AN ADVANCED APPROACH TO RECOGNIZE HUMAN ACTIVITIES VIA DEEP LEARNING

The study of wearable and handheld sensors recognizing human activity improved our understanding of human behaviours and human objectives. Many academics seek to identify the activities of a user from raw data using the fewest necessary resources. In this article, we propose a network of profound beliefs, a full-service architecture for the recognition of activities (DBN-LSTM). This DBN-LSTM method improves the human predictability of raw data and reduces the complexity of the model as well as the requirement for comprehensive workmanship. A geographically and temporally rich network is CNN-LSTM. Our proposed model for the UCI HAR Public Data Set can achieve 99% accuracy and 92% precision.

Download Full-text

An Efficient and Lightweight Deep Learning Model for Human Activity Recognition Using Smartphones

Sensors ◽

10.3390/s21113845 ◽

2021 ◽

Vol 21 (11) ◽

pp. 3845

Author(s):

Ankita ◽

Shalli Rani ◽

Himanshi Babbar ◽

Sonya Coleman ◽

Aman Singh ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Activity Recognition ◽

Human Activity ◽

Human Activities ◽

Human Activity Recognition ◽

Alternative Form ◽

Accelerometer Data ◽

Time Step ◽

Proposed Model

Traditional pattern recognition approaches have gained a lot of popularity. However, these are largely dependent upon manual feature extraction, which makes the generalized model obscure. The sequences of accelerometer data recorded can be classified by specialized smartphones into well known movements that can be done with human activity recognition. With the high success and wide adaptation of deep learning approaches for the recognition of human activities, these techniques are widely used in wearable devices and smartphones to recognize the human activities. In this paper, convolutional layers are combined with long short-term memory (LSTM), along with the deep learning neural network for human activities recognition (HAR). The proposed model extracts the features in an automated way and categorizes them with some model attributes. In general, LSTM is alternative form of recurrent neural network (RNN) which is famous for temporal sequences’ processing. In the proposed architecture, a dataset of UCI-HAR for Samsung Galaxy S2 is used for various human activities. The CNN classifier, which should be taken single, and LSTM models should be taken in series and take the feed data. For each input, the CNN model is applied, and each input image’s output is transferred to the LSTM classifier as a time step. The number of filter maps for mapping of the various portions of image is the most important hyperparameter used. Transformation on the basis of observations takes place by using Gaussian standardization. CNN-LSTM, a proposed model, is an efficient and lightweight model that has shown high robustness and better activity detection capability than traditional algorithms by providing the accuracy of 97.89%.

Download Full-text

Human Activity Recognition using Fourier Transform Inspired Deep Learning Combination Model

International Journal of Sensors Wireless Communications and Control ◽

10.2174/2210327908666180727123657 ◽

2019 ◽

Vol 9 (1) ◽

pp. 16-31

Author(s):

Kyungkoo Jun

Keyword(s):

Fourier Transform ◽

Deep Learning ◽

Short Term Memory ◽

Window Size ◽

Sensor Data ◽

Data Sets ◽

Data Set ◽

Proposed Model ◽

Testing Data ◽

Labeling Scheme

Background & Objective: This paper proposes a Fourier transform inspired method to classify human activities from time series sensor data. Methods: Our method begins by decomposing 1D input signal into 2D patterns, which is motivated by the Fourier conversion. The decomposition is helped by Long Short-Term Memory (LSTM) which captures the temporal dependency from the signal and then produces encoded sequences. The sequences, once arranged into the 2D array, can represent the fingerprints of the signals. The benefit of such transformation is that we can exploit the recent advances of the deep learning models for the image classification such as Convolutional Neural Network (CNN). Results: The proposed model, as a result, is the combination of LSTM and CNN. We evaluate the model over two data sets. For the first data set, which is more standardized than the other, our model outperforms previous works or at least equal. In the case of the second data set, we devise the schemes to generate training and testing data by changing the parameters of the window size, the sliding size, and the labeling scheme. Conclusion: The evaluation results show that the accuracy is over 95% for some cases. We also analyze the effect of the parameters on the performance.

