Philippe Lalanda
YOU?
Author Swipe
View article: TaskVAE: Task-Specific Variational Autoencoders for Exemplar Generation in Continual Learning for Human Activity Recognition
TaskVAE: Task-Specific Variational Autoencoders for Exemplar Generation in Continual Learning for Human Activity Recognition Open
As machine learning based systems become more integrated into daily life, they unlock new opportunities but face the challenge of adapting to dynamic data environments. Various forms of data shift-gradual, abrupt, or cyclic-threaten model …
View article: Microservice-based edge platform for AI services
Microservice-based edge platform for AI services Open
Pervasive computing promotes the integration of smart electronic devices in our living and working spaces to provide advanced services. Recently, two major evolutions are changing the way pervasive applications are developed. The first dea…
View article: FedAli: Personalized Federated Learning Alignment with Prototype Layers for Generalized Mobile Services
FedAli: Personalized Federated Learning Alignment with Prototype Layers for Generalized Mobile Services Open
Personalized Federated Learning (PFL) enables distributed training on edge devices, allowing models to collaboratively learn global patterns while tailoring their parameters to better fit each client's local data, all while preserving data…
View article: Comparing Self-Supervised Learning Techniques for Wearable Human Activity Recognition
Comparing Self-Supervised Learning Techniques for Wearable Human Activity Recognition Open
Human Activity Recognition (HAR) based on the sensors of mobile/wearable devices aims to detect the physical activities performed by humans in their daily lives. Although supervised learning methods are the most effective in this task, the…
View article: Cross-Dataset Continual Learning: Assessing Pre-Trained Models to Enhance Generalization in HAR
Cross-Dataset Continual Learning: Assessing Pre-Trained Models to Enhance Generalization in HAR Open
International audience
View article: AI-based controller for grid-forming inverter-based generators under extreme dynamics
AI-based controller for grid-forming inverter-based generators under extreme dynamics Open
International audience
View article: Combining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity
Combining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity Open
The use of supervised learning for Human Activity Recognition (HAR) on mobile devices leads to strong classification performances. Such an approach, however, requires large amounts of labeled data, both for the initial training of the mode…
View article: Combining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity
Combining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity Open
IEEE SMARTCOMP 2023
View article: Evaluation of Regularization-based Continual Learning Approaches: Application to HAR
Evaluation of Regularization-based Continual Learning Approaches: Application to HAR Open
Pervasive computing allows the provision of services in many important areas, including the relevant and dynamic field of health and well-being. In this domain, Human Activity Recognition (HAR) has gained a lot of attention in recent years…
View article: Artificial Intelligence-Based Controller for Grid-Forming Inverter-Based Generators
Artificial Intelligence-Based Controller for Grid-Forming Inverter-Based Generators Open
International audience
View article: Transformer-based Models to Deal with Heterogeneous Environments in Human Activity Recognition
Transformer-based Models to Deal with Heterogeneous Environments in Human Activity Recognition Open
Human Activity Recognition (HAR) on mobile devices has been demonstrated to be possible using neural models trained on data collected from the device's inertial measurement units. These models have used Convolutional Neural Networks (CNNs)…
View article: Federated Continual Learning through distillation in pervasive computing
Federated Continual Learning through distillation in pervasive computing Open
Federated Learning has been introduced as a new machine learning paradigm enhancing the use of local devices. At a server level, FL regularly aggregates models learned locally on distributed clients to obtain a more general model. Current …
View article: Federated Continual Learning through distillation in pervasive computing
Federated Continual Learning through distillation in pervasive computing Open
Federated Learning has been introduced as a new machine learning paradigm\nenhancing the use of local devices. At a server level, FL regularly aggregates\nmodels learned locally on distributed clients to obtain a more general model.\nCurre…
View article: Federated Learning and catastrophic forgetting in pervasive computing: demonstration in HAR domain
Federated Learning and catastrophic forgetting in pervasive computing: demonstration in HAR domain Open
A. Usmanova, F. Portet, P. Lalanda and G. Vega, "Federated Learning and catastrophic forgetting in pervasive computing: demonstration in HAR domain," 2022 IEEE International Conference on Pervasive Computing and Communications Workshops an…
View article: Work in Progress - Welcome and Committees
Work in Progress - Welcome and Committees Open
The WiP session aims to provide a venue for exciting early-stage work in pervasive computing from academia and industry.We have received a total of 30 submissions and selected 17
View article: Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR
Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR Open
Federated Learning is a new machine learning paradigm dealing with\ndistributed model learning on independent devices. One of the many advantages\nof federated learning is that training data stay on devices (such as\nsmartphones), and only…
View article: A distillation-based approach integrating continual learning and federated learning for pervasive services
A distillation-based approach integrating continual learning and federated learning for pervasive services Open
Federated Learning, a new machine learning paradigm enhancing the use of edge devices, is receiving a lot of attention in the pervasive community to support the development of smart services. Nevertheless, this approach still needs to be a…
View article: A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison
A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison Open
Pervasive computing promotes the installation of connected devices in our\nliving spaces in order to provide services. Two major developments have gained\nsignificant momentum recently: an advanced use of edge resources and the\nintegratio…
View article: On the Relevance of Extracting Macro-operators with Non-adjacent Actions: Does It Matter?
On the Relevance of Extracting Macro-operators with Non-adjacent Actions: Does It Matter? Open
International audience
View article: Evaluating Federated Learning for human activity recognition
Evaluating Federated Learning for human activity recognition Open
International audience
View article: ERA: Extracting planning macro-operators from adjacent and non-adjacent sequences
ERA: Extracting planning macro-operators from adjacent and non-adjacent sequences Open
International audience