arXiv subjects

Paul Lukowicz

Publications and source records attributed to Paul Lukowicz.

At least 55 records · Page 3Linked to original sources

arXiv2025

DisQu: Investigating the Impact of Disorder in Quantum Generative Models

Disordered Quantum many-body Systems (DQS) and Quantum Neural Networks (QNN) have many structural features in common. However, a DQS is essentially an initialized QNN with random weights, often leading to non-random outcomes. In this work, we emphasize the possibilities of random processes being a deceptive quantum-generating model effectively hidden in a QNN. When we choose weights in a QNN randomly the unitarity property of quantum gates is unchanged. As we show, this can lead to memory effects with multiple consequences on the learnability and trainability of QNN one would not expect from a classical neural network with random weights. This phenomenon may lead to a fundamental misunderstanding of the capabilities of common quantum generative models, where the generation of new samples is essentially averaging over random outputs. While we suggest that DQS can be effectively used for tasks like image augmentation, we draw the attention that overly simple datasets are often used to show the generative capabilities of quantum models, potentially leading to overestimation of their effectiveness.

cond-mat.dis-nn↗

arXiv2025

MuJo: Multimodal Joint Feature Space Learning for Human Activity Recognition

Human activity recognition (HAR) is a long-standing problem in artificial intelligence with applications in a broad range of areas, including healthcare, sports and fitness, security, and more. The performance of HAR in real-world settings is strongly dependent on the type and quality of the input signal that can be acquired. Given an unobstructed, high-quality camera view of a scene, computer vision systems, in particular in conjunction with foundation models, can today fairly reliably distinguish complex activities. On the other hand, recognition using modalities such as wearable sensors (which are often more broadly available, e.g., in mobile phones and smartwatches) is a more difficult problem, as the signals often contain less information and labeled training data is more difficult to acquire. To alleviate the need for labeled data, we introduce our comprehensive Fitness Multimodal Activity Dataset (FiMAD) in this work, which can be used with the proposed pre-training method MuJo (Multimodal Joint Feature Space Learning) to enhance HAR performance across various modalities. FiMAD was created using YouTube fitness videos and contains parallel video, language, pose, and simulated IMU sensor data. MuJo utilizes this dataset to learn a joint feature space for these modalities. We show that classifiers pre-trained on FiMAD can increase the performance on real HAR datasets such as MM-Fit, MyoGym, MotionSense, and MHEALTH. For instance, on MM-Fit, we achieve a Macro F1-Score of up to 0.855 when fine-tuning on only 2% of the training data and 0.942 when utilizing the complete training set for classification tasks. We compare our approach with other self-supervised ones and show that, unlike them, ours consistently improves compared to the baseline network performance while also providing better data efficiency.

cs.LG↗

arXiv2025

Assessing the Impact of Sampling Irregularity in Time Series Data: Human Activity Recognition As A Case Study

Human activity recognition (HAR) ideally relies on data from wearable or environment-instrumented sensors sampled at regular intervals, enabling standard neural network models optimized for consistent time-series data as input. However, real-world sensor data often exhibits irregular sampling due to, for example, hardware constraints, power-saving measures, or communication delays, posing challenges for deployed static HAR models. This study assesses the impact of sampling irregularities on HAR by simulating irregular data through two methods: introducing slight inconsistencies in sampling intervals (timestamp variations) to mimic sensor jitter, and randomly removing data points (random dropout) to simulate missing values due to packet loss or sensor failure. We evaluate both discrete-time neural networks and continuous-time neural networks, which are designed to handle continuous-time data, on three public datasets. We demonstrate that timestamp variations do not significantly affect the performance of discrete-time neural networks, and the continuous-time neural network is also ineffective in addressing the challenges posed by irregular sampling, possibly due to limitations in modeling complex temporal patterns with missing data. Our findings underscore the necessity for new models or approaches that can robustly handle sampling irregularity in time-series data, like the reading in human activity recognition, paving the way for future research in this domain.

eess.SP↗

arXiv2025

Initial Findings on Sensor based Open Vocabulary Activity Recognition via Text Embedding Inversion

