PP15 Predicting variations of calls to an ambulance service in the UK caused by circulating infections using-deep learning methods

2019 ◽  
Vol 36 (10) ◽  
pp. e7.2-e7
Author(s):  
Thilo Reich ◽  
Marcin Budka
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Prehospital Care ◽  
Machine Learning Algorithms ◽  
Ambulance Service ◽  
Percentage Error ◽  
Learning Methods ◽  
Average Percentage ◽  
Average Percentage Error ◽  
The Uk

BackgroundDigital patient records in the ambulance service have opened up new opportunities for prehospital care. Previously it was demonstrated that prehospital pyrexia numbers are linked to an increase in overall calls to the ambulance service. This study aims to predict the future number of calls using deep-learning methods.MethodsTemperature readings for 280,447 patients were generously provided by the South Western Ambulance Service Trust. The data covered the time between 05/01/2016 and 30/04/2017 with overall 44,472 patients being pyretic. A rolling window of 10 days was applied to daily sums for both pyretic and apyretic patients. These windows were used as input features to train machine-learning algorithms predicting the number of calls 10 days ahead. Algorithms tested include Linear Regression (LR), basic Recurrent Neural Networks (RNN), Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures. A genetic approach was used to optimise the architecture, in which parameters were randomly modified and over several generations the best performing algorithm will be selected to be further manipulated. To assess performance the Mean Average Percentage Error (MAPE) was used.ResultsThe initial analysis showed that the total patient number and pyretic patient numbers are correlated. The best performing algorithms with varying numbers of hidden units had the following MAPE in comparison to simple LR: LR=19.4%, LSTM (104 units) = 6.1%, RNN (79 units)=6.01%, GRU (80 units)=5.97%.ConclusionsThese preliminary results suggest that deep-learning methods allow to predict the variations in total number of calls caused by circulating infections. Further investigations will aim to confirm these findings. Once fully verified these algorithms could play a major role in operational planning of any ambulance service by predicting increases in demand.

scholarly journals COVID-19 in Iran: Forecasting Pandemic Using Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Rahele Kafieh ◽  
Roya Arian ◽  
Narges Saeedizadeh ◽  
Zahra Amini ◽  
Nasim Dadashi Serej ◽  
...  
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Percentage Error ◽  
Mean Square ◽  
Short Term ◽  
Average Percentage ◽  
The Usa ◽  
Long Short Term Memory ◽  
Average Percentage Error ◽  
Almost All

COVID-19 has led to a pandemic, affecting almost all countries in a few months. In this work, we applied selected deep learning models including multilayer perceptron, random forest, and different versions of long short-term memory (LSTM), using three data sources to train the models, including COVID-19 occurrences, basic information like coded country names, and detailed information like population, and area of different countries. The main goal is to forecast the outbreak in nine countries (Iran, Germany, Italy, Japan, Korea, Switzerland, Spain, China, and the USA). The performances of the models are measured using four metrics, including mean average percentage error (MAPE), root mean square error (RMSE), normalized RMSE (NRMSE), and R 2 . The best performance was found for a modified version of LSTM, called M-LSTM (winner model), to forecast the future trajectory of the pandemic in the mentioned countries. For this purpose, we collected the data from January 22 till July 30, 2020, for training, and from 1 August 2020 to 31 August 2020, for the testing phase. Through experimental results, the winner model achieved reasonably accurate predictions (MAPE, RMSE, NRMSE, and R 2 are 0.509, 458.12, 0.001624, and 0.99997, respectively). Furthermore, we stopped the training of the model on some dates related to main country actions to investigate the effect of country actions on predictions by the model.

scholarly journals A Survey of Forex and Stock Price Prediction Using Deep Learning

2021 ◽  
Vol 4 (1) ◽  
pp. 9 ◽  
Author(s):  
Zexin Hu ◽  
Yiqi Zhao ◽  
Matloob Khushi
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Reinforcement Learning ◽  
Mean Square Error ◽  
Performance Metrics ◽  
Short Term Memory ◽  
Percentage Error ◽  
Mean Square ◽  
Learning Methods ◽  
Stock Price Prediction

Predictions of stock and foreign exchange (Forex) have always been a hot and profitable area of study. Deep learning applications have been proven to yield better accuracy and return in the field of financial prediction and forecasting. In this survey, we selected papers from the Digital Bibliography & Library Project (DBLP) database for comparison and analysis. We classified papers according to different deep learning methods, which included Convolutional neural network (CNN); Long Short-Term Memory (LSTM); Deep neural network (DNN); Recurrent Neural Network (RNN); Reinforcement Learning; and other deep learning methods such as Hybrid Attention Networks (HAN), self-paced learning mechanism (NLP), and Wavenet. Furthermore, this paper reviews the dataset, variable, model, and results of each article. The survey used presents the results through the most used performance metrics: Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Mean Square Error (MSE), accuracy, Sharpe ratio, and return rate. We identified that recent models combining LSTM with other methods, for example, DNN, are widely researched. Reinforcement learning and other deep learning methods yielded great returns and performances. We conclude that, in recent years, the trend of using deep-learning-based methods for financial modeling is rising exponentially.

