Dengue is a mosquito-transmitted viral disease that causes mild to severe infection. In the tropics, the risk of high infection is driven by factors that influence its vector’s population density such as meteorological variables and unplanned rapid urbanization. In the Philippines, dengue remains endemic in all regions reporting hundreds of thousands of cases annually. The continuous development of data-based infectious disease prediction models plays a vital role in overcoming this persistent adversity. This study explored the application of artificial intelligence (AI) through a deep learning approach using the long short-term memory (LSTM) architecture in our prediction model. This is compared with the traditional feed-forward network approach using a multilayer perceptron (MLP) model and a statistical approach using non-seasonal and seasonal autoregressive integrated moving average (ARIMA). The forecasting models predicted the monthly number of reported dengue cases in Davao City using temperature, rainfall, relative humidity, and previous monthly cases. Model performance was evaluated using the root mean square error (RMSE). The LSTM model recorded the highest accuracy among the models, reporting two times lower RMSE than the MLP model and four times lower RMSE than the statistical models. This result demonstrated the feasibility of deep learning techniques to capture nonlinear characteristics of data and the ability of the LSTM to effectively incorporate information from longer past periods in its prediction.
Changes that occurred in the agriculture-food system – for instance, increase in disease incidence compounded by climate change, as well as changes in contractual arrangements and policies – pose challenges to small-scale Cavendish banana farmers in the Davao region, the top producer of Cavendish in the Philippines, in terms of their vulnerability and ability to survive. The current challenges can be addressed by increasing the opportunity of small-scale farmers to increase their profit by exploring alternative enterprises. The current system of the farmers is to allocate their entire harvested Cavendish bananas into the contractual market or the spot market. While these farmers can improve their profit by processing raw bananas into alternative products such as banana flour, very few of them have embarked on this enterprise. One reason for this is the limited understanding of this market potential and its profitability relative to contractual or spot market. Hence, in this study, we explored through a model simulation – a novel yet simplistic approach – different scenarios of a farmer’s profit as they venture into the banana flour market. Some model considerations include flour demand, the volatility of spot market prices, and banana production rates. Our simulations show that the total profit of the model farmer varies significantly with different allocations of bananas to contractual or spot markets for various demands in the banana flour market. Additionally, with our model assumptions, model farmers can further increase their profit if all their unsold fresh bananas have been processed to banana flour and sold them during high demand. Finally, we highlight the novelty of our approach as a diagnostic tool to initially assess the profitability of a commodity among different market options especially when there are unexplored scenarios and data is scarce.
Problems concerning low-profit-generating production occur in many small producer enterprises, including banana flour production by small-scale Cavendish banana farmers. One usual difficulty is the inability of these small producers to adjust to market conditions due to limited resources. These farmers are unable to allocate adequate resources such as transport vehicles, equipment, and laborers to various activities in the production process. This paper formulated a mixed-integer linear programming model based on a supply chain network design for banana flour production. This model aimed to determine the optimal number of resources for a producer organization to maximize its total profit. The deterministic branch-and-bound technique and metaheuristic binary firefly algorithm were implemented to obtain the model solution. Based on a case study, both approaches consistently showed that to maximize the profit for small-scale banana flour production, they must operate one mill and one truck with a 4,000- kg maximum capacity and hire nine non-regular and 14 regular laborers. The methodology developed in this study can also be applied to other banana producer organizations with a similar supply chain network to explore alternative enterprises and improve profitability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.