Conventional human activity recognition (HAR) relies on classifiers trained to predict discrete activity classes, inherently limiting recognition to activities explicitly present in the training set. Such classifiers would invariably fail, putting zero likelihood, when encountering unseen activities. We propose Open Vocabulary HAR (OV-HAR), a framework that overcomes this limitation by first converting each activity into natural language and breaking it into a sequence of elementary motions. This descriptive text is then encoded into a fixed-size embedding. The model is trained to regress this embedding, which is subsequently decoded back into natural language using a pre-trained embedding inversion model. Unlike other works that rely on auto-regressive large language models (LLMs) at their core, OV-HAR achieves open vocabulary recognition without the computational overhead of such models. The generated text can be transformed into a single activity class using LLM prompt engineering. We have evaluated our approach on different modalities, including vision (pose), IMU, and pressure sensors, demonstrating robust generalization across unseen activities and modalities, offering a fundamentally different paradigm from contemporary classifiers.

cs.AI↗

arXiv2025

Collaborative Human Activity Recognition with Passive Inter-Body Electrostatic Field

The passive body-area electrostatic field has recently been aspiringly explored for wearable motion sensing, harnessing its two thrilling characteristics: full-body motion sensitivity and environmental sensitivity, which potentially empowers human activity recognition both independently and jointly from a single sensing front-end and theoretically brings significant competition against traditional inertial sensor that is incapable in environmental variations sensing. While most works focus on exploring the electrostatic field of a single body as the target, this work, for the first time, quantitatively evaluates the mutual effect of inter-body electrostatic fields and its contribution to collaborative activity recognition. A wearable electrostatic field sensing front-end and wrist-worn prototypes are built, and a sixteen-hour, manually annotated dataset is collected, involving an experiment of manipulating objects both independently and collaboratively. A regression model is finally used to recognize the collaborative activities among users. Despite the theoretical advantages of the body electrostatic field, the recognition of both single and collaborative activities shows unanticipated less-competitive recognition performance compared with the accelerometer. However, It is worth mentioning that this novel sensing modality improves the recognition F-score of user collaboration by 16\% in the fusion result of the two wearable motion sensing modalities, demonstrating the potential of bringing body electrostatic field as a complementary power-efficient signal for collaborative activity tracking using wearables.

eess.SY↗

arXiv2025

Quantum-inspired Embeddings Projection and Similarity Metrics for Representation Learning

Over the last decade, representation learning, which embeds complex information extracted from large amounts of data into dense vector spaces, has emerged as a key technique in machine learning. Among other applications, it has been a key building block for large language models and advanced computer vision systems based on contrastive learning. A core component of representation learning systems is the projection head, which maps the original embeddings into different, often compressed spaces, while preserving the similarity relationship between vectors. In this paper, we propose a quantum-inspired projection head that includes a corresponding quantum-inspired similarity metric. Specifically, we map classical embeddings onto quantum states in Hilbert space and introduce a quantum circuit-based projection head to reduce embedding dimensionality. To evaluate the effectiveness of this approach, we extended the BERT language model by integrating our projection head for embedding compression. We compared the performance of embeddings, which were compressed using our quantum-inspired projection head, with those compressed using a classical projection head on information retrieval tasks using the TREC 2019 and TREC 2020 Deep Learning benchmarks. The results demonstrate that our quantum-inspired method achieves competitive performance relative to the classical method while utilizing 32 times fewer parameters. Furthermore, when trained from scratch, it notably excels, particularly on smaller datasets. This work not only highlights the effectiveness of the quantum-inspired approach but also emphasizes the utility of efficient, ad hoc low-entanglement circuit simulations within neural networks as a powerful quantum-inspired technique.

cs.CL↗

arXiv2025

Past, Present, and Future of Sensor-Based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task

