Selected work

Representative Papers

A Low-Cost IoT Device for Environmental Monitoring and Embedded Solar Forecasting with On-Device Incremental Learning

Aug 09, 2026

This study addresses the high cost and limited spatial resolution of professional weather stations for hyper-local solar forecasting by developing a low-cost IoT device integrated with embedded neural networks. We propose a hybrid architecture that decouples training from inference, enabling on-device incremental gradient descent and autonomous model adaptation on ESP32 microcontrollers without cloud dependency. Field deployment achieved zero data loss, yielding an R² of 0.9165 and a Mean Absolute Error of 4.65%, significantly outperforming climatological baselines. This work validates the efficacy of edge incremental learning in resource-constrained environments, providing a high-accuracy, cost-effective solution for distributed solar energy prediction.

0 citationsRead paper

Delay Attacks on the German Smart Metering Infrastructure: A Security Analysis of CLS Channel Timing Constraints

Aug 04, 2026

This study addresses the risk of delay attacks targeting the Controllable Local System (CLS) channel within Germany’s smart metering infrastructure. By integrating threat modeling, network experimentation, and protocol analysis, it quantifies—for the first time—the theoretical upper bound of such attacks at approximately 48 hours and demonstrates their potential to destabilize grid frequency and trigger large-scale load shedding. The work proposes a TLS 1.3–compatible, protocol-level extension enforcing temporal constraints and validates the practical feasibility of these attacks through real-world smart meter gateway configurations. Findings indicate that combining vendor-specific implementation refinements with protocol enhancements can effectively mitigate the identified risks, while also cautioning that ongoing standardization efforts may inadvertently lower the barrier to launching such attacks.

0 citationsRead paper

Representing and Detecting Label Ambiguity in IMU-Based Exercise Evaluation

Jul 06, 2026

This work addresses a key limitation in traditional IMU-based movement assessment methods, which rely on one-hot labels and thereby ignore the inherent ambiguity in class boundaries across repeated actions—failing to capture the reasonable disagreement often observed among human raters. To overcome this, the authors propose a method that automatically generates label distributions without requiring extensive manual scoring, leveraging KL divergence to jointly optimize a deep network for both high-accuracy classification and detection of ambiguous samples. Evaluated on four IMU datasets, the approach matches or surpasses cross-entropy baselines in classification performance while reliably identifying ambiguous instances and their associated classes. This represents the first effective modeling and utilization of label ambiguity in IMU-based movement evaluation.

0 citationsRead paper

Sawtooth Sampling for Time Series Denoising Diffusion Implicit Models

Nov 26, 2025

To address the low sampling efficiency and high computational cost of diffusion models in time-series synthesis, this paper proposes a general-purpose acceleration framework based on implicit diffusion modeling. We introduce a novel Sawtooth sampler that accelerates the denoising process without modifying pre-trained models. The sampler employs non-uniform step-size scheduling and gradient-guided trajectory optimization to reduce the number of iterations while preserving generation fidelity. Evaluated on standard time-series benchmarks, our method achieves an average 30× speedup over vanilla DDPM, with generated samples exhibiting superior statistical similarity and higher downstream classification accuracy compared to both DDPM and state-of-the-art acceleration baselines. Our key contribution lies in the first integration of implicit diffusion with structured sampling strategies—achieving a favorable trade-off among inference efficiency, sample quality, and model-agnostic applicability.

0 citationsRead paper

GAITEX: Human motion dataset of impaired gait and rehabilitation exercises using inertial and optical sensors

Jun 06, 2025

High-quality, multimodal motion data are critically needed for physical therapy and gait analysis, yet existing datasets suffer from high acquisition costs and poor generalizability. To address this, we introduce the first open-source, multimodal dataset specifically designed for rehabilitation assessment. It comprises synchronized inertial measurement unit (IMU) data (9 channels) and optical motion capture data (68 markers) from 19 participants performing 12 standardized rehabilitation and gait tasks. Our key contributions include: (i) millisecond-level temporal synchronization between IMU and optical data; (ii) IMU orientation calibration within a standardized anatomical coordinate system; (iii) subject-specific OpenSim model–driven inverse kinematics outputs; and (iv) comprehensive temporal annotations and clinical expert ratings for all movements. We publicly release preprocessing code, validation tools, and an interactive visualization platform. This resource significantly enhances reproducibility and generalizability in movement quality assessment, temporal segmentation, and biomechanical modeling.

