Application of CNN for Human Activity Recognition with FFT Spectrogram of Acceleration and Gyro Sensors

Ito, Chihiro; Cao, Xin; Shimizu, Masaki; Maeda, Eriko

doi:10.1145/3267305.3267517

Cited by 37 publications

(40 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recurring neural networks (RNNs) remove temporal addiction and slowly acquire information over time to transmit sensory input to understand human behavior. • Deep neural networking can be detachable and scalable into interconnected networks with a global optimization feature that promotes various profound learning strategies like profound communication learning [14], deep active education [15], a framework for deeper attention [16] and other approaches that are not systemic and effective [17], [18]. Works which take these techniques into account serve to numerous deep learning challenges.…”

Section: B Context Of Deep Learningmentioning

confidence: 99%

RETRACTED ARTICLE: Human activity recognition with deep learning: overview, challenges and possibilities

Kumar

Chauhan

2021

CCF Trans. Pervasive Comp. Interact.

View full text Add to dashboard Cite

The growing use of sensor tools and the Internet of Things requires sensors to understand the applications. There are major difficulties in realistic situations, though, that can impact the efficiency of the recognition system. Recently, as the utility of deep learning in many fields has been shown, various deep approaches were researched to tackle the challenges of detection and recognition. We present in this review a sample of specialized deep learning approaches for the identification of sensor based human behavior. Next, we present the multi-modal sensory data and include information for the public databases which can be used in different challenge tasks for study. A new taxonomy is then suggested, to organize deep approaches according to challenges. Deep problems and approaches connected to problems are summarized and evaluated to provide an analysis of the ongoing advancement in science. By the conclusion of this research, we are answering unanswered issues and providing perspectives into the future.

show abstract

Section: B Context Of Deep Learningmentioning

confidence: 99%

RETRACTED ARTICLE: Human activity recognition with deep learning: overview, challenges and possibilities

Kumar

Chauhan

2021

CCF Trans. Pervasive Comp. Interact.

View full text Add to dashboard Cite

show abstract

“…Many methods are used to convert the one-dimensional sensor data into the two-dimensional data through the matrix rearrangement [14], [29], [30], which is the simple listing and superposition of the data, but lacks interpretability. In [15], [31], [32], the one-dimensional time series were converted to the two-dimensional time-frequency images by Fourier transform, which led to a sharp increase in the amount of computations. Due to the requirements of portability and real-time property of wearable sensor devices, it is inevitable that sensor-based activity recognition methods require fewer computing resources and faster calculation speed.…”

Section: Introductionmentioning

confidence: 99%

Human Activity Recognition Based on Gramian Angular Field and Deep Convolutional Neural Network

Yuan

et al. 2020

IEEE Access

View full text Add to dashboard Cite

With the development of the Internet of things (IoT) and wearable devices, the sensor-based human activity recognition (HAR) has attracted more and more attentions from researchers due to its outstanding characteristics of convenience and privacy. Meanwhile, deep learning algorithms can extract high-dimensional features automatically, which makes it possible to achieve the end-to-end learning. Especially the convolutional neural network (CNN) has been widely used in the field of computer vision, while the influence of environmental background, camera shielding, and other factors are the biggest challenges to it. However, the sensor-based HAR can circumvent these problems well. Two improved HAR methods based on Gramian angular field (GAF) and deep CNN are proposed in this paper. Firstly, the GAF algorithm is used to transform the one-dimensional sensor data into the two-dimensional images. Then, through the multi-dilated kernel residual (Mdk-Res) module, a new improved deep CNN network Mdk-ResNet is proposed, which extracts the features among sampling points with different intervals. Furthermore, the Fusion-Mdk-ResNet is adopted to process and fuse data collected by different sensors automatically. The comparative experiments are conducted on three public activity datasets, which are WISDM, UCI HAR and OPPORTUNITY. The optimal results are obtained by using the indexes such as accuracy, precision, recall and F-measure, which verifies the effectiveness of the proposed methods.

show abstract

“…Most submission utilize all the 7 sensor modalities for the recognition task. However, one submission [3] utilizing two sensor modalities only (accelerometer and gyroscope) achieves quite good performance (88.8%), ranking 3rd among all the candidates.…”

Section: Resultsmentioning

confidence: 99%

“…Since JSI-Deep and JSI-Classic are submitted from the same research group, it might imply that DL does not bring significant advantage over ML if both of them are fully optimized. In addition, the second best DL approach (Tesaguri [3], 88.8%), which uses a pure deep classifier, obtains even lower F1 score than JSI-Classic. Fig.…”

Section: Summary Of Approachesmentioning

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

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

Application of CNN for Human Activity Recognition with FFT Spectrogram of Acceleration and Gyro Sensors

Cited by 37 publications

References 3 publications

RETRACTED ARTICLE: Human activity recognition with deep learning: overview, challenges and possibilities

RETRACTED ARTICLE: Human activity recognition with deep learning: overview, challenges and possibilities

Human Activity Recognition Based on Gramian Angular Field and Deep Convolutional Neural Network

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

Contact Info

Product

Resources

About