scholarly journals Forecasting Bitcoin closing price series using linear regression and neural networks models

2020 ◽  
Vol 6 ◽  
pp. e279
Author(s):  
Nicola Uras ◽  
Lodovica Marchesi ◽  
Michele Marchesi ◽  
Roberto Tonelli
Keyword(s):  
Neural Networks ◽  
Linear Regression ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Percentage Error ◽  
Volume Data ◽  
Stock Market Index ◽  
Price Series ◽  
Closing Price ◽  
Financial Prices

In this article we forecast daily closing price series of Bitcoin, Litecoin and Ethereum cryptocurrencies, using data on prices and volumes of prior days. Cryptocurrencies price behaviour is still largely unexplored, presenting new opportunities for researchers and economists to highlight similarities and differences with standard financial prices. We compared our results with various benchmarks: one recent work on Bitcoin prices forecasting that follows different approaches, a well-known paper that uses Intel, National Bank shares and Microsoft daily NASDAQ closing prices spanning a 3-year interval and another, more recent paper which gives quantitative results on stock market index predictions. We followed different approaches in parallel, implementing both statistical techniques and machine learning algorithms: the Simple Linear Regression (SLR) model for uni-variate series forecast using only closing prices, and the Multiple Linear Regression (MLR) model for multivariate series using both price and volume data. We used two artificial neural networks as well: Multilayer Perceptron (MLP) and Long short-term memory (LSTM). While the entire time series resulted to be indistinguishable from a random walk, the partitioning of datasets into shorter sequences, representing different price “regimes”, allows to obtain precise forecast as evaluated in terms of Mean Absolute Percentage Error(MAPE) and relative Root Mean Square Error (relativeRMSE). In this case the best results are obtained using more than one previous price, thus confirming the existence of time regimes different from random walks. Our models perform well also in terms of time complexity, and provide overall results better than those obtained in the benchmark studies, improving the state-of-the-art.

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.

Patient visit forecasting in an emergency department using a deep neural network approach

Kybernetes ◽  
2019 ◽  
Vol 49 (9) ◽  
pp. 2335-2348 ◽  
Author(s):  
Milad Yousefi ◽  
Moslem Yousefi ◽  
Masood Fathi ◽  
Flavio S. Fogliatto
Keyword(s):  
Neural Network ◽  
Emergency Department ◽  
Linear Regression ◽  
Deep Neural Network ◽  
Short Term Memory ◽  
Demand Forecasting ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Neural Network Approach ◽  
Content Type

Purpose This study aims to investigate the factors affecting daily demand in an emergency department (ED) and to provide a forecasting tool in a public hospital for horizons of up to seven days. Design/methodology/approach In this study, first, the important factors to influence the demand in EDs were extracted from literature then the relevant factors to the study are selected. Then, a deep neural network is applied to constructing a reliable predictor. Findings Although many statistical approaches have been proposed for tackling this issue, better forecasts are viable by using the abilities of machine learning algorithms. Results indicate that the proposed approach outperforms statistical alternatives available in the literature such as multiple linear regression, autoregressive integrated moving average, support vector regression, generalized linear models, generalized estimating equations, seasonal ARIMA and combined ARIMA and linear regression. Research limitations/implications The authors applied this study in a single ED to forecast patient visits. Applying the same method in different EDs may give a better understanding of the performance of the model to the authors. The same approach can be applied in any other demand forecasting after some minor modifications. Originality/value To the best of the knowledge, this is the first study to propose the use of long short-term memory for constructing a predictor of the number of patient visits in EDs.

scholarly journals A Comparison of Power Quality Disturbance Detection and Classification Methods Using CNN, LSTM and CNN-LSTM

2020 ◽  
Vol 10 (19) ◽  
pp. 6755
Author(s):  
Carlos Iturrino Garcia ◽  
Francesco Grasso ◽  
Antonio Luchetta ◽  
Maria Cristina Piccirilli ◽  
Libero Paolucci ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Data Augmentation ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Validation Dataset ◽  
Short Term ◽  
Current Time ◽  
Term Memory ◽  
Long Short Term Memory