In the many years since the inception of wearable sensor-based Human Activity Recognition (HAR), a wide variety of methods have been introduced and evaluated for their ability to recognize activities. Substantial gains have been made since the days of hand-crafting heuristics as features, yet, progress has seemingly stalled on many popular benchmarks, with performance falling short of what may be considered 'sufficient'-- despite the increase in computational power and scale of sensor data, as well as rising complexity in techniques being employed. The HAR community approaches a new paradigm shift, this time incorporating world knowledge from foundational models. In this paper, we take stock of sensor-based HAR -- surveying it from its beginnings to the current state of the field, and charting its future. This is accompanied by a hands-on tutorial, through which we guide practitioners in developing HAR systems for real-world application scenarios. We provide a compendium for novices and experts alike, of methods that aim at finally solving the activity recognition problem.

eess.SP↗

arXiv2024

OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models

Understanding human-to-human interactions, especially in contexts like public security surveillance, is critical for monitoring and maintaining safety. Traditional activity recognition systems are limited by fixed vocabularies, predefined labels, and rigid interaction categories that often rely on choreographed videos and overlook concurrent interactive groups. These limitations make such systems less adaptable to real-world scenarios, where interactions are diverse and unpredictable. In this paper, we propose an open vocabulary human-to-human interaction recognition (OV-HHIR) framework that leverages large language models to generate open-ended textual descriptions of both seen and unseen human interactions in open-world settings without being confined to a fixed vocabulary. Additionally, we create a comprehensive, large-scale human-to-human interaction dataset by standardizing and combining existing public human interaction datasets into a unified benchmark. Extensive experiments demonstrate that our method outperforms traditional fixed-vocabulary classification systems and existing cross-modal language models for video understanding, setting the stage for more intelligent and adaptable visual understanding systems in surveillance and beyond.

cs.CV↗

arXiv2024

LLMs Enable Context-Aware Augmented Reality in Surgical Navigation

Wearable Augmented Reality (AR) technologies are gaining recognition for their potential to transform surgical navigation systems. As these technologies evolve, selecting the right interaction method to control the system becomes crucial. Our work introduces a voice-controlled user interface (VCUI) for surgical AR assistance systems (ARAS), designed for pancreatic surgery, that integrates Large Language Models (LLMs). Employing a mixed-method research approach, we assessed the usability of our LLM-based design in both simulated surgical tasks and during pancreatic surgeries, comparing its performance against conventional VCUI for surgical ARAS using speech commands. Our findings demonstrated the usability of our proposed LLM-based VCUI, yielding a significantly lower task completion time and cognitive workload compared to speech commands. Additionally, qualitative insights from interviews with surgeons aligned with the quantitative data, revealing a strong preference for the LLM-based VCUI. Surgeons emphasized its intuitiveness and highlighted the potential of LLM-based VCUI in expediting decision-making in surgical environments.

cs.HC↗

arXiv2024

Beyond Confusion: A Fine-grained Dialectical Examination of Human Activity Recognition Benchmark Datasets

The research of machine learning (ML) algorithms for human activity recognition (HAR) has made significant progress with publicly available datasets. However, most research prioritizes statistical metrics over examining negative sample details. While recent models like transformers have been applied to HAR datasets with limited success from the benchmark metrics, their counterparts have effectively solved problems on similar levels with near 100% accuracy. This raises questions about the limitations of current approaches. This paper aims to address these open questions by conducting a fine-grained inspection of six popular HAR benchmark datasets. We identified for some parts of the data, none of the six chosen state-of-the-art ML methods can correctly classify, denoted as the intersect of false classifications (IFC). Analysis of the IFC reveals several underlying problems, including ambiguous annotations, irregularities during recording execution, and misaligned transition periods. We contribute to the field by quantifying and characterizing annotated data ambiguities, providing a trinary categorization mask for dataset patching, and stressing potential improvements for future data collections.

