Gabriele Civitarese
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Gabriele Civitarese has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
- Claudio Bettini
University of Milan
35 shared publications - Heiner Stuckenschmidt
University of Mannheim
6 shared publications - Luca Arrotta
University of Milan
6 shared publications Daniele Riboni
5 shared publications- Daniele Riboni
Department of Mathematics and Computer Science, University of Cagliari, Cagliari, Italy
5 shared publications - Riccardo Presotto
EveryWare Lab, University of Milan, Milan, Italy
4 shared publications
Latest Publications
- Open Access
- 3 June 2026
- Published by Elsevier in Safety Science
- Vol. 202
Technology acceptance and perceived safety in AI-driven home monitoring for mild cognitive impairment
- 3 June 2026
- Published by Elsevier in Safety Science
- Vol. 202
Open AccessTechnology acceptance and perceived safety in AI-driven home monitoring for mild cognitive impairment
- Open Access
- 13 March 2026
- Published by Elsevier in SSRN Electronic Journal
Technology Acceptance and Perceived Safety in AI-Driven Home Monitoring for Mild Cognitive Impairment
Digital health technologies and AI-driven home monitoring systems are increasingly deployed to support individuals with Mild Cognitive Impairment or cognitive decline, offering opportunities for early detection, continuous assessment, and enhanced safety. While prior research has predominantly focused on technical performance and data accuracy, less attention has been dedicated to patients’ lived experiences. This study adopts a qualitative approach to explore the experiences of patients participating in the SERENADE project. Seventeen participants engaged in semi-structured interviews after one year of adoption of smart home monitoring technologies. Thematic analysis revealed that safety emerges as an experiential and relational process, co-produced through interactions among patients, caregivers, clinicians, and technological systems. Cognitive decline shaped how monitoring technologies were perceived, with some participants reporting reassurance and enhanced control, while others reported frustration when system features conflicted with daily routines or autonomy. Technology acceptance was influenced by effort expectancy, performance expectancy, facilitating conditions, social influence and relationship with monitoring tools. Findings advance current understanding of perceived safety in home-based digital care, demonstrating that it extends beyond technical reliability to encompass emotional, relational, and cognitive dimensions. These insights inform the design of adaptive, user-centered monitoring systems that enhance perceived safety and support autonomy, reassurance, and continuity of care in cognitively vulnerable populations.
- 13 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTechnology Acceptance and Perceived Safety in AI-Driven Home Monitoring for Mild Cognitive Impairment
Digital health technologies and AI-driven home monitoring systems are increasingly deployed to support individuals with Mild Cognitive Impairment or cognitive decline, offering opportunities for early detection, continuous assessment, and enhanced safety. While prior research has predominantly focused on technical performance and data accuracy, less attention has been dedicated to patients’ lived experiences. This study adopts a qualitative approach to explore the experiences of patients participating in the SERENADE project. Seventeen participants engaged in semi-structured interviews after one year of adoption of smart home monitoring technologies. Thematic analysis revealed that safety emerges as an experiential and relational process, co-produced through interactions among patients, caregivers, clinicians, and technological systems. Cognitive decline shaped how monitoring technologies were perceived, with some participants reporting reassurance and enhanced control, while others reported frustration when system features conflicted with daily routines or autonomy. Technology acceptance was influenced by effort expectancy, performance expectancy, facilitating conditions, social influence and relationship with monitoring tools. Findings advance current understanding of perceived safety in home-based digital care, demonstrating that it extends beyond technical reliability to encompass emotional, relational, and cognitive dimensions. These insights inform the design of adaptive, user-centered monitoring systems that enhance perceived safety and support autonomy, reassurance, and continuity of care in cognitively vulnerable populations.
- Open Access
DomusFM: A Foundation Model for Smart-Home Sensor Data
Smart-home sensor data holds significant potential for several applications, including healthcare monitoring and assistive technologies. Existing approaches, however, face critical limitations. Supervised models require impractical amounts of labeled data. Foundation models for activity recognition focus only on inertial sensors, failing to address the unique characteristics of smart-home binary sensor events: their sparse, discrete nature combined with rich semantic associations. LLM-based approaches, while tested in this domain, still raise several issues regarding the need for natural language descriptions or prompting, and reliance on either external services or expensive hardware, making them infeasible in real-life scenarios due to privacy and cost concerns. We introduce DomusFM, the first foundation model specifically designed and pretrained for smart-home sensor data. DomusFM employs a self-supervised dual contrastive learning paradigm to capture both token-level semantic attributes and sequence-level temporal dependencies. By integrating semantic embeddings from a lightweight language model and specialized encoders for temporal patterns and binary states, DomusFM learns generalizable representations that transfer across environments and tasks related to activity and event analysis. Through leave-one-dataset-out evaluation across seven public smart-home datasets, we demonstrate that DomusFM outperforms state-of-the-art baselines on different downstream tasks, achieving superior performance even with only 5% of labeled training data available for fine-tuning. Our approach addresses data scarcity while maintaining practical deployability for real-world smart-home systems.
