GAN for Generating User-Specific Human Activity Data From An Incomplete Training Corpus

Deep learning models for human activity recognition (HAR) based on sensor data have been heavily studied recently. However, the generalization ability of deep models on complex real-world HAR data is limited by the availability of high-quality labeled activity data, which are hard to obtain. In this article, we design a similarity embedding neural network that maps input sensor signals onto real vectors through carefully designed convolutional and Long Short-Term Memory (LSTM) layers. The embedding network is trained with a pairwise similarity loss, encouraging the clustering of samples from the same class in the embedded real space, and can be effectively trained on a small dataset and even on a noisy dataset with mislabeled samples. Based on the learned embeddings, we further propose both nonparametric and parametric approaches for activity recognition. Extensive evaluation based on two public datasets has shown that the proposed similarity embedding network significantly outperforms state-of-the-art deep models on HAR classification tasks, is robust to mislabeled samples in the training set, and can also be used to effectively denoise a noisy dataset.

Download Full-text

Data Augmentation Strategies for Human Activity Data Using Generative Adversarial Neural Networks

2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops) ◽

10.1109/percomworkshops51409.2021.9431046 ◽

2021 ◽

Author(s):

Alexander Hoelzemann ◽

Nimish Sorathiya ◽

Kristof Van Laerhoven

Keyword(s):

Neural Networks ◽

Human Activity ◽

Data Augmentation ◽

Activity Data ◽

Augmentation Strategies

Download Full-text

On-Device Deep Learning Inference for Efficient Activity Data Collection

Sensors ◽

10.3390/s19153434 ◽

2019 ◽

Vol 19 (15) ◽

pp. 3434 ◽

Cited By ~ 2

Author(s):

Nattaya Mairittha ◽

Tittaya Mairittha ◽

Sozo Inoue

Keyword(s):

Deep Learning ◽

Data Collection ◽

Activity Recognition ◽

Human Activity ◽

Short Term Memory ◽

Human Activity Recognition ◽

Classification Model ◽

Activity Data ◽

Ground Truth Data ◽

Recognition Systems

Labeling activity data is a central part of the design and evaluation of human activity recognition systems. The performance of the systems greatly depends on the quantity and “quality” of annotations; therefore, it is inevitable to rely on users and to keep them motivated to provide activity labels. While mobile and embedded devices are increasingly using deep learning models to infer user context, we propose to exploit on-device deep learning inference using a long short-term memory (LSTM)-based method to alleviate the labeling effort and ground truth data collection in activity recognition systems using smartphone sensors. The novel idea behind this is that estimated activities are used as feedback for motivating users to collect accurate activity labels. To enable us to perform evaluations, we conduct the experiments with two conditional methods. We compare the proposed method showing estimated activities using on-device deep learning inference with the traditional method showing sentences without estimated activities through smartphone notifications. By evaluating with the dataset gathered, the results show our proposed method has improvements in both data quality (i.e., the performance of a classification model) and data quantity (i.e., the number of data collected) that reflect our method could improve activity data collection, which can enhance human activity recognition systems. We discuss the results, limitations, challenges, and implications for on-device deep learning inference that support activity data collection. Also, we publish the preliminary dataset collected to the research community for activity recognition.

Download Full-text

Human activity data discovery from triaxial accelerometer sensor: Non-supervised learning sensitivity to feature extraction parametrization

Information Processing & Management ◽

10.1016/j.ipm.2014.07.008 ◽

2015 ◽

Vol 51 (2) ◽

pp. 204-214 ◽

Cited By ~ 32

Author(s):

Inês P. Machado ◽

A. Luísa Gomes ◽

Hugo Gamboa ◽

Vítor Paixão ◽

Rui M. Costa

Keyword(s):

Feature Extraction ◽

Supervised Learning ◽

Human Activity ◽

Triaxial Accelerometer ◽

Data Discovery ◽

Accelerometer Sensor ◽

Activity Data

Download Full-text

Understanding core districts of city using human activity data

Advances in Modelling and Analysis B ◽

10.18280/ama_b.600114 ◽

2017 ◽

Vol 60 (1) ◽

pp. 224-238

Author(s):

