检索结果-内蒙古大学图书馆

Scalable Federated Learning with System Heterogeneity

学校读者我要写书评

暂无评论

Scalable Federated Learning with System Heterogeneity

International Conference on Distributed Computing Systems

作者： Fatih Ilhan Gong Su Qingyang Wang Ling Liu School of Computer Science Georgia Institute of Technology Atlanta GA USA IBM T. J. Watson Reesarch Center Yorktown Heights NY USA Department of Computer Science and Engineering Louisiana State University Baton Rouge LA USA

Federated learning (FL) is a distributed learning framework that inherently provides data privacy and parallel computation capability over a set of participating devices (clients). In real-life applications, these clients can have a great variety in terms of resources (storage, RAM, CPU/GPU speed, network speed, etc.). However, most previous FL studies do not consider this scenario with system heterogeneity and assume that all clients can operate on the same full-size deep neural network (DNN) model. In this work, we demonstrate a scalable FL approach, ScaleFL, which tackles system heterogeneity through hierarchically downscaling the DNN model for clients with limited resources. ScaleFL utilizes early exits to form multi-exit DNN models by injecting early exit networks into the given DNN. During FL, the model is adaptively split along depth (exits) and width (hidden dimensions) based on the resource budget of each participating client. A proof-of-concept demonstration is provided with interactive features, demonstrating the system flow on image classification and NLP benchmark workloads.

关键词：

Design of an adaptive fuzzy-neural inference system-based control approach for robotic manipulators

学校读者我要写书评

暂无评论

Applied Soft Computing 2023年第PartA期149卷

作者： Barhaghtalab, Mojtaba Hadi Sepestanaki, Mohammadreza Askari Mobayen, Saleh Jalilvand, Abolfazl Fekih, Afef Meigoli, Vahid Department of Electrical Engineering Faculty of Engineering University of Zanjan Zanjan Iran Graduate School of Intelligent Data Science National Yunlin University of Science and Technology 123 University Road Section 3 Douliou Yunlin640301 Taiwan Department of Electrical and Computer Engineering University of Louisiana at Lafayette LafayetteLA70504 United States Department of Electrical Engineering Faculty of Engineering Persian Gulf University Bushehr Iran

This paper proposes an adaptive fuzzy-neural inference system (ANFIS)-based control approach for a six degrees of freedom (6-DoF) robotic manipulator. Its main objective is to guarantee the error convergence of the controlled system in the presence of uncertainties and unknown disturbances. The suggested controller is a parallel combination of an ANFIS network with a proportional-integral-derivative (PID) controller. The ANFIS system is used as an estimator to approximate a part of the system and then applied as the feedback linearization in the suggested control structure. The convergence of system errors to zero was proven using Barbalat's lemma. The suggested control law combines the simplicity and ease of implementation of PID control with the estimation properties of ANFIS networks. The suggested approach was evaluated using a simulation study and further validated experimentally using the 6-DoF IRB-120 robotic manipulator (IRB-120-RM). The obtained results confirmed its superior performance and suitability for practical implementation to industrial actuators. © 2023 Elsevier B.V.

关键词： Feedback linearization

Self-Supervised Multimodal Fusion Network for Knee Osteoarthritis Severity Grading

学校读者我要写书评

暂无评论

Self-Supervised Multimodal Fusion Network for Knee Osteoarth...

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Wenhua Wu Kun Hu Wenxi Yue Wei Li Milena Simic Changyang Li Wei Xiang Zhiyong Wang School of Computer Science The University of Sydney Camperdown NSW Australia Faculty of Medicine and Health The University of Sydney Camperdown NSW Australia Sydney Polytechnic Institute Pty Ltd Sydney NSW Australia School of Computing Engineering & Mathematical Sciences La Trobe University

Knee osteoarthritis (OA) is a highly prevalent form of arthritis and a leading cause of physical disability, given the growing aging population. To assist the knee OA assessment, there is a demanding interest in computer-aided grading algorithms. Existing grading methods generally require resource-intensive annotated datasets for supervised training. Moreover, they only consider unimodal data, whilst multimodal medical images are rarely utilised to formulate better knee OA patterns. Therefore, in this study, a novel Self-supervised Multimodal Fusion Network (S-MFN) is proposed for multimodal unsupervised knee OA grading with X-ray and magnetic resonance imaging (MRI) modalities. Specifically, S-MFN involves two modality-specific streams to obtain knee OA representations from the two corresponding modalities. A modality-aware information exchange mechanism is devised to interactively formulate cross-modal patterns in a multi-scale manner regarding the scales of feature maps. To this end, a multimodal contrastive learning is introduced in a self-supervised manner through modality-specific and cross-modal modelling. Comprehensive experimental results on the widely used dataset, Osteoarthritis Initiative (OAI), demonstrate the effectiveness of the proposed method.

