Human Activity Recognition using Fourier Transform Inspired Deep Learning Combination Model

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.

A Robust Deep Learning Segmentation Method for Hematoma Volumetric Detection in Intracerebral Hemorrhage

Stroke ◽  
2021 ◽  
Author(s):  
Nannan Yu ◽  
He Yu ◽  
Haonan Li ◽  
Nannan Ma ◽  
Chunai Hu ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Image Segmentation ◽  
Deep Learning ◽  
Intracerebral Hemorrhage ◽  
Epidural Hematoma ◽  
Contour Method ◽  
Data Sets ◽  
Segmentation Method ◽  
Data Set ◽  
Testing Data

Background and Purpose: Hematoma volume (HV) is a significant diagnosis for determining the clinical stage and therapeutic approach for intracerebral hemorrhage (ICH). The aim of this study is to develop a robust deep learning segmentation method for the fast and accurate HV analysis using computed tomography. Methods: A novel dimension reduction UNet (DR-UNet) model was developed for computed tomography image segmentation and HV measurement. Two data sets, 512 ICH patients with 12 568 computed tomography slices in the retrospective data set and 50 ICH patients with 1257 slices in the prospective data set, were used for network training, validation, and internal and external testing. Moreover, 13 irregular hematoma cases, 11 subdural and epidural hematoma cases, and 50 different HV cases into 3 groups (<30, 30–60, and >60 mL) were selected to further evaluate the robustness of DR-UNet. The image segmentation performance of DR-UNet was compared with those of UNet, the fuzzy clustering method, and the active contour method. The HV measurement performance was compared using DR-UNet, UNet, and the Coniglobus formula method. Results: Using DR-UNet, the segmentation model achieved a performance similar to that of expert clinicians in 2 independent test data sets containing internal testing data (Dice of 0.861±0.139) and external testing data (Dice of 0.874±0.130). The HV measurement derived from DR-UNet was strongly correlated with that from manual segmentation (R 2 =0.9979; P <0.0001). In the irregularly shaped hematoma group and the subdural and epidural hematoma group, DR-UNet was more robust than UNet in both hematoma segmentation and HV measurement. There is no statistical significance in segmentation accuracy among 3 different HV groups. Conclusions: DR-UNet can segment hematomas from the computed tomography scans of ICH patients and quantify the HV with better accuracy and greater efficiency than the main existing methods and with similar performance to expert clinicians. Due to robust performance and stable segmentation on different ICHs, DR-UNet could facilitate the development of deep learning systems for a variety of clinical applications.

scholarly journals Optimising Deep Learning at the Edge for Accurate Hourly Air Quality Prediction

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1064
Author(s):  
I Nyoman Kusuma Wardana ◽  
Julian W. Gardner ◽  
Suhaib A. Fahmy
Keyword(s):  
Deep Learning ◽  
Air Quality ◽  
Short Term Memory ◽  
Model Performance ◽  
Learning Model ◽  
Sensor Data ◽  
Raspberry Pi ◽  
Learning Models ◽  
Proposed Model ◽  
Deep Learning Model

Accurate air quality monitoring requires processing of multi-dimensional, multi-location sensor data, which has previously been considered in centralised machine learning models. These are often unsuitable for resource-constrained edge devices. In this article, we address this challenge by: (1) designing a novel hybrid deep learning model for hourly PM2.5 pollutant prediction; (2) optimising the obtained model for edge devices; and (3) examining model performance running on the edge devices in terms of both accuracy and latency. The hybrid deep learning model in this work comprises a 1D Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) to predict hourly PM2.5 concentration. The results show that our proposed model outperforms other deep learning models, evaluated by calculating RMSE and MAE errors. The proposed model was optimised for edge devices, the Raspberry Pi 3 Model B+ (RPi3B+) and Raspberry Pi 4 Model B (RPi4B). This optimised model reduced file size to a quarter of the original, with further size reduction achieved by implementing different post-training quantisation. In total, 8272 hourly samples were continuously fed to the edge device, with the RPi4B executing the model twice as fast as the RPi3B+ in all quantisation modes. Full-integer quantisation produced the lowest execution time, with latencies of 2.19 s and 4.73 s for RPi4B and RPi3B+, respectively.

scholarly journals A note on leveraging synergy in multiple meteorological data sets with deep learning for rainfall–runoff modeling

