6,014 Hits in 2.9 sec

A machine learning approach for the spatiotemporal forecasting of ecological phenomena using dates of species occurrence records [article]

César Capinha
2018 bioRxiv   pre-print
This approach is based on 'time-series classification', a field of machine learning, and involves the application of a machine-learning algorithm to classify between time-series representing the environmental  ...  We compared the predictions from this approach with those from a 'null' model, based on the calendar dates of the records.Forecasts made from the environmental-based approach were consistently superior  ...  The workflow of the feature-based approaches include: 1) collecting the time-series from the distinct classes; 2) transforming the time-series into features; 3) fitting a classification algorithm using  ... 
doi:10.1101/435289 fatcat:iytxbgp3mfa75mmq4m52ekhjcq

Machine-learning forecasting for Dengue epidemics - Comparing LSTM, Random Forest and Lasso regression [article]

Elisa Mussumeci, Flavio Codeco Coelho
2020 medRxiv   pre-print
Obtaining such forecasts from classical time series models has proven a difficult task.  ...  Here we propose and compare machine learning models incorporating feature selection,such as LASSO and Random Forest regression with LSTM a deep recurrent neural network, to forecast weekly dengue incidence  ...  In all models we adopted a forecast window of 4 weeks, meaning that from any moment in time the models will produce forecasts for the number of weekly dengue cases in the following 4 weeks, based only  ... 
doi:10.1101/2020.01.23.20018556 fatcat:5bx5inag2berhahqjdt4srxqqu

Cutting Tool Condition Recognition in NC Machining Process of Structural Parts Based on Machining Features

Nanhong Lu, Yingguang Li, Changqing Liu, Wenping Mou
2016 Procedia CIRP  
Aimed at this problem, the recognition of tool-condition based on machining feature in real-time is stated.  ...  A feature database is established with experimental results and a cutting tool condition recognition system is established based on this database.  ...  Feature based monitoring threshold database Fig. 4 . 4 The working NC code Fig. 5 . 5 (a)Part model; (b)Dynamometer installation Fig. 6 . 6 Experimental Table . 1 . .Feature Database No.  ... 
doi:10.1016/j.procir.2016.10.028 fatcat:lbab3a3qzbatzd3bzrnlaoldqa

Forecasting the COVID-19 Pandemic with Climate Variables for Top Five Burdening and Three South Asian Countries [article]

Md. Karimuzzaman, Sabrina Afroz, Md. Moyazzem Hossain, Azizur Rahman
2020 medRxiv   pre-print
As the death count includes zero itself, zero-inflated count time series model has included instead of likelihood-based GLM.  ...  The climate factors of the top-five affected countries and three south Asian countries have considered in this study to have a real-time forecast and robust validation about the impact of climate variables  ...  To select the feature authors, suggest a combined filter with Wrapper approach for time series prediction.  ... 
doi:10.1101/2020.05.12.20099044 fatcat:523fs7wwevc5fcw2azqdbggs7q

Machine Learning Methods For Environmental Monitoring And Flood Protection

Alexander L. Pyayt, Ilya I. Mokhov, Bernhard Lang, Valeria V. Krzhizhanovskaya, Robert J. Meijer
2011 Zenodo  
This paper describes an approach for monitoring of flood protections systems based on machine learning methods.  ...  The AI module has been integrated into an EWS platform of the UrbanFlood project (EU Seventh Framework Programme) and validated on real-time measurements from the sensors installed in a dike.  ...  In many publications floods are forecasted using environmental parameters only (see Fig. 1a ). For example, in [8] flood forecast was based on a river flow.  ... 
doi:10.5281/zenodo.1075059 fatcat:onmhrwyc7fctzjn5vynv6fzvvi

A Short-Term Household Load Forecasting Framework using LSTM and Data Preparation

Derni Ageng, Chin-Ya Huang, Ray-Guang Cheng
2021 IEEE Access  
models with another machine learning model are proposed.  ...  Moreover, machine learning based approaches are also II. EXPLORATORY DATA ANALYSIS AND PROBLEM commonly applied for modeling load consumption.  ... 
doi:10.1109/access.2021.3133702 fatcat:mfvldkm74zfjjm4c4pnhdz4xua

An Hour Ahead Electricity Price Forecasting with Least Square Support Vector Machine and Bacterial Foraging Optimization Algorithm

Intan Azmira Wan Abdul Razak, Izham Zainal Abidin, Yap Keem Siah, Aidil Azwin Zainul Abidin, Titik Khawa Abdul Rahman, Nurliyana Baharin, Mohd. Hafiz Bin Jali
2018 Indonesian Journal of Electrical Engineering and Computer Science  
A huge number of features were selected by five stages of optimization to avoid from missing any important features.  ...  So far, no works has been established on multistage feature and parameter optimization using LSSVM-BFOA for hour-ahead price forecast. The model was examined on the Ontario power market.  ...  Hence, this study introduces a new technique in electricity price forecast by developing hour-ahead electricity price forecasting model with Least Square Support Vector Machine (LSSVM) and Bacterial Foraging  ... 
doi:10.11591/ijeecs.v10.i2.pp748-755 fatcat:grfcqcg7bvel3gwoyovnjwpnyi