关键词：

RoseMatcher: Identifying the Impact of User Reviews on App Updates

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Tianyang Wang, Chong Huang, Kun Liang, Peng Zhang, Beiqi Daneva, Maya van Sinderen, Marten School of Computer Science Wuhan University Hubei Wuhan430072 China Department of Computer Science and Engineering University of California La Jolla San DiegoCA92093 United States Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede7500 AE Netherlands

Context: The release planning of mobile apps has become an area of active research, with most studies centering on app analysis through release notes in the Apple App Store and tracking user reviews via issue trackers. However, the correlation between these release notes and user reviews in App Store remains understudied. Objective: In this paper, we introduce RoseMatcher, a novel automatic approach to match relevant user reviews with app release notes and identify matched pairs with high confidence. Methods: We collected 944 release notes and 1,046,862 user reviews from 5 mobile apps in the Apple App Store as research data to evaluate the effectiveness and accuracy of RoseMatcher, and conducted deep content analysis on matched pairs. Results: Our evaluation shows that RoseMatcher can reach a hit ratio of 0.718 for identifying relevant matched pairs, and with the manual labeling and content analysis of 984 relevant pairs, we identify 8 roles that user reviews play in app updates according to the relationship between release notes and user reviews in the relevant matched pairs. Conclusions: Our findings indicate that both app development teams and users pay close attention to release notes and user reviews, with release notes typically addressing feature requests, bug reports, and complaints, and user reviews offering positive, negative, and constructive feedback. Overall, the study highlights the importance of the communication between app development teams and users in the release planning of mobile apps, with relevant reviews tending to be posed within a short period before and after the release of release notes, with the average time interval between the post time of release notes and user reviews being approximately one year. Copyright © 2022, The Authors. All rights reserved.

关键词： Fruits

Towards 6G MIMO: Massive Spatial Multiplexing, Dense Arrays, and Interplay Between Electromagnetics and Processing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Björnson, Emil Chae, Chan-Byoung Heath, Robert W. Marzetta, Thomas L. Mezghani, Amine Sanguinetti, Luca Rusek, Fredrik Castellanos, Miguel R. Jun, Dongsoo Demir, Özlem Tuğfe The School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden The School of Integrated Technology Yonsei University Seoul03722 Korea Republic of The Department of Electrical and Computer Engineering University of California San Diego La Jolla CA92161 United States The Department of Electrical and Computer Engineering New York University BrooklynNY11201 United States The Department of Electrical and Computer Engineering University of Manitoba WinnipegMBR3T 5V6 Canada The Dipartimento di Ingegneria dell’Informazione University of Pisa Pisa Italy Sony Europe B.V. Lund Sweden The Department of Electrical and Computer Engineering North Carolina State University RaleighNC27695 United States The TOBB University of Economics and Technology Ankara Turkey

The increasing demand for wireless data transfer has been the driving force behind the widespread adoption of Massive MIMO (multiple-input multiple-output) technology in 5G. The next-generation MIMO technology is now being developed to cater to the new data traffic and performance expectations generated by new user devices and services in the next decade. The evolution towards "ultra-massive MIMO (UM-MIMO)" is not only about adding more antennas but will also uncover new propagation and hardware phenomena that can only be treated by jointly utilizing insights from the communication, electromagnetic (EM), and circuit theory areas. This article offers a comprehensive overview of the key benefits of the UM-MIMO technology and the associated challenges. It explores massive multiplexing facilitated by radiative near-field effects, characterizes the spatial degrees-of-freedom, and practical channel estimation schemes tailored for massive arrays. Moreover, we provide a tutorial on EM theory and circuit theory, and how it is used to obtain physically consistent antenna and channel models. Subsequently, the article describes different ways to implement massive and dense antenna arrays, and how to codesign antennas with signal processing. The main open research challenges are identified at the end. Copyright © 2024, The Authors. All rights reserved.

