How ChatGPT Assists Novices in Human Activity Recognition

被引:0
作者
Kazama, Koki [1 ]
Shuzo, Masaki [1 ]
机构
[1] Shonan Inst Technol, Fujisawa, Kanagawa, Japan
来源
COMPANION OF THE 2024 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING, UBICOMP COMPANION 2024 | 2024年
关键词
Human activity recognition; SHL dataset; ChatGPT;
D O I
10.1145/3675094.3678459
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
It is evident that large language models are not only capable of generating text and images but also of facilitating discussions on the latest research in the field of human activity recognition due to their extensive knowledge. The objective of this paper is to observe how novices in machine learning in 2024 can rapidly develop their skills with the assistance of ChatGPT. As an initial introduction, we started with a dialogue-based consultation with ChatGPT and executed a classification task using the Iris dataset on Google Colaboratory. This initial task served to deepen the novices' basic understanding of machine learning. Subsequently, the authors, as part of Team Shonan-Blue, participated in the Sussex-Huawei Locomotion-Transportation (SHL) recognition challenge (hereafter SHL recognition challenge). In this challenge, the authors developed a simple human activity recognition system without expert advice and relying solely on interactions with ChatGPT. The system was constructed by integrating four classical methods: k-Nearest Neighbor algorithm (kNN), Neural Network (NN), Random Forest (RF), and Support Vector Machine (SVM). The models were selected for their differing approaches, which were anticipated to enhance prediction accuracy when combined. For feature extraction, we utilized only the primary four features (maximum, minimum, mean, standard deviation) derived from 5-second sensor data collected by accelerometers, gyroscopes, and magnetometers. The outputs of the four models were then processed ensemble to obtain the final prediction results. This yielded an F1 score of 0.936. Although the limited challenge period may not have permitted the optimal performance, the observed growth of novices who, with the assistance of ChatGPT and without the use of GPU power, managed to develop a functional system, is encouraging for future newcomers in the field of activity recognition.
引用
收藏
页码:575 / 579
页数:5
相关论文
共 8 条
[1]   A Novel Ensemble ELM for Human Activity Recognition Using Smartphone Sensors [J].
Chen, Zhenghua ;
Jiang, Chaoyang ;
Xie, Lihua .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2019, 15 (05) :2691-2699
[2]   The University of Sussex-Huawei Locomotion and Transportation Dataset for Multimodal Analytics With Mobile Devices [J].
Gjoreski, Hristijan ;
Ciliberto, Mathias ;
Wang, Lin ;
Morales, Francisco Javier Ordonez ;
Mekki, Sami ;
Valentin, Stefan ;
Roggen, Daniel .
IEEE ACCESS, 2018, 6 :42592-42604
[3]   Toward Pioneering Sensors and Features Using Large Language Models in Human Activity Recognition [J].
Kaneko, Haru ;
Inoue, Sozo .
ADJUNCT PROCEEDINGS OF THE 2023 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING & THE 2023 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTING, UBICOMP/ISWC 2023 ADJUNCT, 2023, :475-479
[4]  
Sakai Motoki, 2024, P 6 INT C ACT BEH CO
[5]   Ensemble Learning for Human Activity Recognition [J].
Sekiguchi, Ryoichi ;
Abe, Kenji ;
Yokoyama, Takumi ;
Kumano, Masayasu ;
Kawakatsu, Masaki .
UBICOMP/ISWC '20 ADJUNCT: PROCEEDINGS OF THE 2020 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING AND PROCEEDINGS OF THE 2020 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS, 2020, :335-339
[6]   Enabling Reproducible Research in Sensor-Based Transportation Mode Recognition With the Sussex-Huawei Dataset [J].
Wang, Lin ;
Gjoreski, Hristijan ;
Ciliberto, Mathias ;
Mekki, Sami ;
Valentin, Stefan ;
Roggen, Daniel .
IEEE ACCESS, 2019, 7 :10870-10891
[7]  
Wang Lin, 2024, ADJ P 2024 ACM INT J
[8]   Human Activity Recognition Through Ensemble Learning of Multiple Convolutional Neural Networks [J].
Zehra, Narjis ;
Azeem, Syed Hamza ;
Farhan, Muhammad .
2021 55TH ANNUAL CONFERENCE ON INFORMATION SCIENCES AND SYSTEMS (CISS), 2021,