2021 ◽  
Vol 25 (5) ◽  
pp. 2685-2703
Author(s):  
Frederik Kratzert ◽  
Daniel Klotz ◽  
Sepp Hochreiter ◽  
Grey S. Nearing
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Meteorological Data ◽  
Data Sets ◽  
Rainfall Runoff ◽  
Data Set ◽  
Simulation Accuracy ◽  
Meteorological Forcing ◽  
Rainfall Runoff Model ◽  
Land Data Assimilation System

Abstract. A deep learning rainfall–runoff model can take multiple meteorological forcing products as input and learn to combine them in spatially and temporally dynamic ways. This is demonstrated with Long Short-Term Memory networks (LSTMs) trained over basins in the continental US, using the Catchment Attributes and Meteorological data set for Large Sample Studies (CAMELS). Using meteorological input from different data products (North American Land Data Assimilation System, NLDAS, Maurer, and Daymet) in a single LSTM significantly improved simulation accuracy relative to using only individual meteorological products. A sensitivity analysis showed that the LSTM combines precipitation products in different ways, depending on location, and also in different ways for the simulation of different parts of the hydrograph.

scholarly journals Lifelong Machine Learning for Regional-Based Image Classification in Open Datasets

Symmetry ◽  
2020 ◽  
Vol 12 (12) ◽  
pp. 2094
Author(s):  
Hashem Alyami ◽  
Abdullah Alharbi ◽  
Irfan Uddin
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Learning Algorithms ◽  
Open Data ◽  
Research Field ◽  
Learning Problems ◽  
Data Sets ◽  
Data Set ◽  
Proposed Model ◽  
Open Datasets

Deep Learning algorithms are becoming common in solving different supervised and unsupervised learning problems. Different deep learning algorithms were developed in last decade to solve different learning problems in different domains such as computer vision, speech recognition, machine translation, etc. In the research field of computer vision, it is observed that deep learning has become overwhelmingly popular. In solving computer vision related problems, we first take a CNN (Convolutional Neural Network) which is trained from scratch or some times a pre-trained model is taken and further fine-tuned based on the dataset that is available. The problem of training the model from scratch on new datasets suffers from catastrophic forgetting. Which means that when a new dataset is used to train the model, it forgets the knowledge it has obtained from an existing dataset. In other words different datasets does not help the model to increase its knowledge. The problem with the pre-trained models is that mostly CNN models are trained on open datasets, where the data set contains instances from specific regions. This results into predicting disturbing labels when the same model is used for instances of datasets collected in a different region. Therefore, there is a need to find a solution on how to reduce the gap of Geo-diversity in different computer vision problems in developing world. In this paper, we explore the problems of models that were trained from scratch along with models which are pre-trained on a large dataset, using a dataset specifically developed to understand the geo-diversity issues in open datasets. The dataset contains images of different wedding scenarios in South Asian countries. We developed a Lifelong CNN that can incrementally increase knowledge i.e., the CNN learns labels from the new dataset but includes the existing knowledge of open data sets. The proposed model demonstrates highest accuracy compared to models trained from scratch or pre-trained model.

scholarly journals Roll Motion Prediction of Unmanned Surface Vehicle Based on Coupled CNN and LSTM

2019 ◽  
Vol 11 (11) ◽  
pp. 243 ◽  
Author(s):  
Wenjie Zhang ◽  
Pin Wu ◽  
Yan Peng ◽  
Dongke Liu
Keyword(s):  
Neural Network ◽  
Short Term Memory ◽  
Real Data ◽  
Sensor Data ◽  
Motion Prediction ◽  
Roll Motion ◽  
Time Varying ◽  
Motion Modeling ◽  
Data Set ◽  
Proposed Model

The prediction of roll motion in unmanned surface vehicles (USVs) is vital for marine safety and the efficiency of USV operations. However, the USV roll motion at sea is a complex time-varying nonlinear and non-stationary dynamic system, which varies with time-varying environmental disturbances as well as various sailing conditions. The conventional methods have the disadvantages of low accuracy, poor robustness, and insufficient practical application ability. The rise of deep learning provides new opportunities for USV motion modeling and prediction. In this paper, a data-driven neural network model is constructed by combining a convolution neural network (CNN) with long short-term memory (LSTM) for USV roll motion prediction. The CNN is used to extract spatially relevant and local time series features of the USV sensor data. The LSTM layer is exploited to reflect the long-term movement process of the USV and predict roll motion for the next moment. The fully connected layer is utilized to decode the LSTM output and calculate the final prediction results. The effectiveness of the proposed model was proved using USV roll motion prediction experiments based on two case studies from “JingHai-VI” and “JingHai-III” USVS of Shanghai University. Experimental results on a real data set indicated that our proposed model obviously outperformed the state-of-the-art methods.