The use of electronic loads has improved many aspects of everyday life, permitting more efficient, precise and automated process. As a drawback, the nonlinear behavior of these systems entails the injection of electrical disturbances on the power grid that can cause distortion of voltage and current. In order to adopt countermeasures, it is important to detect and classify these disturbances. To do this, several Machine Learning Algorithms are currently exploited. Among them, for the present work, the Long Short Term Memory (LSTM), the Convolutional Neural Networks (CNN), the Convolutional Neural Networks Long Short Term Memory (CNN-LSTM) and the CNN-LSTM with adjusted hyperparameters are compared. As a preliminary stage of the research, the voltage and current time signals are simulated using MATLAB Simulink. Thanks to the simulation results, it is possible to acquire a current and voltage dataset with which the identification algorithms are trained, validated and tested. These datasets include simulations of several disturbances such as Sag, Swell, Harmonics, Transient, Notch and Interruption. Data Augmentation techniques are used in order to increase the variability of the training and validation dataset in order to obtain a generalized result. After that, the networks are fed with an experimental dataset of voltage and current field measurements containing the disturbances mentioned above. The networks have been compared, resulting in a 79.14% correct classification rate with the LSTM network versus a 84.58% for the CNN, 84.76% for the CNN-LSTM and a 83.66% for the CNN-LSTM with adjusted hyperparameters. All of these networks are tested using real measurements.

scholarly journals Prediction of Building’s Thermal Performance Using LSTM and MLP Neural Networks

2020 ◽  
Vol 10 (21) ◽  
pp. 7439 ◽  
Author(s):  
Miguel Martínez Comesaña ◽  
Lara Febrero-Garrido ◽  
Francisco Troncoso-Pastoriza ◽  
Javier Martínez-Torres
Keyword(s):  
Neural Networks ◽  
Short Term Memory ◽  
Public Library ◽  
Thermal Inertia ◽  
Energy Performance ◽  
Machine Learning Algorithms ◽  
Time Lags ◽  
Prediction Errors ◽  
The North ◽  
Complex Nonlinear Systems

Accurate prediction of building indoor temperatures and thermal demand is of great help to control and optimize the energy performance of a building. However, building thermal inertia and lag lead to complex nonlinear systems is difficult to model. In this context, the application of artificial neural networks (ANNs) in buildings has grown considerably in recent years. The aim of this work is to study the thermal inertia of a building by developing an innovative methodology using multi-layered perceptron (MLP) and long short-term memory (LSTM) neural networks. This approach was applied to a public library building located in the north of Spain. A comparison between the prediction errors according to the number of time lags introduced in the models has been carried out. Moreover, the accuracy of the models was measured using the CV(RMSE) as advised by AHSRAE. The main novelty of this work lies in the analysis of the building inertia, through machine learning algorithms, observing the information provided by the input of time lags in the models. The results of the study prove that the best models are those that consider the thermal lag. Errors below 15% for thermal demand and below 2% for indoor temperatures were achieved with the proposed methodology.

scholarly journals A new model for predicting the attributes of suspects

2020 ◽  
Vol 17 (3) ◽  
pp. 705-715
Author(s):  
Chuyue Zhang ◽  
Xiaofan Zhao ◽  
Manchun Cai ◽  
Dawei Wang ◽  
Luzhe Cao
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
New Model ◽  
Text Features ◽  
Combine Machine ◽  
Fully Connected ◽  
Improved Accuracy ◽  
First Time

In this paper, we propose a new model to predict the age and number of suspects through the feature modeling of historical data. We discrete the case information into values of 20 dimensions. After feature selection, we use 9 machine learning algorithms and Deep Neural Networks to extract the numerical features. In addition, we use Convolutional Neural Networks and Long Short- Term Memory to extract the text features of case description. These two types of features are fused and fed into fully connected layer and softmax layer. This work is an extension of our short conference proceeding paper. The experimental results show that the new model improved accuracy by 3% in predicting the number of suspects and improved accuracy by 12% in predicting the number of suspects. To the best of our knowledge, it is the first time to combine machine learning and deep learning in crime prediction.

scholarly journals Renewable Energy Production Forecasting: A Comparative Machine Learning Analysis

2021 ◽  
Vol 10 (6) ◽  
pp. 11-18
Author(s):  
Kazi Md Shahiduzzaman ◽  
◽  
Md Noor Jamal ◽  
Md. Rashed Ibn Nawab ◽  
◽  
...  
Keyword(s):  
Machine Learning ◽  
Renewable Energy ◽  
Standard Deviation ◽  
Linear Regression ◽  
Energy Production ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Forecasting Model ◽  
Renewable Energy Production

As renewable energy has become increasingly popular worldwide, while solar and wind energy has been the leading source of renewable energy up to now, the accuracy of renewable energy forecasts is challenge for the planning, management, and operations of the power system. However, due to the intermediate and frenzied nature of renewable energy data, this is a most challenging task. This study provides a comprehensive and complete review of the renewable energy forecast based on different machine learning algorithms to explore effectiveness, efficiency, competence, and application potential. In this work, we have built time series renewable energy forecasting model with Support Vector Machine (SVM), Linear Regression (LR), and Long Short-Term Memory (LSTM) on twelve (12) countries. The experimental results are very interesting. For example, SVM based forecasting model is a better fit for the countries with small mean and standard deviation while linear regression-based methods show a bit better result in case of larger mean and standard deviation. Meanwhile, LSTM based models provide smoother regular-shaped forecasting. We can forecast two years of daily renewable energy production with these forecasting models. The point should be noted that we have developed different models for different countries. We have able to reach a Root Mean Square (RMS) value of 3.1 38 with SVM based model.

scholarly journals Integrating Traditional Machine Learning and Neural Networks for Image Processing

2021 ◽  
Author(s):  
Nikita Laptev ◽  
Vladislav Laptev ◽  
Olga Gerget ◽  
Dmitriy Kolpashchikov
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Image Processing ◽  
Short Term Memory ◽  
Learning Algorithms ◽  
Input Image ◽  
Machine Learning Algorithms ◽  
Neural Network Models ◽  
Fire Source ◽  
Artificial Neural

The article describes a feasibility study to assess the use of neural networks and traditional machine learning algorithms to solve various problems including image processing. A brief description of some algorithms of traditional machine learning, as well as anautomated service for choosing the best method for a specific task, is given. The authors also describe the features of artificial neural networks and the most popular places for theirapplication. An algorithm for solving the problem of detecting fire hazardous objects andlocalizing a fire source in a forest using video sequence frames is presented. The article compares the characteristics of artificial neural network models according to the followingcriteria: underlying architecture, the number of analyzed frames, the size of the input image, the transfer learning model used as a feature vector composing network. Acomparative analysis of traditional machine learning algorithms and neural networks withlong short-term memory in the problem of classification of forest fire hazards is made. A solution to localization of the source of fire based on clustering is described. A hybrid algorithm for finding a fire source in a forest is developed and illustrated.

Combined Evidence of MFCC and CRP Features Using Machine Learning Algorithms for Singer Identification

2020 ◽  
pp. 2158001
Author(s):  
Sangeetha Rajesh ◽  
N. J. Nalini
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Instrumental Music ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Identification Accuracy ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Identification System ◽  
Singer Identification

Singer identification is a challenging task in music information retrieval because of the combined instrumental music with the singing voice. The previous approaches focus on identification of singers based on individual features extracted from the music clips. The objective of this work is to combine Mel Frequency Cepstral Coefficients (MFCC) and Chroma DCT-reduced Pitch (CRP) features for singer identification system (SID) using machine learning techniques. The proposed system has mainly two phases. In the feature extraction phase, MFCC, [Formula: see text]MFCC, [Formula: see text]MFCC and CRP features are extracted from the music clips. In the identification phase, extracted features are trained with Bidirectional Long Short-Term Memory (BLSTM)-based Recurrent Neural Networks (RNN) and Convolution Neural Networks (CNN) and tested to identify different singer classes. The identification accuracy and Equal Error Rate (EER) are used as performance measures. Further, the experiments also demonstrate the effectiveness of score level fusion of MFCC and CRP feature in the singer identification system. Also, the experimental results are compared with the baseline system using support vector machines (SVM).

Sign in / Sign up

Export Citation Format

Share Document