1. Αποθετήριο Παραδοτέων Υποτρόφων Δράσεων ΕΣΠΑ Τριτοβάθμιας Εκπαίδευσης 2017-2023
2. Όλο το Αποθετήριο
3. Ερευνητικές ομάδες

Τύπος:	Άρθρο σε επιστημονικό περιοδικό
Τίτλος:	Modality-wise relational reasoning for one-shot sensor-based activity recognition
Συγγραφέας:	[EL] Κασνέσης, Παναγιώτης[EN] Kasnesis, Panagiotis [EL] Χατζηγεωργίου, Χρήστος[EN] Chatzigeorgiou, Christos [EL] Πατρικάκης, Χαράλαμπος[EN] Patrikakis, Charalampos [EL] Ραγκούση, Μαρία[EN] Rangoussi, Maria
Ημερομηνία:	17/03/2021
Περίληψη:	Deep learning concepts have been successfully transferred from the computer vision task to that of wearable human activity recognition (HAR) over the last few years. However, deep learning models require a large volume of annotated samples to be efficiently trained, while adding new activities results in training the whole network from scratch. In this paper, we study the use of one-shot learning techniques based on high-level features extracted by deep neural networks that rely on convolutional layers. Using these feature vectors as input we measure the similarity of two activities by computing their Euclidean distance, cosine similarity or applying self-attention to perceive the relations between the signals. We evaluate four different one-shot learning approaches using two publicly available HAR datasets, by keeping out of the training set several activity classes. Our results demonstrate that the model relying on modality-wise relational reasoning surpasses the other three, achieving 94.8% and 84.41% one-shot accuracy on UCL and PAMAP2 dataset respectively, while we demonstrate the model’s sensitivity on fusing sensor modalities and provide explainable attention maps to display the modality-wise similarities.
Γλώσσα:	Αγγλικά
Σελίδες:	10
DOI:	10.1016/j.patrec.2021.03.003
ISSN:	0167-8655
Θεματική κατηγορία:	[EL] Τεχνητή νοημοσύνη[EN] Artificial Intelligence [EL] Ηλεκτρική και Ηλεκτρονική Μηχανική[EN] Electrical and Electronic Engineering
Λέξεις-κλειδιά:	deep learning; human activity recognition; one-shot learning; Relational reasoning; Self-attention
Κάτοχος πνευματικών δικαιωμάτων:	© 2021 Elsevier B.V. All rights reserved.
Ηλεκτρονική διεύθυνση του τεκμηρίου στον εκδότη:	https://www.sciencedirect.com/science/article/pii/S0167865521000829
Ηλεκτρονική διεύθυνση περιοδικού:	https://www.sciencedirect.com/journal/pattern-recognition-letters
Τίτλος πηγής δημοσίευσης:	Pattern Recognition Letters
Τεύχος:	June
Τόμος:	146
Σελίδες τεκμηρίου (στην πηγή):	90-99
Σημειώσεις:	This research is co-financed by Greece and the European Union (European Social Fund-ESF) through the Operational Programme <<Human Resources Development, Education and Lifelong Learning 2014-2020>> in the context of the project "On applying Deep Learning techniques to insufficient labeled sensor data for gesture recognition" (MIS 5050324).
Εμφανίζεται στις συλλογές:	Ερευνητικές ομάδες