Human activity classification based on sound recognition and residual convolutional neural network

Jung, Mi-Ra; Chi, Seokho

doi:10.1016/j.autcon.2020.103177

Cited by 53 publications

(31 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To highlight the advantages of the proposed model, we compared with some of the state-of-the-art baseline models used for CV task and medical images applications as VGG-16 [13], ResNet50v2 [14], DenseNet121 [15] and the LZNet2019 [37] that was the top result until the development of this research.VGG-16 and DenseNet121 use images of dimensions 224 × 224 as input. Moreover, the LZNet2019 uses 150 × 150 as input.…”

Section: Test Resultsmentioning

confidence: 99%

“…Since then, and with the publication of the Deep Learning article [19], baseline models of CNN designed for CV tasks and normally trained in the ILSVRC, have been released to reuse the models. Examples of baseline models are VGG-16 network [13], Inception-v3 network [20], Residual Networks versions 1 and 2 (ResNet) [14,21], depth-wise separable convolutions networks (Xception) [22], Densely Connected Networks (DenseNet) [15], among others. These CNN baseline models are often used to implement new systems for CV task and for CADe and CADx [23].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…Among DL models, there exist Convolutional Neural Networks (CNN) that are widely used in Computer Vision (CV) tasks due to their capabilities for feature extraction [9].Although several works for CNN have been developed in this area in CAD to classify medical images between lesions and non-lesions [6], for automated brain abnormality classification [7], multiple fetal organs segmentation [10], for brain tumor segmentation [11,12], there are possibilities to get better results to help the medical field using CNNs.Therefore, we propose the use of a pre-trained model of CNN that uses Transfer Learning (TL) technique to use it as initialization for the training of the CNN used for classification of CXRAY images of pneumonia and visualization of the possible localization of manifestations like fluid and pus.The main contribution of this research is a TL model of CNN for the classification of CXRAYs in conjunction with a preprocessing technique, and two approaches to solve the imbalance problem of the dataset. The proposed model is competitive compared to baseline architectures of CNN like the VGG-16 network [13], Residual Networks (ResNet-v2) [14], Densely Connected Networks (DenseNet) [15], and some of the state-of-the-art proposals.…”

mentioning

confidence: 99%

“…The main contribution of this research is a TL model of CNN for the classification of CXRAYs in conjunction with a preprocessing technique, and two approaches to solve the imbalance problem of the dataset. The proposed model is competitive compared to baseline architectures of CNN like the VGG-16 network [13], Residual Networks (ResNet-v2) [14], Densely Connected Networks (DenseNet) [15], and some of the state-of-the-art proposals.…”

mentioning

confidence: 99%

See 3 more Smart Citations

A Transfer Learning Method for Pneumonia Classification and Visualization

et al. 2020

View full text Add to dashboard Cite

Pneumonia is an infectious disease that affects the lungs and is one of the principal causes of death in children under five years old. The Chest X-ray images technique is one of the most used for diagnosing pneumonia. Several Machine Learning algorithms have been successfully used in order to provide computer-aided diagnosis by automatic classification of medical images. For its remarkable results, the Convolutional Neural Networks (models based on Deep Learning) that are widely used in Computer Vision tasks, such as classification of injuries and brain abnormalities, among others, stand out. In this paper, we present a transfer learning method that automatically classifies between 3883 chest X-ray images characterized as depicting pneumonia and 1349 labeled as normal. The proposed method uses the Xception Network pre-trained weights on ImageNet as an initialization. Our model is competitive with respect to state-of-the-art proposals. To make comparisons with other models, we have used four well-known performance measures, obtaining the following results: precision (0.84), recall (0.99), F1-score (0.91) and area under the ROC curve (0.97). These positive results allow us to consider our proposal as an alternative that can be useful in countries with a lack of equipment and specialized radiologists.

show abstract

Section: Test Resultsmentioning

confidence: 99%

Section: Convolutional Neural Networkmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

A Transfer Learning Method for Pneumonia Classification and Visualization

et al. 2020

View full text Add to dashboard Cite

show abstract

“…When the diagnosis is unsuccessful, this process is repeated. Detecting snoring problems with automatic classifiers using sound signals is a much faster and more comfortable method [ 13 , 14 ]. Computer-aided automatic detection systems increase the success of accurate diagnosis and treatment.…”

Section: Introductionmentioning

confidence: 99%

An automated snoring sound classification method based on local dual octal pattern and iterative hybrid feature selector

Tuncer

Akbal

Doğan

2021

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

show abstract

Proposed spatio‐temporal features for human activity classification using ensemble classification model

Tyagi

Singh

Dev

2023

Concurrency and Computation

View full text Add to dashboard Cite

Classifying human actions from still images or video sequences is a demanding task owing to issues, like lighting, backdrop clutter, variations in scale, partial occlusion, viewpoint, and appearance. A lot of appliances, together with video systems, human-computer interfaces, and surveillance necessitate a compound action recognition system. Here, the proposed system develops a novel scheme for HAR. Initially, filtering as well as background subtraction is done during preprocessing. Then, the features including local binary pattern (LBP), bag of the virtual word (BOW), and the proposed local spatio-temporal features are extracted. Then, in the recognition phase, an ensemble classification model is introduced that includes Recurrent Neural networks (RNN 1 and RNN 2) and Multi-Layer Perceptron (MLP 1 and MLP 2). The features are classified using RNN 1 and RNN 2, and the outputs from RNN 1 and RNN 2 are further classified using MLP 1 and MLP 2, respectively. Finally, the outputs attained from MLP 1 and MLP 2 are averaged and the final classified output is obtained. At last, the superiority of the developed approach is proved on varied measures. K E Y W O R D Saccuracy, human action, multi-layer perceptron, proposed spatio-temporal features, RNN INTRODUCTION"HAR is defined as a classification task where the movement of a person is categorized based on data received from different sources such as sensors, cameras, etc.". It has different appliances in healthcare, particularly in constant action monitoring and fall recognition of aged persons. [1][2][3] In addition, it has vast prospective to support emerging appliances namely, augmented reality, IoT, and indoor localization in smart construction controlling systems to offer a secure indoor surrounding with higher EE.Diverse studies were carried out on HAR techniques in the state of the works using computer vision, ambient devices, sensors, and smartphones. These approaches are usually classified into two classes, that is, passive and active monitoring schemes. [4][5][6] In an AMS, exterior devices like wearable sensors and cameras were deployed. Sensor-based HAR is extensively deployed in analysis, in which a person has to continually carry sensors such as gyroscope, pedometer, and accelerometer that can turn out to be difficult for the person in numerous cases, particularly for elder ones. [7][8][9]

show abstract

Human activity classification based on sound recognition and residual convolutional neural network

Cited by 53 publications

References 24 publications

A Transfer Learning Method for Pneumonia Classification and Visualization

A Transfer Learning Method for Pneumonia Classification and Visualization

An automated snoring sound classification method based on local dual octal pattern and iterative hybrid feature selector

Proposed spatio‐temporal features for human activity classification using ensemble classification model

Contact Info

Product

Resources

About