Federated Learning (FL) enables collaborative model training on decentralized data without exposing raw data. However, the evaluation phase in FL may leak sensitive information through shared performance metrics. In this paper, we propose a novel protocol that incorporates Zero-Knowledge Proofs (ZKPs) to enable privacy-preserving and verifiable evaluation for FL. Instead of revealing raw loss values, clients generate a succinct proof asserting that their local loss is below a predefined threshold. Our approach is implemented without reliance on external APIs, using self-contained modules for federated learning simulation, ZKP circuit design, and experimental evaluation on both the MNIST and Human Activity Recognition (HAR) datasets. We focus on a threshold-based proof for a simple Convolutional Neural Network (CNN) model (for MNIST) and a multi-layer perceptron (MLP) model (for HAR), and evaluate the approach in terms of computational overhead, communication cost, and verifiability.
Human Activity Recognition (HAR), which uses data from Inertial Measurement Unit (IMU) sensors, has many practical applications in healthcare and assisted living environments. However, its use in real-world scenarios has been limited by the lack of comprehensive IMU-based HAR datasets that cover a wide range of activities and the lack of transparency in existing HAR models. Zero-shot HAR (ZS-HAR) overcomes the data limitations, but current models struggle to explain their decisions, making them less transparent. This paper introduces a novel IMU-based ZS-HAR model called the Self-Explainable Zero-shot Human Activity Recognition Network (SEZ-HARN). It can recognize activities not encountered during training and provide skeleton videos to explain its decision-making process. We evaluate the effectiveness of the proposed SEZ-HARN on four benchmark datasets PAMAP2, DaLiAc, HTD-MHAD and MHealth and compare its performance against three state-of-the-art black-box ZS-HAR models. The experiment results demonstrate that SEZ-HARN produces realistic and understandable explanations while achieving competitive Zero-shot recognition accuracy. SEZ-HARN achieves a Zero-shot prediction accuracy within 3\% of the best-performing black-box model on PAMAP2 while maintaining comparable performance on the other three datasets.
The newly established IEEE 802.11bf Task Group aims to amend the WLAN standard to support advanced sensing applications such as human activity recognition (HAR). Although studies have demonstrated the potential of sub-7 GHz Wi-Fi Channel State Information (CSI) for HAR, no method currently performs reliably in real-world scenarios. This work tackles the poor generalization of Wi-Fi-based HAR by introducing an innovative approach to extracting and utilizing movement-related representations, which makes it robust to noise and static environmental properties. This is achieved by transforming CSI signals into the delay profile space and decomposing them into various Doppler velocities, which serve as informative projections of a mobile point's velocity from different unknown random angles. To mitigate the impact of this randomness, MORIC is introduced as a novel time series classification model based on random convolutional kernels, designed to be invariant to the random order and repetition of input representations, thereby enabling robust Wi-Fi CSI-based activity classification. Experimental results on the collected dataset demonstrate that the proposed method outperforms state-of-the-art approaches in terms of generalization accuracy for hand motion recognition, particularly for challenging gestures. Furthermore, incorporating a small number of calibration samples leads to a significant improvement in accuracy, enhancing the practicality of the method for real-world deployment.
Despite LiDAR (Light Detection and Ranging) being an effective privacy-preserving alternative to RGB cameras to perceive human activities, it remains largely underexplored in the context of multi-modal contrastive pre-training for human activity understanding (e.g., human activity recognition (HAR), retrieval, or person re-identification (RE-ID)). To close this gap, our work explores learning the correspondence between LiDAR point clouds, human skeleton poses, IMU data, and text in a joint embedding space. More specifically, we present DeSPITE, a Deep Skeleton-Pointcloud-IMU-Text Embedding model, which effectively learns a joint embedding space across these four modalities. At the heart of our empirical exploration, we have combined the existing LIPD and Babel datasets, which enabled us to synchronize data of all four modalities, allowing us to explore the learning of a new joint embedding space. Our experiments demonstrate novel human activity understanding tasks for point cloud sequences enabled through DeSPITE, including Skeleton<->Pointcloud<->IMU matching, retrieval, and temporal moment retrieval. Furthermore, we show that DeSPITE is an effective pre-training strategy for point cloud HAR through experiments in MSR-Action3D and HMPEAR.