Actuation and dynamic mechanical characteristics of a core free flat dielectric electro-active polymer soft actuator

2020 ◽  
Vol 14 (4) ◽  
pp. 7396-7404
Author(s):  
Abdul Malek Abdul Wahab ◽  
Emiliano Rustighi ◽  
Zainudin A.
Keyword(s):  
Theoretical Model ◽  
Resonance Frequency ◽  
Dynamic Testing ◽  
Experimental Results ◽  
Percentage Error ◽  
Initial Tension ◽  
Average Percentage ◽  
Soft Actuator ◽  
Average Percentage Error ◽  
Mechanical Dynamics

Various complex shapes of dielectric electro-active polymer (DEAP) actuator have been promoted for several types of applications. In this study, the actuation and mechanical dynamics characteristics of a new core free flat DEAP soft actuator were investigated. This actuator was developed by Danfoss PolyPower. DC voltage of up to 2000 V was supplied for identifying the actuation characteristics of the actuator and compare with the existing formula. The operational frequency of the actuator was determined by dynamic testing. Then, the soft actuator has been modelled as a uniform bar rigidly fixed at one end and attached to mass at another end. Results from the theoretical model were compared with the experimental results. It was found that the deformation of the current actuator was quadratic proportional to the voltage supplied. It was found that experimental results and theory were not in good agreement for low and high voltage with average percentage error are 104% and 20.7%, respectively. The resonance frequency of the actuator was near 14 Hz. Mass of load added, inhomogeneity and initial tension significantly affected the resonance frequency of the soft actuator. The experimental results were consistent with the theoretical model at zero load. However, due to inhomogeneity, the frequency response function’s plot underlines a poor prediction where the theoretical calculation was far from experimental results as values of load increasing with the average percentage error 15.7%. Hence, it shows the proposed analytical procedure not suitable to provide accurate natural frequency for the DEAP soft actuator.

scholarly journals Indicator Selection for Topic Popularity Definition Based on AHP and Deep Learning Models

2020 ◽  
Vol 2020 ◽  
pp. 1-11 ◽  
Author(s):  
Yuling Hong ◽  
Qishan Zhang
Keyword(s):  
Deep Learning ◽  
Social Network ◽  
Evaluation Method ◽  
Short Term Memory ◽  
Selection Model ◽  
Learning Technology ◽  
Prevention Measures ◽  
Learning Methods ◽  
Indicator Selection ◽  
The Social

Purpose. The purpose of this article is to predict the topic popularity on the social network accurately. Indicator selection model for a new definition of topic popularity with degree of grey incidence (DGI) is undertook based on an improved analytic hierarchy process (AHP). Design/Methodology/Approach. Through screening the importance of indicators by the deep learning methods such as recurrent neural networks (RNNs), long short-term memory (LSTM), and gated recurrent unit (GRU), a selection model of topic popularity indicators based on AHP is set up. Findings. The results show that when topic popularity is being built quantitatively based on the DGI method and different weights of topic indicators are obtained from the help of AHP, the average accuracy of topic popularity prediction can reach 97.66%. The training speed is higher and the prediction precision is higher. Practical Implications. The method proposed in the paper can be used to calculate the popularity of each hot topic and generate the ranking list of topics’ popularities. Moreover, its future popularity can be predicted by deep learning methods. At the same time, a new application field of deep learning technology has been further discovered and verified. Originality/Value. This can lay a theoretical foundation for the formulation of topic popularity tendency prevention measures on the social network and provide an evaluation method which is consistent with the actual situation.

A semiautomatic annotation approach for sentiment analysis

2021 ◽  
pp. 016555152110065
Author(s):  
Rahma Alahmary ◽  
Hmood Al-Dossari
Keyword(s):  
Deep Learning ◽  
Sentiment Analysis ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Short Term ◽  
Term Memory ◽  
Annotation Process ◽  
Learning Classifiers ◽  
Long Short Term Memory

