Development of Heatwave Probability Prediction Model Based on Recurrent Neural Network: A Case of Seoul Metropolitan Government

Recently, the incidence of heat waves has increased due to climate change, and the resultant mortalities and socio-economic damage are also increasing in Korea. Hence, emphasis has been placed on research examining heatwaves and their effects. Predicting the probability of heatwave in advance is very important from the perspective of disaster risk management; however, related studies have been insufficient so far. Therefore, in this study, the probability of future heatwave onset was predicted using daily scaled past weather data for Seoul Metropolitan Government. For the analysis, models based on recurrent neural networks (RNN, LSTM, GRU) were used, which are suitable for analyzing time-series data. Upon evaluating the performance of the GRU model, which was selected as the optimized model, no overfitting problem was observed. The prediction accuracy of the model was high as it demonstrated a reproduction of 78% and 86% of actual heatwave days during the validation and test process, respectively. Therefore, this model can be used by each local government to coordinate an efficient response to heat waves.

Download Full-text

Deep Network based on Long Short-Term Memory for Time Series Prediction of Microclimate Data inside the Greenhouse

International Journal of Computational Intelligence and Applications ◽

10.1142/s1469026820500133 ◽

2020 ◽

Vol 19 (02) ◽

pp. 2050013

Author(s):

Sawsan Morkos Gharghory

Keyword(s):

Time Series ◽

Relative Humidity ◽

Time Series Data ◽

Short Term Memory ◽

Weather Data ◽

Series Data ◽

Short Term ◽

Term Memory ◽

Long Short Term Memory ◽

Lstm Network

An enhanced architecture of recurrent neural network based on Long Short-Term Memory (LSTM) is suggested in this paper for predicting the microclimate inside the greenhouse through its time series data. The microclimate inside the greenhouse largely affected by the external weather variations and it has a great impact on the greenhouse crops and its production. Therefore, it is a massive importance to predict the microclimate inside greenhouse as a preceding stage for accurate design of a control system that could fulfill the requirements of suitable environment for the plants and crop managing. The LSTM network is trained and tested by the temperatures and relative humidity data measured inside the greenhouse utilizing the mathematical greenhouse model with the outside weather data over 27 days. To evaluate the prediction accuracy of the suggested LSTM network, different measurements, such as Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), are calculated and compared to those of conventional networks in references. The simulation results of LSTM network for forecasting the temperature and relative humidity inside greenhouse outperform over those of the traditional methods. The prediction results of temperature and humidity inside greenhouse in terms of RMSE approximately are 0.16 and 0.62 and in terms of MAE are 0.11 and 0.4, respectively, for both of them.

Download Full-text

API Call-Based Malware Classification Using Recurrent Neural Networks

Journal of Cyber Security and Mobility ◽

10.13052/jcsm2245-1439.1036 ◽

2021 ◽

Author(s):

Chen Li ◽

Junjun Zheng

Keyword(s):

Neural Networks ◽

Recurrent Neural Networks ◽

Time Series Data ◽

Short Term Memory ◽

Application Programming Interface ◽

Classification Model ◽

Series Data ◽

Process Time ◽

Economic Damage ◽

Malware Classification

Malicious software, called malware, can perform harmful actions on computer systems, which may cause economic damage and information leakage. Therefore, malware classification is meaningful and required to prevent malware attacks. Application programming interface (API) call sequences are easily observed and are good choices as features for malware classification. However, one of the main issues is how to generate a suitable feature for the algorithms of classification to achieve a high classification accuracy. Different malware sample brings API call sequence with different lengths, and these lengths may reach millions, which may cause computation cost and time complexities. Recurrent neural networks (RNNs) is one of the most versatile approaches to process time series data, which can be used to API call-based Malware calssification. In this paper, we propose a malware classification model with RNN, especially the long short-term memory (LSTM) and the gated recurrent unit (GRU), to classify variants of malware by using long-sequences of API calls. In numerical experiments, a benchmark dataset is used to illustrate the proposed approach and validate its accuracy. The numerical results show that the proposed RNN model works well on the malware classification.