A major obstacle in developing robust and generalizable smart home-based Human Activity Recognition (HAR) systems is the lack of large-scale, diverse labeled datasets. Variability in home layouts, sensor configurations, and user behavior adds further complexity, as individuals follow varied routines and perform activities in distinct ways. Building HAR systems that generalize well requires training data that captures the diversity across users and environments. To address these challenges, we introduce AgentSense, a virtual data generation pipeline where diverse personas are generated by leveraging Large Language Models. These personas are used to create daily routines, which are then decomposed into low-level action sequences. Subsequently, the actions are executed in a simulated home environment called VirtualHome that we extended with virtual ambient sensors capable of recording the agents activities as they unfold. Overall, AgentSense enables the generation of rich, virtual sensor datasets that represent a wide range of users and home settings. Across five benchmark HAR datasets, we show that leveraging our virtual sensor data substantially improves performance, particularly when real data are limited. Notably, models trained on a combination of virtual data and just a few days of real data achieve performance comparable to those trained on the entire real datasets. These results demonstrate and prove the potential of virtual data to address one of the most pressing challenges in ambient sensing, which is the distinct lack of large-scale, annotated datasets without requiring any manual data collection efforts.
Hyperdimensional Computing (HDC) is a brain-inspired computing paradigm that represents and manipulates information using high-dimensional vectors, called hypervectors (HV). Traditional HDC methods, while robust to noise and inherently parallel, rely on single-pass, non-parametric training and often suffer from low accuracy. To address this, recent approaches adopt iterative training of base and class HVs, typically accelerated on GPUs. Inference, however, remains lightweight and well-suited for real-time execution. Yet, efficient HDC inference has been studied almost exclusively on specialized hardware such as FPGAs and GPUs, with limited attention to general-purpose multi-core CPUs. To address this gap, we propose ScalableHD for scalable and high-throughput HDC inference on multi-core CPUs. ScalableHD employs a two-stage pipelined execution model, where each stage is parallelized across cores and processes chunks of base and class HVs. Intermediate results are streamed between stages using a producer-consumer mechanism, enabling on-the-fly consumption and improving cache locality. To maximize performance, ScalableHD integrates memory tiling and NUMA-aware worker-to-core binding. Further, it features two execution variants tailored for small and large batch sizes, each designed to exploit compute parallelism based on workload characteristics while mitigating the memory-bound compute pattern that limits HDC inference performance on modern multi-core CPUs. ScalableHD achieves up to 10x speedup in throughput (samples per second) over state-of-the-art baselines such as TorchHD, across a diverse set of tasks ranging from human activity recognition to image classification, while preserving task accuracy. Furthermore, ScalableHD exhibits robust scalability: increasing the number of cores yields near-proportional throughput improvements.
Human activity recognition (HAR) is often limited by the scarcity of labeled datasets due to the high cost and complexity of real-world data collection. To mitigate this, recent work has explored generating virtual inertial measurement unit (IMU) data via cross-modality transfer. While video-based and language-based pipelines have each shown promise, they differ in assumptions and computational cost. Moreover, their effectiveness relative to traditional sensor-level data augmentation remains unclear. In this paper, we present a direct comparison between these two virtual IMU generation approaches against classical data augmentation techniques. We construct a large-scale virtual IMU dataset spanning 100 diverse activities from Kinetics-400 and simulate sensor signals at 22 body locations. The three data generation strategies are evaluated on benchmark HAR datasets (UTD-MHAD, PAMAP2, HAD-AW) using four popular models. Results show that virtual IMU data significantly improves performance over real or augmented data alone, particularly under limited-data conditions. We offer practical guidance on choosing data generation strategies and highlight the distinct advantages and disadvantages of each approach.
After a few years of research in the field of through-the-wall radar (TWR) human activity recognition (HAR), I found that we seem to be stuck in the mindset of training on radar image data through neural network models. The earliest related works in this field based on template matching did not require a training process, and I believe they have never died. Because these methods possess a strong physical interpretability and are closer to the basis of theoretical signal processing research. In this paper, I would like to try to return to the original path by attempting to eschew neural networks to achieve the TWR HAR task and challenge to achieve intelligent recognition as neural network models. In detail, the range-time map and Doppler-time map of TWR are first generated. Then, the initial regions of the human target foreground and noise background on the maps are determined using corner detection method, and the micro-Doppler signature is segmented using the multiphase active contour model. The micro-Doppler segmentation feature is discretized into a two-dimensional point cloud. Finally, the topological similarity between the resulting point cloud and the point clouds of the template data is calculated using Mapper algorithm to obtain the recognition results. The effectiveness of the proposed method is demonstrated by numerical simulated and measured experiments. The open-source code of this work is released at: https://github.com/JoeyBGOfficial/Through-the-Wall-Radar-Human-Activity-Recognition-Without-Using-Neural-Networks.
