In recent years, FPGA platforms have shown significant potential for accelerating artificial intelligence (AI) applications, particularly in Embedded AI. While various studies have explored adaptive AI deployment on F...
详细信息
In recent years, FPGA platforms have shown significant potential for accelerating artificial intelligence (AI) applications, particularly in Embedded AI. While various studies have explored adaptive AI deployment on FPGAs, there remains a gap in methodologies fully integrating software adaptability with FPGA hardware reconfigurability. This article presents a novel end-to-end co-design methodology for deploying adaptable and scalable Convolutional Neural networks (CNNs) on FPGA platforms. The framework enhances computational performance and reduces latency by dynamically modifying hardware acceleration units by combining CNN architecture adaptability with dynamic partial reconfiguration of FPGA hardware. The proposed methodology enables automated synthesis and runtime customization of both hardware accelerators and CNN architectures, eliminating the need for iterative synthesis. This approach has been implemented and tested on a Xilinx XC7020 FPGA board for a CNN-based image classifier, achieving superior computation performance (0.68s/image) and accuracy (97%) compared to state-of-the-art alternatives.
The prediction of stock prices has recently gained considerable attention as a complex and challenging issue within the realms of economics and finance. Stock prices are affected by various factors, such as the busine...
详细信息
ISBN:
(纸本)9783031820724;9783031820731
The prediction of stock prices has recently gained considerable attention as a complex and challenging issue within the realms of economics and finance. Stock prices are affected by various factors, such as the business environment, stock market operations, inflation, and unexpected events. Since the stock market is volatile and nonlinear, finding the most effective model to forecast stock prices is one of the most challenging problems. Researchers have increasingly explored various Machine Learning (ML) and Deep Learning (DL) models to address this issue due to their capacity to handle time series data and nonlinear patterns. These models often outperform traditional approaches in predicting stock prices with high accuracy and lower root mean square error (RMSE). This paper reviews various works that have utilized ML approaches for stock price prediction, covering research published between 2017 and 2023. This literature review discusses various techniques, their performance, limitations, and future work. We assess the latest techniques in many studies, including ML and DL models. The findings of this review conclude that Neural networks (NNs) are the most commonly used approaches in predicting stock prices due to their effectiveness in detecting complex patterns in financial data.
This paper deals with local certification, specifically locally checkable proofs: given a graph property, the task is to certify whether a graph satisfies the property. The verification of this certification needs to ...
详细信息
Federated learning (FL) is a distributed Machine Learning (ML) framework that is capable of training a new global model by aggregating clients' locally trained models without sharing users' original data. Fede...
详细信息
ISBN:
(纸本)9789819608041;9789819608058
Federated learning (FL) is a distributed Machine Learning (ML) framework that is capable of training a new global model by aggregating clients' locally trained models without sharing users' original data. Federated learning as a service (FLaaS) offers a privacy-preserving approach for training machine learning models on devices with various computational resources. Most proposed FL-based methods train the same model in all client devices regardless of their computational resources. However, in practical Internet of Things (IoT) scenarios, IoT devices with limited computational resources may not be capable of training models that client devices with greater hardware performance hosted. Most of the existing FL frameworks that aim to solve the problem of aggregating heterogeneous models are designed for Independent and Identical distributed (IID) data, which may make it hard to reach the target algorithm performance when encountering non-IID scenarios. To address these problems in hierarchical networks, in this paper, we propose a heterogeneous aggregation framework for hierarchical edge systems called HAF-Edge. In our proposed framework, we introduce a communication-efficient model aggregation method designed for FL systems with two-level model aggregations running at the edge and cloud levels. This approach enhances the convergence rate of the global model by leveraging selective knowledge transfer during the aggregation of heterogeneous models. To the best of our knowledge, this work is pioneering in addressing the problem of aggregating heterogeneous models within hierarchical FL systems spanning IoT, edge, and cloud environments. We conducted extensive experiments to validate the performance of our proposed method. The evaluation results demonstrate that HAF-Edge significantly outperforms state-of-the-art methods.
Software-defined networking (SDN) is a transformative technology that systematically centralises and manages network resources. This paradigm shift allows for greater flexibility, agility, and efficiency in network ma...
详细信息
Advanced train control systems, such as ERTMS-ETCS and its future successors, that aim to increase the degree of autonomy of train driving, are based on algorithms strongly based on communication between geographicall...
详细信息
This study explores the design of a multimodal language model (MLLM) for the Internet of Things (IoT), emphasizing the synergy between software algorithms and intelligent hardware systems. With the increasing prolifer...
详细信息
This paper presents a blockchain-integrated deep neural network (DNN) model designed to enhance both data security and scheduling accuracy in modern power grid systems. By combining federated learning with blockchain ...
详细信息
In distributed multi-robot systems, ensuring collision-free motion planning is a complex challenge, especially in dynamic environments where multiple robots are operating simultaneously. Traditional path-planning algo...
详细信息
The proceedings contain 33 papers. The special focus in this conference is on Stabilization, Safety, and Security of distributedsystems. The topics include: Invited Paper: Gathering Oblivious Robots in the ...
ISBN:
(纸本)9783031744976
The proceedings contain 33 papers. The special focus in this conference is on Stabilization, Safety, and Security of distributedsystems. The topics include: Invited Paper: Gathering Oblivious Robots in the Plane;invited Paper: The Smart Contract Model;invited Paper: Using Signed Formulas for Online Certification;optimal Asynchronous Perpetual Grid Exploration;gathering of Robots in Butterfly networks;brief Announcement: Pebble Guided Rendezvous Despite Fault;complete Graph Identification in Population Protocols;efficient Self-stabilizing Simulations of Energy-Restricted Mobile Robots by Asynchronous Luminous Mobile Robots;brief Announcement: Perpetual Exploration of Triangular Grid by Myopic Oblivious Robots Without Chirality;an Optimal Algorithm for Geodesic Mutual Visibility on Hexagonal Grids;Coating in SILBOT with One Axis Agreement;rendezvous and Merging for Two Metamorphic Robotic systems Without Global Compass;gathering Semi-Synchronously Scheduled Two-State Robots;selective Population Protocols;partially Disjoint Shortest Paths and Near-Shortest Paths Trees;brief Announcement: Towards Proportionate Fair Assignment;BlindexTEE: A Blind Index Approach Towards TEE-Supported End-to-End Encrypted DBMS;tight Bounds for Constant-Round Domination on Graphs of High Girth and Low Expansion;adding All Flavors: A Hybrid Random Number Generator for dApps and Web3;SUPI-Rear: Privacy-Preserving Subscription Permanent Identification Strategy in 5G-AKA;anomaly Detection Within Mission-Critical Call Processing;brief Announcement: Make Master Private-Keys Secure by Keeping It Public;Selection Guidelines for Geographical SMR Protocols: A Communication Pattern-Based Latency Modeling Approach;byzantine Reliable Broadcast with One Trusted Monotonic Counter;brief Announcement: On the Feasibility of Local Failover Routing on Directed Graphs;TRAIL: Cross-Shard Validation for Byzantine Shard Protection;softening the Impact of Collisions in Contention Resolution;generating the Converge
暂无评论