Download Full-text

Use of discriminant function analysis for forecasting crop yield

MAUSAM ◽

10.54302/mausam.v63i3.1241 ◽

2022 ◽

Vol 63 (3) ◽

pp. 455-458

Author(s):

RANJANA AGRAWAL ◽

CHANDRA HAS ◽

KAUSTAV ADITYA

Keyword(s):

Discriminant Function ◽

Discriminant Function Analysis ◽

Time Series Data ◽

Function Analysis ◽

Wheat Yield ◽

Quadratic Function ◽

Qualitative Assessment ◽

Weather Data ◽

Series Data ◽

Yield Forecast

The present paper deals with use of discriminant function analysis for developing wheat yield forecast model for Kanpur (India). Discriminant function analysis is a technique of obtaining linear/Quadratic function which discriminates the best among populations and as such, provides qualitative assessment of the probable yield. In this study, quantitative forecasts of yield have been obtained using multiple regression technique taking regressors as weather scores obtained through discriminant function analysis. Time series data of 30 years (1971-2000) have been divided into three categories: congenial, normal and adverse, based on yield distribution. Taking these three groups as three populations, discriminant function analysis has been carried out. Discriminant scores obtained from this have been used as regressors in the modelling. Various strategies of using weekly weather data have been proposed. The models have been used to forecast yield in the subsequent three years 2000-01 to 2002-03 (which were not included in model development). The approach provided reliable yield forecast about two months before harvest.

Download Full-text

IMPLIKASI TRANSFER FISKAL TERHADAP DISPARITAS INCOME

Musamus Journal of Economics Development ◽

10.35724/feb.v2i1.2478 ◽

2019 ◽

Vol 2 (1) ◽

pp. 24-28

Author(s):

Yuan Williamson Tamberan ◽

Romualdus Turu Putra Maro Djanggo

Keyword(s):

Time Series Data ◽

Series Data ◽

The Internet ◽

Income Disparity ◽

Regional Autonomy ◽

Fiscal Transfers ◽

Fiscal Transfer ◽

Transfer Income ◽

Analysis Models ◽

Positive Effect

This study aims to determine the implications of fiscal transfer to income disparity in Merauke Regency. The type of data used is time series data which began in 2010-2018 and the data collection was carried out using the documentation method sourced from the Central Statistics Agency of Merauke Regency and the Internet. Data were analyzed using regression analysis models with the help of SPSS 21 software. The results showed that partially or simultaneously fiscal transfers in the form of general allocation fund variables and special autonomy fund variables had a significant positive effect on income disparity variables in Merauke Regency. Keywords: fiscal transfer, income disparity, regional autonomy

Download Full-text

Cluster Analysis on Dengue Incidence and Weather Data Using K-Medoids and Fuzzy C-Means Clustering Algorithms (Case Study: Spread of Dengue in the DKI Jakarta Province)

Journal of Mathematical and Fundamental Sciences ◽

10.5614/j.math.fund.sci.2021.53.3.9 ◽

2022 ◽

Vol 53 (3) ◽

pp. 466-486

Author(s):

Cindy Cindy ◽

Cynthia Cynthia ◽

Valentino Vito ◽

Devvi Sarwinda ◽

Bevina Desjwiandra Handari ◽

...

Keyword(s):

Time Series ◽

Time Series Data ◽

Clustering Algorithms ◽

Capital City ◽

Weather Data ◽

Series Data ◽

Weather Factors ◽

Fuzzy C Means ◽

Fuzzy C Means Clustering ◽

The Government

In Indonesia, Dengue incidence tends to increase every year but has been fluctuating in recent years. The potential for Dengue outbreaks in DKI Jakarta, the capital city, deserves serious attention. Weather factors are suspected of being associated with the incidence of Dengue in Indonesia. This research used weather and Dengue incidence data for five regions of DKI Jakarta, Indonesia, from December 30, 2008, to January 2, 2017. The study used a clustering approach on time-series and non-time-series data using K-Medoids and Fuzzy C-Means Clustering. The clustering results for the non-time-series data showed a positive correlation between the number of Dengue incidents and both average relative humidity and amount of rainfall. However, Dengue incidence and average temperature were negatively correlated. Moreover, the clustering implementation on the time-series data showed that rainfall patterns most closely resembled those of Dengue incidence. Therefore, rainfall can be used to estimate Dengue incidence. Both results suggest that the government could utilize weather data to predict possible spikes in DHF incidence, especially when entering the rainy season and alert the public to greater probability of a Dengue outbreak.

