A Comprehensive Survey on Deep Learning Methods in Human Activity Recognition

M Kaseris, I Kostavelis, S Malassiotis - Machine Learning and Knowledge …, 2024 - mdpi.com
Human activity recognition (HAR) remains an essential field of research with increasing real-
world applications ranging from healthcare to industrial environments. As the volume of …

Toward pioneering sensors and features using large language models in human activity recognition

H Kaneko, S Inoue - Adjunct Proceedings of the 2023 ACM International …, 2023 - dl.acm.org
In this paper, we propose a feature pioneering method using Large Language Models
(LLMs). In the proposed method, we use ChatGPT 1 to find new sensor locations and new …

Avian Activity Classification Using Recurrent Networks to Fuse Videos with Metadata on Imbalanced Datasets

X Wang, A Szymanski, Y Hamada… - Proceedings of the 2024 …, 2024 - dl.acm.org
Activity classification plays a crucial role in various real-life scenarios involving both humans
and animals. There is an increasing need for precise activity classification focused on avian …

Enhancing Human Activity Recognition: An Exploration of Machine Learning Models and Explainable AI Approaches for Feature Contribution Analysis

AR Kaushik, KS Gurucharan… - … Conference on Energy …, 2023 - ieeexplore.ieee.org
Human Activity Recognition (HAR) holds significant importance in people's daily lives due o
its capability to extract comprehensive high-level insights into human activities from …

Deep Learning Applied to Image and Video Processing

X Wang - 2024 - search.proquest.com
NORTHWESTERN UNIVERSITY Deep Learning Applied to Image and Video Processing A
DISSERTATION SUBMITTED TO THE GRADUATE SCHOOL IN P Page 1 NORTHWESTERN …

A Twin XCBR System Using Supportive and Contrastive Explanations

B Bayrak, K Bach - ICCBR 2023 Workshop Proceedings, 2023 - ntnuopen.ntnu.no
Machine learning models are increasingly being applied in safety-critical domains.
Therefore, ensuring their trustworthiness and reliability has become a priority. Uncertainty …

[HTML][HTML] Improved training approaches for embedded learning with heterogeneous sensor data

A Hölzemann - 2023 - dspace.ub.uni-siegen.de
The papers published as part of this doctoral thesis address significant challenges in the
areas of annotation and synchronization of datasets, data-driven studies in the field of …