iSEC: An Optimized Deep Learning Model for Image Classification on Edge Computing

Kristiani, Endah; Yang, Chao-Tung; Huang, Chin‐Yin

doi:10.1109/access.2020.2971566

Cited by 39 publications

(15 citation statements)

References 28 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inception-V3 is used for image classification, which is extended from the GoogLeNet network suggested by Google in 2014. 29 Inception-V3 consists of performing several small convolutions on the same level instead of using large convolutions. 32 The first level of the Inception module is composed of three convolutions and one maxpooling.…”

Section: Inception-v3mentioning

confidence: 99%

Cataract grading method based on deep convolutional neural networks and stacking ensemble learning

Elloumi

2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The cataract is the most common cause of severe vision impairment or blindness worldwide. A periodical diagnosis is recommended in order to prevent cataract severity, where screening might be feasibly ensured through fundus images. In this paper, we propose a CAD system to efficiently grade the cataract from fundus images. For such a need, an ensemble learning framework is put forward where the knowledge of three convolutional deep neural networks is stacked in order to perform an efficient cataract prediction. The main contributions of this work are given as follows: (1) Preprocessing and data augmentation of fundus images are carried out to ensure the robustness of the cataract grading; (2) The well‐known DL architectures (Inception‐V3, MobileNet‐V2 and NasNet‐Mobile) are fine‐tuned and learned as base classifiers; (3) An Extreme Learning Machine (ELM) is performed as a meta classifier to stack the predictions of base classifiers. The evaluation is conducted using a dataset of 590 fundus images selected from two public databases. The suggested framework achieves 94.07% accuracy, 94.37% sensitivity, 93.62% specificity, 95.71% precision and 95.04% F‐measure for cataract grading. The experimentation proves that the proposed framework successfully grades fundus images into cataract severity. Moreover, stacking ensemble learning allows achieving a performance that significantly surpasses the ones realized by each DL architecture, applied separately.

show abstract

Section: Inception-v3mentioning

confidence: 99%

Cataract grading method based on deep convolutional neural networks and stacking ensemble learning

Elloumi

2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…This type of technology is becoming increasingly valuable in the development of smart systems, as evidenced by Kristianin et al in [ 19 ] by designing an object classification system, or Adnan et al in [ 20 ] with the optimisation of a detection system on a Rasberry. Moreover, in the field of astronomy, Surabhi Agarwal et al [ 21 ] describe the design of a star tracker using an NCS2.…”

Section: Previous Related Workmentioning

confidence: 99%

Smart Video Surveillance System Based on Edge Computing

Cob-Parro

Losada

Marrón

et al. 2021

Sensors

View full text Add to dashboard Cite

New processing methods based on artificial intelligence (AI) and deep learning are replacing traditional computer vision algorithms. The more advanced systems can process huge amounts of data in large computing facilities. In contrast, this paper presents a smart video surveillance system executing AI algorithms in low power consumption embedded devices. The computer vision algorithm, typical for surveillance applications, aims to detect, count and track people’s movements in the area. This application requires a distributed smart camera system. The proposed AI application allows detecting people in the surveillance area using a MobileNet-SSD architecture. In addition, using a robust Kalman filter bank, the algorithm can keep track of people in the video also providing people counting information. The detection results are excellent considering the constraints imposed on the process. The selected architecture for the edge node is based on a UpSquared2 device that includes a vision processor unit (VPU) capable of accelerating the AI CNN inference. The results section provides information about the image processing time when multiple video cameras are connected to the same edge node, people detection precision and recall curves, and the energy consumption of the system. The discussion of results shows the usefulness of deploying this smart camera node throughout a distributed surveillance system.

show abstract

“…We based our work on the popular bottom-up method Lightweight OpenPose [13], for mainly two reasons. Firstly, this work heavily optimizes the original OpenPose [3] implementation to reach real-time inference speeds on CPU with negligible accuracy drop, which can further be optimized for Edge Devices using Intel® OpenVINO™ Toolkit, as done in other researches [9]. Secondly, in the context of finding the levels of alertness in a person, our work is dependent on the angles generated by different body joints.…”

Section: Our Workmentioning

confidence: 99%

ActiveNet: A computer-vision based approach to determine lethargy

Gupta

Agarwal

2021

Proceedings of the 3rd ACM India Joint International Conference on Data Science &Amp; Management of Data (8th ACM IKDD CODS &Am

View full text Add to dashboard Cite

The outbreak of COVID-19 has forced everyone to stay indoors, fabricating a significant drop in physical activeness. Our work is constructed upon the idea to formulate a backbone mechanism, to detect levels of activeness in real-time, using a single monocular image of a target person. The scope can be generalized under many applications, be it in an interview, online classes, security surveillance, et cetera.We propose a Computer Vision based multi-stage approach, wherein the pose of a person is first detected, encoded with a novel approach, and then assessed by a classical machine learning algorithm to determine the level of activeness. An alerting system is wrapped around the approach to provide a solution to inhibit lethargy by sending notification alerts to individuals involved.

show abstract

iSEC: An Optimized Deep Learning Model for Image Classification on Edge Computing

Cited by 39 publications

References 28 publications

Cataract grading method based on deep convolutional neural networks and stacking ensemble learning

Cataract grading method based on deep convolutional neural networks and stacking ensemble learning

Smart Video Surveillance System Based on Edge Computing

ActiveNet: A computer-vision based approach to determine lethargy

Contact Info

Product

Resources

About