On the Generality of Codebook Approach for Sensor-Based Human Activity Recognition

Shirahama, Kimiaki; Grzegorzek, Marcin

doi:10.3390/electronics6020044

Cited by 23 publications

(27 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Codebook-based methods can be regarded as one-layer CNN, as codewords are learned in a similar unsupervised way to convolutional kernels. They were used in previous works for time series classification [ 23 ] or HAR [ 24 ].…”

Section: Methodsmentioning

confidence: 99%

Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors

Shirahama

Nisar

et al. 2018

Sensors

Self Cite

246

200

View full text Add to dashboard Cite

Getting a good feature representation of data is paramount for Human Activity Recognition (HAR) using wearable sensors. An increasing number of feature learning approaches—in particular deep-learning based—have been proposed to extract an effective feature representation by analyzing large amounts of data. However, getting an objective interpretation of their performances faces two problems: the lack of a baseline evaluation setup, which makes a strict comparison between them impossible, and the insufficiency of implementation details, which can hinder their use. In this paper, we attempt to address both issues: we firstly propose an evaluation framework allowing a rigorous comparison of features extracted by different methods, and use it to carry out extensive experiments with state-of-the-art feature learning approaches. We then provide all the codes and implementation details to make both the reproduction of the results reported in this paper and the re-use of our framework easier for other researchers. Our studies carried out on the OPPORTUNITY and UniMiB-SHAR datasets highlight the effectiveness of hybrid deep-learning architectures involving convolutional and Long-Short-Term-Memory (LSTM) to obtain features characterising both short- and long-term time dependencies in the data.

show abstract

Section: Methodsmentioning

confidence: 99%

Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors

Shirahama

Nisar

et al. 2018

Sensors

Self Cite

246

200

View full text Add to dashboard Cite

show abstract

“…We conducted learning and recognition tasks with all methods for RCE-NN on two datasets for a gas sensor and motion-capture hand postures (MCHP) [18,19]. Two datasets have been used in gas detection and human machine interation (HMI) [20,21]. The gas sensor dataset contains 128-dimensional feature vectors taken from 16 gas sensor arrays for 36 months to detect six toxic gase.…”

Section: Performance Evaluation Resultsmentioning

confidence: 99%

VLSI Implementation of Restricted Coulomb Energy Neural Network with Improved Learning Scheme

et al. 2019

View full text Add to dashboard Cite

This paper proposes a restricted coulomb energy neural network (RCE-NN) with an improved learning algorithm and presents the hardware architecture design and VLSI implementation results. The learning algorithm of the existing RCE-NN applies an inefficient radius adjustment, such as learning all neurons at the same radius or reducing the radius excessively in the learning process. Moreover, since the reliability of eliminating unnecessary neurons is estimated without considering the activation region of each neuron, it is inaccurate and leaves unnecessary neurons extant. To overcome this problem, the proposed learning algorithm divides each neuron region in the learning process and measures the reliability with different factors for each region. In addition, it applies a process of gradual radius reduction by a pre-defined reduction rate. In performance evaluations using two datasets, RCE-NN with the proposed learning algorithm showed high recognition accuracy with fewer neurons compared to existing RCE-NNs. The proposed RCE-NN processor was implemented with 197.8K logic gates in 0.535 mm 2 using a 55 nm CMOS process and operated at the clock frequency of 150 MHz.

show abstract

“…In Learning-based methods, we can discover adequate features without expert knowledge and systematic exploration of the feature space. Conventional methods in our comparative study include Hand-Crafted Features (HC) [21], Codebook approach (CB) [22]. The learning-based methods include Autoencoders approach (AE) [24], Multi-Layer Perceptron (MLP) [25], Convolutional Neural Network (CNN) [14], Long-Short Term Memory Networks (LSTM) [26], Hybrid Convolutional and Recurrent Networks (Hybrid) [27], Deep Residual Learning (ResNet) [20].…”

Section: Related Work I Methods For Human Activity Recognitionmentioning

confidence: 99%

“…We compared our proposed ARN method against some classic or state-of-the-art activity recognition methods. We roughly divided these methods into categories: conventional recognition methods include HC [21], CBH [22], CBS [23]. The learning-based methods include AE [24], MLP [25], CNN [14], LSTM [26], Hybrid [27], ResNet [20].…”

Section: Baselinementioning

confidence: 99%

Asymmetric Residual Neural Network for Accurate Human Activity Recognition

et al. 2019

View full text Add to dashboard Cite

Human Activity Recognition (HAR) using deep neural network has become a hot topic in human-computer interaction. Machine can effectively identify human naturalistic activities by learning from a large collection of sensor data. Activity recognition is not only an interesting research problem, but also has many real-world practical applications. Based on the success of residual networks in achieving a high level of aesthetic representation of the automatic learning, we propose a novel Asymmetric Residual Network, named ARN. ARN is implemented using two identical path frameworks consisting of (1) a short time window, which is used to capture spatial features, and (2) a long time window, which is used to capture fine temporal features. The long time window path can be made very lightweight by reducing its channel capacity, yet still being able to learn useful temporal representations for activity recognition. In this paper, we mainly focus on proposing a new model to improve the accuracy of HAR. In order to demonstrate the effectiveness of ARN model, we carried out extensive experiments on benchmark datasets (i.e., OPPORTUNITY, UniMiB-SHAR) and compared with some conventional and state-of-the-art learning-based methods. Then, we discuss the influence of networks parameters on performance to provide insights about its optimization. Results from our experiments show that ARN is effective in recognizing human activities via wearable datasets.

show abstract

On the Generality of Codebook Approach for Sensor-Based Human Activity Recognition

Cited by 23 publications

References 42 publications

Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors

Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors

VLSI Implementation of Restricted Coulomb Energy Neural Network with Improved Learning Scheme

Asymmetric Residual Neural Network for Accurate Human Activity Recognition

Contact Info

Product

Resources

About