This paper aims to develop an energy-efficient classifier for time-series data by introducing PatchEchoClassifier, a novel model that leverages a reservoir-based mechanism known as the Echo State Network (ESN). The model is designed for human activity recognition (HAR) using one-dimensional sensor signals and incorporates a tokenizer to extract patch-level representations. To train the model efficiently, we propose a knowledge distillation framework that transfers knowledge from a high-capacity MLP-Mixer teacher to the lightweight reservoir-based student model. Experimental evaluations on multiple HAR datasets demonstrate that our model achieves over 80 percent accuracy while significantly reducing computational cost. Notably, PatchEchoClassifier requires only about one-sixth of the floating point operations (FLOPS) compared to DeepConvLSTM, a widely used convolutional baseline. These results suggest that PatchEchoClassifier is a promising solution for real-time and energy-efficient human activity recognition in edge computing environments.
While prior work has shown that Federated Learning updates can leak sensitive information, label reconstruction attacks, which aim to recover input labels from shared gradients, have not yet been examined in the context of Human Activity Recognition (HAR). Given the sensitive nature of activity labels, this study evaluates the effectiveness of state-of-the-art gradient-based label leakage attacks on HAR benchmark datasets. Our findings show that the number of activity classes, sampling strategy, and class imbalance are critical factors influencing the extent of label leakage, with reconstruction accuracies reaching up to 90% on two benchmark datasets, even for trained models. Moreover, we find that Local Differential Privacy techniques such as gradient noise and clipping offer only limited protection, as certain attacks still reliably infer both majority and minority class labels. We conclude by offering practical recommendations for the privacy-aware deployment of federated HAR systems and identify open challenges for future research. Code to reproduce our experiments is publicly available via github.com/mariusbock/leakage_har.
Despite recognized limitations in modeling long-range temporal dependencies, Human Activity Recognition (HAR) has traditionally relied on a sliding window approach to segment labeled datasets. Deep learning models like the DeepConvLSTM typically classify each window independently, thereby restricting learnable temporal context to within-window information. To address this constraint, we propose DeepConvContext, a multi-scale time series classification framework for HAR. Drawing inspiration from the vision-based Temporal Action Localization community, DeepConvContext models both intra- and inter-window temporal patterns by processing sequences of time-ordered windows. Unlike recent HAR models that incorporate attention mechanisms, DeepConvContext relies solely on LSTMs -- with ablation studies demonstrating the superior performance of LSTMs over attention-based variants for modeling inertial sensor data. Across six widely-used HAR benchmarks, DeepConvContext achieves an average 10% improvement in F1-score over the classic DeepConvLSTM, with gains of up to 21%. Code to reproduce our experiments is publicly available via github.com/mariusbock/context_har.
Wearable human activity recognition has been shown to benefit from the inclusion of acoustic data, as the sounds around a person often contain valuable context. However, due to privacy concerns, it is usually not ethically feasible to record and save microphone data from the device, since the audio could, for instance, also contain private conversations. Rather, the data should be processed locally, which in turn requires processing power and consumes energy on the wearable device. One special use case of contextual information that can be utilized to augment special tasks in human activity recognition is water flow detection, which can, e.g., be used to aid wearable hand washing detection. We created a new label called tap water for the recently released HD-Epic data set, creating 717 hand-labeled annotations of tap water flow, based on existing annotations of the water class. We analyzed the relation of tap water and water in the dataset and additionally trained and evaluated two lightweight classifiers to evaluate the newly added label class, showing that the new class can be learned more easily.