关键词： Degrees of freedom (mechanics)

TRANSCENDENCE AND NORMALITY OF COMPLEX NUMBERS VIA HURWITZ CONTINUED FRACTIONS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： García-Ramos, Felipe Robert, Gerardo González Hussain, Mumtaz Physics Institute Universidad Autónoma de San luis Potosí Mexico Faculty of Mathematics and Computer Science Uniwersytet Jagielloński Poland Department of Mathematical and Physical Sciences La Trobe University Bendigo3552 Australia

We study the topological, dynamical, and descriptive set-theoretic properties of Hurwitz continued fractions. Hurwitz continued fractions associate an infinite sequence of Gaussian integers to every complex number which is not a Gaussian rational. The resulting space of sequences of Gaussian integers Ω is not closed. Using an iterative procedure, we show that Ω contains a natural subset whose closure R encodes continued fraction expansions of complex numbers which are not Gaussian rationals. We prove that (R, σ) is a subshift with a feeble specification property. As an application, we determine the rank in the Borel hierarchy of the set of Hurwitz normal numbers with respect to the complex Gauss measure. We also construct a family of complex transcendental numbers with bounded partial *** Codes 11J70 (Primary) 03E15, 11J81 (Secondary) © 2023, CC BY.

关键词： Topology

Electro-Polymerization Process with Double-Sided Electrodes for Supercapacitors

学校读者我要写书评

暂无评论

Electro-Polymerization Process with Double-Sided Electrodes ...

International Flexible Electronics Technology Conference (IFETC)

作者： Nandu Koripally Lulu Yao Naresh Eedugurala Jason D. Azoulay Tse Nga Ng Department of Electrical and Computer Engineering University of California San Diego La Jolla CA USA Materials Science Engineering Program University of California San Diego La Jolla CA USA Chemisty Department Georgia Institute of Technology Atlanta GA USA

Supercapacitors are known for longer cycle life and faster charging rate compared to batteries. However, the energy density of supercapacitors requires improvement to expand their application space. To raise the energy density of redox supercapacitors, this work demonstrates electro-polymerization on both sides of electrodes to increase material loading, reduce overall device mass, and consequently increase the capacitance, power, and energy density of supercapacitors. We achieved an energy density of 1823 mWh kg -1 and a power density of 16.5 W kg -1 with a wide potential window of 3 V.

关键词：

Deep learning assisted high resolution microscopy image processing for phase segmentation in functional composite materials

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Raghavendran, Ganesh Han, Bing Adekogbe, Fortune Bai, Shuang Lu, Bingyu Wu, William Zhang, Minghao Meng, Ying Shirley Department of NanoEngineering University of California San Diego La Jolla CA92093 United States Pritzker School of Molecular Engineering University of Chicago ChicagoIL60637 United States Department of Chemical and Petroleum Engineering University of Lagos Lagos101017 Nigeria Department of Computer Science University of California San Diego La Jolla CA92093 United States

In the domain of battery research, the processing of high-resolution microscopy images is a challenging task, as it involves dealing with complex images and requires a prior understanding of the components involved. The utilization of deep learning methodologies for image analysis has attracted considerable interest in recent years, with multiple investigations employing such techniques for image segmentation and analysis within the realm of battery research. However, the automated analysis of high-resolution microscopy images for detecting phases and components in composite materials is still an underexplored area. This work proposes a novel workflow for FFT-based segmentation, periodic component detection and phase segmentation from raw high resolution Transmission Electron Microscopy (TEM) images using a trained U-Net segmentation model. The developed model can expedite the detection of components and their phase segmentation, diminishing the temporal and cognitive demands associated with scrutinizing an extensive array of TEM images, thereby mitigating the potential for human errors. This approach presents a novel and efficient image analysis approach with broad applicability beyond the battery field and holds potential for application in other related domains characterized by phase and composition distribution, such as alloy production. © 2024, CC BY.

关键词： Image segmentation

Physics-Based ML and Polarimetric SAR for Soil Moisture Retrieval

学校读者我要写书评

暂无评论

Physics-Based ML and Polarimetric SAR for Soil Moisture Retr...

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Lorenzo G. Papale Fabio Del Frate Leila Guerriero Giovanni Schiavon Jean Bouchat Department of Civil Engineering and Computer Science Engineering (DICII) Tor Vergata University of Rome Rome Italy Earth and Life Institute Universitè Catholique de Louvain Louvain-la-Nueve Belgium

Soil moisture represents a significant guiding factor for agricultural activities, especially for smart irrigation and crop yield estimation. In this context, SAR data is one of the most valuable sources of information for accurate and continuative estimation of soil moisture in agricultural areas. However, SAR-derived soil moisture retrievals are affected by several factors, including the vegetation cover, which is responsible for additional signal attenuation and scattering mechanisms. Concerning the algorithms for soil moisture estimation, Machine Learning (ML) has proved to be a valuable instrument for finding relations between SAR data and the soil dielectric properties. For this purpose, this study aims to synergically adopt electromagnetic data modelling and a ML algorithm to estimate the scattering contributions associated with the ground and demonstrate that they are more sensitive to soil moisture than the total received signal. To apply such approach to real SAR data, airborne acquisitions at L-band will be considered.

关键词：