Over the past decade, there has been a significant increase in interest in digital twin (DT) technology in a variety of domains. While research on DTs of single assets was initially prevalent, there has been a notable...
详细信息
As of today, research in vulnerable road users (VRUs) applications is mainly focused on safety in urban road scenarios. There is little to be found in the literature with respect to VRUs in mountain areas, where mount...
详细信息
ISBN:
(数字)9783903176713
ISBN:
(纸本)9798331522025
As of today, research in vulnerable road users (VRUs) applications is mainly focused on safety in urban road scenarios. There is little to be found in the literature with respect to VRUs in mountain areas, where mountain biking and hiking also present risks of collision. Here, it is not yet clear whether existing localization and communication technologies would provide sufficient performance in such harsh environments. In this work, we start answering this question by presenting the results of a measurement campaign which took place in a mountain area in Northern Italy during Summer 2024. With respect to localization, we show that global navigation satellite system (GNSS)-based localization alone often provides unreliable results due to vegetation and terrain. Trilateration with Bluetooth Low Energy (BLE) and beacons mounted at fixed positions performs well in some circumstances and can be used to enhance GNSS, however, we also observed many unclear effects that require further investigations. Concerning communication, the results indicate that both direct short range communications (DSRC) and cellular V2X (C-V2X) works fairly well in most cases, but terrain characteristics might induce packet losses or low signal quality, whereas instabilities in GNSS fixes might also cause C-V2X outages.
To evaluate novel solutions for edge computing systems, suitable distribution models for simulation are essential. The extensive use of deep learning (DL) in video analytics has altered traffic patterns on edge and cl...
ISBN:
(纸本)9798331534202
To evaluate novel solutions for edge computing systems, suitable distribution models for simulation are essential. The extensive use of deep learning (DL) in video analytics has altered traffic patterns on edge and cloud servers, necessitating innovative models. Queuing models are used to simulate the performance and stability of edge-enabled systems, particularly video streaming applications. This paper demonstrates that traditional Markovian M/M/s and general distribution G/G/s queuing models must be revamped for accurate simulation. We examined these queuing models by characterizing the real data with discrete and continuous distributions for arrival rates to homogenous servers in AI-based video analytics edge systems. Based on achieved results, traditional methods for finding general distributions are inadequate, and an automation method for finding empirical distribution is needed. Therefore, we introduce a novel approach using a generative adversarial network (WGAN) to generate artificial data to automate the process of estimating empirical distribution for modeling these applications.
In this paper, we propose a heterogeneous federated learning (HFL) system for sparse time series prediction in healthcare, which is a decentralized federated learning algorithm with heterogeneous transfers. We design ...
详细信息
With the emergence of AI for good, there has been an increasing interest in building computer vision data-driven deep learning inclusive AI solutions. Sign language Recognition (SLR) has gained attention recently. It ...
详细信息
With the emergence of AI for good, there has been an increasing interest in building computer vision data-driven deep learning inclusive AI solutions. Sign language Recognition (SLR) has gained attention recently. It is an essential component of a sign-to-text translation system to support the deaf and hard-of-hearing population. This paper presents a computer VISIOn data-driven deep learning framework for Sign Language video Recognition (VisoSLR). VisioSLR provides a precise measurement of translating signs for developing an end-to-end computational translation system. Considering the scarcity of sign language datasets, which hinders the development of an accurate recognition model, we evaluate the performance of our framework by fine-tuning the very well-known YOLO models, which are built from a signs-unrelated collection of images and videos, using a small-sized sign language dataset. Gathering a sign language dataset for signs training would involve an enormous amount of time to collect and annotate videos in different environmental setups and multiple signers, in addition to the training time of a model. Numerical evaluations of VisioSLR show that our framework recognizes signs with a mean average precision of 97.4%, 97.1%, and 95.5% and 11, 12, and 12 milliseconds of recognition time on YOLOv8m, YOLOv9m, and YOLOv11m, respectively.
Time-series prediction is increasingly popular in a variety of applications, such as smart factories and smart transportation. Researchers have used various techniques to predict power consumption, but existing models...
详细信息
The Hospital Emergency department (ED) provides critical care for acute and urgent conditions, making it one of the most complex areas in healthcare. Optimizing staff configurations to reduce patient waiting times and...
详细信息
As a key technology of intelligent satellite-enabled services in B5G or 6G networks, deploying Deep Neural Networks (DNN) models on satellites has been a notable trend, catering to the daily demand for extensive compu...
详细信息
As a cutting-edge technology of low-altitude Artificial Intelligence of Thing (AIoT), UAV object detection significantly enhances the surveillance services capabilities of low-altitude AIoT. However, the difficulty of...
详细信息
暂无评论