Human Activity Recognition (HAR) with wearable sensors is challenged by limited interpretability, which significantly impacts cross-dataset generalization. To address this challenge, we propose Motion-Primitive Transformer (MoPFormer), a novel self-supervised framework that enhances interpretability by tokenizing inertial measurement unit signals into semantically meaningful motion primitives and leverages a Transformer architecture to learn rich temporal representations. MoPFormer comprises two-stages. first stage is to partition multi-channel sensor streams into short segments and quantizing them into discrete "motion primitive" codewords, while the second stage enriches those tokenized sequences through a context-aware embedding module and then processes them with a Transformer encoder. The proposed MoPFormer can be pre-trained using a masked motion-modeling objective that reconstructs missing primitives, enabling it to develop robust representations across diverse sensor configurations. Experiments on six HAR benchmarks demonstrate that MoPFormer not only outperforms state-of-the-art methods but also successfully generalizes across multiple datasets. Most importantly, the learned motion primitives significantly enhance both interpretability and cross-dataset performance by capturing fundamental movement patterns that remain consistent across similar activities regardless of dataset origin.
Human Activity Recognition (HAR) using wearable sensor data has become a central task in mobile computing, healthcare, and human-computer interaction. Despite the success of traditional deep learning models such as CNNs and RNNs, they often struggle to capture long-range temporal dependencies and contextual relevance across multiple sensor channels. To address these limitations, we propose SETransformer, a hybrid deep neural architecture that combines Transformer-based temporal modeling with channel-wise squeeze-and-excitation (SE) attention and a learnable temporal attention pooling mechanism. The model takes raw triaxial accelerometer data as input and leverages global self-attention to capture activity-specific motion dynamics over extended time windows, while adaptively emphasizing informative sensor channels and critical time steps. We evaluate SETransformer on the WISDM dataset and demonstrate that it significantly outperforms conventional models including LSTM, GRU, BiLSTM, and CNN baselines. The proposed model achieves a validation accuracy of 84.68\% and a macro F1-score of 84.64\%, surpassing all baseline architectures by a notable margin. Our results show that SETransformer is a competitive and interpretable solution for real-world HAR tasks, with strong potential for deployment in mobile and ubiquitous sensing applications.
In this paper, we propose a novel few-shot optimization with HED-LM (Hybrid Euclidean Distance with Large Language Models) to improve example selection for sensor-based classification tasks. While few-shot prompting enables efficient inference with limited labeled data, its performance largely depends on the quality of selected examples. HED-LM addresses this challenge through a hybrid selection pipeline that filters candidate examples based on Euclidean distance and re-ranks them using contextual relevance scored by large language models (LLMs). To validate its effectiveness, we apply HED-LM to a fatigue detection task using accelerometer data characterized by overlapping patterns and high inter-subject variability. Unlike simpler tasks such as activity recognition, fatigue detection demands more nuanced example selection due to subtle differences in physiological signals. Our experiments show that HED-LM achieves a mean macro F1-score of 69.13$\pm$10.71%, outperforming both random selection (59.30$\pm$10.13%) and distance-only filtering (67.61$\pm$11.39%). These represent relative improvements of 16.6% and 2.3%, respectively. The results confirm that combining numerical similarity with contextual relevance improves the robustness of few-shot prompting. Overall, HED-LM offers a practical solution to improve performance in real-world sensor-based learning tasks and shows potential for broader applications in healthcare monitoring, human activity recognition, and industrial safety scenarios.
This work develops the underpinnings of self-supervised placement-aware representation learning given spatially-distributed (multi-view and multimodal) sensor observations, motivated by the need to represent external environmental state in multi-sensor IoT systems in a manner that correctly distills spatial phenomena from the distributed multi-vantage observations. The objective of sensing in IoT systems is, in general, to collectively represent an externally observed environment given multiple vantage points from which sensory observations occur. Pretraining of models that help interpret sensor data must therefore encode the relation between signals observed by sensors and the observers' vantage points in order to attain a representation that encodes the observed spatial phenomena in a manner informed by the specific placement of the measuring instruments, while allowing arbitrary placement. The work significantly advances self-supervised model pretraining from IoT signals beyond current solutions that often overlook the distinctive spatial nature of IoT data. Our framework explicitly learns the dependencies between measurements and geometric observer layouts and structural characteristics, guided by a core design principle: the duality between signals and observer positions. We further provide theoretical analyses from the perspectives of information theory and occlusion-invariant representation learning to offer insight into the rationale behind our design. Experiments on three real-world datasets--covering vehicle monitoring, human activity recognition, and earthquake localization--demonstrate the superior generalizability and robustness of our method across diverse modalities, sensor placements, application-level inference tasks, and spatial scales.
