Marc Langheinrich |

ERIS: Enhancing Privacy and Communication Efficiency in Serverless Federated Learning

Thu, 01 Jan 2026 00:00:00 +0000

Federated Concept-Based Models: Interpretable models with distributed supervision

Thu, 01 Jan 2026 00:00:00 +0000

Federated Learning with Energy-Based Structured Probabilistic Inference

Thu, 01 Jan 2026 00:00:00 +0000

Federated Learning with Profile Mapping under Distribution Shifts and Drifts

Thu, 01 Jan 2026 00:00:00 +0000

In-Context Symbolic Regression for Robustness-Improved Kolmogorov-Arnold Networks

Thu, 01 Jan 2026 00:00:00 +0000

Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation

Thu, 01 Jan 2026 00:00:00 +0000

Platform and Study Design for Adaptive EMA Using Smart Glasses to Monitor Affective States

Thu, 01 Jan 2026 00:00:00 +0000

The Power of 10: New Rules for the Digital World

Thu, 01 Jan 2026 00:00:00 +0000

LIFETRACE

Tue, 02 Dec 2025 00:00:00 +0000

Digital technologies and wearable devices have emerged as critical tools for developing personalized well-being/health interventions, closely supported by psychological experience sampling instruments. While existing public datasets often focus on clinical populations and controlled environments, this paper presents a comprehensive dataset integrating anthropometric and health measurements, in-the-wild longitudinal physical activity monitoring, environmental context data, socio-demographic factors, and standardized psychological well-being metrics. By monitoring relevant behavioral and health data, this dataset investigates those relevant determinants to form long-term physical activity habits. Over a 14-week period, we collected data from 88 participants. Of these, 59 followed a daily walking protocol during the first 7 weeks, with the remaining 29 participants serving as a control group, with no physical activity required. This paper presents an exploratory data analysis (EDA) to test the reliability and completeness of the collected data, together with a baseline machine learning model to assess the predictive power of included variables, relative to the well-being metrics. Moreover, by using the feature importance method, a preliminary explainability approach is applied to evaluate the soundness of predictions regarding feature contributions. Several applications are envisioned, including the impact of environmental conditions on behavior, exploring the contribution of each observed variable to habit formation, and providing a benchmark for future machine learning models in this field.

Data from \"LIFETRACE: A Longitudinal Multimodal Dataset on Daily Physical Activity, Well-Being, and Habits\" (Version 1)

Mon, 01 Dec 2025 00:00:00 +0000

Data from \"LIFETRACE: A Longitudinal Multimodal Dataset on Daily Physical Activity, Well-Being, and Habits\" (Version 1)

Mon, 01 Dec 2025 00:00:00 +0000

PhD position: XAI-FinCrime

Mon, 20 Jan 2025 00:00:00 +0000

The People-Centered Computing Lab is looking for a PhD student in machine learning and explainable AI applied to financial crime detection.

Source: .

Postdoc position: XAI-FinCrime

Mon, 20 Jan 2025 00:00:00 +0000

The People-Centered Computing Lab is looking for a postdoctoral researcher in machine learning and explainable AI for financial crime detection and prevention.

Source: .

A Review of Methods for Unobtrusive Measurement of Work-Related Well-Being

Wed, 01 Jan 2025 00:00:00 +0000

A Survey on Federated Learning in Human Sensing

Wed, 01 Jan 2025 00:00:00 +0000

Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning

Wed, 01 Jan 2025 00:00:00 +0000

Counterfactual Concept Bottleneck Models

Wed, 01 Jan 2025 00:00:00 +0000

FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts

Wed, 01 Jan 2025 00:00:00 +0000

LIFETRACE: A Longitudinal Multimodal Dataset on Daily Physical Activity, Well-Being, and Habits

Wed, 01 Jan 2025 00:00:00 +0000

Multi-Frequency Federated Learning for Human Activity Recognition Using Head-Worn Sensors

Wed, 01 Jan 2025 00:00:00 +0000

On the interplay of Explainability, Privacy and Predictive Performance with Explanation-assisted Model Extraction

Wed, 01 Jan 2025 00:00:00 +0000

On the Interplay of Explainability, Privacy and Predictive Performance with Explanation-assisted Model Extraction

Wed, 01 Jan 2025 00:00:00 +0000

Towards Transparent Reasoning: What Drives Faithfulness in Large Language Models?