Sentiment analysis (SA) aims to extract users’ opinions automatically from their posts and comments. Almost all prior works have used machine learning algorithms. Recently, SA research has shown promising performance in using the deep learning approach. However, deep learning is greedy and requires large datasets to learn, so it takes more time for data annotation. In this research, we proposed a semiautomatic approach using Naïve Bayes (NB) to annotate a new dataset in order to reduce the human effort and time spent on the annotation process. We created a dataset for the purpose of training and testing the classifier by collecting Saudi dialect tweets. The dataset produced from the semiautomatic model was then used to train and test deep learning classifiers to perform Saudi dialect SA. The accuracy achieved by the NB classifier was 83%. The trained semiautomatic model was used to annotate the new dataset before it was fed into the deep learning classifiers. The three deep learning classifiers tested in this research were convolutional neural network (CNN), long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM). Support vector machine (SVM) was used as the baseline for comparison. Overall, the performance of the deep learning classifiers exceeded that of SVM. The results showed that CNN reported the highest performance. On one hand, the performance of Bi-LSTM was higher than that of LSTM and SVM, and, on the other hand, the performance of LSTM was higher than that of SVM. The proposed semiautomatic annotation approach is usable and promising to increase speed and save time and effort in the annotation process.

scholarly journals Comparative analysis of Kernel-based versus BFGS-ANN and deep learning methods in monthly reference evaporation estimation

2020 ◽  
Author(s):  
Mohammad Taghi Sattari ◽  
Halit Apaydin ◽  
Shahab Shamshirband ◽  
Amir Mosavi
Keyword(s):  
Deep Learning ◽  
Minimum Temperature ◽  
Meteorological Parameters ◽  
Short Term Memory ◽  
Sunshine Duration ◽  
Gaussian Process Regression ◽  
Support Vector ◽  
Ann Model ◽  
Learning Methods ◽  
Average Maximum

Abstract. Proper estimation of the reference evapotranspiration (ET0) amount is an indispensable matter for agricultural water management in the efficient use of water. The aim of study is to estimate the amount of ET0 with a different machine and deep learning methods by using minimum meteorological parameters in the Corum region which is an arid and semi-arid climate with an important agricultural center of Turkey. In this context, meteorological variables of average, maximum and minimum temperature, sunshine duration, wind speed, average, maximum, and minimum relative humidity are used as input data monthly. Two different kernel-based (Gaussian Process Regression (GPR) and Support Vector Regression (SVR)) methods, BFGS-ANN and Long short-term memory models were used to estimate ET0 amounts in 10 different combinations. According to the results obtained, all four methods used predicted ET0 amounts in acceptable accuracy and error levels. BFGS-ANN model showed higher success than the others. In kernel-based GPR and SVR methods, Pearson VII function-based universal kernel was the most successful kernel function. Besides, the scenario that is related to temperature in all scenarios used, including average temperature, maximum and minimum temperature, and sunshine duration gave the best results. The second-best scenario was the one that covers only the sunshine duration. In this case, the ANN (BFGS-ANN) model, which is optimized with the BFGS method that uses only the sunshine duration, can be estimated with the 0.971 correlation coefficient of ET0 without the need for other meteorological parameters.

scholarly journals Validity of Consumer Activity Monitors and an Algorithm Using Smartphone Data for Measuring Steps during Different Activity Types

2020 ◽  
Vol 17 (24) ◽  
pp. 9314
Author(s):  
Verena Hartung ◽  
Mustafa Sarshar ◽  
Viktoria Karle ◽  
Layal Shammas ◽  
Asarnusch Rashid ◽  
...  
Keyword(s):  
Physical Activity ◽  
Arm Movements ◽  
Percentage Error ◽  
Activity Measurement ◽  
Overground Walking ◽  
Activity Monitors ◽  
Average Percentage ◽  
Study Results ◽  
Promotion Of Physical Activity ◽  
Average Percentage Error

Background: Consumer activity monitors and smartphones have gained relevance for the assessment and promotion of physical activity. The aim of this study was to determine the concurrent validity of various consumer activity monitor models and smartphone models for measuring steps. Methods: Participants completed three activity protocols: (1) overground walking with three different speeds (comfortable, slow, fast), (2) activities of daily living (ADLs) focusing on arm movements, and (3) intermittent walking. Participants wore 11 activity monitors (wrist: 8; hip: 2; ankle: 1) and four smartphones (hip: 3; calf: 1). Observed steps served as the criterion measure. The mean average percentage error (MAPE) was calculated for each device and protocol. Results: Eighteen healthy adults participated in the study (age: 28.8 ± 4.9 years). MAPEs ranged from 0.3–38.2% during overground walking, 48.2–861.2% during ADLs, and 11.2–47.3% during intermittent walking. Wrist-worn activity monitors tended to misclassify arm movements as steps. Smartphone data collected at the hip, analyzed with a separate algorithm, performed either equally or even superiorly to the research-grade ActiGraph. Conclusion: This study highlights the potential of smartphones for physical activity measurement. Measurement inaccuracies during intermittent walking and arm movements should be considered when interpreting study results and choosing activity monitors for evaluation purposes.

