Complex Daily Activities, Country-Level Diversity, and Smartphone Sensing: A Study in Denmark, Italy, Mongolia, Paraguay, and UK
Karim Assi, Lakmal Meegahapola, William Droz, Peter Kun, Amalia de Götzen, Miriam Bidoglia, Sally Stares, George Gaskell, Altangerel Chagnaa, Amarsanaa Ganbold, Tsolmon Zundui, Carlo Caprini
Abstract
Smartphones enable understanding human behavior with activity recognition to support people’s daily lives. Prior studies focused on using inertial sensors to detect simple activities (sitting, walking, running, etc.) and were mostly conducted in homogeneous populations within a country. However, people are more sedentary in the post-pandemic world with the prevalence of remote/hybrid work/study settings, making detecting simple activities less meaningful for context-aware applications. Hence, the understanding of (i) how multimodal smartphone sensors and machine learning models could be used to detect complex daily activities that can better inform about people’s daily lives, and (ii) how models generalize to unseen countries, is limited. We analyzed in-the-wild smartphone data and ∼ 216K self-reports from 637 college students in five countries (Italy, Mongolia, UK, Denmark, Paraguay). Then, we defined a 12-class complex daily activity recognition task and evaluated the performance with different approaches. We found that even though the generic multi-country approach provided an AUROC of 0.70, the country-specific approach performed better with AUROC scores in [0.79-0.89]. We believe that research along the lines of diversity awareness is fundamental for advancing human behavior understanding through smartphones and machine learning, for more real-world utility across countries.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
5 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Generalization and Personalization of Mobile Sensing-Based Mood Inference Models: An Analysis of College Students in Eight Countries cites A Systematic Study of Unsupervised Domain Adaptation for Robust Human-Activity Recognition
- Generalization and Personalization of Mobile Sensing-Based Mood Inference Models: An Analysis of College Students in Eight Countries cites One More Bite?: Inferring Food Consumption Level of College Students Using Smartphone Sensing and Self-Reports
- DiversityOne: A Multi-Country Smartphone Sensor Dataset for Everyday Life Behavior Modeling cites Generalization and Personalization of Mobile Sensing-Based Mood Inference Models: An Analysis of College Students in Eight Countries
- DiversityOne: A Multi-Country Smartphone Sensor Dataset for Everyday Life Behavior Modeling cites GLOBEM: Cross-Dataset Generalization of Longitudinal Human Behavior Modeling
- DiversityOne: A Multi-Country Smartphone Sensor Dataset for Everyday Life Behavior Modeling cites A Reproducible Stress Prediction Pipeline with Mobile Sensor Data
- DiversityOne: A Multi-Country Smartphone Sensor Dataset for Everyday Life Behavior Modeling cites A Systematic Study of Unsupervised Domain Adaptation for Robust Human-Activity Recognition
- DiversityOne: A Multi-Country Smartphone Sensor Dataset for Everyday Life Behavior Modeling cites M3BAT: Unsupervised Domain Adaptation for Multimodal Mobile Sensing with Multi-Branch Adversarial Training
- A Reproducible Stress Prediction Pipeline with Mobile Sensor Data cites Generalization and Personalization of Mobile Sensing-Based Mood Inference Models: An Analysis of College Students in Eight Countries
- A Reproducible Stress Prediction Pipeline with Mobile Sensor Data cites GLOBEM: Cross-Dataset Generalization of Longitudinal Human Behavior Modeling
- A Reproducible Stress Prediction Pipeline with Mobile Sensor Data cites One More Bite?: Inferring Food Consumption Level of College Students Using Smartphone Sensing and Self-Reports
- A Reproducible Stress Prediction Pipeline with Mobile Sensor Data cites M3BAT: Unsupervised Domain Adaptation for Multimodal Mobile Sensing with Multi-Branch Adversarial Training
- Imputation Matters: A Deeper Look into an Overlooked Step in Longitudinal Health and Behavior Sensing Research cites GLOBEM: Cross-Dataset Generalization of Longitudinal Human Behavior Modeling
- Imputation Matters: A Deeper Look into an Overlooked Step in Longitudinal Health and Behavior Sensing Research cites Predicting Subjective Measures of Social Anxiety from Sparsely Collected Mobile Sensor Data
