Germination Quality Prognosis: Classifying Spectroscopic Images of the Seed Samples  

作　　者：Saud S.Alotaibi 

机构地区：[1]Department of Information Systems,College of Computer and Information Systems,Umm Al-Qura University,Makkah,Saudi Arabia

出　　处：《Intelligent Automation & Soft Computing》2023年第2期1815-1829,共15页智能自动化与软计算（英文）

摘　　要：One of the most critical objectives of precision farming is to assess the germination quality of seeds.Modern models contribute to thisfield primarily through the use of artificial intelligence techniques such as machine learning,which present difficulties in feature extraction and optimization,which are critical factors in predicting accuracy with few false alarms,and another significant dif-ficulty is assessing germination quality.Additionally,the majority of these contri-butions make use of benchmark classification methods that are either inept or too complex to train with the supplied features.This manuscript addressed these issues by introducing a novel ensemble classification strategy dubbed“Assessing Germination Quality of Seed Samples(AGQSS)by Adaptive Boosting Ensemble Classification”that learns from quantitative phase features as well as universal features in greyscale spectroscopic images.The experimental inquiry illustrates the significance of the proposed model,which outperformed the currently avail-able models when performance analysis was performed.

关 键 词：Precision farming ensemble classification germination quality machine learning predictive analytics 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]