Download Full-text

Applied Data Analytics to Buoy Records for Weather Window Evaluation

10.5957/smc-2021-082 ◽

2021 ◽

Author(s):

Tirtharaj Bhaumik ◽

Shiladitya Basu

Keyword(s):

Wave Height ◽

Significant Wave Height ◽

Data Analytics ◽

Time Series Data ◽

Weather Data ◽

Series Data ◽

Wave Direction ◽

Significant Wave ◽

Using Data ◽

Future Work

This paper analyzes weather data recorded by typical oceanographic buoys using data analytics and regression techniques. Time series data over a period of more than four decades (1976 – 2020) are reviewed and profiled. A set of key variables including seasonality, wind speed, wind direction, wave period, wave direction, etc., are screened from the buoy measurements to build a predictive model based on multiple linear regression for significant wave height prediction. A sensitivity analysis is then conducted for the available weather window corresponding to specified threshold operational limits of the significant wave height. Key insights are presented along with suggestions for future work to assist marine operators in planning and derisking offshore operations. Utilizing the algorithms and workflows presented in this paper, a user can increase confidence in weather window prediction, and develop safer, efficient offshore operation plans.

Download Full-text

Crop Yield Prediction Using Multitemporal UAV Data and Spatio-Temporal Deep Learning Models

Remote Sensing ◽

10.3390/rs12234000 ◽

2020 ◽

Vol 12 (23) ◽

pp. 4000

Author(s):

Petteri Nevavuori ◽

Nathaniel Narra ◽

Petri Linna ◽

Tarmo Lipping

Keyword(s):

Time Series ◽

Deep Learning ◽

Crop Yield ◽

Time Series Data ◽

Weather Data ◽

Series Data ◽

Percentage Error ◽

Time Series Modelling ◽

Spatio Temporal ◽

3D Cnn

Unmanned aerial vehicle (UAV) based remote sensing is gaining momentum worldwide in a variety of agricultural and environmental monitoring and modelling applications. At the same time, the increasing availability of yield monitoring devices in harvesters enables input-target mapping of in-season RGB and crop yield data in a resolution otherwise unattainable by openly availabe satellite sensor systems. Using time series UAV RGB and weather data collected from nine crop fields in Pori, Finland, we evaluated the feasibility of spatio-temporal deep learning architectures in crop yield time series modelling and prediction with RGB time series data. Using Convolutional Neural Networks (CNN) and Long-Short Term Memory (LSTM) networks as spatial and temporal base architectures, we developed and trained CNN-LSTM, convolutional LSTM and 3D-CNN architectures with full 15 week image frame sequences from the whole growing season of 2018. The best performing architecture, the 3D-CNN, was then evaluated with several shorter frame sequence configurations from the beginning of the season. With 3D-CNN, we were able to achieve 218.9 kg/ha mean absolute error (MAE) and 5.51% mean absolute percentage error (MAPE) performance with full length sequences. The best shorter length sequence performance with the same model was 292.8 kg/ha MAE and 7.17% MAPE with four weekly frames from the beginning of the season.