Open AccessDomusFM: A Foundation Model for Smart-Home Sensor Data
Smart-home sensor data holds significant potential for several applications, including healthcare monitoring and assistive technologies. Existing approaches, however, face critical limitations. Supervised models require impractical amounts of labeled data. Foundation models for activity recognition focus only on inertial sensors, failing to address the unique characteristics of smart-home binary sensor events: their sparse, discrete nature combined with rich semantic associations. LLM-based approaches, while tested in this domain, still raise several issues regarding the need for natural language descriptions or prompting, and reliance on either external services or expensive hardware, making them infeasible in real-life scenarios due to privacy and cost concerns. We introduce DomusFM, the first foundation model specifically designed and pretrained for smart-home sensor data. DomusFM employs a self-supervised dual contrastive learning paradigm to capture both token-level semantic attributes and sequence-level temporal dependencies. By integrating semantic embeddings from a lightweight language model and specialized encoders for temporal patterns and binary states, DomusFM learns generalizable representations that transfer across environments and tasks related to activity and event analysis. Through leave-one-dataset-out evaluation across seven public smart-home datasets, we demonstrate that DomusFM outperforms state-of-the-art baselines on different downstream tasks, achieving superior performance even with only 5% of labeled training data available for fine-tuning. Our approach addresses data scarcity while maintaining practical deployability for real-world smart-home systems.
- Open Access
Improving Zero-shot ADL Recognition with Large Language Models through Event-based Context and Confidence
Unobtrusive sensor-based recognition of Activities of Daily Living (ADLs) in smart homes by processing data collected from IoT sensing devices supports applications such as healthcare, safety, and energy management. Recent zero-shot methods based on Large Language Models (LLMs) have the advantage of removing the reliance on labeled ADL sensor data. However, existing approaches rely on time-based segmentation, which is poorly aligned with the contextual reasoning capabilities of LLMs. Moreover, existing approaches lack methods for estimating prediction confidence. This paper proposes to improve zero-shot ADL recognition with event-based segmentation and a novel method for estimating prediction confidence. Our experimental evaluation shows that event-based segmentation consistently outperforms time-based LLM approaches on complex, realistic datasets and surpasses supervised data-driven methods, even with relatively small LLMs (e.g., Gemma 3 27B). The proposed confidence measure effectively distinguishes correct from incorrect predictions.
Open AccessImproving Zero-shot ADL Recognition with Large Language Models through Event-based Context and Confidence
Unobtrusive sensor-based recognition of Activities of Daily Living (ADLs) in smart homes by processing data collected from IoT sensing devices supports applications such as healthcare, safety, and energy management. Recent zero-shot methods based on Large Language Models (LLMs) have the advantage of removing the reliance on labeled ADL sensor data. However, existing approaches rely on time-based segmentation, which is poorly aligned with the contextual reasoning capabilities of LLMs. Moreover, existing approaches lack methods for estimating prediction confidence. This paper proposes to improve zero-shot ADL recognition with event-based segmentation and a novel method for estimating prediction confidence. Our experimental evaluation shows that event-based segmentation consistently outperforms time-based LLM approaches on complex, realistic datasets and surpasses supervised data-driven methods, even with relatively small LLMs (e.g., Gemma 3 27B). The proposed confidence measure effectively distinguishes correct from incorrect predictions.
- 2 January 2026
- Published by Springer Nature
- p. 341-360
GNN-XAR: A Graph Neural Network for Explainable Activity Recognition in Smart Homes
- 2 January 2026
- Published by Springer Nature
- p. 341-360
GNN-XAR: A Graph Neural Network for Explainable Activity Recognition in Smart Homes
- Open Access
- 18 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Internet of Things
- Vol. 6 (4) , 1-25
Leveraging Large Language Models for Explainable Activity Recognition in Smart Homes: A Critical Evaluation
Explainable Artificial Intelligence (XAI) aims to uncover the inner reasoning of machine learning models. In IoT systems, XAI improves the transparency of models processing sensor data from multiple heterogeneous devices, ensuring end-users understand and trust their outputs. Among the many applications, XAI has also been applied to sensor-based Activities of Daily Living (ADLs) recognition in smart homes. Existing approaches highlight which sensor events are most important for each predicted activity, using simple rules to convert these events into natural language explanations for non-expert users. However, these methods produce rigid explanations lacking natural language flexibility and are not scalable. With the recent rise of Large Language Models (LLMs), it is worth exploring whether they can enhance explanation generation, considering their proven knowledge of human activities. This article investigates potential approaches to combine XAI and LLMs for sensor-based ADL recognition. We evaluate if LLMs can be used: (a) as explainable zero-shot ADL recognition models, avoiding costly labeled data collection, and (b) to automate the generation of explanations for existing data-driven XAI approaches when training data is available and the goal is higher recognition rates. Our critical evaluation provides insights into the benefits and challenges of using LLMs for explainable ADL recognition.
