Resource Aware Long Short-Term Memory Model (RALSTMM) Based On-Device Incremental Learning for Industrial Internet of Things

Takele, Atallo Kassaw; Villányi, Balázs

doi:10.1109/access.2023.3289076

Cited by 4 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the proposed method takes sample of the former sub-datasets during the instant training phases. The processing time, accuracy, precision, recall, information criteria (Akaike Information Criteria (AIC) and Bayesian Information Criteria (BIC)) have been used for comparative evaluation [2], [31]. Accuracy, precision, and recall are common metrics for evaluating the performance of a classification model and processing time has been applied for evaluating the resource utilization.…”

Section: Resultsmentioning

confidence: 99%

“…The Industrial Internet of Things (IIoT) is a sub-category of IoT which is utilized in industrial scenarios. The IIoT is enabled by intelligence data analytics, sophisticated application software, controllers, sensors, actuators, and communication gateways [2], [3]. The IIoT devices deployed in the industrial environment collect information and transmit it to the cloud or edge server for subsequent analysis.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

LSTM-Autoencoder-Based Incremental Learning for Industrial Internet of Things

Takele,

Villányi

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Edge-based intelligent data analytics supports the Industrial Internet of Things (IIoT) to enable efficient manufacturing. Incremental learning in the edge-based data analytics has the potential to analyze continuously collected real-time data. However, additional efforts are needed to address performance, latency, resource utilization and storage of historical data challenges. This paper introduces an incremental learning approach based on Long-Short Term Memory (LSTM) autoencoders, by sparsening the weight matrix and taking samples from previously trained sub-datasets. The aim is to minimize the resources utilized while training redundant knowledge for edge devices of IIoT. The degree of sparsity can be determined by the redundancy of patterns, and the inverse of the coefficient of variation has been utilized to recognize it. A higher value of the inverse of the coefficient of variation shows that the values of the weight matrix are close to each other, which indicates the redundancy of knowledge, and vice versa. In addition, the coefficient of variation has been applied for limiting the size of samples from the previously trained sub-datasets. The experiment conducted using the IIoT testbed dataset demonstrates substantial enhancements in resource optimization without compromising performance.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%