Download Full-text

Forecast of weather parameters using time series data

MAUSAM ◽

10.54302/mausam.v65i4.1185 ◽

2021 ◽

Vol 65 (4) ◽

pp. 509-520

Author(s):

A.K. SHUKLA ◽

Y.A. GARDE ◽

INA JAIN

Keyword(s):

Time Series ◽

Time Series Data ◽

Weather Forecasting ◽

Forecast Error ◽

Moving Average ◽

Kendall Test ◽

Weather Data ◽

Series Data ◽

Maximum Temperature ◽

Weather Parameters

The present study is undertaken to develop area specific weather forecasting models based on time series data for Pantnagar, Uttarakhand. The study was carried out by using time series secondary monthly weather data of 27 years (from 1981-82 to 2007-08). The trend analysis of weather parameters was done by Mann-Kendall test statistics. The methodologies adopted to forecast weather parameters were the winter’s exponential smoothing model and Seasonal Autoregressive Integrated Moving Average (SARIMA). Comparative study has been carried out by using forecast error percentage and mean square error. The study showed that knowledge of this trend is likely to be helpful in planning and production of enterprises/crops. The study of forecast models revealed that SARIMA model is the most efficient model for forecasting of monthly maximum temperature, monthly minimum temperature and monthly humidity I. The Winter’s model was found to be the most efficient model for forecasting Monthly Humidity II but no model was found to be appropriate to forecast monthly total rainfall.

Download Full-text

Eigenstate Transition of Multi-Channel Time Series Data around Earthquakes

Applied Sciences ◽

10.3390/app112311407 ◽

2021 ◽

Vol 11 (23) ◽

pp. 11407

Author(s):

Akihisa Okada ◽

Yoshiyuki Kaneda

Keyword(s):

Time Series ◽

Early Warning ◽

Time Series Data ◽

Series Data ◽

Economic Damage ◽

First Eigenvalue ◽

Warning Signals ◽

Early Warning Signals ◽

The First Eigenvalue ◽

The Matrix

To decrease human and economic damage owing to earthquakes, it is necessary to discover signals preceding earthquakes. We focus on the concept of “early warning signals” developed in bifurcation analysis, in which an increase in the variances of variables precedes its transition. If we can treat earthquakes as one of the transition phenomena that moves from one state to the other state, this concept is useful for detecting earthquakes before they start. We develop a covariance matrix from multi-channel time series data observed by an observatory on the seafloor and calculate the first eigenvalue and corresponding eigenstate of the matrix. By comparing the time dependence of the eigenstate to some past earthquakes, it is shown that the contribution from specific observational channels to the eigenstate increases before earthquakes, and there is a case in which the eigenvalue increases as predicted in early warning signals. This result suggests the first eigenvalue and eigenstate of multi-channel data are useful to identify signals preceding earthquakes.

Download Full-text

Study of Cubic Splines and Fourier Series as Interpolation Techniques for Filling in Short Periods of Missing Building Energy Use and Weather Data

Journal of Solar Energy Engineering ◽

10.1115/1.2189872 ◽

2005 ◽

Vol 128 (2) ◽

pp. 226-230 ◽

Cited By ~ 7

Author(s):

Juan-Carlos Baltazar ◽

David E. Claridge

Keyword(s):

Time Series ◽

Fourier Series ◽

Energy Use ◽

Time Series Data ◽

Linear Interpolation ◽

Cubic Splines ◽

Weather Data ◽

Series Data ◽

Data Sets ◽

Data Points

A study of cubic splines and Fourier series as interpolation techniques for filling in missing hourly data in energy and meteorological time series data sets is presented. The procedure developed in this paper is based on the local patterns of the data around the gaps. Artificial gaps, or “pseudogaps,” created by deleting consecutive data points from the measured data sets, were filled using four variants of the cubic spline technique and 12 variants of the Fourier series technique. The accuracy of these techniques was compared to the accuracy of results obtained using linear interpolation to fill the same pseudogaps. The pseudogaps filled were 1–6 data points in length created in 18 year-long sets of hourly energy use and weather data. More than 1000 pseudogaps of each gap length were created in each of the 18 data sets and filled using each of the 17 techniques evaluated. Use of mean bias error as the selection criterion found that linear interpolation is superior to the cubic spline and Fourier series methodologies for filling gaps of dry bulb and dew point temperature time series data. For hourly building cooling and heating use data, the Fourier series approach with 24 data points before and after each gap and six terms was found to be the most suitable; where there are insufficient data points to apply this approach, simple linear interpolation is recommended.

Download Full-text