Duan Hu ◽

Jie Yang ◽

Benxiong Huang

Keyword(s):

Human Activity ◽

Activity Data

Download Full-text

Active tool for human activity data collection

Electronics Letters ◽

10.1049/el.2011.2705 ◽

2011 ◽

Vol 47 (25) ◽

pp. 1370-1372 ◽

Cited By ~ 1

Author(s):

M. Shoyaib ◽

O. Chae ◽

Y.K. Lee ◽

A.M.J. Sarkar ◽

A.M. Khan

Keyword(s):

Data Collection ◽

Human Activity ◽

Activity Data

Download Full-text

Simulating Offender Mobility: Modeling Activity Nodes from Large-Scale Human Activity Data

Journal of Artificial Intelligence Research ◽

10.1613/jair.1.11831 ◽

2020 ◽

Vol 68 ◽

pp. 541-570

Author(s):

Raquel Rosés ◽

Cristina Kadar ◽

Charlotte Gerritsen ◽

Chris Rouly

Keyword(s):

Human Activity ◽

Urban Areas ◽

Large Scale ◽

Complex Dynamics ◽

Open Data ◽

Human Movement ◽

Urban Structure ◽

Real World Data ◽

Activity Data ◽

Agent Based

In recent years, simulation techniques have been applied to investigate the spatiotemporal dynamics of crime. Researchers have instantiated mobile offenders in agent-based simulations for theory testing, experimenting with crime prevention strategies, and exploring crime prediction techniques, despite facing challenges due to the complex dynamics of crime and the lack of detailed information about offender mobility. This paper presents a simulation model to explore offender mobility, focusing on the interplay between the agent's awareness space and activity nodes. The simulation generates patterns of individual mobility aiming to cumulatively match crime patterns. To instantiate a realistic urban environment, we use open data to simulate the urban structure, location-based social networks data to represent activity nodes as a proxy for human activity, and taxi trip data as a proxy for human movement between regions of the city. We analyze and systematically compare 35 different mobility strategies and demonstrate the benefits of using large-scale human activity data to simulate offender mobility. The strategies combining taxi trip data or historic crime data with popular activity nodes perform best compared to other strategies, especially for robbery. Our approach provides a basis for building agent-based crime simulations that infer offender mobility in urban areas from real-world data.

Download Full-text

Sensor Data Acquisition and Multimodal Sensor Fusion for Human Activity Recognition Using Deep Learning

Sensors ◽

10.3390/s19071716 ◽

2019 ◽

Vol 19 (7) ◽

pp. 1716 ◽

Cited By ~ 20

Author(s):

Seungeun Chung ◽

Jiyoun Lim ◽

Kyoung Ju Noh ◽

Gague Kim ◽

Hyuntae Jeong

Keyword(s):

Deep Learning ◽

Data Acquisition ◽

Sensor Fusion ◽

Activity Recognition ◽

Human Activity ◽

Short Term Memory ◽

Sampling Rate ◽

Human Activity Recognition ◽

Sensor Data ◽

Activity Data

In this paper, we perform a systematic study about the on-body sensor positioning and data acquisition details for Human Activity Recognition (HAR) systems. We build a testbed that consists of eight body-worn Inertial Measurement Units (IMU) sensors and an Android mobile device for activity data collection. We develop a Long Short-Term Memory (LSTM) network framework to support training of a deep learning model on human activity data, which is acquired in both real-world and controlled environments. From the experiment results, we identify that activity data with sampling rate as low as 10 Hz from four sensors at both sides of wrists, right ankle, and waist is sufficient in recognizing Activities of Daily Living (ADLs) including eating and driving activity. We adopt a two-level ensemble model to combine class-probabilities of multiple sensor modalities, and demonstrate that a classifier-level sensor fusion technique can improve the classification performance. By analyzing the accuracy of each sensor on different types of activity, we elaborate custom weights for multimodal sensor fusion that reflect the characteristic of individual activities.

