The demand for optimized and efficient embedded software is increasing in many applications such as the Internet of Things (IoT) or other Cyber-Physical Systems (CPS). Hence, early performance analysis of embedded sof...
详细信息
ISBN:
(纸本)9798350398519
The demand for optimized and efficient embedded software is increasing in many applications such as the Internet of Things (IoT) or other Cyber-Physical Systems (CPS). Hence, early performance analysis of embedded software is essential to perform Design Space Exploration (DSE), ensure efficiency, and meet time-to-market constraints. Designers usually use real hardware, simulators, or static analyzers to obtain the performance. However, these methods suffer from serious drawbacks as real hardware is not available in the early stage of the design process, simulators either do not support any timing accuracy or require large execution time, and static analyzers need details of the hardware microarchitecture. In this paper, we present a novel Artificial Neural Network (ANN)-based approach that allows a fast and accurate performance estimation of embedded software for RISC-V processors in the early design phases. This can significantly reduce the burden on designers to perform DSE. The proposed approach takes advantage of the dynamic analysis technique and analytical models and does not require any microarchitecturerelated parameters such as cache misses, cache hits, and memorylevel parallelism. We compare our proposed microarchitectureindependent approach with state-of-the-art in terms of speed and accuracy. Our experiments on various benchmarks demonstrate that the proposed approach achieves a speed-up of 4.41x compared to a RISC-V Virtual Prototype (VP) at the Electronic System Level (ESL), while the estimation results have only a Mean Absolute Percentage Error (MAPE) of 2%.
This study focuses on the development of an innovative fire accident indication system for buildings in Hong Kong, leveraging the Internet of Things (IoT) technology. The proposed system integrates IoT devices and sen...
详细信息
The proceedings contain 21 papers. The topics discussed include: a preliminary study of on/off-body propagation channels for brain telemetry using a flexible wearable antenna;estimation of source direction with spheri...
ISBN:
(纸本)9798350304176
The proceedings contain 21 papers. The topics discussed include: a preliminary study of on/off-body propagation channels for brain telemetry using a flexible wearable antenna;estimation of source direction with spherical array receiver in molecular communication;medical imaging system design using microwave antennas and portable platform;channel modeling activities of international standardization on ieee 802.15 TG6MA for human and vehicle body area networks;standardization activities of ieee P802.15.6ma wireless human and vehicle area networks;hybrid smartwatch multi-factor authentication;simulation and implementation of an IoT-based secure smart biology laboratory for smart cities;reinforcement learning based cloud and edge resource allocation for real-time telemedicine;and visible light communications for healthcare applications: opportunities and challenges.
Networked embedded devices are increasingly deployed in safety critical environments such as robotics, smart manufacturing and autonomous vehicles. Availability is an essential prerequisite of safety critical systems,...
详细信息
ISBN:
(数字)9798350367294
ISBN:
(纸本)9798350367324
Networked embedded devices are increasingly deployed in safety critical environments such as robotics, smart manufacturing and autonomous vehicles. Availability is an essential prerequisite of safety critical systems, which depend upon timely access to sensed data to inform the real-time control of actuators. Recent work has demonstrated that trusted computing features can be used to guarantee the availability of local resources to the safety-critical applications. However, prior work fails to guarantee the availability of a network connection, which is essential for correct system operation. To address this issue, we contribute NetReach, which uses Arm TrustZone to guarantee network availability to, and the reachability of, critical applications via a secure backup channel. Evaluation of NetReach shows that it can preserve the network connectivity of critical applications while under attack, with a worst case overhead of 18.66 % for networked software running in the Normal World. Furthermore, NetReach introduces minimal additional code in the Secure World (only 418 lines of code). The presented features of NetReach enable future work toward resilient networks.
This paper presents a comparative analysis of hardware resource utilization for three Maximum Power Point Tracking (MPPT) techniques: Perturb and Observe (P&O), Incremental Conductance (IC), and Artificial Neural ...
详细信息
Execution of resource-intensive tasks, such as artificial intelligence (AI), big-data algorithms, video processing, etc. is a common requirement in distributed embedded systems today. The typical solution is to execut...
详细信息
Due to the vulnerability of H.264/AVC video streams to tampering or substitution attacks during network transmission, the integrity and authenticity of transmitted video stream data cannot be guaranteed. To address th...
详细信息
Distracted driving is a critical safety issue that leads to numerous fatalities and injuries worldwide. This study addresses the urgent need for efficient and real-time machine learning models to detect distracted dri...
详细信息
As a fundamental task in computer vision, object detection serves as critical infrastructure for advanced image understanding by providing structured localization and classification data. Addressing the limitation of ...
详细信息
ISBN:
(数字)9798331542856
ISBN:
(纸本)9798331542863
As a fundamental task in computer vision, object detection serves as critical infrastructure for advanced image understanding by providing structured localization and classification data. Addressing the limitation of existing lightweight models in feature representation within complex scenarios, this study proposes an enhanced architecture based on YOLOv7-tiny. The integration of Efficient Channel Attention (ECA) modules establishes cross-channel interaction mechanisms, which significantly improves discriminative feature capture while preserving real-time inference capabilities. Experimental results demonstrate a $1.1 \%$ absolute improvement in mAP metrics on coco dataset, offering a novel technical solution for high-precision real-time detection on embedded systems.
暂无评论