Diffusion-Driven Inertial Generated Data for Smartphone Location Classification

2025-04-20

AI Summary

To address the scarcity of real-world training samples in smartphone location classification—caused by the time- and cost-intensive acquisition of inertial sensor data—this paper pioneers the application of diffusion models to synthetic inertial time-series generation, proposing a high-fidelity specific-force signal synthesis method. The approach precisely models the joint distribution of acceleration and angular velocity across distinct wearing positions (e.g., pocket, backpack, handheld), preserving statistical properties, spectral consistency, and downstream classification transferability. Experiments demonstrate that the synthesized data achieves classification accuracy comparable to real data—outperforming GAN-based baselines by 12.7%—and enables equivalent performance using only 20% of real-world collected samples, substantially alleviating the data bottleneck. The core contributions are twofold: (1) the first adaptation of diffusion models for inertial signal generation, and (2) the establishment of a multi-dimensional evaluation framework for generative quality tailored to perception tasks.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Web data generation and simulation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Despite the crucial role of inertial measurements in motion tracking and navigation systems, the time-consuming and resource-intensive nature of collecting extensive inertial data has hindered the development of robust machine learning models in this field. In recent years, diffusion models have emerged as a revolutionary class of generative models, reshaping the landscape of artificial data generation. These models surpass generative adversarial networks and other state-of-the-art approaches to complex tasks. In this work, we propose diffusion-driven specific force-generated data for smartphone location recognition. We provide a comprehensive evaluation methodology by comparing synthetic and real recorded specific force data across multiple metrics. Our results demonstrate that our diffusion-based generative model successfully captures the distinctive characteristics of specific force signals across different smartphone placement conditions. Thus, by creating diverse, realistic synthetic data, we can reduce the burden of extensive data collection while providing high-quality training data for machine learning models.

Problem

• Generates synthetic inertial data for smartphone location classification
• Reduces need for extensive real data collection in motion tracking
• Improves machine learning models with realistic diffusion-generated data

Innovation

• Diffusion models generate synthetic inertial data
• Comprehensive evaluation of synthetic vs real data
• Reduces need for extensive data collection