Grain is by far the largest amount of food stored in the world. The early prediction of grain mold (GM) is mainly to be able to detect it in time before its significant growth activity to avoid causing loss of stored grain. Microorganisms are tiny and not visible to the naked eye in the early stage, if microbial colonies can be observed in the grain pile, these parts of the grain often already have serious deterioration, mold metabolism is more hazardous to produce mycotoxins, which has a more adverse impact on the safe storage of grain, in fact, as long as there is the growth of microorganisms such as mold in the grain, even if the colonies of mold are not visible to the naked eye, the grain quality will have significant changes. In order to ensure the quality of grain output, the best way is to prevent GM. In this regard, this paper suggests a model for predicting the probability of GM based on the Naive Bayes(NB) algorithm, cultivating GM samples, and comparing the prediction errors of these three models with the PSO-LSSVM model and ARIMA model to predict the probability of mold in samples, we know that the prediction error(PE) of the NB model is the smallest, which means that the difference between the predicted value of GM and the real value of the model is small, and the accuracy of using this model for prediction is more reliable. The accuracy of the model is more reliable.

Rajit Mansour. Prediction Model of Grain Mold Probability Based on Naive Bayes Algorithm. Machine Learning Theory and Practice (2021), Vol. 2, Issue 3: 36-43. https://doi.org/10.38007/ML.2021.020305.

[1] Kristin McCullough, Tatiana Dmitrieva, Nader Ebrahimi: New approximate Bayesian computation algorithm for censored data. Comput. Stat. 37(3): 1369-1397 (2021). https://doi.org/10.1007/s00180-021-01167-3

[2] Ciniro Aparecido Leite Nametala, Wandry R. Faria, Benvindo R. Pereira Junior: On the performance of the Bayesian optimization algorithm with combined scenarios of search algorithms and scoring metrics. Genet. Program. Evolvable Mach. 23(2): 193-223 (2021). 

[3] Vicente P. Soloviev, Pedro Larranaga, Concha Bielza: Estimation of distribution algorithms using Gaussian Bayesian networks to solve industrial optimization problems constrained by environment variables. J. Comb. Optim.44(2): 1077-1098 (2021). 

[4] Jakeoung Koo, Abderrahim Halimi, Stephen McL aughlin: A Bayesian Based Deep Unrolling Algorithm for Single-Photon Lidar Systems. IEEEJ. Sel. Top. Signal Process. 16(4): 762-774 (2021). 

[5] Vahid Rafe, Somayeh Mohammady, Erik Cuevas: Using Bayesian optimization algorithm for model-based integration testing. Soft Comput.26(7): 3503-3525 (2021). https://doi.org/10.1007/s00500-021-06476-9

[6] Raymond Leung, Alexander Lowe, Anna Chlingaryan, Arman Melkumyan, John N. Zigman: Bayesian Surface Warping Approach for Rectifying Geological Boundaries Using Displacement Likelihood and Evidence from Geochemical Assays. ACM Trans. Spatial Algorithms Syst. 8(1): 1-23 (2021). https://doi.org/10.1145/3476979

[7] Thomas Callens, Tuur van der Have, Sam Van Rossom, Joris De Schutter, Erwin Aertbelien: A Framework for Recognition and Prediction of Human Motions in Human-Robot Collaboration Using Probabilistic Motion Models. IEEE Robotics Autom. Lett. 5(4): 5151-5158 (2020). https://doi.org/10.1109/LRA.2020.3005892

[8] Alberto Castellini, Federico Bianchi, Alessandro Farinelli: Generation and interpretation of parsimonious predictive models for load forecasting in smart heating networks. Appl. Intell. 52(9): 9621-9637 (2021). https://doi.org/10.1007/s10489-021-02949-4

[9] Oscar Serradilla, Ekhi Zugasti, Jon Rodriguez, Urko Zurutuza: Deep learning models for predictive maintenance: a survey, comparison, challenges and prospects. Appl. Intell. 52(10): 10934-10964 (2021). https://doi.org/10.1007/s10489-021-03004-y

[10] Anne-Christin Hauschild, Marta Lemanczyk, Julian. Matschinske, Tobias Frisch, Olga 1. Zolotareva, Andreas Holzinger, Jan Baumbach, Dominik Heider: Federated Random Forests can improve local performance of predictive models for various healthcare applications. Bioinform. 38(8): 2278-2286 (2021). https://doi.org/10.1093/bioinformatics/btac065

[11] Faygal Hamdi, Abderaouf Khalfi: Predictive density criterion for SETAR models. Commun. Stat. Simul. Comput. 51(2): 443-459 (2021). https://doi.org/10.1080/03610918.2019.1653915

[12] Eleonora Proia, Alessio Ragno, Lorenzo Antonini, Manuela Sabatino, Milan Mladenovic, Roberto Capobianco, Rino Ragno: Ligand-based and structure-based studies to develop predictive models for SARS-CoV-2 main protease inhibitors through the 3d-qsar.com portal. J. Comput. Aided Mol.Des.36(7): 483-505 (2021) 

[13] Cinzia Giannetti, Aniekan Essien: Towards scalable and reusable predictive models for cyber twins in manufacturing systems. J. Intell. Manuf. 33(2): 441-455 (2021). https://doi.org/10.1007/s10845-021-01804-0

[14] Williams Rizzi, Chiara Di Francescomarino, Chiara Ghidini, Fabrizio Maria Maggi: How do I update my model? On the resilience of Predictive Process Monitoring models to change. Knowl. Inf. Syst. 64(5): 1385-1416 (2021). 

[15] Maxime De Bois, Mounim A. EI-Yacoubi, Mehdi Ammi: GLYFE: review and benchmark of personalized glucose predictive models in type 1 diabetes. Medical Biol. Eng. Comput.60(1): 1-17 (2021). https://doi.org/10.1007/s11517-021-02437-4

[16] Ebru Akis, Gural Guven, Bahram Lotfi Sadigh: Predictive models for mechanical properties of expanded polystyrene (EPS) geofoam using regression analysis and artificial neural networks. Neural Comput. Appl. 34(13):10845-10884 (2021). 

[17] Krisztian Mark Balla, Christian Schou, Jan Dimon Bendtsen, Carlos Ocampo-Martinez, Carsten Skovmose Kallesoe: A Nonlinear Predictive Control Approach for Urban Drainage Networks Using Data-Driven Models and Moving Horizon Estimation. IEEE Trans. Control. Syst. Technol. 30(5):21 47-2162 (2021). https://doi.org/10.1109/TCST.2021.3137712

[18] Daehee Kwon, Eunseop Yeom: Shape evaluation of highly overlapped powder grains using U-Net-based deep learning segmentation network. J. Vis. 24(5): 931-942 (2021). https://doi.org/10.1007/s12650-021-00748-0

[19] Petra Perner: Detection of Hygiene-Relevant Parameters from Cereal Grains such as Mycotoxinbased on Microscopic lmaging, Intelligent lmage Processing and Data Mining. Trans. Mass Data Anal. Images Signals 12(1): 13-21 (2021).