Wed, 01 Jan 2025 00:00:00 +0000

AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Model

Mon, 01 Jan 2024 00:00:00 +0000

AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Model

Mon, 01 Jan 2024 00:00:00 +0000

Causal Concept Embedding Models: Beyond Causal Opacity in Deep Learning

Mon, 01 Jan 2024 00:00:00 +0000

Climbing the Ladder of Interpretability with Counterfactual Concept Bottleneck Models

Mon, 01 Jan 2024 00:00:00 +0000

Counterfactual Explanations for Clustering Models

Mon, 01 Jan 2024 00:00:00 +0000

Differential Privacy for Anomaly Detection: Analyzing the Trade-off Between Privacy and Explainability

Mon, 01 Jan 2024 00:00:00 +0000

Differential Privacy for Anomaly Detection: Analyzing the Trade-Off Between Privacy and Explainability

Mon, 01 Jan 2024 00:00:00 +0000

Evaluating Explanations Through LLMs: Beyond Traditional User Studies

Mon, 01 Jan 2024 00:00:00 +0000

Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning

Mon, 01 Jan 2024 00:00:00 +0000

Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning

Mon, 01 Jan 2024 00:00:00 +0000

FedMMA-HAR: Federated Learning for Human Activity Recognition With Missing Modalities Using Head-Worn Wearables

Mon, 01 Jan 2024 00:00:00 +0000

Generative Models for Counterfactual Explanations

Mon, 01 Jan 2024 00:00:00 +0000

How to Validate XAI in Longitudinal Studies?

Mon, 01 Jan 2024 00:00:00 +0000

Multi-Frequency Federated Learning for Human Activity Recognition Using Head-Worn Sensors

Mon, 01 Jan 2024 00:00:00 +0000

LAUREATE

Wed, 27 Sep 2023 00:00:00 +0000

The latest developments in wearable sensors have resulted in a wide range of devices available to consumers, allowing users to monitor and improve their physical activity, sleep patterns, cognitive load, and stress levels. However, the lack of out-of-the-lab labelled data hinders the development of advanced machine learning models for predicting affective states. Furthermore, to the best of our knowledge, there are no publicly available datasets in the area of Human Memory Augmentation. This paper presents a dataset we collected during a 13-week study in a university setting. The dataset, named LAUREATE, contains the physiological data of 42 students during 26 classes (including exams), daily self-reports asking the students about their lifestyle habits (e.g. studying hours, physical activity, and sleep quality) and their performance across multiple examinations. In addition to the raw data, we provide expert features from the physiological data, and baseline machine learning models for estimating self-reported affect, models for recognising classes vs breaks, and models for user identification. Besides the use cases presented in this paper, among which Human Memory Augmentation, the dataset represents a rich resource for the UbiComp community in various domains, including affect recognition, behaviour modelling, user privacy, and activity and context recognition.

A Federated Unsupervised Personalisation for Cognitive Workload Estimation

Sun, 01 Jan 2023 00:00:00 +0000

Exploring Transformer and Graph Convolutional Networks for Human Mobility Modeling

Sun, 01 Jan 2023 00:00:00 +0000

Federated Learning for Privacy-aware Cognitive Workload Estimation

Sun, 01 Jan 2023 00:00:00 +0000

GANs for Privacy-Aware Mobility Modeling

Sun, 01 Jan 2023 00:00:00 +0000

LAUREATE: A Dataset for Supporting Research in Affective Computing and Human Memory Augmentation

Sun, 01 Jan 2023 00:00:00 +0000

Prof. Silvia Santini’s contribution on La Regione

Mon, 21 Nov 2022 00:00:00 +0000

Professor Silvia Santini discussed how digital devices and apps are increasingly integrated into daily life and how this creates both concerns and opportunities for well-being.

Source: .

Our group members ranked among the world’s top 2% of scientists

Wed, 26 Oct 2022 00:00:00 +0000

Marc Langheinrich and Martin Gjoreski were included in Stanford University and Elsevier science-wide citation indicator lists for top scientists.

Source: .

Daniel Gatica-Perez presents Towards Increasing Diversity in Mobile Sensing Research

Tue, 18 Oct 2022 00:00:00 +0000

Professor Silvia Santini hosted Daniel Gatica-Perez from EPFL for a seminar on diversity and mobile sensing research.

Source: .

Prof. Marc Langheinrich’s contribution on La Regione

Mon, 21 Feb 2022 00:00:00 +0000

Professor Marc Langheinrich discussed digital privacy and the evolution of personal data handling in a feature with La Regione.

