A distributed HAR framework in which five wearable sensors are associated with local embedded nodes that perform acquisition, windowing, preprocessing, and convolutional neural network–long short-term memory (CNN–LSTM) inference.
Abstract
Real-time multi-sensor human activity recognition (HAR) requires accurate models and a system architecture capable of distributing computation, exchanging compact outputs, and maintaining temporal consistency across asynchronous streams. This paper presents a distributed HAR framework in which five wearable sensors are associated with local embedded nodes that perform acquisition, windowing, preprocessing, and convolutional neural network–long short-term memory (CNN–LSTM) inference. Each node transmits a timestamped six-class softmax vector, and a central node applies approximate synchronization and learned probability-level fusion. The framework was evaluated with ten participants whose data were not used for model development. It achieved 95.868% accuracy and a 95.642% macro-F1-score. During continuous operation, the system sustained 47.949 predictions/s, with a mean post-window end-to-end latency of 33.963 ms and a mean synchronization span of 13.788 ms. Relative to complete-window transmission, the numerical payload decreased by 97.69%, and central-node energy per prediction decreased by 52.2% compared with centralized real-time processing. Under 30% independent probability-message loss, accuracy remained at 94.31%.
On-device Human Activity Recognition (HAR) requires balancing accuracy and deployment efficiency on constrained hardware. We present Lightweight Human Activity Recognition (L-HAR), a controlled comparison of Baseline and Lightweight Temporal Convolutional Network (TCN), Transformer, and Long Short-Term Memory (LSTM) models using data sampled at 100Hz from three inertial measurement units (IMUs) worn by one participant. Evaluations covered classification, model footprint, multiply–accumulate operations (MACs), offline CPU latency, Desktop/Raspberry Pi streaming, 8-bit integer (INT8) quantization, and software-estimated Raspberry Pi energy efficiency. Lightweighting reduced parameters by up to 95.5%, model size by 94.0%, and MACs by 87.6–95.5%, with accuracy reductions of 0.8–2.2 percentage points (pp) and sub-millisecond offline latency for all Lightweight models. Baseline and Lightweight models sustained approximately 100Hz message/inference rates on Desktop, whereas no Raspberry Pi configuration reached 100Hz inference. Among Lightweight models, Transformer achieved 9.381ms End-to-End (E2E) latency and 66.925Hz inference. INT8 quantization changed accuracy and F1-score by less than 0.13 pp; Quantized TCN achieved the best Raspberry Pi streaming result (9.066ms E2E; 69.928Hz) with an estimated 49.933mJ per inference. These results demonstrate architecture- and backend-dependent deployment behavior and the need for direct target-platform evaluation.
Unknown authors· Italian National Conference...· 0 citations
Wearable-based human activity recognition (HAR) has emerged as a valuable method for capturing activities across diverse domains, including rehabilitation, occupational ergonomics, sports, and human-computer interaction (HCI). While recognition performance can be significantly enhanced by leveraging multiple complementary sensors, this approach requires accurately synchronized time bases across all devices. Although previous studies on synchronization in HAR suggested that sub-second accuracy is advisable while sub-100 ms accuracy is unnecessary, the specific effect of time discrepancies on machine learning models has, so far, remained unexplored. We address this gap by introducing an experimental paradigm for systematically evaluating the impact of time discrepancies in multi-wearable HAR, which we evaluated in two experiments. In our first experiment, we use the example of multi-stage temporal convolutional networks (MS-TCN) for sequence-to-sequence action segmentation, simulating the time discrepancies of time offset and clock skew via rational resampling. Our evaluation spanned 30,025 training and validation runs across different model configurations, totaling over one million core-hours of computation. Our results reveal that time offsets larger than 167 ms should be avoided in training datasets, and offsets beyond 333 ms can already significantly degrade HAR performance for typical activities of daily living (ADLs). Subsequently, we performed a second experiment focusing on the impact of time offsets on inference in models trained on synchronized datasets. Our evaluation spanned temporal convolutional networks, LSTMs, and Transformer architectures across five architectural configurations, each with two different temporal input lengths. The results indicate that LSTMs for action segmentation are more robust to desynchronization, while other architectures exhibited a marked performance degradation beyond desynchronization offsets spanning 167 ms. Our findings have implications for the design and deployment of multi-wearable HAR systems and may extend to other multi-sensor contexts.
David Kostolani, Florian Wolling, S. Schlund et al.· Frontiers of Computer Scienc...· 0 citations
A deep learning–based HAR framework utilizing hip-mounted accelerometer and gyroscope signals from the USC-HAD dataset, which contains readings from healthy participants only, is evaluated, providing a more realistic assessment of subject-independent generalization across unseen individuals.