0 citationsRead paper

Recent publications

Latest Papers

A Low-Cost IoT Device for Environmental Monitoring and Embedded Solar Forecasting with On-Device Incremental Learning

Aug 09, 2026

This study addresses the high cost and limited spatial resolution of professional weather stations for hyper-local solar forecasting by developing a low-cost IoT device integrated with embedded neural networks. We propose a hybrid architecture that decouples training from inference, enabling on-device incremental gradient descent and autonomous model adaptation on ESP32 microcontrollers without cloud dependency. Field deployment achieved zero data loss, yielding an R² of 0.9165 and a Mean Absolute Error of 4.65%, significantly outperforming climatological baselines. This work validates the efficacy of edge incremental learning in resource-constrained environments, providing a high-accuracy, cost-effective solution for distributed solar energy prediction.

0 citationsRead paper

Delay Attacks on the German Smart Metering Infrastructure: A Security Analysis of CLS Channel Timing Constraints

Aug 04, 2026

This study addresses the risk of delay attacks targeting the Controllable Local System (CLS) channel within Germany’s smart metering infrastructure. By integrating threat modeling, network experimentation, and protocol analysis, it quantifies—for the first time—the theoretical upper bound of such attacks at approximately 48 hours and demonstrates their potential to destabilize grid frequency and trigger large-scale load shedding. The work proposes a TLS 1.3–compatible, protocol-level extension enforcing temporal constraints and validates the practical feasibility of these attacks through real-world smart meter gateway configurations. Findings indicate that combining vendor-specific implementation refinements with protocol enhancements can effectively mitigate the identified risks, while also cautioning that ongoing standardization efforts may inadvertently lower the barrier to launching such attacks.

0 citationsRead paper

Representing and Detecting Label Ambiguity in IMU-Based Exercise Evaluation

Jul 06, 2026

This work addresses a key limitation in traditional IMU-based movement assessment methods, which rely on one-hot labels and thereby ignore the inherent ambiguity in class boundaries across repeated actions—failing to capture the reasonable disagreement often observed among human raters. To overcome this, the authors propose a method that automatically generates label distributions without requiring extensive manual scoring, leveraging KL divergence to jointly optimize a deep network for both high-accuracy classification and detection of ambiguous samples. Evaluated on four IMU datasets, the approach matches or surpasses cross-entropy baselines in classification performance while reliably identifying ambiguous instances and their associated classes. This represents the first effective modeling and utilization of label ambiguity in IMU-based movement evaluation.

0 citationsRead paper

Sawtooth Sampling for Time Series Denoising Diffusion Implicit Models

Nov 26, 2025

To address the low sampling efficiency and high computational cost of diffusion models in time-series synthesis, this paper proposes a general-purpose acceleration framework based on implicit diffusion modeling. We introduce a novel Sawtooth sampler that accelerates the denoising process without modifying pre-trained models. The sampler employs non-uniform step-size scheduling and gradient-guided trajectory optimization to reduce the number of iterations while preserving generation fidelity. Evaluated on standard time-series benchmarks, our method achieves an average 30× speedup over vanilla DDPM, with generated samples exhibiting superior statistical similarity and higher downstream classification accuracy compared to both DDPM and state-of-the-art acceleration baselines. Our key contribution lies in the first integration of implicit diffusion with structured sampling strategies—achieving a favorable trade-off among inference efficiency, sample quality, and model-agnostic applicability.

0 citationsRead paper

GAITEX: Human motion dataset of impaired gait and rehabilitation exercises using inertial and optical sensors

Jun 06, 2025

High-quality, multimodal motion data are critically needed for physical therapy and gait analysis, yet existing datasets suffer from high acquisition costs and poor generalizability. To address this, we introduce the first open-source, multimodal dataset specifically designed for rehabilitation assessment. It comprises synchronized inertial measurement unit (IMU) data (9 channels) and optical motion capture data (68 markers) from 19 participants performing 12 standardized rehabilitation and gait tasks. Our key contributions include: (i) millisecond-level temporal synchronization between IMU and optical data; (ii) IMU orientation calibration within a standardized anatomical coordinate system; (iii) subject-specific OpenSim model–driven inverse kinematics outputs; and (iv) comprehensive temporal annotations and clinical expert ratings for all movements. We publicly release preprocessing code, validation tools, and an interactive visualization platform. This resource significantly enhances reproducibility and generalizability in movement quality assessment, temporal segmentation, and biomechanical modeling.

0 citationsRead paper