DeepFeatIoT: Unifying Deep Learned, Randomized, and LLM Features for Enhanced IoT Time Series Sensor Data Classification in Smart Industries

2025-08-12

AI Summary

IoT time-series data suffer from poor interpretability and classification performance due to missing metadata, heterogeneous sampling frequencies, irregular timestamps, and inconsistent measurement units. To address these challenges, this paper proposes an end-to-end hybrid feature fusion framework that jointly models deep neural network features, ROCKET (Random Convolutional Kernel Transform) features, and semantic embeddings derived from large language models (LLMs), enabling effective representation learning for cross-source heterogeneous time series under low-label regimes. Extensive experiments on multiple real-world IoT datasets demonstrate that our approach significantly outperforms existing state-of-the-art methods, achieving superior generalization, robustness to distribution shifts, and strong few-shot adaptability. The framework provides a scalable, interpretable classification paradigm for time-series-aware systems in smart cities, industrial monitoring, and remote healthcare applications.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Internet of Things (IoT) sensors are ubiquitous technologies deployed across smart cities, industrial sites, and healthcare systems. They continuously generate time series data that enable advanced analytics and automation in industries. However, challenges such as the loss or ambiguity of sensor metadata, heterogeneity in data sources, varying sampling frequencies, inconsistent units of measurement, and irregular timestamps make raw IoT time series data difficult to interpret, undermining the effectiveness of smart systems. To address these challenges, we propose a novel deep learning model, DeepFeatIoT, which integrates learned local and global features with non-learned randomized convolutional kernel-based features and features from large language models (LLMs). This straightforward yet unique fusion of diverse learned and non-learned features significantly enhances IoT time series sensor data classification, even in scenarios with limited labeled data. Our model's effectiveness is demonstrated through its consistent and generalized performance across multiple real-world IoT sensor datasets from diverse critical application domains, outperforming state-of-the-art benchmark models. These results highlight DeepFeatIoT's potential to drive significant advancements in IoT analytics and support the development of next-generation smart systems.

Problem

• Classify IoT time series data with metadata challenges
• Handle heterogeneous sensor data sources effectively
• Improve classification with limited labeled data

Innovation

• Integrates deep learned local and global features
• Combines randomized convolutional kernel features
• Incorporates large language model features