scholarly journals Comparison of Otolith Readability and Reproducibility of Counts of Translucent Zones Using Different Otolith Preparation Methods for Four Endemic Labeobarbus Species in Lake Tana, Ethiopia

Water ◽  
2019 ◽  
Vol 11 (7) ◽  
pp. 1336 ◽  
Author(s):  
Gebremedhin ◽  
Bekaert ◽  
Getahun ◽  
Bruneel ◽  
Anteneh ◽  
...  
Keyword(s):  
Management Strategies ◽  
Tropical Fish ◽  
Percentage Error ◽  
Systematic Bias ◽  
Preparation Technique ◽  
Lake Tana ◽  
Preparation Methods ◽  
Average Percentage ◽  
Average Percentage Error ◽  
Preparation Techniques

The analysis of fish age data is vital for the successful conservation of fish. Attempts to develop optimal management strategies for effective conservation of the endemic Labeobarbus species are strongly affected by the lack of accurate age estimates. Although methodological studies are key to acquiring a good insight into the age of fishes, up to now, there have not been any studies comparing different methods for these species. Thus, this study aimed at determining the best method for the endemic Labeobarbus species. Samples were collected from May 2016 to April 2017. Asteriscus otoliths from 150 specimens each of L. intermedius, L. tsanensis, L. platydorsus, and L. megastoma were examined. Six methods were evaluated; however, only three methods resulted in readable images. The procedure in which whole otoliths were first submerged in water, and subsequently placed in glycerol to take the image (MO1), was generally best. Except for L. megastoma, this method produced the clearest image as both the coefficient of variation and average percentage error between readers were lowest. Furthermore, except for L. megastoma, MO1 had high otolith readability and no systematic bias. Therefore, we suggest that MO1 should be used as the standard otolith preparation technique for the first three species, while for L. megastoma, other preparation techniques should be evaluated. This study provides a reference for researchers from Africa, particularly Ethiopia, to develop a suitable otolith preparation method for the different tropical fish species.

scholarly journals A Comparative Study of Bitcoin Price Prediction Using Deep Learning

Mathematics ◽  
2019 ◽  
Vol 7 (10) ◽  
pp. 898 ◽  
Author(s):  
Suhwan Ji ◽  
Jongmin Kim ◽  
Hyeonseung Im
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Prediction Models ◽  
Short Term Memory ◽  
Learning Methods ◽  
The Public ◽  
Price Prediction ◽  
Profitability Analysis ◽  
The Media ◽  
Long Short Term Memory

Bitcoin has recently received a lot of attention from the media and the public due to its recent price surge and crash. Correspondingly, many researchers have investigated various factors that affect the Bitcoin price and the patterns behind its fluctuations, in particular, using various machine learning methods. In this paper, we study and compare various state-of-the-art deep learning methods such as a deep neural network (DNN), a long short-term memory (LSTM) model, a convolutional neural network, a deep residual network, and their combinations for Bitcoin price prediction. Experimental results showed that although LSTM-based prediction models slightly outperformed the other prediction models for Bitcoin price prediction (regression), DNN-based models performed the best for price ups and downs prediction (classification). In addition, a simple profitability analysis showed that classification models were more effective than regression models for algorithmic trading. Overall, the performances of the proposed deep learning-based prediction models were comparable.

Stock-specific assessment of precise age and growth in the long-whiskered catfish Sperata aor from the Ganges River

2020 ◽  
Vol 71 (12) ◽  
pp. 1693
Author(s):  
Aafaq Nazir ◽  
M. Afzal Khan
Keyword(s):  
Age And Growth ◽  
Percentage Error ◽  
Specific Information ◽  
Ganges River ◽  
Average Percentage ◽  
Marginal Increment ◽  
Hard Structures ◽  
Average Percentage Error ◽  
Anthropogenic Threats ◽  
The Ganges

Sustainable management of the long-whiskered catfish Sperata aor (Hamilton, 1822) in the Ganges River justifies precise stock-specific information on age and growth. The aim of the present study was to estimate the age and growth of three stocks, namely Narora–Kanpur, Varanasi and Bhagalpur, of S. aor from the Ganges River. Among the hard structures chosen for analysis, vertebrae provided precise age estimates up to 9 years of age in all the three stocks of S. aor based on average percentage error. Edge analysis of vertebrae and marginal increment ratio analysis of sectioned otoliths showed annulus formation once per year during April–June. The von Bertalanffy growth rates showed significant differences between the sexes and among the stocks. The growth coefficient k (0.24–0.30 year–1) showed rapid growth relative to asymptotic length (L∞) in all three stocks. The growth performance index was nearly the same for all three stocks. The results of the present study can be used in formulating scientifically sound management policies in view of anthropogenic threats to the populations of S. aor from the Ganges River.

Sign in / Sign up

Export Citation Format

Share Document