Download Full-text

Recognizing Human Daily Activity Using Social Media Sensors and Deep Learning

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph16203955 ◽

2019 ◽

Vol 16 (20) ◽

pp. 3955 ◽

Cited By ~ 2

Author(s):

Junfang Gong ◽

Runjia Li ◽

Hong Yao ◽

Xiaojun Kang ◽

Shengwen Li

Keyword(s):

Social Media ◽

Deep Learning ◽

Human Activity ◽

Daily Activity ◽

Low Cost ◽

Contextual Information ◽

Learning Sequence ◽

Proposed Model ◽

Application Fields ◽

Access Data

The human daily activity category represents individual lifestyle and pattern, such as sports and shopping, which reflect personal habits, lifestyle, and preferences and are of great value for human health and many other application fields. Currently, compared to questionnaires, social media as a sensor provides low-cost and easy-to-access data sources, providing new opportunities for obtaining human daily activity category data. However, there are still some challenges to accurately recognizing posts because existing studies ignore contextual information or word order in posts and remain unsatisfactory for capturing the activity semantics of words. To address this problem, we propose a general model for recognizing the human activity category based on deep learning. This model not only describes how to extract a sequence of higher-level word phrase representations in posts based on the deep learning sequence model but also how to integrate temporal information and external knowledge to capture the activity semantics in posts. Considering that no benchmark dataset is available in such studies, we built a dataset that was used for training and evaluating the model. The experimental results show that the proposed model significantly improves the accuracy of recognizing the human activity category compared with traditional classification methods.

Download Full-text

Classification of electrocardiogram signal using an ensemble of deep learning models

Data Technologies and Applications ◽

10.1108/dta-05-2020-0108 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Saroj Kumar Pandey ◽

Rekh Ram Janghel

Keyword(s):

Deep Learning ◽

Majority Voting ◽

Classification Model ◽

World Health ◽

Product Rule ◽

Learning Models ◽

Data Set ◽

Raw Data ◽

Content Type ◽

Heartbeat Classification

PurposeAccording to the World Health Organization, arrhythmia is one of the primary causes of deaths across the globe. In order to reduce mortality rate, cardiovascular disease should be properly identified and the proper treatment for the same should be immediately provided to the patients. The objective of this paper was to implement a better heartbeat classification model which will work better than the other implemented heartbeat classification methods.Design/methodology/approachIn this paper, the ensemble of two deep learning models is proposed to classify the MIT-BIH arrhythmia database into four different classes according to ANSI-AAMI standards. First, a convolutional neural network (CNN) model is used to classify heartbeats on a raw data set. Secondly, four features (wavelets, R-R intervals, morphological and higher-order statistics) are extracted from the data set and then applied to a long short-term memory (LSTM) model to classify the heartbeats. Finally, the ensemble of CNN and LSTM model with sum rule, product rule and majority voting has been used to identify the heartbeat classes.FindingsAmong these, the highest accuracy obtained is 98.58% using ensemble method with product rule. The results show that the ensemble of CNN and BLSTM has offered satisfactory performance compared to other techniques discussed in this study.Originality/valueIn this study, we have developed a new combination of two deep learning models to enhance the performance of arrhythmia classification using segmentation of input ECG signals. The contributions of this study are as follows: First, a deep CNN model is built to classify ECG heartbeat using a raw data set. Second, four types of features (R-R interval, HOS, morphological and wavelet) were extracted from the raw data set and then applied to the bidirectional LSTM model to classify the ECG heartbeat. Third, combination rules (sum rules, product rules and majority voting rules) were tested to ensure the accumulated probabilities of the CNN and LSTM models.

Download Full-text

MIScnn: a framework for medical image segmentation with convolutional neural networks and deep learning

BMC Medical Imaging ◽

10.1186/s12880-020-00543-7 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Dominik Müller ◽

Frank Kramer

Keyword(s):

Image Segmentation ◽

Deep Learning ◽

Medical Image ◽

Cross Validation ◽

Data Augmentation ◽

Semantic Segmentation ◽

Medical Image Segmentation ◽

Tumor Segmentation ◽

Data Set ◽

Public Data

Abstract Background The increased availability and usage of modern medical imaging induced a strong need for automatic medical image segmentation. Still, current image segmentation platforms do not provide the required functionalities for plain setup of medical image segmentation pipelines. Already implemented pipelines are commonly standalone software, optimized on a specific public data set. Therefore, this paper introduces the open-source Python library MIScnn. Implementation The aim of MIScnn is to provide an intuitive API allowing fast building of medical image segmentation pipelines including data I/O, preprocessing, data augmentation, patch-wise analysis, metrics, a library with state-of-the-art deep learning models and model utilization like training, prediction, as well as fully automatic evaluation (e.g. cross-validation). Similarly, high configurability and multiple open interfaces allow full pipeline customization. Results Running a cross-validation with MIScnn on the Kidney Tumor Segmentation Challenge 2019 data set (multi-class semantic segmentation with 300 CT scans) resulted into a powerful predictor based on the standard 3D U-Net model. Conclusions With this experiment, we could show that the MIScnn framework enables researchers to rapidly set up a complete medical image segmentation pipeline by using just a few lines of code. The source code for MIScnn is available in the Git repository: https://github.com/frankkramer-lab/MIScnn.