Source: .

Affect and Learning in the LAUREATE Dataset

Sat, 01 Jan 2022 00:00:00 +0000

BayCon: Model-agnostic Bayesian Counterfactual Generator

Sat, 01 Jan 2022 00:00:00 +0000

CONFIG.SYS

Sat, 01 Jan 2022 00:00:00 +0000

Exploring LAUREATE - the Longitudinal multimodAl stUdent expeRience datasEt for AffecT and mEmory research

Sat, 01 Jan 2022 00:00:00 +0000

Federated Learning for Privacy-Aware Human Mobility Modeling

Sat, 01 Jan 2022 00:00:00 +0000

Hello, Goodbye

Sat, 01 Jan 2022 00:00:00 +0000

Introduction of the LAUREATE dataset: the Longitudinal multimodAl stUdent expeRience datasEt for AffecT and mEmory research

Sat, 01 Jan 2022 00:00:00 +0000

Standing on the Platforms of Giants

Sat, 01 Jan 2022 00:00:00 +0000

Technobubble

Sat, 01 Jan 2022 00:00:00 +0000

Toward privacy-aware federated analytics of cohorts for smart mobility

Sat, 01 Jan 2022 00:00:00 +0000

Tutorial at the Neuroergonomics 2021 conference in Munich

Mon, 23 Aug 2021 00:00:00 +0000

Martin Gjoreski co-organized a tutorial on machine learning for cognitive load inference from physiological signals at Neuroergonomics 2021.

Source: .

A Longitudinal Study of Pervasive Display Personalisation

Fri, 01 Jan 2021 00:00:00 +0000

Dependence Day

Fri, 01 Jan 2021 00:00:00 +0000

Detecting Verbal and Non-Verbal Gestures Using Earables

Fri, 01 Jan 2021 00:00:00 +0000

Prepare for Impact!

Fri, 01 Jan 2021 00:00:00 +0000

The Internet of Thugs?

Fri, 01 Jan 2021 00:00:00 +0000

To FLoC or Not?

Fri, 01 Jan 2021 00:00:00 +0000

Designing for conflict: a design space for multi-viewer support in future display networks

Wed, 01 Jan 2020 00:00:00 +0000

Engineering Privacy by Design: Are engineers ready to live up to the challenge?

Wed, 01 Jan 2020 00:00:00 +0000

First Contact!

Wed, 01 Jan 2020 00:00:00 +0000

IoT '20 Companion: 10th International Conference on the Internet of Things Companion, Malmö Sweden, October 6-9, 2020

Wed, 01 Jan 2020 00:00:00 +0000

IoT '20: 10th International Conference on the Internet of Things, Malmö, Sweden, October 6-9, 2020

Wed, 01 Jan 2020 00:00:00 +0000

Is Privacy Regulation Slowing Down Research on Pervasive Computing?

Wed, 01 Jan 2020 00:00:00 +0000

Is There an App for That?

Wed, 01 Jan 2020 00:00:00 +0000

Long Live the IoT

Wed, 01 Jan 2020 00:00:00 +0000

The New Normal

Wed, 01 Jan 2020 00:00:00 +0000

A Plan B for Plan S?

Tue, 01 Jan 2019 00:00:00 +0000

Engineering Privacy by Design: Are engineers ready to live up to the challenge?

Tue, 01 Jan 2019 00:00:00 +0000

Inside the Organization: Why Privacy and Security Engineering Is a Challenge for Engineers

Tue, 01 Jan 2019 00:00:00 +0000

Let's Talk About the Weather

Tue, 01 Jan 2019 00:00:00 +0000

Movie+: Towards Exploring Social Effects of Emotional Fingerprints for Video Clips and Movies

Tue, 01 Jan 2019 00:00:00 +0000

Scheduling Content in Pervasive Display Systems

Tue, 01 Jan 2019 00:00:00 +0000

Securely Storing and Sharing Memory Cues in Memory Augmentation Systems: A Practical Approach

Tue, 01 Jan 2019 00:00:00 +0000

Sharing Economy Design Cards

Tue, 01 Jan 2019 00:00:00 +0000

The Internet of Data

Tue, 01 Jan 2019 00:00:00 +0000

The Paperless Magazine

Tue, 01 Jan 2019 00:00:00 +0000

Augmenting Humans

Mon, 01 Jan 2018 00:00:00 +0000

Augmenting Humans on the Slope: Two Electronic Devices That Enhance Safety and Decision Making

