Deep learning predicts network hardware failure using thermal imaging and sensor fusion

Researchers have developed a deep learning strategy for predictive maintenance of network hardware, utilizing thermal imaging and power sensor data. The study evaluated several models, including ResNet-50, InceptionV3, and VGG16, alongside a CNN-LSTM fusion model. Performance significantly improved with domain-specific pre-processing, such as region-of-interest extraction, boosting ResNet-50 accuracy to 91%. The CNN-LSTM model achieved the highest accuracy of 94%, demonstrating the effectiveness of fusing visual and sensor time-series information for proactive hardware maintenance. AI

IMPACT This research could lead to more reliable data center operations through proactive maintenance, reducing downtime and costs.

RANK_REASON The cluster contains a research paper detailing a novel deep learning approach for network hardware failure detection. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• Hugging Face
• ImageNet
• Inceptionv3
• ResNet-50
• Vgg16

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →