A comparative study on SoC embedded low power GPUs for real‐time edge‐based automated traffic surveillance

AbstractIn this paper, we propose three methods for door state classification with the goal to improve robot navigation in indoor spaces. These methods were also developed to be used in other areas and applications since they are not limited to door detection as other related works are. Our methods work offline, in low-powered computers as the Jetson Nano, in real-time with the ability to differentiate between open, closed and semi-open doors. We use the 3D object classification, PointNet, real-time semantic segmentation algorithms such as, FastFCN, FC-HarDNet, SegNet and BiSeNet, the object detection algorithm, DetectNet and 2D object classification networks, AlexNet and GoogleNet. We built a 3D and RGB door dataset with images from several indoor environments using a 3D Realsense camera D435. This dataset is freely available online. All methods are analysed taking into account their accuracy and the speed of the algorithm in a low powered computer. We conclude that it is possible to have a door classification algorithm running in real-time on a low-power device.

Download Full-text

Real-time, High-resolution Depth Upsampling on Embedded Accelerators

ACM Transactions on Embedded Computing Systems ◽

10.1145/3436878 ◽

2021 ◽

Vol 20 (3) ◽

pp. 1-22

Author(s):

David Langerman ◽

Alan George

Keyword(s):

High Resolution ◽

Low Power ◽

Real Time ◽

Mixed Reality ◽

Graphics Processing Unit ◽

Processing Unit ◽

Reconfigurable Logic ◽

Depth Sensors ◽

Time Requirements ◽

Graphics Processing

High-resolution, low-latency apps in computer vision are ubiquitous in today’s world of mixed-reality devices. These innovations provide a platform that can leverage the improving technology of depth sensors and embedded accelerators to enable higher-resolution, lower-latency processing for 3D scenes using depth-upsampling algorithms. This research demonstrates that filter-based upsampling algorithms are feasible for mixed-reality apps using low-power hardware accelerators. The authors parallelized and evaluated a depth-upsampling algorithm on two different devices: a reconfigurable-logic FPGA embedded within a low-power SoC; and a fixed-logic embedded graphics processing unit. We demonstrate that both accelerators can meet the real-time requirements of 11 ms latency for mixed-reality apps. 1

Download Full-text

A novel approach to optimize the production cost of railway coaches of India using situational-based composite triangular and trapezoidal fuzzy LPP models

Complex & Intelligent Systems ◽

10.1007/s40747-021-00313-0 ◽

2021 ◽

Author(s):

Rakesh Kumar ◽

Gaurav Dhiman ◽

Neeraj Kumar ◽

Rajesh Kumar Chandrawat ◽

Varun Joshi ◽

...

Keyword(s):

Comparative Study ◽

Real Time ◽

Production Cost ◽

Upper Bounds ◽

Production Costs ◽

Cost Data ◽

Novel Approach ◽

Membership Grade ◽

Minimum Costs

AbstractThis article offers a comparative study of maximizing and modelling production costs by means of composite triangular fuzzy and trapezoidal FLPP. It also outlines five different scenarios of instability and has developed realistic models to minimize production costs. Herein, the first attempt is made to examine the credibility of optimized cost via two different composite FLP models, and the results were compared with its extension, i.e., the trapezoidal FLP model. To validate the models with real-time phenomena, the Production cost data of Rail Coach Factory (RCF) Kapurthala has been taken. The lower, static, and upper bounds have been computed for each situation, and then systems of optimized FLP are constructed. The credibility of each model of composite-triangular and trapezoidal FLP concerning all situations has been obtained, and using this membership grade, the minimum and the greatest minimum costs have been illustrated. The performance of each composite-triangular FLP model was compared to trapezoidal FLP models, and the intense effects of trapezoidal on composite fuzzy LPP models are investigated.

Download Full-text

An edge based hybrid intrusion detection framework for mobile edge computing

Complex & Intelligent Systems ◽

10.1007/s40747-021-00498-4 ◽

2021 ◽

Author(s):

Ashish Singh ◽

Kakali Chatterjee ◽

Suresh Chandra Satapathy

Keyword(s):

Intrusion Detection ◽

Real Time ◽

Network Architecture ◽

Denial Of Service ◽

Edge Computing ◽

Mobile Edge Computing ◽

Hybrid Detection ◽

Game Theoretical Approach ◽

Improved Performance ◽

Edge Based

AbstractThe Mobile Edge Computing (MEC) model attracts more users to its services due to its characteristics and rapid delivery approach. This network architecture capability enables users to access the information from the edge of the network. But, the security of this edge network architecture is a big challenge. All the MEC services are available in a shared manner and accessed by users via the Internet. Attacks like the user to root, remote login, Denial of Service (DoS), snooping, port scanning, etc., can be possible in this computing environment due to Internet-based remote service. Intrusion detection is an approach to protect the network by detecting attacks. Existing detection models can detect only the known attacks and the efficiency for monitoring the real-time network traffic is low. The existing intrusion detection solutions cannot identify new unknown attacks. Hence, there is a need of an Edge-based Hybrid Intrusion Detection Framework (EHIDF) that not only detects known attacks but also capable of detecting unknown attacks in real time with low False Alarm Rate (FAR). This paper aims to propose an EHIDF which is mainly considered the Machine Learning (ML) approach for detecting intrusive traffics in the MEC environment. The proposed framework consists of three intrusion detection modules with three different classifiers. The Signature Detection Module (SDM) uses a C4.5 classifier, Anomaly Detection Module (ADM) uses Naive-based classifier, and Hybrid Detection Module (HDM) uses the Meta-AdaboostM1 algorithm. The developed EHIDF can solve the present detection problems by detecting new unknown attacks with low FAR. The implementation results illustrate that EHIDF accuracy is 90.25% and FAR is 1.1%. These results are compared with previous works and found improved performance. The accuracy is improved up to 10.78% and FAR is reduced up to 93%. A game-theoretical approach is also discussed to analyze the security strength of the proposed framework.

Download Full-text