Download Full-text

Margin-Based Deep Learning Networks for Human Activity Recognition

Sensors ◽

10.3390/s20071871 ◽

2020 ◽

Vol 20 (7) ◽

pp. 1871 ◽

Cited By ~ 2

Author(s):

Tianqi Lv ◽

Xiaojuan Wang ◽

Lei Jin ◽

Yabo Xiao ◽

Mei Song

Keyword(s):

Deep Learning ◽

Activity Recognition ◽

Human Activity ◽

Human Activities ◽

Human Activity Recognition ◽

Learning Networks ◽

Class Separation ◽

Open Set ◽

Challenging Research ◽

Classification Tasks

Human activity recognition (HAR) is a popular and challenging research topic, driven by a variety of applications. More recently, with significant progress in the development of deep learning networks for classification tasks, many researchers have made use of such models to recognise human activities in a sensor-based manner, which have achieved good performance. However, sensor-based HAR still faces challenges; in particular, recognising similar activities that only have a different sequentiality and similarly classifying activities with large inter-personal variability. This means that some human activities have large intra-class scatter and small inter-class separation. To deal with this problem, we introduce a margin mechanism to enhance the discriminative power of deep learning networks. We modified four kinds of common neural networks with our margin mechanism to test the effectiveness of our proposed method. The experimental results demonstrate that the margin-based models outperform the unmodified models on the OPPORTUNITY, UniMiB-SHAR, and PAMAP2 datasets. We also extend our research to the problem of open-set human activity recognition and evaluate the proposed method’s performance in recognising new human activities.

Download Full-text

Convolution Based Neural Network Model to Prevent Diseases Classification and Prediction Using Deep Learning

International Journal of Computer Science and Mobile Computing ◽

10.47760/ijcsmc.2021.v10i08.008 ◽

2021 ◽

Vol 10 (8) ◽

pp. 46-50

Author(s):

D J Samatha Naidu ◽

M.Gurivi Reddy

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Deep Learning ◽

The Internet ◽

Learning Models ◽

Data Set ◽

Proposed Model ◽

Recent Developments ◽

Automatic Image Recognition ◽

Recognition Systems

The farmer is a backbone to nation, but majority of the cultivated crops in india affecting by various diseases at various stages of its cultivation. Recent research works shows that diseases are not providing accurate results and few identifying but not providing optimized solutions to the system. In proposed work, the recent developments of Artificial intelligence through Deep Learning show that AIR (Automatic Image Recognition systems) using CNN algorithm models can be very beneficial in such scenarios. The Rice leaf diseases images related dataset is not easily available to automate , so that we have created our own trained data set which is small in size hence we have used transfer learning to develop our Proposed model which supports deep learning models. The Proposed CNN architecture illustrated based on VGG-16 model and it is trained, tested on given dataset collected from rice fields and the internet. The accuracy of the proposed model is moderately accurate with 92.46%.

Download Full-text

Adaptation and Selection Techniques Based on Deep Learning for Human Activity Recognition Using Inertial Sensors

Engineering Proceedings ◽

10.3390/ecsa-7-08159 ◽

2020 ◽

Vol 2 (1) ◽

pp. 22

Author(s):

Manuel Gil-Martín ◽

José Antúnez-Durango ◽

Rubén San-Segundo

Keyword(s):

Deep Learning ◽

Activity Recognition ◽

Human Activity ◽

Inertial Sensors ◽

Human Activity Recognition ◽

Training Data ◽

Generative Adversarial Networks ◽

Data Set ◽

Physical Activity Monitoring ◽

Training Data Selection

Deep learning techniques have been widely applied to Human Activity Recognition (HAR), but a specific challenge appears when HAR systems are trained and tested with different subjects. This paper describes and evaluates several techniques based on deep learning algorithms for adapting and selecting the training data used to generate a HAR system using accelerometer recordings. This paper proposes two alternatives: autoencoders and Generative Adversarial Networks (GANs). Both alternatives are based on deep neural networks including convolutional layers for feature extraction and fully-connected layers for classification. Fast Fourier Transform (FFT) is used as a transformation of acceleration data to provide an appropriate input data to the deep neural network. This study has used acceleration recordings from hand, chest and ankle sensors included in the Physical Activity Monitoring Data Set (PAMAP2) dataset. This is a public dataset including recordings from nine subjects while performing 12 activities such as walking, running, sitting, ascending stairs, or ironing. The evaluation has been performed using a Leave-One-Subject-Out (LOSO) cross-validation: all recordings from a subject are used as testing subset and recordings from the rest of the subjects are used as training subset. The obtained results suggest that strategies using autoencoders to adapt training data to testing data improve some users’ performance. Moreover, training data selection algorithms with autoencoders provide significant improvements. The GAN approach, using the generator or discriminator module, also provides improvement in selection experiments.

Download Full-text