cs.LG↗

arXiv2024

Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition

Human Activity Recognition using time-series data from wearable sensors poses unique challenges due to complex temporal dependencies, sensor noise, placement variability, and diverse human behaviors. These factors, combined with the nontransparent nature of black-box Machine Learning models impede interpretability and hinder human comprehension of model behavior. This paper addresses these challenges by exploring strategies to enhance interpretability through white-box approaches, which provide actionable insights into latent space dynamics and model behavior during training. By leveraging human intuition and expertise, the proposed framework improves explainability, fosters trust, and promotes transparent Human Activity Recognition systems. A key contribution is the proposal of a Human-in-the-Loop framework that enables dynamic user interaction with models, facilitating iterative refinements to enhance performance and efficiency. Additionally, we investigate the usefulness of Large Language Model as an assistance to provide users with guidance for interpreting visualizations, diagnosing issues, and optimizing workflows. Together, these contributions present a scalable and efficient framework for developing interpretable and accessible Human Activity Recognition systems.

cs.HC↗

arXiv2024

Enhancing Interpretability Through Loss-Defined Classification Objective in Structured Latent Spaces

Supervised machine learning often operates on the data-driven paradigm, wherein internal model parameters are autonomously optimized to converge predicted outputs with the ground truth, devoid of explicitly programming rules or a priori assumptions. Although data-driven methods have yielded notable successes across various benchmark datasets, they inherently treat models as opaque entities, thereby limiting their interpretability and yielding a lack of explanatory insights into their decision-making processes. In this work, we introduce Latent Boost, a novel approach that integrates advanced distance metric learning into supervised classification tasks, enhancing both interpretability and training efficiency. Thus during training, the model is not only optimized for classification metrics of the discrete data points but also adheres to the rule that the collective representation zones of each class should be sharply clustered. By leveraging the rich structural insights of intermediate model layer latent representations, Latent Boost improves classification interpretability, as demonstrated by higher Silhouette scores, while accelerating training convergence. These performance and latent structural benefits are achieved with minimum additional cost, making it broadly applicable across various datasets without requiring data-specific adjustments. Furthermore, Latent Boost introduces a new paradigm for aligning classification performance with improved model transparency to address the challenges of black-box models.

cs.LG↗

arXiv2024

Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization

A fundamental step in the development of machine learning models commonly involves the tuning of hyperparameters, often leading to multiple model training runs to work out the best-performing configuration. As machine learning tasks and models grow in complexity, there is an escalating need for solutions that not only improve performance but also address sustainability concerns. Existing strategies predominantly focus on maximizing the performance of the model without considering energy efficiency. To bridge this gap, in this paper, we introduce Spend More to Save More (SM2), an energy-aware hyperparameter optimization implementation based on the widely adopted successive halving algorithm. Unlike conventional approaches including energy-intensive testing of individual hyperparameter configurations, SM2 employs exploratory pretraining to identify inefficient configurations with minimal energy expenditure. Incorporating hardware characteristics and real-time energy consumption tracking, SM2 identifies an optimal configuration that not only maximizes the performance of the model but also enables energy-efficient training. Experimental validations across various datasets, models, and hardware setups confirm the efficacy of SM2 to prevent the waste of energy during the training of hyperparameter configurations.

cs.LG↗

arXiv2024

CoSS: Co-optimizing Sensor and Sampling Rate for Data-Efficient AI in Human Activity Recognition

Recent advancements in Artificial Neural Networks have significantly improved human activity recognition using multiple time-series sensors. While employing numerous sensors with high-frequency sampling rates usually improves the results, it often leads to data inefficiency and unnecessary expansion of the ANN, posing a challenge for their practical deployment on edge devices. Addressing these issues, our work introduces a pragmatic framework for data-efficient utilization in HAR tasks, considering the optimization of both sensor modalities and sampling rate simultaneously. Central to our approach are the designed trainable parameters, termed 'Weight Scores,' which assess the significance of each sensor modality and sampling rate during the training phase. These scores guide the sensor modalities and sampling rate selection. The pruning method allows users to make a trade-off between computational budgets and performance by selecting the sensor modalities and sampling rates according to the weight score ranking. We tested our framework's effectiveness in optimizing sensor modality and sampling rate selection using three public HAR benchmark datasets. The results show that the sensor and sampling rate combination selected via CoSS achieves similar classification performance to configurations using the highest sampling rate with all sensors but at a reduced hardware cost.

eess.SP↗

arXiv2024

The Power of Training: How Different Neural Network Setups Influence the Energy Demand

