An Affordable Fast Early Warning System for Edge Computing in Assembly Line

Syafrudin, Muhammad; Fitriyani, Norma Latif; Alfian, Ganjar; Rhee, Jongtae

doi:10.3390/app9010084

Cited by 39 publications

(27 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Park et al [16] proposed an edge-based fault detection using an LSTM model in an industrial robot manipulator that incorporated vibration, temperature sensors, and the use of one edge device attached to the machine and pressure sensors. Syafrudin et al [17] proposed edge-based fault detection using density-based spatial clustering and a random forest algorithm for an automobile parts factory that employed an edge model on each workstation of the assembly line. Li et al [18] proposed edge-based visual defect detection using a convolutional neural network (CNN) model in a tile production factory that deployed multiple cameras to capture visual information of the products [19].…”

Section: Related Workmentioning

confidence: 99%

Real-Time and Robust Hydraulic System Fault Detection via Edge Computing

Fawwaz

Chung

2020

Applied Sciences

View full text Add to dashboard Cite

We consider fault detection in a hydraulic system that maintains multivariate time-series sensor data. Such a real-world industrial environment could suffer from noisy data resulting from inaccuracies in hardware sensing or external interference. Thus, we propose a real-time and robust fault detection method for hydraulic systems that leverages cooperation between cloud and edge servers. The cloud server employs a new approach that includes a genetic algorithm (GA)-based feature selection that identifies feature-to-label correlations and feature-to-feature redundancies. A GA can efficiently process large search spaces, such as solving a combinatorial optimization problem to identify the optimal feature subset. By using fewer important features that require transmission and processing, this approach reduces detection time and improves model performance. We propose a long short-term memory autoencoder for a robust fault detection model that leverages temporal information on time-series sensor data and effectively handles noisy data. This detection model is then deployed at edge servers that provide computing resources near the data source to reduce latency. Our experimental results suggest that this method outperforms prior approaches by demonstrating lower detection times, higher accuracy, and increased robustness to noisy data. While we have a 63% reduction of features, our model obtains a high accuracy of approximately 98% and is robust to noisy data with a signal-to-noise ratio near 0 dB. Our method also performs at an average detection time of only 9.42 ms with a reduced average packet size of 179.98 KB from the maximum of 343.78 KB.

show abstract

Section: Related Workmentioning

confidence: 99%

Real-Time and Robust Hydraulic System Fault Detection via Edge Computing

Fawwaz

Chung

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…When bringing computation and data storage closer to where events are being detected and processed, the EDU could be divided in multiple processing cells for faster detection of some more critical events such as noxious gases (depending on wind conditions, they may be hard to quickly identify in some areas) and fire. Concerning the IoT scope of problems, some works have exploited edge computing to achieve some kind of efficient and quick event detection, as in [55,56]. Additionally, frameworks and models on how to exploit edge computing in IoT systems for some specialized detection have also been designed.…”

Section: A Smart City Perspective Of Emergency Alertingmentioning

confidence: 99%

A Distributed Multi-Tier Emergency Alerting System Exploiting Sensors-Based Event Detection to Support Smart City Applications

Costa

Vasques

Portugal

et al. 2019

Sensors

View full text Add to dashboard Cite

The development of efficient sensing technologies and the maturation of the Internet of Things (IoT) paradigm and related protocols have considerably fostered the expansion of sensor-based monitoring applications. A great number of those applications has been developed to monitor a set of information for better perception of the environment, with some of them being dedicated to identifying emergency situations. Current IoT-based emergency systems have limitations when considering the broader scope of smart cities, exploiting one or just a few monitoring variables or even allocating high computational burden to regular sensor nodes. In this context, we propose a distributed multi-tier emergency alerting system built around a number of sensor-based event detection units, providing real-time georeferenced information about the occurrence of critical events, while taking as input a configurable number of different scalar sensors and GPS data. The proposed system could then be used to detect and to deliver emergency alarms, which are computed based on the detected events, the previously known risk level of the affected areas and temporal information. Doing so, modularized and flexible perceptions of critical events are provided, according to the particularities of each considered smart city scenario. Besides implementing the proposed system in open-source electronic platforms, we also created a real-time visualization application to dynamically display emergency alarms on a map, demonstrating a feasible and useful application of the system as a supporting service. Therefore, this innovative approach and its corresponding physical implementation can bring valuable results for smart cities, potentially supporting the development of adaptive IoT-based emergency-aware applications.

show abstract

“…Figure 8a shows prototype real-time monitoring system architecture to filter false positives, ensuring only products actually moved through the gate are sent to the representational state transfer application programming interface (REST API), for presentation in web dashboard(s) and/or database storage. We used the MongoDB V3.4.9 database since it can efficiently store continuously-generated sensor/RFID data from manufacturing [56][57][58], healthcare [59], and supply chain [60]. The real-time monitoring system used java programming language V1.8.0 to receive tag information from the readers, filter false positives using trained RF, and send products moved through the gate information to the server via REST API.…”

Section: Management Implicationsmentioning

confidence: 99%

False Positive RFID Detection Using Classification Models

et al. 2019

Self Cite

View full text Add to dashboard Cite

Radio frequency identification (RFID) is an automated identification technology that can be utilized to monitor product movements within a supply chain in real-time. However, one problem that occurs during RFID data capturing is false positives (i.e., tags that are accidentally detected by the reader but not of interest to the business process). This paper investigates using machine learning algorithms to filter false positives. Raw RFID data were collected based on various tagged product movements, and statistical features were extracted from the received signal strength derived from the raw RFID data. Abnormal RFID data or outliers may arise in real cases. Therefore, we utilized outlier detection models to remove outlier data. The experiment results showed that machine learning-based models successfully classified RFID readings with high accuracy, and integrating outlier detection with machine learning models improved classification accuracy. We demonstrated the proposed classification model could be applied to real-time monitoring, ensuring false positives were filtered and hence not stored in the database. The proposed model is expected to improve warehouse management systems by monitoring delivered products to other supply chain partners.

show abstract

An Affordable Fast Early Warning System for Edge Computing in Assembly Line

Cited by 39 publications

References 54 publications

Real-Time and Robust Hydraulic System Fault Detection via Edge Computing

Real-Time and Robust Hydraulic System Fault Detection via Edge Computing

A Distributed Multi-Tier Emergency Alerting System Exploiting Sensors-Based Event Detection to Support Smart City Applications

False Positive RFID Detection Using Classification Models

Contact Info

Product

Resources

About