A Convection Nowcasting Method Based on Machine Learning

Aifang Su, Han Li, Liman Cui, Yungang Chen
2020 Advances in Meteorology  
In this study, a convection nowcasting method based on machine learning was proposed. First, the historical data were back-calculated using the pyramid optical flow method.  ...  Based on learning through the above features, this algorithm can forecast the generation and dissipation trends of convective cells to some extent.  ...  Figure 6 shows the echo forecast based on optical flow and machine learning. e forecasting start time was 1100UTC July 14 2017, and the valid periods of the forecast were the next 30, 60, 90, and 120  ... 
doi:10.1155/2020/5124274 fatcat:cgbfwmxppfgczoob6ujdyapep4

Predicting Dengue Fever in Brazilian Cities [article]

Kirstin Roster, Colm Connaughton, Francisco A. Rodrigues
2021 bioRxiv   pre-print
We compare different machine learning approaches as well as different sets of input features based on epidemiological and meteorological data.  ...  We find that different models work best in different cities, and a random forests model trained on data of historical Dengue cases performs best overall.  ...  DISCUSSION We compared machine learning algorithms and input feature sets, and show that a Random Forests model trained on eleven lags of historical Dengue cases is effective at forecasting Dengue one  ... 
doi:10.1101/2021.02.17.430949 fatcat:6icwavujnbfodkczgyrxmxnhry

A Recurrent Neural Network and Differential Equation Based Spatiotemporal Infectious Disease Model with Application to COVID-19 [article]

Zhijian Li, Yunling Zheng, Jack Xin, Guofa Zhou
2020 medRxiv   pre-print
Modeling the trend of infection and real-time forecasting of cases can help decision making and control of the disease spread.  ...  The former after simplification and discretization is a compact model of temporal infection trend of a region while the latter models the effect of nearest neighboring regions.  ...  Derivation of Discrete-Time I-Equation Based on SIR model, we add an additional feature I e that represents the external infection influence from the neighbors of a region.  ... 
doi:10.1101/2020.07.20.20158568 fatcat:hymtogwz5jb4rdtxna47d7xdae

Makine Öğrenmesi Algoritmalarını Kullanarak Rüzgar Enerjisi Üretimi Tahmini

Özlem YÜREK, Derya BİRANT, İ̇smail YÜREK
2021 Deu Muhendislik Fakultesi Fen ve Muhendislik  
machine learning (ML) techniques using historical wind power generation data and weather forecasting reports.  ...  This study proposes a prediction model to solve a real-life problem in the renewable energy sector by accurately estimating the amount of wind energy production per hour in the next 24 hours by applying  ...  We created the features of weather forecasting information for the hourly time horizon. Table 1 shows a sample subset of the dataset after the feature generation process.  ... 
doi:10.21205/deufmd.2021236709 fatcat:siobtzo3z5eqlmpb44agoiwnha

Intelligent Methods Used for Obtaining Weather Derivatives: A Review

Gujanatti Rudrappa, Nataraj Vijapur
2019 Engineering and Applied Sciences  
The distinct nature of the model forecasting in all situations accurately is challenging.  ...  Weather forecasting is a formidable challenge as weather is a multi-dimensional, continuous and chaotic process.  ...  Based on time or duration of forecasting period, the weather forecasting can be divided into six categories: [3] Now-casting (NC), Very short range forecasting, Short range forecasting, Medium range  ... 
doi:10.11648/j.eas.20190406.12 fatcat:y5m2rweezjc4zlopm3xckp5rqi

Renewable Energy Production Forecasting: A Comparative Machine Learning Analysis

Kazi Md Shahiduzzaman, Department of Electrical and Electronic Engineering, Jatiya Kazi Nazrul Islam University, Mymensingh, Bangladesh., Md Noor Jamal, Md. Rashed Ibn Nawab, School of Electronics, Information and Communication, Huazhong University of Science and Technology, Wuhan, China., School of Computer Science and Technology, Northwestern Polytechnical University, China.
2021 International Journal of Engineering and Advanced Technology  
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.  ...  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  ...  It takes least amount of time. But time taken by SVM based model can also be considered as less. Model based on SVM are also lightweight.  ... 
doi:10.35940/ijeat.e2689.0810621 fatcat:7efih2augjaeneydhe5gvgkxiu

Short-term Forecasting of Intermodal Freight Using ANNs and SVR: Case of the Port of Algeciras Bay

J.A. Moscoso-López, I.J. Turias Turias, M.J. Come, J.J. Ruiz-Aguilar, M. Cerbán
2016 Transportation Research Procedia  
In this paper, two forecasting-models are presented and compared to predict the freight volume. The models developed and tested are based on Artificial Neural Networks and Support Vector Machines.  ...  Both techniques are based in a historical data and these methods forecast the daily weight of the freight with one week in advance.  ...  The most widely used model for time series modelling and forecasting is a single hidden layer network.  ... 
doi:10.1016/j.trpro.2016.12.015 fatcat:72cpckrw2fgtpnplnj33l42mly

Synthetic Error Modeling for NC Machine Tools based on Intelligent Technology

Xinhua Yao, Jianzhong Fu, Yuetong Xu, Yong He
2013 Procedia CIRP  
The works in this paper make a special summary of the error modeling with intelligent technology, and provide a useful guidance to further research on error compensation of NC machine tools.  ...  The intelligent technology methods of neural network, support vector machines, Bayesian networks are the effective modeling and forecasting methods for machine errors.  ...  To sum up the above arguments the LS-SVM model has comprehensive performance in forecast accuracy and calculating time, so it is extremely suitable for modeling synthetic error of NC machine tools on-line  ... 
doi:10.1016/j.procir.2013.08.017 fatcat:ob7ckcchlvchtccy6monoyqy3q
« Previous Showing results 1 — 15 out of 6,014 results