Total hatching egg set (for both egg production chicks and broilers) in the Agriculture and Agri-Food Canada report 2017 was over 1.0 billion. With the fertility rate for this year observed to be around 82%, there were about 180 million unhatched eggs (worth over 300 million Canadian dollars) incubated in Canada for the year 2017 alone. These non-hatching (non-fertile) eggs can find useful applications as commercial table eggs or low-grade food stock if they can be detected early and isolated accordingly preferably prior to incubation. The conventional method of chicken egg fertility assessment termed candling, is subjective, cumbersome, slow, and eventually inefficient, leading to huge economic losses. Hence, there is a need for a non-destructive, fast and online prediction technology to assist with early chicken egg fertility identification problem. This paper reviewed existing non-destructive approaches including ultrasound and dielectric measurements, thermal imaging, machine vision, spectroscopy, and hyperspectral imaging. Hyperspectral imaging was extensively discussed, being an emerging new technology with great potential. Suggestions were finally proffered towards building futuristic robust model(s) for early detection of chicken egg fertility.

No abstract

Quality detection has been a major problem in the agriculture and food industries. This operation is mostly done by a subjective sensory method which is prone to high error and food destruction. Therefore, there is a need to apply artificial intelligence using a machine learning approach. This study developed two intelligent acoustic yam quality detection and classification devices using two sound-generating techniques. The software (multi-wave frequency generator) sound-generating technique generated sound from a laptop to a speaker inside a detecting chamber. This sound passes through the yam and was received on the opposite side by a microphone, into another laptop for analysis using visual analyzer software. The impact sound-generating technique used sound generated from a gentle impact of the yam on a flat surface placed inside the detection chamber. The sound produced was picked up by a microphone into a laptop for analysis. Acoustic properties considered were amplitude, frequency, sound velocity, wavelength, period and sound intensity. Discriminant analysis algorithm only was used in this first stage of the study to prove the applicability of machine learning. Three qualities (good, diseased damaged and insect-damaged) of two yam varieties (white and yellow yam) were tested. The device's performance of white yam was 79 % and 68.7 %, yellow yam was 82.3 % and 68.7 % for the software sound generation-technique and surface impact sound-generating technique, respectively. The study shows that the software sound-generating technique performed better in terms of overall yam quality detection and also proves the applicability of machine learning.

Partial least square (PLS) regression is a well-known chemometric method used for predictive modelling, especially in the presence of many variables. Although PLS was not initially developed as a technique for classification tasks, scientists have reportedly used this approach successfully for discrimination purposes. Whereas some non-supervised learning approaches including but not limited to PCA, and k-means clustering do well in identifying/understanding grouping and clustering patterns in multidimensional data, they are limited when the end target is discrimination, making PLS a preferable alternative. A total of fertilized 672 chicken egg hyperspectral imaging data, consisting of 336 white eggs and 336 brown eggs were used in this study. Hyperspectral images in the NIR region of 900-1700 nm wavelength range were captured prior to incubation on day 0 and on days 1-4 after incubation. Eggs were candled on incubation day 5 and broken out on day 10 to confirm fertility. While a total number of 312 and 314 eggs were found to be fertile in the brown and white egg batches respectively, total numbers of non-fertile eggs in the same set of batches were 23 and 21 respectively. Spectral information was extracted from a segmented region of interest (ROI) of each hyperspectral image and spectral transmission characteristics were obtained by averaging the spectral information. A moving-thresholding technique was implemented for discrimination based on PLS regression results on the calibration set. With true positive rates (TPR) of up to 100% obtained at selected threshold values of between 0.50-0.85 and on different days of incubation, the results indicated that the proposed PLS technique can accurately discriminate between fertile and non-fertile eggs. The adaptive PLS approach was thereby presented as suitable for handling hyperspectral imaging-based chicken egg fertility data