By replacing standard non-linearities with polynomial activations, Polynomial Neural Networks (PNNs) are pivotal for applications such as privacy-preserving inference via Homomorphic Encryption (HE). However, training PNNs effectively presents a significant challenge: low-degree polynomials can limit model expressivity, while higher-degree polynomials, crucial for capturing complex functions, often suffer from numerical instability and gradient explosion. We introduce a robust and versatile training framework featuring two synergistic innovations: 1) a novel Boundary Loss that exponentially penalizes activation inputs outside a predefined stable range, and 2) Selective Gradient Clipping that effectively tames gradient magnitudes while preserving essential Batch Normalization statistics. We demonstrate our framework's broad efficacy by training PNNs within deep architectures composed of HE-compatible layers (e.g., linear layers, average pooling, batch normalization, as used in ResNet variants) across diverse image, audio, and human activity recognition datasets. These models consistently achieve high accuracy with low-degree polynomial activations (such as degree 2) and, critically, exhibit stable training and strong performance with polynomial degrees up to 22, where standard methods typically fail or suffer severe degradation. Furthermore, the performance of these PNNs achieves a remarkable parity, closely approaching that of their original ReLU-based counterparts. Extensive ablation studies validate the contributions of our techniques and guide hyperparameter selection. We confirm the HE-compatibility of the trained models, advancing the practical deployment of accurate, stable, and secure deep learning inference.
Denoising diffusion probabilistic models are able to generate synthetic sensor signals. The training process of such a model is controlled by a loss function which measures the difference between the noise that was added in the forward process and the noise that was predicted by the diffusion model. This enables the generation of realistic data. However, the randomness within the process and the loss function itself makes it difficult to estimate the quality of the data. Therefore, we examine multiple similarity metrics and adapt an existing metric to overcome this issue by monitoring the training and synthetisation process using those metrics. The adapted metric can even be fine-tuned on the input data to comply with the requirements of an underlying classification task. We were able to significantly reduce the amount of training epochs without a performance reduction in the classification task. An optimized training process not only saves resources, but also reduces the time for training generative models.
Many deep architectures and self-supervised pre-training techniques have been proposed for human activity recognition (HAR) from wearable multimodal sensors. Scaling laws have the potential to help move towards more principled design by linking model capacity with pre-training data volume. Yet, scaling laws have not been established for HAR to the same extent as in language and vision. By conducting an exhaustive grid search on both amount of pre-training data and Transformer architectures, we establish the first known scaling laws for HAR. We show that pre-training loss scales with a power law relationship to amount of data and parameter count and that increasing the number of users in a dataset results in a steeper improvement in performance than increasing data per user, indicating that diversity of pre-training data is important, which contrasts to some previously reported findings in self-supervised HAR. We show that these scaling laws translate to downstream performance improvements on three HAR benchmark datasets of postures, modes of locomotion and activities of daily living: UCI HAR and WISDM Phone and WISDM Watch. Finally, we suggest some previously published works should be revisited in light of these scaling laws with more adequate model capacities.
Federated Learning (FL) enables collaborative model training while preserving privacy by allowing clients to share model updates instead of raw data. Pervasive computing environments (e.g., for Human Activity Recognition, HAR), which we focus on in this paper, are characterized by resource-constrained end devices, streaming sensor data and intermittent client participation. Variations in user behavior, common in HAR environments, often result in non-stationary data distributions. As such, existing FL approaches face challenges in HAR settings due to differing assumptions. The combined effects of HAR characteristics, namely heterogeneous data and intermittent participation, can lead to a severe issue called catastrophic forgetting (CF). Unlike Continuous Learning (CL), which addresses CF using memory and replay mechanisms, FL's privacy constraints prohibit such strategies. To tackle CF in HAR environments, we propose FlexFed, a novel FL approach that prioritizes data retention for efficient memory use and dynamically adjusts offline training frequency based on distribution shifts, client capability and offline duration. To better quantify CF in FL, we introduce a new metric that accounts for under-represented data, enabling more accurate evaluations. We also develop a realistic HAR-based evaluation framework that simulates streaming data, dynamic distributions, imbalances and varying availability. Experiments show that FlexFed mitigates CF more effectively, improves FL efficiency by 10 to 15 % and achieves faster, more stable convergence, especially for infrequent or under-represented data.