3 citations · 13 across the 23 of their papers we have counts for
24 papers
KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition
Mengxi Liu, Sizhen Bian, Vitor Fortes +5
Kolmogorov-Arnold Networks (KANs) have demonstrated an exceptional ability to learn complex functions on clean, low-dimensional data but struggle to maintain performance on noisy a…
ActivityNarrated: An Open-Ended Narrative Paradigm for Wearable Human Activity Understanding
Lala Shakti Swarup Ray, Mengxi Liu, Alcina Pinto +4
Wearable human activity recognition (HAR) has made steady progress, yet much of this progress remains grounded in fixed-window, closed-set classification benchmarks. This formulati…
This Is Taking Too Long -- Investigating Time as a Proxy for Energy Consumption of LLMs
Lars Krupp, Daniel Geißler, Francisco M. Calatrava-Nicolas +3
The energy consumption of Large Language Models (LLMs) is raising growing concerns due to their adverse effects on environmental stability and resource use. Yet, these energy costs…
Promoting Sustainable Web Agents: Benchmarking and Estimating Energy Consumption through Empirical and Theoretical Analysis
Lars Krupp, Daniel Geißler, Vishal Banwari +2
Web agents, like OpenAI's Operator and Google's Project Mariner, are powerful agentic systems pushing the boundaries of Large Language Models (LLM). They can autonomously interact…
TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices
Sizhen Bian, Mengxi Liu, Vitor Fortes Rey +2
Human Activity Recognition (HAR) on resource-constrained wearable devices demands inference models that harmonize accuracy with computational efficiency. This paper introduces Tini…
iBreath: Usage Of Breathing Gestures as Means of Interactions
Mengxi Liu, Daniel Geißler, Deepika Gurung +5
Breathing is a spontaneous but controllable body function that can be used for hands-free interaction. Our work introduces "iBreath", a novel system to detect breathing gestures si…
Human in the Latent Loop (HILL): Interactively Guiding Model Training Through Human Intuition
Daniel Geissler, Lars Krupp, Vishal Banwari +4
Latent space representations are critical for understanding and improving the behavior of machine learning models, yet they often remain obscure and intricate. Understanding and ex…
Talk2X -- An Open-Source Toolkit Facilitating Deployment of LLM-Powered Chatbots on the Web
Lars Krupp, Daniel Geißler, Peter Hevesi +3
Integrated into websites, LLM-powered chatbots offer alternative means of navigation and information retrieval, leading to a shift in how users access information on the web. Yet,…
Towards Sustainable Web Agents: A Plea for Transparency and Dedicated Metrics for Energy Consumption
Lars Krupp, Daniel Geißler, Paul Lukowicz +1
Improvements in the area of large language models have shifted towards the construction of models capable of using external tools and interpreting their outputs. These so-called we…
Assessing the Impact of Sampling Irregularity in Time Series Data: Human Activity Recognition As A Case Study
Mengxi Liu, Daniel Geißler, Sizhen Bian +2
Human activity recognition (HAR) ideally relies on data from wearable or environment-instrumented sensors sampled at regular intervals, enabling standard neural network models opti…
Beyond Confusion: A Fine-grained Dialectical Examination of Human Activity Recognition Benchmark Datasets
Daniel Geissler, Dominique Nshimyimana, Vitor Fortes Rey +3
The research of machine learning (ML) algorithms for human activity recognition (HAR) has made significant progress with publicly available datasets. However, most research priorit…
Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization
Daniel Geissler, Bo Zhou, Sungho Suh +1
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…
Enhancing Interpretability Through Loss-Defined Classification Objective in Structured Latent Spaces
Daniel Geissler, Bo Zhou, Mengxi Liu +1
Supervised machine learning often operates on the data-driven paradigm, wherein internal model parameters are autonomously optimized to converge predicted outputs with the ground t…
Strategies and Challenges of Efficient White-Box Training for Human Activity Recognition
Daniel Geissler, Bo Zhou, Paul Lukowicz
Human Activity Recognition using time-series data from wearable sensors poses unique challenges due to complex temporal dependencies, sensor noise, placement variability, and diver…
Towards certifiable AI in aviation: landscape, challenges, and opportunities
Hymalai Bello, Daniel Geißler, Lala Ray +6
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…
TSAK: Two-Stage Semantic-Aware Knowledge Distillation for Efficient Wearable Modality and Model Optimization in Manufacturing Lines
Hymalai Bello, Daniel Geißler, Sungho Suh +2
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 co…
ALS-HAR: Harnessing Wearable Ambient Light Sensors to Enhance IMU-based Human Activity Recogntion
Lala Shakti Swarup Ray, Daniel Geißler, Mengxi Liu +3
Despite the widespread integration of ambient light sensors (ALS) in smart devices commonly used for screen brightness adaptation, their application in human activity recognition (…
Misinforming LLMs: vulnerabilities, challenges and opportunities
Bo Zhou, Daniel Geißler, Paul Lukowicz
Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. Despite exhibiting coherent ans…
Leveraging Hybrid Intelligence Towards Sustainable and Energy-Efficient Machine Learning
Daniel Geissler, Paul Lukowicz
Hybrid intelligence aims to enhance decision-making, problem-solving, and overall system performance by combining the strengths of both, human cognitive abilities and artificial in…
Initial Investigation of Kolmogorov-Arnold Networks (KANs) as Feature Extractors for IMU Based Human Activity Recognition
Mengxi Liu, Daniel Geißler, Dominique Nshimyimana +3
In this work, we explore the use of a novel neural network architecture, the Kolmogorov-Arnold Networks (KANs) as feature extractors for sensor-based (specifically IMU) Human Activ…
CoSS: Co-optimizing Sensor and Sampling Rate for Data-Efficient AI in Human Activity Recognition
Mengxi Liu, Zimin Zhao, Daniel Geißler +3
Recent advancements in Artificial Neural Networks have significantly improved human activity recognition using multiple time-series sensors. While employing numerous sensors with h…
The Power of Training: How Different Neural Network Setups Influence the Energy Demand
Daniel Geißler, Bo Zhou, Mengxi Liu +2
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…
Origami Single-end Capacitive Sensing for Continuous Shape Estimation of Morphing Structures
Lala Shakti Swarup Ray, Daniel Geißler, Bo Zhou +2
In this work, we propose a novel single-end morphing capacitive sensing method for shape tracking, FxC, by combining Folding origami structures and Capacitive sensing to detect the…
CaptAinGlove: Capacitive and Inertial Fusion-Based Glove for Real-Time on Edge Hand Gesture Recognition for Drone Control
Hymalai Bello, Sungho Suh, Daniel Geißler +3
We present CaptAinGlove, a textile-based, low-power (1.15Watts), privacy-conscious, real-time on-the-edge (RTE) glove-based solution with a tiny memory footprint (2MB), designed to…