laboratory Phonon Optimized Engineered Materials Center Department of Electrical and Computer Engineering University of California RiversideCA92521 United States Department of Mechanical Engineering Materials Science and Engineering Program University of California RiversideCA92521 United States School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85281 United States Department of Electrical and Computer Engineering Michigan State University East LansingMI48824 United States Fraunhofer USA Center Midwest East LansingMI48824 United States

We report the results of the investigation of bulk and surface acoustic phonons in the undoped and boron-doped single-crystal diamond films using the Brillouin-Mandelstam light scattering spectroscopy. The evolution of the optical phonons in the same set of samples was monitored with Raman spectroscopy. It was found that the frequency and the group velocity of acoustic phonons decrease non-monotonically with the increasing boron doping concentration, revealing pronounced phonon softening. The change in the velocity of the shear horizontal and the high-frequency pseudo-longitudinal acoustic phonons in the degenerately doped diamond, as compared to the undoped diamond, was as large as ~ 15% and ~12%, respectively. As a result of boron doping, the velocity of the bulk longitudinal and transverse acoustic phonons decreased correspondingly. The frequency of the optical phonons was unaffected at low boron concentration but experienced a strong decrease at the high doping level. The density-functional-theory calculations of the phonon band structure for the pristine and highly-doped sample confirm the phonon softening as a result of boron doping in diamond. The obtained results have important implications for thermal transport in heavily doped diamond, which is a promising material for ultra-wide-band-gap electronics. Copyright © 2022, The Authors. All rights reserved.

关键词： Density functional theory

A Direction Vector-Guided Multi-Objective Evolutionary Algorithm for Variable Linkages Problems

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Gu, Qinghua Zhang, Shaopeng Wang, Qian Xiong, Neal N. School of Resources Engineering Xi’an University of Architecture and Technology Shaanxi Xi’an710055 China Xi’an Key Laboratory for Intelligent Industrial Perception Calculation and Decision Xi'an University of Architecture and Technology Shaanxi Xi’an710055 China Department of Mathematics and Computer Science Northeastern State University TahlequahOK United States School of Management Xi’an University of Architecture and Technology Shaanxi Xi’an710055 China

Recombination is a key component for the evolutionary algorithm to provide promising offspring solutions. However, conventional recombination operators cannot generate high-quality solutions for variable linkages problems due to the particularity of Pareto sets(PS). To tackle this problem, a two-stage multi-objective evolutionary algorithm based on direction vector guidance(DSMOEA) is proposed in this paper. Firstly, a portion of the population is transformed by a covariance matrix to increase the probability of generating high-quality offspring. Then the representative solutions are selected in the transformed population to create the direction vectors. Under the guidance of the direction vectors, the population rapidly approaches PS and generates promising offspring solutions. Finally, DE is performed for searching globally to increase the diversity of the population. The proposed algorithm is tested on RM, IM, and UF test problems with 30, 50, and 100 dimensions to verify its performance. The experimental results show that the algorithm is promising for variable linkages problems. © 2023, The Authors. All rights reserved.

关键词： Covariance matrix

2D/2D heterostructure Ni-Fe LDH/black phosphorus nanosheets with AuNP for noxious substance diphenylamine detection in food samples

学校读者我要写书评

暂无评论

Food Chemistry 2024年 432卷 137295页

作者： Prasanna, Sanjay Ballur Lin, Yu-Chien Ramaraj, Sayee Kannan Dhawan, Udesh Liu, Xinke Tung, Ching-Wei Sakthivel, Rajalakshmi Chung, Ren-Jei Taipei10608 Taiwan PG& Research Department of Chemistry Thiagarajar College Tamilnadu Madurai 09 India Centre for the Cellular Microenvironment Division of Biomedical Engineering James Watt School of Engineering Mazumdar-Shaw Advanced Research Centre University of Glasgow GlasgowG116EW United Kingdom College of Materials Science and Engineering Chinese Engineering and Research Institute of Microelectronics Shenzhen University Shenzhen518060 China Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore117583 Singapore Department of Materials Engineering Ming Chi University of Technology New Taipei City Taiwan Taipei10608 Taiwan

In this study, gold nanoparticles decorated on nickel–iron layered double hydroxide with black phosphorus nanosheets (AuNP/Ni-Fe LDH/BPNSs) composite were prepared using a stirring method. Analyte tracing is required for developing viable sensors. The AuNP/Ni-Fe LDH/BPNSs composite exhibited a large specific surface area, high conductivity, high electrocatalytic activity, and rapid electron transfer. These properties play a vital role in monitoring diphenylamine (DPA) in food samples. The formation of the AuNP/Ni-Fe LDH/BPNSs composite was confirmed using various structural and morphological characterization techniques. The electroanalytical character of the AuNP/Ni-Fe LDH/BPNSs composite was evaluated using voltammetry. Interestingly, the AuNP/Ni-Fe LDH/BPNSs showed a wide linear range of 0.0125–1003.82 μM and a detection limit of 4.63 nM with a sensitivity of 0.399 µA µM−1 cm−2. The constructed sensor shows considerable selectivity, stability, repeatability, and reproducibility, and the practicability of DPA was monitored in the apples, sweet tomatoes, pears, and grapes with satisfactory recoveries. © 2023 Elsevier Ltd

关键词： Electrooxidation

Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fei, Ben Yang, Weidong Chen, Wen-Ming Li, Zhijun Li, Yikang Ma, Tao Hu, Xing Ma, Lipeng Shanghai Key Laboratory of Data Science The School of Computer Science Fudan University Shanghai200433 China The Academy for Engineering and Technology Fudan University Shanghai200433 China The Department of Automation University of Science and Technology of China Hefei230060 China Shanghai AI Laboratory Shanghai China School of Optical-electrical Information and Computer Engineering University of Shanghai for Science and Technology 516 JunGong Road Shanghai China

Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications of 3D computer vision. The progress of deep learning (DL) has impressively improved the capability and robustness of point cloud completion. However, the quality of completed point clouds is still needed to be further enhanced to meet the practical utilization. Therefore, this work aims to conduct a comprehensive survey on various methods, including point-based, view-based, convolution-based, graph-based, generative model-based, transformer-based approaches, etc. And this survey summarizes the comparisons among these methods to provoke further research insights. Besides, this review sums up the commonly used datasets and illustrates the applications of point cloud completion. Eventually, we also discussed possible research trends in this promptly expanding field. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning