Related references
Note: Only part of the references are listed.
Article
Computer Science, Information Systems
S. Raghavendra et al.
Summary: This paper presents a method applied to networks of primary convolutional neurons to locate the area connected to the Person attribute. By using Individual Feature Identification, the features of a person, such as gender, age, fashion sense, and equipment, are focused on in video surveillance analytics. The extensive experimental results demonstrate that the proposed hybrid technique outperforms current strategies on four unique private characteristic datasets.
Article
Computer Science, Theory & Methods
Yuhao Zhou et al.
Summary: In this article, the authors propose an innovative framework for federated learning called Overlap-FedAvg, which reduces communication overhead by parallelizing model training and model communication phases. Extensive experiments demonstrate that the proposed framework substantially reduces communication overhead and achieves good performance on multiple tasks and datasets.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2022)
Review
Computer Science, Artificial Intelligence
Rodolfo Stoffel Antunes et al.
Summary: The use of machine learning with electronic health records is gaining popularity for improving healthcare decision-making. Federated learning is a promising solution to protect data privacy and improve trustworthiness. However, there are still many challenges to be addressed before widespread adoption.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2022)
Article
Computer Science, Hardware & Architecture
Bipin Gaikwad et al.
Summary: This study presents a real-time end-to-end person re-identification system developed for a realistic unconstrained open-world environment. The system analyzes raw surveillance videos to provide a ranked list of person images matched with the user's query. Two frameworks based on distributed-computing and edge-based computing, utilizing NVIDIA Jetson Nano and TX2 respectively, have been developed to achieve the objective. The study addresses various practical aspects of deploying an end-to-end Re-ID system over an edge-cloud environment and proposes an improvised omni-scale network for handling complex variations in person appearance.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Mang Ye et al.
Summary: Person re-identification (Re-ID) has gained significant interest in the computer vision community, with the advancement of deep neural networks. It is categorized into closed-world and open-world settings. While closed-world setting has achieved inspiring success, the research focus has shifted to the more challenging open-world setting. We summarize the open-world Re-ID in five different aspects and introduce a new evaluation metric. This metric provides an additional criteria for evaluating Re-ID systems in real applications.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Construction & Building Technology
Swarna Priya Ramu et al.
Summary: Recent advances in AI and IoT have contributed to the improvement of smart city applications. However, the adoption of Digital Twin (DT) in smart city applications is still at an early stage due to trust and privacy concerns. Federated Learning (FL) can be integrated with DT to address these issues. This paper focuses on the integration of FL and DT and its application in real-time and life-critical scenarios in smart city contexts.
SUSTAINABLE CITIES AND SOCIETY
(2022)
Article
Energy & Fuels
Muhammad Mansoor Ashraf et al.
Summary: This research addresses the challenge of energy theft detection and data privacy protection in smart grids. A novel federated learning framework, FedDP, is proposed to enable on-device prediction and learning from other clients' experiences with the help of a central server. Additionally, a federated voting classifier is introduced for accurate identification of energy theft.
Article
Computer Science, Artificial Intelligence
Castro Elizondo Jose Ezequiel et al.
Summary: Human mobility modeling is vital for studying spatiotemporal events, and this work explores the use of Federated Learning (FL) to create spatiotemporal models. The study compared different centralized models for next-place prediction, with Flashback and GRU models showing the best performance. However, the training process of federated models was less stable, leading to slower convergence and poorer performance compared to centralized models. Model performance was also influenced by the number of federated clients and data sparsity.
FRONTIERS IN ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Pengyu Xie et al.
Summary: Video person re-identification methods have gained attention due to their ability to extract richer features from video tracklets. However, existing supervised methods require a large number of cross-camera identity labels which is impractical for large-scale datasets. In this study, we propose a Sampling and Re-weighting for Clustering (SRC) method to obtain robust and discriminative person feature representations. The method considers the influence of detection errors and varying frame difficulty levels, and uses a dynamic noise trimming module and diverse frame re-weighting module to enhance the accuracy and learning of the tracklets.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Engineering, Electrical & Electronic
Krishna Pillutla et al.
Summary: A novel federated learning approach, RFA, is proposed with robustness to local data poisoning and high corruption levels. The algorithm aggregates updates using geometric median and maintains individual device privacy. Variants of RFA are also presented for improved speed or on-device personalization, showing competitive performance with classical aggregation under low corruption and greater robustness under high corruption.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Bipin Gaikwad et al.
Summary: This work presents an end-to-end multi-person multi-camera tracking (MPMCT) surveillance system with privacy-aware and scalable processing pipeline on an edge platform for real-time performance. Through training and evaluating the system on a realistic dataset, real-time MPMCT system has been implemented on NVIDIA Jetson TX2 platform.
JOURNAL OF REAL-TIME IMAGE PROCESSING
(2021)
Article
Multidisciplinary Sciences
Mingzhe Chen et al.
Summary: Federated Learning allows edge devices to collaboratively train ML models without sharing private data, but communication delays are a major bottleneck. A communication-efficient framework is proposed, incorporating device selection and parameter quantization to improve convergence speed and training accuracy.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2021)
Article
Computer Science, Information Systems
Sawsan AbdulRahman et al.
Summary: Driven by privacy concerns and deep learning visions, a paradigm shift has occurred in the applicability mechanism of machine learning (ML) over the past four years. A new model called federated learning (FL) has emerged as a privacy-preserving decentralized approach that involves local ML training and eliminates data communication overhead. This article explores and compares various ML-based deployment architectures, with a focus on in-depth investigation of FL, providing a new classification of FL topics and research fields based on analysis of technical challenges and current work in the field.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Jie Xu et al.
Summary: With the increasing availability of healthcare data, the fragmented and private nature of these data poses challenges for generating robust results. Federated learning technology shows promise in protecting privacy and connecting disparate healthcare data sources. This survey reviews the applications and potential of federated learning in the biomedical space.
JOURNAL OF HEALTHCARE INFORMATICS RESEARCH
(2021)
Article
Computer Science, Information Systems
Jed Mills et al.
IEEE INTERNET OF THINGS JOURNAL
(2020)
Article
Computer Science, Artificial Intelligence
Felix Sattler et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2020)
Article
Chemistry, Analytical
Yanming Chen et al.
Article
Computer Science, Information Systems
Yunfan Ye et al.
Article
Computer Science, Information Systems
Xiaofei Wang et al.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2020)
Article
Computer Science, Information Systems
Mohammed Aledhari et al.
Article
Computer Science, Artificial Intelligence
Qiang Yang et al.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2019)
Article
Engineering, Electrical & Electronic
Zhi Zhou et al.
PROCEEDINGS OF THE IEEE
(2019)
Article
Engineering, Electrical & Electronic
Zhedong Zheng et al.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2019)
Article
Computer Science, Artificial Intelligence
Yutian Lin et al.
PATTERN RECOGNITION
(2019)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Zakaria Maamar et al.
SAC '19: PROCEEDINGS OF THE 34TH ACM/SIGAPP SYMPOSIUM ON APPLIED COMPUTING
(2019)
Article
Computer Science, Hardware & Architecture
He Li et al.
Article
Computer Science, Artificial Intelligence
Kejun Wang et al.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2018)
Article
Telecommunications
Zakaria Maamar et al.
INTERNET TECHNOLOGY LETTERS
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Wei Li et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Article
Chemistry, Analytical
Jin Kyu Kang et al.
Proceedings Paper
Computer Science, Artificial Intelligence
Patrick Sudowe et al.
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOP (ICCVW)
(2015)
Proceedings Paper
Computer Science, Theory & Methods
Yubin Deng et al.
PROCEEDINGS OF THE 2014 ACM CONFERENCE ON MULTIMEDIA (MM'14)
(2014)
