AdaBoost classifiers for pecan defect classification

Mathanker, Sunil K.; Weckler, Paul; Bowser, Timothy J.; Wang, N.; Maness, Niels O.

doi:10.1016/j.compag.2011.03.008

Cited by 64 publications

(32 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this approach, a model was ''trained'' utilizing the calibration data set and tested for validity using the validation data set. Twenty random runs were made following the methodology of Mathanker et al (2011). Average prediction errors and root mean square errors for the twenty random runs were calculated.…”

Section: Methodsmentioning

confidence: 99%

Stem bending force and hydraulic system pressure sensing for predicting napiergrass yield during harvesting

Mathanker

Buss

Gan

et al. 2015

Computers and Electronics in Agriculture

Self Cite

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Stem bending force and hydraulic system pressure sensing for predicting napiergrass yield during harvesting

Mathanker

Buss

Gan

et al. 2015

Computers and Electronics in Agriculture

Self Cite

View full text Add to dashboard Cite

“…The classifier combination technology is widely adopted in agricultural fields, such as pecan quality inspection (Mathanker et al 2011), automatic shrimp shape grading (Zhang et al 2014), and fish classification duty (Dios et al 2003;Hu et al 2012). Combination idea does not rely on a single decision-making scheme.…”

Section: Combination Classifier For Shrimp Classificationmentioning

confidence: 99%

Identification of Impurities in Fresh Shrimp Using Improved Majority Scheme-Based Classifier

2016

View full text Add to dashboard Cite

The efficient removal of impurities from postharvest raw shrimp is beneficial to improve the quality of shrimp products. Single feature combined with single classifier results in poor classification rate. Moreover, accuracy of combined classifiers remains unsatisfactory, especially when sound shrimp is mixed with various defective shrimp and impurities. In this study, an improved majority rule (IMAJ) classifier combination scheme was proposed to address this problem. The accuracy of IMAJ (91.53 %) was compared with six other kinds of classifier combination schemes proposed by Kittler. The schemes include Sum (89.93 %), Product (65.99 %), Max (89.76 %), Min (80 %), Median (88.18 %), and Majority (89.2 %). Comparison results indicate that the combination classifier based on IMAJ rule is superior.

show abstract

“…Bagging [21], AdaBoost [22] and Random Forest [23] are used generally to sample a diversity of training sets from original data, then a series of classifiers on these new training sets are trained independently. These new produced classifiers can be combined together using majority voting or other methods to make a final decision on testing set.…”

Section: Ensemble Svc On Different Thresholds Of Pcamentioning

confidence: 99%