F. Naveed, Hamza Khan, Zaki Uddin et al.· Scientific Reports· 0 citations
Fall detection for wearable health monitoring must combine subject-independent accuracy, low false-alarm risk, real-time response, and multi-day battery operation. Deep learning can capture fall dynamics, but recurrent or long-window models often increase memory access, inference latency, and energy use on microcontroller-class devices. This paper introduces CNN-FIFO-LSTM, a compact TinyML architecture that decouples spatial and temporal processing for real-time fall detection. A convolutional neural network maps each four-channel inertial window to a 32-dimensional embedding, a first-in-first-out (FIFO) buffer stores recent embeddings, and a lightweight LSTM classifies the resulting temporal sequence. Applying recurrence to compressed embeddings rather than raw sensor windows preserves temporal context while reducing both the sequence-model input volume and computational resource use. On KFall, leave-one-subject-out (LOSO) validation achieves 98.85% accuracy, 97.04% precision, 98.95% recall, and a 97.98% F1-score. When trained on KFall and evaluated on SisFall, the model maintains 97.4% accuracy and a 96.7% F1-score. The selected floating-point ESP32-S3 deployment requires 227 KB for the models, 573 KB of firmware flash, and 132.3 KB of RAM, with 48.9 ms of model inference, 56.6 ms of the full cycle, and 5.3 days of estimated continuous operation from a 1000 mAh battery. A mixed-precision post-training quantization variant, using an int8 CNN and a float32 LSTM, reduces inference latency to 28.3 ms and extends estimated battery life to 7.8 days, with a modest reduction in F1-score to 97.67%. Together, these results show that CNN-FIFO-LSTM achieves a practical trade-off among detection performance, response time, and battery life in evaluations using public datasets and prototype hardware.
Duan Luong Cong, Cuong Chu Van, Anh Pham Hoang et al.· IEEE Access· 0 citations
Continuous human activity recognition (HAR) with distributed radar sensor networks is challenging because Doppler signatures depend strongly on aspect angle, the informativeness of individual radar views varies with motion direction, and activity transitions in uninterrupted sequences are often ambiguous. This paper proposes a ConvNeXt-MHSA-BiGRU framework for frame-wise continuous HAR from Doppler-time spectrograms acquired by five spatially distributed radar nodes. A shared ConvNeXt-inspired encoder extracts time-frequency representations from each radar stream, while radar-wise multi-head self attention (MHSA) models inter-node dependencies and adaptively fuses complementary views. RadarDropout and SpecAugment-style time-frequency masking regularize the network against unreliable radar views and local spectrogram perturbations, whereas stacked bidirectional gated recurrent units (BiGRUs) exploit temporal context for frame-wise classification across activity transitions. The framework is evaluated on nine activities performed by 14 participants using leave-one-person-out (L1PO) subject-independent testing with fivefold cross-validation. It achieves a mean L1PO test accuracy of 87.56% across the 14 held-out subjects and improves recognition performance over the published CNN-RNN baseline. The results demonstrate that combining modern spectrogram encoding, adaptive radar view fusion, and bidirectional temporal modeling provides an effective framework for continuous and distributed radar-based HAR.
Human Action Recognition (HAR) is becoming increasingly important in areas such as intelligent surveillance, healthcare monitoring, and facilitating human-computer interaction. However, most current techniques use RGB-based deep learning, which is computationally intensive and cannot run on low-resource edge devices. This study presents a lightweight, skeleton-based Human Action Recognition (HAR) framework. The framework utilizes MediaPipe pose estimation, spatiotemporal normalization, and LSTM-based temporal modeling to efficiently recognize kinetically distinct human movements on resource-limited Internet of Things (IoT) edge devices. It combines MediaPipe pose estimation with Long Short-Term Memory (LSTM) networks to model temporal motion efficiently in resource-constrained IoT edge computing environments. Twelve kinetically unique actions from the UCF50 dataset were rendered into skeletal representations by temporally interpolating and spatially normalizing the action sequences. The HAR framework achieved 85.14% classification accuracy, indicating that sufficient motion-related information can be inferred from skeletal topology, allowing for reliable recognition at a reduced computational cost. The results demonstrate a practical balance between efficiency and performance, positioning the framework as an effective tool for edge-oriented HAR applications. From an IoT perspective, the framework has the potential to support IoT-enabled smart surveillance, assisted living, and intelligent monitoring systems by making it suitable for connected cameras and edge devices for local action recognition, even with limited computing power and communication bandwidth. This makes it a promising candidate for deployment across diverse real-world environments while preserving privacy through skeleton-based representations.
Shubbar Salman Baqer Alkhafaji, Ali Abdulazeez Mohammed Baqer Qazzaz, Yousif Samer Mudhafar· Journal of Trends in Compute...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
