Highly Efficient Direct Analytics on Semantic-aware Time Series Data Compression

2025-03-17

AI Summary

To address the low co-efficiency of time-series data compression and analysis in resource-constrained IoT environments, this paper proposes the first lightweight framework enabling semantic compression-domain in-situ analysis. Methodologically, it integrates SHRINK—a lightweight compression scheme—with semantic-aware feature encoding and direct computation within the compressed domain, thereby eliminating decompression overhead; it further introduces an optimized indexing access strategy to enable zero-decompression anomaly detection at the edge. The key contribution is the first demonstration of executing analytical tasks directly on highly compressed time-series data—retaining only semantic features—thus achieving both high-fidelity semantic representation and ultra-low computational load. Experiments show that, compared to raw-data analysis, the framework achieves a 4× speedup in average runtime, reduces data access volume by 90%, and incurs ≤1% accuracy degradation in anomaly detection, significantly enhancing real-time and reliable edge-based anomaly detection.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Data Compression
• Search and Optimization: Distributed Search

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Semantic communication has emerged as a promising paradigm to tackle the challenges of massive growing data traffic and sustainable data communication. It shifts the focus from data fidelity to goal-oriented or task-oriented semantic transmission. While deep learning-based methods are commonly used for semantic encoding and decoding, they struggle with the sequential nature of time series data and high computation cost, particularly in resource-constrained IoT environments. Data compression plays a crucial role in reducing transmission and storage costs, yet traditional data compression methods fall short of the demands of goal-oriented communication systems. In this paper, we propose a novel method for direct analytics on time series data compressed by the SHRINK compression algorithm. Through experimentation using outlier detection as a case study, we show that our method outperforms baselines running on uncompressed data in multiple cases, with merely 1% difference in the worst case. Additionally, it achieves four times lower runtime on average and accesses approximately 10% of the data volume, which enables edge analytics with limited storage and computation power. These results demonstrate that our approach offers reliable, high-speed outlier detection analytics for diverse IoT applications while extracting semantics from time-series data, achieving high compression, and reducing data transmission.

Problem

• Efficient analytics on compressed time series data
• Overcoming high computation costs in IoT environments
• Achieving high compression and reduced data transmission

Innovation

• Direct analytics on SHRINK-compressed time series data
• Outperforms baselines with minimal accuracy loss
• Reduces runtime and data access significantly