scholarly journals PseUdeep: RNA Pseudouridine Site Identification with Deep Learning Algorithm

2021 ◽  
Vol 12 ◽  
Author(s):  
Jujuan Zhuang ◽  
Danyang Liu ◽  
Meng Lin ◽  
Wenjing Qiu ◽  
Jinyang Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Machine Learning Algorithms ◽  
Data Sets ◽  
Biological Processes ◽  
Rna Sequences ◽  
Frequency Pattern ◽  
Data Set ◽  
Testing Data

Background: Pseudouridine (Ψ) is a common ribonucleotide modification that plays a significant role in many biological processes. The identification of Ψ modification sites is of great significance for disease mechanism and biological processes research in which machine learning algorithms are desirable as the lab exploratory techniques are expensive and time-consuming.Results: In this work, we propose a deep learning framework, called PseUdeep, to identify Ψ sites of three species: H. sapiens, S. cerevisiae, and M. musculus. In this method, three encoding methods are used to extract the features of RNA sequences, that is, one-hot encoding, K-tuple nucleotide frequency pattern, and position-specific nucleotide composition. The three feature matrices are convoluted twice and fed into the capsule neural network and bidirectional gated recurrent unit network with a self-attention mechanism for classification.Conclusion: Compared with other state-of-the-art methods, our model gets the highest accuracy of the prediction on the independent testing data set S-200; the accuracy improves 12.38%, and on the independent testing data set H-200, the accuracy improves 0.68%. Moreover, the dimensions of the features we derive from the RNA sequences are only 109,109, and 119 in H. sapiens, M. musculus, and S. cerevisiae, which is much smaller than those used in the traditional algorithms. On evaluation via tenfold cross-validation and two independent testing data sets, PseUdeep outperforms the best traditional machine learning model available. PseUdeep source code and data sets are available at https://github.com/dan111262/PseUdeep.

A Deep Learning based Arabic Script Recognition System: Benchmark on KHAT

2020 ◽  
Vol 17 (3) ◽  
pp. 299-305 ◽  
Author(s):  
Riaz Ahmad ◽  
Saeeda Naz ◽  
Muhammad Afzal ◽  
Sheikh Rashid ◽  
Marcus Liwicki ◽  
...  
Keyword(s):  
Deep Learning ◽  
Character Recognition ◽  
Data Augmentation ◽  
Short Term Memory ◽  
Recognition System ◽  
Learning Approach ◽  
Arabic Text ◽  
Data Set ◽  
Processing Step ◽  
Handwritten Arabic

This paper presents a deep learning benchmark on a complex dataset known as KFUPM Handwritten Arabic TexT (KHATT). The KHATT data-set consists of complex patterns of handwritten Arabic text-lines. This paper contributes mainly in three aspects i.e., (1) pre-processing, (2) deep learning based approach, and (3) data-augmentation. The pre-processing step includes pruning of white extra spaces plus de-skewing the skewed text-lines. We deploy a deep learning approach based on Multi-Dimensional Long Short-Term Memory (MDLSTM) networks and Connectionist Temporal Classification (CTC). The MDLSTM has the advantage of scanning the Arabic text-lines in all directions (horizontal and vertical) to cover dots, diacritics, strokes and fine inflammation. The data-augmentation with a deep learning approach proves to achieve better and promising improvement in results by gaining 80.02% Character Recognition (CR) over 75.08% as baseline.

scholarly journals Investigating the impact of pre-processing techniques and pre-trained word embeddings in detecting Arabic health information on social media

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Yahya Albalawi ◽  
Jim Buckley ◽  
Nikola S. Nikolov
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Comprehensive Evaluation ◽  
Classification Problem ◽  
Data Sets ◽  
Word Embeddings ◽  
Data Set ◽  
Lower Accuracy ◽  
Health Related ◽  
The Impact

