A comparative study of Machine Learning-based classification of Tomato fungal diseases: Application of GLCM texture features.

Globally, agriculture remains an important source of food and economic development. Due to various plant diseases, farmers continue to suffer huge yield losses in both quality and quantity. In this study, we explored the potential of using Artificial Neural Networks, K-Nearest Neighbors, Random Forest, and Support Vector Machine to classify tomato fungal leaf diseases: Alternaria, Curvularia, Helminthosporium, and Lasiodiplodi based on Gray Level Co-occurrence Matrix texture features. Small differences between symptoms of these diseases make it difficult to use the naked eye to obtain better results in detecting and distinguishing these diseases. The Artificial Neural Network outperformed other classifiers with an overall accuracy of 94% and average scores of 93.6% for Precision, 93.8% for Recall, and 93.8% for F1-score. Generally, the models confused samples originally belonging to Helminthosporium with Curvularia. The extracted texture features show great potential to classify the different tomato leaf fungal diseases. The results of this study show that texture characteristics of the Gray Level Co-occurrence Matrix play a critical role in the establishment of tomato leaf disease classification systems and can facilitate the implementation of preventive measures by farmers, resulting in enhanced yield quality and quantity.

Deciphering urban consumer requirements for rice quality gives insights for driving the future acceptability of local rice in Africa: Case study in the city of Saint-Louis in senegal.

Rice is the staple cereal in Senegal. Despite the many policies implemented over the last decade, Senegalese consumers still prefer imported over local rice. To understand this preference, this study compares consumer acceptability of three local rice samples versus two imported rice samples. Two focus groups and a consumer test with 120 women were carried out in the city of Saint-Louis in Senegal. The results concerning consumption habits showed that about 85% of the surveyed women consume rice at least once a day (at lunch). The hedonic test showed that consumers appreciated all five rice samples, but the most liked samples were obtained from industrial processing of either local or imported whole and fragrant rice. The least liked sample was a local semi-industrial rice, including 50% broken grains. The results of the just-about-right (JAR) test and check-all-that-apply (CATA) test showed that the sensory descriptors such as white color, well-cooked, and homogeneous grain size had an influence on the consumers' choice of rice samples. However, the most important selection criteria were the homogeneous size of the rice grains, the absence of impurities, both of which are directly linked to the milling conditions, and fragrance, which is related to the variety. The origin of the rice samples did not influence the consumers' choice. This study showed that local rice can compete with imported rice if processing is improved in some small-scale rice mills.