arXiv subjects

Ming-Chun Huang

Publications and source records attributed to Ming-Chun Huang.

4 recordsLinked to original sources

arXiv2026

SolarChain: A Physics-Grounded Embodied IoT System for Verifiable Urban Solar Market Design

Distributed solar markets must coordinate physical reports, economic allocation, and public settlement even when IoT data can be manipulated. We present SolarChain, a controlled Embodied Intelligence of Things (EIoT) prototype that integrates four functions: physics-bounded screening of photovoltaic reports, persistent agent and planner coordination, configurable allocation between producer rewards and market liquidity, and replayable hash-linked auditing of settlement decisions. The benchmark combines city-level historical weather inputs with physics-modeled generation bounds and synthetic nodes, demand, trades, and scripted attacks. On 36,000 monthly records, an IQR/MAD baseline attains F1=1.000, while the rule-based adaptive verifier attains F1=0.988 and provides physically interpretable decision evidence; it is not uniformly superior across attack classes. A sensitivity sweep selects a 20/80 reward/liquidity default under the stated simulation assumptions, while showing the incentive-liquidity trade-off. These results provide reproducible evidence from a controlled prototype, not proof of deployment readiness. We release the code, data, and audit artifacts in the spirit of open science.

cs.CY↗

arXiv2025

Reliable Vertical Ground Reaction Force Estimation with Smart Insole During Walking

The vertical ground reaction force (vGRF) and its characteristic weight acceptance and push-off peaks measured during walking are important for gait and biomechanical analysis. Current wearable vGRF estimation methods suffer from drifting errors or low generalization performances, limiting their practical application. This paper proposes a novel method for reliably estimating vGRF and its characteristic peaks using data collected from the smart insole, including inertial measurement unit data and the newly introduced center of the pressed sensor data. These data were fused with machine learning algorithms including artificial neural networks, random forest regression, and bi-directional long-short-term memory. The proposed method outperformed the state-of-the-art methods with the root mean squared error, normalized root mean squared error, and correlation coefficient of 0.024 body weight (BW), 1.79% BW, and 0.997 in intra-participant testing, and 0.044 BW, 3.22% BW, and 0.991 in inter-participant testing, respectively. The difference between the reference and estimated weight acceptance and push-off peak values are 0.022 BW and 0.017 BW with a delay of 1.4% and 1.8% of the gait cycle for the intra-participant testing and 0.044 BW and 0.025 BW with a delay of 1.5% and 2.3% of the gait cycle for the inter-participant testing. The results indicate that the proposed vGRF estimation method has the potential to achieve accurate vGRF measurement during walking in free living environments.

cs.HC↗

arXiv2023

HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimation

Transformer-based approaches have been successfully proposed for 3D human pose estimation (HPE) from 2D pose sequence and achieved state-of-the-art (SOTA) performance. However, current SOTAs have difficulties in modeling spatial-temporal correlations of joints at different levels simultaneously. This is due to the poses' spatial-temporal complexity. Poses move at various speeds temporarily with various joints and body-parts movement spatially. Hence, a cookie-cutter transformer is non-adaptable and can hardly meet the "in-the-wild" requirement. To mitigate this issue, we propose Hierarchical Spatial-Temporal transFormers (HSTFormer) to capture multi-level joints' spatial-temporal correlations from local to global gradually for accurate 3D HPE. HSTFormer consists of four transformer encoders (TEs) and a fusion module. To the best of our knowledge, HSTFormer is the first to study hierarchical TEs with multi-level fusion. Extensive experiments on three datasets (i.e., Human3.6M, MPI-INF-3DHP, and HumanEva) demonstrate that HSTFormer achieves competitive and consistent performance on benchmarks with various scales and difficulties. Specifically, it surpasses recent SOTAs on the challenging MPI-INF-3DHP dataset and small-scale HumanEva dataset, with a highly generalized systematic approach. The code is available at: https://github.com/qianxiaoye825/HSTFormer.

cs.CV↗

arXiv2021

Soft Sensing Model Visualization: Fine-tuning Neural Network from What Model Learned

The growing availability of the data collected from smart manufacturing is changing the paradigms of production monitoring and control. The increasing complexity and content of the wafer manufacturing process in addition to the time-varying unexpected disturbances and uncertainties, make it infeasible to do the control process with model-based approaches. As a result, data-driven soft-sensing modeling has become more prevalent in wafer process diagnostics. Recently, deep learning has been utilized in soft sensing system with promising performance on highly nonlinear and dynamic time-series data. Despite its successes in soft-sensing systems, however, the underlying logic of the deep learning framework is hard to understand. In this paper, we propose a deep learning-based model for defective wafer detection using a highly imbalanced dataset. To understand how the proposed model works, the deep visualization approach is applied. Additionally, the model is then fine-tuned guided by the deep visualization. Extensive experiments are performed to validate the effectiveness of the proposed system. The results provide an interpretation of how the model works and an instructive fine-tuning method based on the interpretation.

cs.LG↗