AbstractThis paper presents a comprehensive evaluation of data pre-processing and word embedding techniques in the context of Arabic document classification in the domain of health-related communication on social media. We evaluate 26 text pre-processings applied to Arabic tweets within the process of training a classifier to identify health-related tweets. For this task we use the (traditional) machine learning classifiers KNN, SVM, Multinomial NB and Logistic Regression. Furthermore, we report experimental results with the deep learning architectures BLSTM and CNN for the same text classification problem. Since word embeddings are more typically used as the input layer in deep networks, in the deep learning experiments we evaluate several state-of-the-art pre-trained word embeddings with the same text pre-processing applied. To achieve these goals, we use two data sets: one for both training and testing, and another for testing the generality of our models only. Our results point to the conclusion that only four out of the 26 pre-processings improve the classification accuracy significantly. For the first data set of Arabic tweets, we found that Mazajak CBOW pre-trained word embeddings as the input to a BLSTM deep network led to the most accurate classifier with F1 score of 89.7%. For the second data set, Mazajak Skip-Gram pre-trained word embeddings as the input to BLSTM led to the most accurate model with F1 score of 75.2% and accuracy of 90.7% compared to F1 score of 90.8% achieved by Mazajak CBOW for the same architecture but with lower accuracy of 70.89%. Our results also show that the performance of the best of the traditional classifier we trained is comparable to the deep learning methods on the first dataset, but significantly worse on the second dataset.

scholarly journals A fast methodology for large-scale focusing inversion of gravity and magnetic data using the structured model matrix and the 2-D fast Fourier transform

2020 ◽  
Vol 223 (2) ◽  
pp. 1378-1397
Author(s):  
Rosemary A Renaut ◽  
Jarom D Hogue ◽  
Saeed Vatankhah ◽  
Shuang Liu
Keyword(s):  
Fourier Transform ◽  
Fast Fourier Transform ◽  
Linear Systems ◽  
Large Scale ◽  
Surface Measurement ◽  
Magnetic Data ◽  
Uniform Grid ◽  
Data Sets ◽  
Inversion Algorithm ◽  
Data Set

SUMMARY We discuss the focusing inversion of potential field data for the recovery of sparse subsurface structures from surface measurement data on a uniform grid. For the uniform grid, the model sensitivity matrices have a block Toeplitz Toeplitz block structure for each block of columns related to a fixed depth layer of the subsurface. Then, all forward operations with the sensitivity matrix, or its transpose, are performed using the 2-D fast Fourier transform. Simulations are provided to show that the implementation of the focusing inversion algorithm using the fast Fourier transform is efficient, and that the algorithm can be realized on standard desktop computers with sufficient memory for storage of volumes up to size n ≈ 106. The linear systems of equations arising in the focusing inversion algorithm are solved using either Golub–Kahan bidiagonalization or randomized singular value decomposition algorithms. These two algorithms are contrasted for their efficiency when used to solve large-scale problems with respect to the sizes of the projected subspaces adopted for the solutions of the linear systems. The results confirm earlier studies that the randomized algorithms are to be preferred for the inversion of gravity data, and for data sets of size m it is sufficient to use projected spaces of size approximately m/8. For the inversion of magnetic data sets, we show that it is more efficient to use the Golub–Kahan bidiagonalization, and that it is again sufficient to use projected spaces of size approximately m/8. Simulations support the presented conclusions and are verified for the inversion of a magnetic data set obtained over the Wuskwatim Lake region in Manitoba, Canada.

scholarly journals A Hybrid Optimized LSTM Models for Human Activity Recognition with IOT Devices

2021 ◽  
pp. 182-189
Author(s):  
S. Arokiaraj ◽  
Dr. N. Viswanathan
Keyword(s):  
Deep Learning ◽  
Internet Of Things ◽  
Short Term Memory ◽  
The Other ◽  
Learning Models ◽  
Computational Overhead ◽  
Temporal Features ◽  
Human Movements ◽  
Proposed Model ◽  
Iot Devices

With the advent of Internet of things(IoT),HA (HA) recognition has contributed the more application in health care in terms of diagnosis and Clinical process. These devices must be aware of human movements to provide better aid in the clinical applications as well as user’s daily activity.Also , In addition to machine and deep learning algorithms, HA recognition systems has significantly improved in terms of high accurate recognition. However, the most of the existing models designed needs improvisation in terms of accuracy and computational overhead. In this research paper, we proposed a BAT optimized Long Short term Memory (BAT-LSTM) for an effective recognition of human activities using real time IoT systems. The data are collected by implanting the Internet of things) devices invasively. Then, proposed BAT-LSTM is deployed to extract the temporal features which are then used for classification to HA. Nearly 10,0000 dataset were collected and used for evaluating the proposed model. For the validation of proposed framework, accuracy, precision, recall, specificity and F1-score parameters are chosen and comparison is done with the other state-of-art deep learning models. The finding shows the proposed model outperforms the other learning models and finds its suitability for the HA recognition.

Sign in / Sign up

Export Citation Format

Share Document