A Comparative Approach to Classification of Locomotion and Transportation Modes Using Smartphone Sensor Data

Antar, Anindya Das; Ahmed, Masud; Ishrak, Mohammad Shadman; Ahad, Md. Atiqur Rahman

doi:10.1145/3267305.3267516

Cited by 34 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…S304 feeds sensor features to a multi-layer perceptron neural network and then smooths the estimation with HMM [4]. Confusion Matrix employs a random forest model and then smooths the estimation with major voting [5].…”

Section: Resultsmentioning

confidence: 99%

Summary of the Sussex-Huawei Locomotion-Transportation Recognition Challenge

Wang

Gjoreski

Murao

et al. 2018

Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computi

View full text Add to dashboard Cite

In this paper we summarize the contributions of participants to the Sussex-Huawei Transportation-Locomotion (SHL) Recognition Challenge organized at the HASCA Workshop of UbiComp 2018. The SHL challenge is a machine learning and data science competition, which aims to recognize eight transportation activities (Still, Walk, Run, Bike, Bus, Car, Train, Subway) from the inertial and pressure sensor data of a smartphone. We introduce the dataset used in the challenge and the protocol for the competition. We present a meta-analysis of the contributions from 19 submissions, their approaches, the software tools used, computational cost and the achieved results. Overall, two entries achieved F1 scores above 90%, eight with F1 scores between 80% and 90%, and nine between 50% and 80%.

show abstract

Section: Resultsmentioning

confidence: 99%

Summary of the Sussex-Huawei Locomotion-Transportation Recognition Challenge

Wang

Gjoreski

Murao

et al. 2018

Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computi

View full text Add to dashboard Cite

show abstract

“…Ensemble method is another effective to tackle the overfitting problem, e.g. by using XGBoost [2] and RF [5].…”

Section: Discussion On Over-fittingmentioning

confidence: 99%

Summary of the Sussex-Huawei locomotion-transportation recognition challenge 2019

Wang

Gjoreski

Ciliberto

et al. 2019

Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of The

View full text Add to dashboard Cite

show abstract

“…The SHL data is low-pass filtered, using a 3 rd -order Butterworth filter with a corner frequency 20Hz. This was then segmented using a 3s window [41]. The SHL dataset is sampled at 100Hz, the length of the window size was 3 seconds, and there are 12 sensor channels, so the raw matrix size for each frame is (300,12).…”

Section: A Datasetsmentioning

confidence: 99%

Synthetic Sensor Data for Human Activity Recognition

Alharbi

Ouarbya

Ward

2020

2020 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Human activity recognition (HAR) based onwearable sensors has emerged as an active topic of research in machine learning and human behavior analysis because of its applications in several fields, including health, security and surveillance, and remote monitoring. Machine learning algorithms are frequently applied in HAR systems to learn from labeled sensor data. The effectiveness of these algorithms generally relies on having access to lots of accurately labeled training data. But labeled data for HAR is hard to come by and is often heavily imbalanced in favor of one or other dominant classes, which in turn leads to poor recognition performance.In this study we introduce a generative adversarial network (GAN)-based approach for HAR that we use to automatically synthesize balanced and realistic sensor data. GANs are robust generative networks, typically used to create synthetic images that cannot be distinguished from real images. Here we explore and construct a model for generating several types of human activity sensor data using a Wasserstein GAN (WGAN). We assess the synthetic data using two commonly-used classifier models, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). We evaluate the quality and diversity of the synthetic data by training on synthetic data and testing on real sensor data, and vice versa. We then use synthetic sensor data to oversample the imbalanced training set. We demonstrate the efficacy of the proposed method on two publicly available human activity datasets, the Sussex-Huawei Locomotion (SHL) and Smoking Activity Dataset (SAD). We achieve improvements of using WGAN augmented training data over the imbalanced case, for both SHL (0.85 to 0.95 F1-score), and for SAD (0.70 to 0.77 F1-score) when using a CNN activity classifier.

show abstract

A Comparative Approach to Classification of Locomotion and Transportation Modes Using Smartphone Sensor Data

Cited by 34 publications

References 9 publications

Summary of the Sussex-Huawei Locomotion-Transportation Recognition Challenge

Summary of the Sussex-Huawei Locomotion-Transportation Recognition Challenge

Summary of the Sussex-Huawei locomotion-transportation recognition challenge 2019

Synthetic Sensor Data for Human Activity Recognition

Contact Info

Product

Resources

About