- 18 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Internet of Things
- Vol. 6 (4) , 1-25
Open AccessLeveraging Large Language Models for Explainable Activity Recognition in Smart Homes: A Critical Evaluation
Explainable Artificial Intelligence (XAI) aims to uncover the inner reasoning of machine learning models. In IoT systems, XAI improves the transparency of models processing sensor data from multiple heterogeneous devices, ensuring end-users understand and trust their outputs. Among the many applications, XAI has also been applied to sensor-based Activities of Daily Living (ADLs) recognition in smart homes. Existing approaches highlight which sensor events are most important for each predicted activity, using simple rules to convert these events into natural language explanations for non-expert users. However, these methods produce rigid explanations lacking natural language flexibility and are not scalable. With the recent rise of Large Language Models (LLMs), it is worth exploring whether they can enhance explanation generation, considering their proven knowledge of human activities. This article investigates potential approaches to combine XAI and LLMs for sensor-based ADL recognition. We evaluate if LLMs can be used: (a) as explainable zero-shot ADL recognition models, avoiding costly labeled data collection, and (b) to automate the generation of explanations for existing data-driven XAI approaches when training data is available and the goal is higher recognition rates. Our critical evaluation provides insights into the benefits and challenges of using LLMs for explainable ADL recognition.
- Top Cited PapersOpen Access
- 10 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 16 (4) , 1-32
Large Language Models Are Zero-Shot Recognizers for Activities of Daily Living
The sensor-based recognition of Activities of Daily Living (ADLs) in smart home environments enables several applications in the areas of energy management, safety, well-being, and healthcare. ADL recognition is typically based on deep learning methods requiring large datasets to be trained. Recently, several studies proved that Large Language Models (LLMs) effectively capture common-sense knowledge about human activities. However, the effectiveness of LLMs for ADL recognition in smart home environments still deserves to be investigated. In this work, we propose ADL-LLM, a novel LLM-based ADL recognition system. ADL-LLM transforms raw sensor data into textual representations, that are processed by an LLM to perform zero-shot ADL recognition. Moreover, in the scenario where a small labeled dataset is available, ADL-LLM can also be empowered with few-shot prompting. We evaluated ADL-LLM on two public datasets, showing its effectiveness in this domain.
- 10 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 16 (4) , 1-32
Top Cited PapersOpen AccessLarge Language Models Are Zero-Shot Recognizers for Activities of Daily Living
The sensor-based recognition of Activities of Daily Living (ADLs) in smart home environments enables several applications in the areas of energy management, safety, well-being, and healthcare. ADL recognition is typically based on deep learning methods requiring large datasets to be trained. Recently, several studies proved that Large Language Models (LLMs) effectively capture common-sense knowledge about human activities. However, the effectiveness of LLMs for ADL recognition in smart home environments still deserves to be investigated. In this work, we propose ADL-LLM, a novel LLM-based ADL recognition system. ADL-LLM transforms raw sensor data into textual representations, that are processed by an LLM to perform zero-shot ADL recognition. Moreover, in the scenario where a small labeled dataset is available, ADL-LLM can also be empowered with few-shot prompting. We evaluated ADL-LLM on two public datasets, showing its effectiveness in this domain.
- Open Access
- 18 December 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 267
Multi-subject human activities: A survey of recognition and evaluation methods based on a formal framework
- 18 December 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 267
Open AccessMulti-subject human activities: A survey of recognition and evaluation methods based on a formal framework
- Open Access
- 5 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 881-884
Using Large Language Models to Compare Explainable Models for Smart Home Human Activity Recognition
Recognizing daily activities with unobtrusive sensors in smart environments enables various healthcare applications. Monitoring how subjects perform activities at home and their changes over time can reveal early symptoms of health issues, such as cognitive decline. Most approaches in this field use deep learning models, which are often seen as black boxes mapping sensor data to activities. However, non-expert users like clinicians need to trust and understand these models' outputs. Thus, eXplainable AI (XAI) methods for Human Activity Recognition have emerged to provide intuitive natural language explanations from these models. Different XAI methods generate different explanations, and their effectiveness is typically evaluated through user surveys, that are often challenging in terms of costs and fairness. This paper proposes an automatic evaluation method using Large Language Models (LLMs) to identify, in a pool of candidates, the best XAI approach for non-expert users. Our preliminary results suggest that LLM evaluation aligns with user surveys.
- 5 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 881-884
Open AccessUsing Large Language Models to Compare Explainable Models for Smart Home Human Activity Recognition
Recognizing daily activities with unobtrusive sensors in smart environments enables various healthcare applications. Monitoring how subjects perform activities at home and their changes over time can reveal early symptoms of health issues, such as cognitive decline. Most approaches in this field use deep learning models, which are often seen as black boxes mapping sensor data to activities. However, non-expert users like clinicians need to trust and understand these models' outputs. Thus, eXplainable AI (XAI) methods for Human Activity Recognition have emerged to provide intuitive natural language explanations from these models. Different XAI methods generate different explanations, and their effectiveness is typically evaluated through user surveys, that are often challenging in terms of costs and fairness. This paper proposes an automatic evaluation method using Large Language Models (LLMs) to identify, in a pool of candidates, the best XAI approach for non-expert users. Our preliminary results suggest that LLM evaluation aligns with user surveys.