Mon, 01 Jan 2018 00:00:00 +0000

Augmenting Memory Recall in Work Meetings: Establishing a Quantifiable Baseline

Mon, 01 Jan 2018 00:00:00 +0000

Bibliometrics - Measuring Pervasive Computing's Impact

Mon, 01 Jan 2018 00:00:00 +0000

Co-creation and Risk-Taking - In Pursuit of New Technology for Human Augmentation: An Interview with Pranav Mistry

Mon, 01 Jan 2018 00:00:00 +0000

For the Benefit of Humanity

Mon, 01 Jan 2018 00:00:00 +0000

Got Change?

Mon, 01 Jan 2018 00:00:00 +0000

Memstone: a tangible interface for controlling capture and sharing of personal memories

Mon, 01 Jan 2018 00:00:00 +0000

Privacy in Mobile and Pervasive Computing

Mon, 01 Jan 2018 00:00:00 +0000

Roaming Objects: Encoding Digital Histories of Use into Shared Objects and Tools

Mon, 01 Jan 2018 00:00:00 +0000

Sharing physical objects using smart contracts

Mon, 01 Jan 2018 00:00:00 +0000

Supporting the design of sharing economy services: learning from technology-mediated sharing practices of both digital and physical artifacts

Mon, 01 Jan 2018 00:00:00 +0000

The Golden Age of Privacy?

Mon, 01 Jan 2018 00:00:00 +0000

Amplifying human cognition: bridging the cognitive gap between human and machine

Sun, 01 Jan 2017 00:00:00 +0000

Audience monitor: an open source tool for tracking audience mobility in front of pervasive displays

Sun, 01 Jan 2017 00:00:00 +0000

Augmenting skiers' peripheral perception

Sun, 01 Jan 2017 00:00:00 +0000

Can Less be More?: Contrasting Limited, Unlimited, and Automatic Picture Capture for Augmenting Memory Recall

Sun, 01 Jan 2017 00:00:00 +0000

From Travel Plans to Magic Wands: A Cross-Domain Study of Practices and Privacy Requirements for Sharing Emerging Types of Online Content

Sun, 01 Jan 2017 00:00:00 +0000

Proceedings of the 6th ACM International Symposium on Pervasive Displays, PerDis 2017, Lugano, Switzerland, June 7-9, 2017

Sun, 01 Jan 2017 00:00:00 +0000

Understanding the potential of human-machine crowdsourcing for weather data

Sun, 01 Jan 2017 00:00:00 +0000

A good balance of costs and benefits: convincing a university administration to support the installation of an interactive multi-application display system on campus

Fri, 01 Jan 2016 00:00:00 +0000

Collecting Shared Experiences through Lifelogging: Lessons Learned

Fri, 01 Jan 2016 00:00:00 +0000

Design and evaluation of a wearable AR system for sharing personalized content on ski resort maps

Fri, 01 Jan 2016 00:00:00 +0000

Measuring the effect of cued recall on work meetings

Fri, 01 Jan 2016 00:00:00 +0000

Mobile first?: understanding device usage practices in novel content sharing services

Fri, 01 Jan 2016 00:00:00 +0000

Multimedia Memory Cues for Augmenting Human Memory

Fri, 01 Jan 2016 00:00:00 +0000

Pervasive Displays [Guest editors' introduction]

Fri, 01 Jan 2016 00:00:00 +0000

Quantifying the Uncertainty of Next-Place Predictions

Fri, 01 Jan 2016 00:00:00 +0000

Remembering through lifelogging: A survey of human memory augmentation

Fri, 01 Jan 2016 00:00:00 +0000

s-Helmet: A Ski Helmet for Augmenting Peripheral Perception

Fri, 01 Jan 2016 00:00:00 +0000

Secure Personal Memory-Sharing with Co-located People and Places

Fri, 01 Jan 2016 00:00:00 +0000

SkiAR: Wearable Augmented Reality System for Sharing Personalized Content on Ski Resort Maps

Fri, 01 Jan 2016 00:00:00 +0000

Towards understanding digital sharing practices in outdoor sports

Fri, 01 Jan 2016 00:00:00 +0000

WeatherUSI: User-Based Weather Crowdsourcing on Public Displays

Fri, 01 Jan 2016 00:00:00 +0000

Digitally Enhanced Reality