Download Full-text

A Fast and Robust Deep Convolutional Neural Networks for Complex Human Activity Recognition Using Smartphone

Sensors ◽

10.3390/s19173731 ◽

2019 ◽

Vol 19 (17) ◽

pp. 3731 ◽

Cited By ~ 17

Author(s):

Wen Qi ◽

Hang Su ◽

Chenguang Yang ◽

Giancarlo Ferrigno ◽

Elena De Momi ◽

...

Keyword(s):

Activity Recognition ◽

Human Activity ◽

Human Activity Recognition ◽

Streaming Data ◽

Computational Method ◽

Measurement Unit ◽

Deep Convolutional Neural Networks ◽

Activity Data ◽

Intelligent Sensors ◽

Signal Processing Algorithms

As a significant role in healthcare and sports applications, human activity recognition (HAR) techniques are capable of monitoring humans’ daily behavior. It has spurred the demand for intelligent sensors and has been giving rise to the explosive growth of wearable and mobile devices. They provide the most availability of human activity data (big data). Powerful algorithms are required to analyze these heterogeneous and high-dimension streaming data efficiently. This paper proposes a novel fast and robust deep convolutional neural network structure (FR-DCNN) for human activity recognition (HAR) using a smartphone. It enhances the effectiveness and extends the information of the collected raw data from the inertial measurement unit (IMU) sensors by integrating a series of signal processing algorithms and a signal selection module. It enables a fast computational method for building the DCNN classifier by adding a data compression module. Experimental results on the sampled 12 complex activities dataset show that the proposed FR-DCNN model is the best method for fast computation and high accuracy recognition. The FR-DCNN model only needs 0.0029 s to predict activity in an online way with 95.27% accuracy. Meanwhile, it only takes 88 s (average) to establish the DCNN classifier on the compressed dataset with less precision loss 94.18%.

Download Full-text

A Comparative Study of Feature Selection Approaches for Human Activity Recognition Using Multimodal Sensory Data

Sensors ◽

10.3390/s21072368 ◽

2021 ◽

Vol 21 (7) ◽

pp. 2368

Author(s):

Fatima Amjad ◽

Muhammad Hassan Khan ◽

Muhammad Adeel Nisar ◽

Muhammad Shahid Farid ◽

Marcin Grzegorzek

Keyword(s):

Activity Recognition ◽

Human Activity ◽

Human Body ◽

Human Activities ◽

Wearable Sensors ◽

Human Activity Recognition ◽

Motion Sensors ◽

Activity Data ◽

Sensory Data ◽

Atomic Actions

Human activity recognition (HAR) aims to recognize the actions of the human body through a series of observations and environmental conditions. The analysis of human activities has drawn the attention of the research community in the last two decades due to its widespread applications, diverse nature of activities, and recording infrastructure. Lately, one of the most challenging applications in this framework is to recognize the human body actions using unobtrusive wearable motion sensors. Since the human activities of daily life (e.g., cooking, eating) comprises several repetitive and circumstantial short sequences of actions (e.g., moving arm), it is quite difficult to directly use the sensory data for recognition because the multiple sequences of the same activity data may have large diversity. However, a similarity can be observed in the temporal occurrence of the atomic actions. Therefore, this paper presents a two-level hierarchical method to recognize human activities using a set of wearable sensors. In the first step, the atomic activities are detected from the original sensory data, and their recognition scores are obtained. Secondly, the composite activities are recognized using the scores of atomic actions. We propose two different methods of feature extraction from atomic scores to recognize the composite activities, and they include handcrafted features and the features obtained using the subspace pooling technique. The proposed method is evaluated on the large publicly available CogAge dataset, which contains the instances of both atomic and composite activities. The data is recorded using three unobtrusive wearable devices: smartphone, smartwatch, and smart glasses. We also investigated the performance evaluation of different classification algorithms to recognize the composite activities. The proposed method achieved 79% and 62.8% average recognition accuracies using the handcrafted features and the features obtained using subspace pooling technique, respectively. The recognition results of the proposed technique and their comparison with the existing state-of-the-art techniques confirm its effectiveness.

Download Full-text