Reconstructed Phase Space and Convolutional Neural Networks for Classifying Voice Pathologies

Marinus, João Vilian de Moraes Lima; Araújo, José Mário; Gomes, Herman Martins

doi:10.1007/978-3-030-13469-3_92

Cited by 1 publication

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also in a smart city scenario, visual inspections (e.g., power consumption readings [da Silva Marques et al 2019]) performed at the edge could drastically reduce the costs of cloud processing, since the core processing (image analysis) is distributed among commodity smartphones. In the medical domain, for instance, existing approaches for voice pathology recognition [Marinus et al 2018] and skin lesion classification [dos Santos and Ponti 2018] could be implemented for edge execution (e.g., in a smartphone) and compose a tool for pre-screening patients before a doctor sees them. Whenever inferences are below a given confidence level, a more robust model running in the cloud could be queried to confirm/discard those inferences.…”

Section: Introductionmentioning

confidence: 99%

Evaluating Edge-Cloud Computing Trade-Offs for Mobile Object Detection and Classification with Deep Learning

Magalhães

Farias

Marinho

et al. 2020

jidm

View full text Add to dashboard Cite

Internet-of-Things (IoT) applications based on Artificial Intelligence, such as mobile object detection and recognition from images and videos, may greatly benefit from inferences made by state-of-the-art Deep Neural Network(DNN) models. However, adopting such models in IoT applications poses an important challenge since DNNs usually require lots of computational resources (i.e. memory, disk, CPU/GPU, and power), which may prevent them to run on resource-limited edge devices. On the other hand, moving the heavy computation to the Cloud may significantly increase running costs and latency of IoT applications. Among the possible strategies to tackle this challenge are: (i) DNN model partitioning between edge and cloud; and (ii) running simpler models in the edge and more complex ones in the cloud, with information exchange between models, when needed. Variations of strategy (i) also include: running the entire DNN on the edge device (sometimes not feasible) and running the entire DNN on the cloud. All these strategies involve trade-offs in terms of latency, communication, and financial costs. In this article we investigate such trade-offs in real-world scenarios. We conduct several experiments using deep learning models for image-based object detection and classification. Our setup includes a Raspberry PI 3 B+ and a cloud server equipped with a GPU. Different network bandwidths are also evaluated. Our results provide useful insights about the aforementioned trade-offs. The partitioning experiment showed that, overall, running the inferences entirely on the edge or entirely on the cloud server are the best options. The collaborative approach yielded a significant increase in accuracy without penalizing running costs too much.

show abstract

Section: Introductionmentioning

confidence: 99%