- Stress Mindset Matters: Rethinking Mental Stress Detection with Multimodal Wearable Sensors cites Generalization and Personalization of Mobile Sensing-Based Mood Inference Models: An Analysis of College Students in Eight Countries
- Stress Mindset Matters: Rethinking Mental Stress Detection with Multimodal Wearable Sensors cites One More Bite?: Inferring Food Consumption Level of College Students Using Smartphone Sensing and Self-Reports
- Stress Mindset Matters: Rethinking Mental Stress Detection with Multimodal Wearable Sensors cites M3BAT: Unsupervised Domain Adaptation for Multimodal Mobile Sensing with Multi-Branch Adversarial Training
- M3BAT: Unsupervised Domain Adaptation for Multimodal Mobile Sensing with Multi-Branch Adversarial Training cites Generalization and Personalization of Mobile Sensing-Based Mood Inference Models: An Analysis of College Students in Eight Countries
- M3BAT: Unsupervised Domain Adaptation for Multimodal Mobile Sensing with Multi-Branch Adversarial Training cites GLOBEM: Cross-Dataset Generalization of Longitudinal Human Behavior Modeling
- M3BAT: Unsupervised Domain Adaptation for Multimodal Mobile Sensing with Multi-Branch Adversarial Training cites A Systematic Study of Unsupervised Domain Adaptation for Robust Human-Activity Recognition
- M3BAT: Unsupervised Domain Adaptation for Multimodal Mobile Sensing with Multi-Branch Adversarial Training cites One More Bite?: Inferring Food Consumption Level of College Students Using Smartphone Sensing and Self-Reports
Cited by top-tier papers5
- M3BAT: Unsupervised Domain Adaptation for Multimodal Mobile Sensing with Multi-Branch Adversarial TrainingLakmal Meegahapola, Hamza Hassoune, Daniel Gatica-PerezUbiComp 2024 · 30 citations
- A Reproducible Stress Prediction Pipeline with Mobile Sensor DataPanyu Zhang, Gyuwon Jung, Jumabek Alikhanov, Uzair Ahmed et al.UbiComp 2024 · 21 citations
- DiversityOne: A Multi-Country Smartphone Sensor Dataset for Everyday Life Behavior ModelingMatteo Busso, Andrea Bontempelli, Leonardo Javier Malcotti, Lakmal Meegahapola et al.UbiComp 2025 · 12 citations
- Imputation Matters: A Deeper Look into an Overlooked Step in Longitudinal Health and Behavior Sensing ResearchAkshat Choube, Sohini Bhattacharya, Rahul Majethia, Jiachen Li et al.UbiComp 2026 · 4 citations
- Stress Mindset Matters: Rethinking Mental Stress Detection with Multimodal Wearable SensorsLakmal Meegahapola, Marios Constantinides, Zoran Radivojevic, Hongwei Li et al.CHI 2026 · 2 citations
Builds on12
- A Systematic Study of Unsupervised Domain Adaptation for Robust Human-Activity RecognitionYoungjae Chang, Akhil Mathur, Anton Isopoussu, Junehwa Song et al.UbiComp 2020 · 136 citations
- GLOBEM: Cross-Dataset Generalization of Longitudinal Human Behavior ModelingXuhai Xu, Xin Liu, Han Zhang, Weichen Wang et al.UbiComp 2023 · 96 citations
- Generalization and Personalization of Mobile Sensing-Based Mood Inference Models: An Analysis of College Students in Eight CountriesLakmal Meegahapola, William Droz, Peter Kun, Amalia de Götzen et al.UbiComp 2023 · 55 citations
- Predicting Subjective Measures of Social Anxiety from Sparsely Collected Mobile Sensor DataHaroon Rashid, Sanjana Mendu, Katharine E. Daniel, Miranda L. Beltzer et al.UbiComp 2020 · 47 citations
- One More Bite?: Inferring Food Consumption Level of College Students Using Smartphone Sensing and Self-ReportsLakmal Meegahapola, Salvador Ruiz-Correa, Viridiana del Carmen Robledo-Valero, Emilio Ernesto Hernandez-Huerfano et al.UbiComp 2021 · 37 citations
Related papers
- Learning About Social Context From Smartphone Data: Generalization Across Countries and Daily Life MomentsAurel Ruben Mäder, Lakmal Meegahapola, Daniel Gatica-PerezCHI 2024 · 11 citations
- Leveraging Sound and Wrist Motion to Detect Activities of Daily Living with Commodity SmartwatchesSarnab Bhattacharya, Rebecca Adaimi, Edison ThomazUbiComp 2022 · 41 citations
- Beyond Screen Time: Inferring Everyday Life Context from Diverse Smartphone DataGujun Chen, Xinyao Yang, Yutong Han, Shuning Zhang et al.UbiComp 2026
- The Physical Activity Assessment Using Wearable Sensors (PAAWS) Dataset: Labeled Laboratory and Free-Living Accelerometer DataVeronika Potter, Hoan Tran, Daniel Mobley, Suzanne M. Bertisch et al.UbiComp 2026 · 2 citations
- Multimodal Daily-Life Logging in Free-living Environment Using Non-Visual Egocentric Sensors on a SmartphoneKe Sun, Chunyu Xia, Xinyu Zhang, Hao Chen et al.UbiComp 2024 · 15 citations
