Claim Missing Document
Check
Articles

Found 3 Documents
Search

Predicting Impact of COVID-19 on Crude Oil Price Image with Directed Acyclic Graph Deep Convolution Neural Network O. Oyewola, David; Femi Augustine, Akomolafe; Gbenga Dada, Emmanuel; Ibrahim, Asabe
Journal of Robotics and Control (JRC) Vol 2, No 2 (2021): March
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.2261

Abstract

Deep learning methods have achieved amazing results in sequential input, prediction and image classification. In this study, we propose image transformation of time series crude oil price by incorporating 2-D Directed Acyclic Graph to Convolutional Neural Network (DAG) based on image processing properties. Crude oil price time series is converted into 2-D images, utilizing 10 distinctive technical indicators. Geometric Brownian Motion was utilized to produces data for a 10-day time span. Thus, 10x10 sized 2-D images are constructed. Each image is then labelled as Buy or Sell depending on the returns of the time series. The results show that integrating DAG with CNN improves the prediction accuracy by 14.18%.  DAG perform best with an accuracy of 99.16%, sensitivity of 100% and specificity of 99.19%. COVID-19 has negatively affected Nigeria crude oil price which indicates a downward trend of crude oil price. The study recommends poly-cultural economy of Nigeria economy for national development of the nation.
Buys Ballot Approach in Time Series Analysis of Typhoid Fever Dalatu, Paul I.; Ibrahim, Asabe
Sigma&Mu: Journal of Mathematics, Statistics and Data Science Vol. 1 No. 1 (2023): March
Publisher : Balai Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56566/sigmamu.v1i1.60

Abstract

Typhoid fever (is also called enteric fever) is a bacterial disease spread through contaminated food, water or close contact. However, where it is prevalence government usually recommend vaccines to curtail its deadly spreading in the affected area. The fever is caused by Salmonella typhi bacteria. Therefore, we had adopted the Buys Ballot approach by using time series analysis for the estimation of trend of typhoid fever disease from the year 2011 to 2020 and predicts the future occurrence of the disease in Mubi South Local Government Area (LGA) of Adamawa State, Nigeria. However, based on the data used the result shows that there is significant increase in the recorded cases of typhoid fever disease, it has forecasted and predicted that more number of people may be affected in future compared to the study results obtained. Hence, this study has given some recommendations in order to reduce the prevalence of typhoid fever disease in future
Empirical Analysis of Five Child-Killer Diseases and Under Five Mortality in Adamawa State, Nigeria Dalatu, Paul Inuwa; Ibrahim, Asabe; Kwanamu, Joshua A.
Sigma&Mu: Journal of Mathematics, Statistics and Data Science Vol. 2 No. 2 (2024): September
Publisher : Balai Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56566/sigmamu.v2i2.204

Abstract

Under-Five Mortality rate refers to the probability a new-born would die before reaching exactly 5 years of age, expressed per 1,000 or 100,000 live births. The Five Child-Killer Diseases used in this study are Pneumonia, Diarrhoea, Measles, Tetanus and Polio. The study used Ex post facto design with quantitative approach. A secondary data of the Five-Child Killer Diseases and Under-Five Mortality were obtained from the twenty-one (21) Local Government Primary Health Care Development Agency in Adamawa State between the periods of 2008 to 2022. The study measured the mortality rate due to the Five Child-Killer Diseases and its Cause-effect on the Overall Under-Five Mortality Irrespective of Diseases in the study area and then develop a model for future prediction. Based on the finding, the Overall Under-Five Mortality rate increases from 112 to 314 deaths per thousand live births between 2008 and 2012, followed by a sudden decrease from 261 to 90 deaths from 2013 to 2016 and then fluctuate throughout the rest of the period under review.  Individually, the largest contributor of Under-Five Mortality among the Five Child-killer Diseases is Diarrhea with 89 deaths per thousand live births in 2011, followed by Measles with 39 deaths in the same year. The regression model revealed a positive and insignificant causal relationship between deaths due to Pneumonia, Diarrhoea and Measles on Overall Under-Five Mortality in the study area. The regression model also explained that; at zero deaths due to the Five Child-Killer Diseases, the Overall Under-Five Mortality is more than 105 deaths in the study area.