This work offers a heuristic evaluation of the effects of variations in machine learning training regimes and learning paradigms on the energy consumption of computing, especially HPC hardware with a life-cycle aware perspective. While increasing data availability and innovation in high-performance hardware fuels the training of sophisticated models, it also fosters the fading perception of energy consumption and carbon emission. Therefore, the goal of this work is to raise awareness about the energy impact of general training parameters and processes, from learning rate over batch size to knowledge transfer. Multiple setups with different hyperparameter configurations are evaluated on three different hardware systems. Among many results, we have found out that even with the same model and hardware to reach the same accuracy, improperly set training hyperparameters consume up to 5 times the energy of the optimal setup. We also extensively examined the energy-saving benefits of learning paradigms including recycling knowledge through pretraining and sharing knowledge through multitask training.

cs.LG↗

arXiv2024

Towards certifiable AI in aviation: landscape, challenges, and opportunities

Artificial Intelligence (AI) methods are powerful tools for various domains, including critical fields such as avionics, where certification is required to achieve and maintain an acceptable level of safety. General solutions for safety-critical systems must address three main questions: Is it suitable? What drives the system's decisions? Is it robust to errors/attacks? This is more complex in AI than in traditional methods. In this context, this paper presents a comprehensive mind map of formal AI certification in avionics. It highlights the challenges of certifying AI development with an example to emphasize the need for qualification beyond performance metrics.

cs.LG↗

arXiv2024

A Wearable Multi-Modal Edge-Computing System for Real-Time Kitchen Activity Recognition

In the human activity recognition research area, prior studies predominantly concentrate on leveraging advanced algorithms on public datasets to enhance recognition performance, little attention has been paid to executing real-time kitchen activity recognition on energy-efficient, cost-effective edge devices. Besides, the prevalent approach of segregating data collection and context extraction across different devices escalates power usage, latency, and user privacy risks, impeding widespread adoption. This work presents a multi-modal wearable edge computing system for human activity recognition in real-time. Integrating six different sensors, ranging from inertial measurement units (IMUs) to thermal cameras, and two different microcontrollers, this system achieves end-to-end activity recognition, from data capture to context extraction, locally. Evaluation in an unmodified realistic kitchen validates its efficacy in recognizing fifteen activities, including a null class. Employing a compact machine learning model (184.5 kbytes) yields an average accuracy of 87.83 \%, with model inference completed in 25.26 ms on the microcontroller. Comparative analysis with alternative microcontrollers showcases power consumption and inference speed performance, demonstrating the proposed system's viability.

eess.SP↗

arXiv2024

TSAK: Two-Stage Semantic-Aware Knowledge Distillation for Efficient Wearable Modality and Model Optimization in Manufacturing Lines

Smaller machine learning models, with less complex architectures and sensor inputs, can benefit wearable sensor-based human activity recognition (HAR) systems in many ways, from complexity and cost to battery life. In the specific case of smart factories, optimizing human-robot collaboration hinges on the implementation of cutting-edge, human-centric AI systems. To this end, workers' activity recognition enables accurate quantification of performance metrics, improving efficiency holistically. We present a two-stage semantic-aware knowledge distillation (KD) approach, TSAK, for efficient, privacy-aware, and wearable HAR in manufacturing lines, which reduces the input sensor modalities as well as the machine learning model size, while reaching similar recognition performance as a larger multi-modal and multi-positional teacher model. The first stage incorporates a teacher classifier model encoding attention, causal, and combined representations. The second stage encompasses a semantic classifier merging the three representations from the first stage. To evaluate TSAK, we recorded a multi-modal dataset at a smart factory testbed with wearable and privacy-aware sensors (IMU and capacitive) located on both workers' hands. In addition, we evaluated our approach on OpenPack, the only available open dataset mimicking the wearable sensor placements on both hands in the manufacturing HAR scenario. We compared several KD strategies with different representations to regulate the training process of a smaller student model. Compared to the larger teacher model, the student model takes fewer sensor channels from a single hand, has 79% fewer parameters, runs 8.88 times faster, and requires 96.6% less computing power (FLOPS).

cs.LG↗