Bootstrapping random forest and CHAID for prediction of white spot disease among shrimp farmers

Abstract

Technology is playing an important role is healthcare particularly as it relates to disease prevention and detection. This is evident in the COVID-19 era as different technologies were deployed to test, detect and track patients and ensure COVID-19 protocol compliance. The White Spot Disease (WSD) is a very contagious disease caused by virus. It is widespread among shrimp farmers due to its mode of transmission and source. Considering the growing concern about the severity of the disease, this study provides a predictive model for diagnosis and detection of WSD among shrimp farmers using visualization and machine learning algorithms. The study made use of dataset from Mendeley repository. Machine learning algorithms; Random Forest classification and CHAID were applied for the study, while Python was used for implementation of algorithms and for visualization of results. The results achieved showed high prediction accuracy (98.28%) which is an indication of the suitability of the model for accurate prediction of the disease. The study would add to growing knowledge about use of technology to manage White Spot Disease among shrimp farmers and ensure real-time prediction during and post COVID-19.

Using the Term Frequency-Inverse Document Frequency for the Problem of Identifying Shrimp Diseases with State Description Text

“…This method can be divided into different categories. The first is an image-based shrimp disease classification method using deep learning models such as Convolutional Neural Network (CNN) [12], [13], [21], YOLO model [22], and machine learning [23], [24]. The effectiveness of this strategy depends mainly on the picture size and quality.…”

Experimental Infection Models and Their Usefulness for White Spot Syndrome Virus (WSSV) Research in Shrimp

“…Although our understanding of WSSV infection and pathogenesis in shrimp is incomplete, the urgent need for effective control measures has led to the exploration of multiple potential mitigation strategies [96]. Antiviral therapies [227][228][229], the use of immunomodulators [230][231][232][233][234][235], genetic selection for WSSV resistance [210,211,213], and even artificial intelligence (AI) could play a significant role in WSSV mitigation [236][237][238][239][240][241][242][243]. The use of high throughput standardized in vivo challenge tests is commonly deemed to be a necessary and appropriate method to support their development [88].…”

“…Liu et al [240] for instance, suggest that the innovative fusion of predictive modeling and smart nanotechnology, offers a cutting-edge approach to combat WSD, because it enables precise drug delivery and targeted interventions at the molecular level. Moreover, some researchers are developing machine learning models for the prediction of the occurrence of disease, because based on such information, shrimp farmers could easily determine suitable locations for new farms or prepare appropriate solutions to avoid infection [239,243]. Lastly, machine learning methods to enhance early WSD detection in shrimp using computer vision systems and image analysis algorithms have been proposed, although limited visibility combined with bottom dwelling behavior may present unique challenges [236,237,241,242].…”

Aprendizado de Máquina na Carcinicultura: Diagnóstico da Doença da Mancha Branca em Camarões

“…Na Tabela 2 são exibidos os dados comparativos entre metodologias utilizadas para o diagnóstico de doenc ¸as em camarões. Apenas o trabalho de [Edeh et al 2022] O estudo da Tabela 2 apresenta um resultado notável se comparada com as demais, atingindo uma acurácia de 98,61% no diagnóstico do WSSV com apenas três atributos e algoritmos simples, destacando a eficácia da abordagem adotada, tornando-a uma promissora ferramenta para o diagnóstico preciso da WSSV. Os artigos relatados nessa comparac ¸ão foram expostos na primeira sec ¸ão deste trabalho.…”

“…Utilizando o mesmo conjunto de dados deste trabalho [Hasan and Haque 2020], o estudo de [Edeh et al 2022] aplicou os algoritmos floresta aleatória e CHAID para implementac ¸ão e visualizac ¸ão dos resultados, obtendo uma predic ¸ão de 98,28%, indicando a eficácia do modelo na previsão, permitindo melhor controle da doenc ¸a e tomada de decisões mais eficientes pelos produtores.…”