Prediction of chick hatching time using visible transmission spectroscopy combined with partial least squares regression

Islam, Hamidul; Kondo, Naoshi; Ogawa, Yuichi; Fujiura, Tateshi; Nakajima, Shusaku; Fujitani, Shinichi

doi:10.1016/j.eaef.2014.10.001

Cited by 19 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the prediction model was evaluated using coefficient of determination (R 2 ), root mean square error of prediction (RMSEP), ratio of prediction difference (RPD) and range error ratio (RER) values. A good calibration model should have a high correlation coefficient (R) and a low RMSEP 8 . The RPD value, a measure of usefulness or goodness of fit, is higher when the error of prediction is smaller; thus higher RPD value means a better model 19 .…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Nondestructive Eggshell Thickness Measurement Technique Using Terahertz Waves

Khaliduzzaman

Konagaya

Suzuki

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

eggshells play a number of important roles in the avian and reptile kingdom: protection of internal contents and as a major source of minerals for developing embryos. However, when researching these respective roles, eggshell thickness measurement remains a bottleneck due to the lack of a non-destructive measurement techniques. As a result, many avian and reptile research protocols omit consideration of eggshell thickness bias on egg or embryo growth and development. Here, we validate a non-destructive method to estimate eggshell thickness based on terahertz (THz) reflectance spectroscopy using chicken white coloured eggs. Since terahertz waves are reflected from outer aireggshell interface, as well as the inner eggshell-membrane boundary, the resulting interference signals depend on eggshell thickness. Thus, it is possible to estimate shell thickness from the oscillation distance in frequency-domain. A linear regression-based prediction model for non-destructive eggshell thickness measurement was developed, which had a coefficient of determination (R 2) of 0.93, RMSEP of 0.009, RPD of 3.45 and RER 13.67. This model can estimate eggshell thickness to a resolution of less than 10 μm. This method has the potential to expand the protocols in the field of avian and reptile research, as well as be applied to industrial grading of eggs.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Moreover, eggshell colour pigment (i.e. protoporphyrin) further masks measurements in the visible region 8 . Therefore, we examined the use of THz waves (electromagnetic waves with a lower frequency than the above) to measure chicken eggshell thickness.…”

mentioning

confidence: 99%

A Nondestructive Eggshell Thickness Measurement Technique Using Terahertz Waves

Khaliduzzaman

Konagaya

Suzuki

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the previous work, Islam, et al [8] used visible transmission spectroscopy for prediction of chick hatch- The transmission spectra of the eggs were measured over the spectral range of 200 to 950 nm at 1 nm intervals. The integration time for one scan was 100 ms and the spectrum of each egg contains an average of 10 scans.…”

Section: Methodsmentioning

confidence: 99%

“…The prediction performance of the iPLS model was tested with the samples independent from the calibration sample set. The overall results were compared and discussed in comparison with results obtained in the previous report using a full-spectrum PLS (FS-PLS) calibration model [8].…”

Section: Introductionmentioning

confidence: 96%

Interval Partial Least Squares (iPLS) Regression Approach to Predict Hatching Time of Chick

Islam¹,

Kondo²,

Ogawa³

et al. 2018

Int J Exp Spectroscopic Tech

Self Cite

View full text Add to dashboard Cite

Due to a wide hatch window, hatchery managers need to deal with chicks of different biological ages at takeoff , which negatively affects the chick's post-hatched performance. Consequently, it is important to control the spread of the hatch window in order to have a batch of chicks with the same biological age. Since the spread of the hatch window is influenced by the hatching time of individual chicks, early prediction of hatching time can be used to limit the hatch window. In this study, the feasibility of using visible transmission spectroscopy combined with partial least squares (PLS) regression for the prediction of chick hatching time was investigated. An experiment was conducted with 100 chicken eggs in which transmission spectra were measured between incubation day 0 (non-incubated egg) and 8 and subsequent hatching time was recorded. Several spectral pre-processing procedures, including smoothing, baseline offset correction, multiplicative scatter correction (MSC) and first order derivative, were compared during data analysis. Full spectrum PLS (FS-PLS) and iPLS regression methods were used to developed calibration models using different pre-processed spectra. The results showed that an iPLS model based on MSC pre-processed spectra resulted in superior performance compared to that of the best FS-PLS model. The root mean square error of prediction (RMSEP) was 3.23 hours and 3.49 hours for the iPLS model and FS-PLS model, respectively. The result indicates that the use of visible transmission spectroscopy combined with multivariate analysis has the potential to accurately predict chick hatching time.

show abstract

“…Upon completion of the measurements, the eggs were immediately stored at 15 (±0.5)ºC and 80 (±5)% relative humidity (RH) following standard poultry hatchery practice to prevent embryonic development prior to incubation. For incubation, the eggs were preheated for 16 h (first 6 h at 28ºC and the remaining 10 h at 30ºC) followed by incubation and hatching, as reported by Islam et al (2015). Two eggs were randomly selected, and each sacrificed for microscopic (KEYENCE VHX-500F Digital Microscope, KEYENCE CORPORATION, USA) observation of embryonic development at d 1 and 2.5, respectively.…”

Section: Experimental Designmentioning

confidence: 99%

Nondestructive sex-specific monitoring of early embryonic development rate in white layer chicken eggs using visible light transmission

Rahman

Syduzzaman

Khaliduzzaman

et al. 2020

British Poultry Science

View full text Add to dashboard Cite

1. Sex-specific variations in early embryonic development rates may preempt later variations in embryonic development through to pipping and hatching. Given that erythropoiesis (blood production) can be equated with early embryonic growth rate, it was hypothesised that blood pigment haemoglobin can act as a specific spectral fingerprint for changes in growth rate. Moreover, by measuring longitudinal, rather than lateral, spectral transmission through the egg, a more consistent spectrum with a higher signal-to-noise ratio could be captured. 2. Longitudinal visible transmission (T575/T598 ratio), which is sensitive to haemoglobin, was used to monitor sex-specific early embryonic development rate in white layer chicken eggs from d 0 to 8 of incubation. The sex of these eggs was subsequently confirmed two days after hatching. 3. Embryonic development was detectable from d 3 (72 h) of incubation, 36 h earlier than previously reported lateral spectral measurements, supporting the greater sensitivity of longitudinal measurements. 4. At d 3, the mean T575/T598 ratio for male embryos was significantly lower (P < 0.001) (i.e. higher absorbance of haemoglobin) than for female embryos, which was thought to be due to sexdifferences in early embryogenesis. On the other hand, female embryos had a significantly lower (P < 0.05) mean T575/T598 ratio than male embryos at d 7 of incubation, presumably due to the combined effects of oestrogen synthesis receptors and enzymes on erythropoiesis in female embryos at this time. 5. In conclusion, the proposed methodology has the sensitivity to differentiate sex-specific embryonic development rates during early incubation and the potentiality to advance precision incubation management and poultry research.

show abstract

Prediction of chick hatching time using visible transmission spectroscopy combined with partial least squares regression

Cited by 19 publications

References 17 publications

A Nondestructive Eggshell Thickness Measurement Technique Using Terahertz Waves

A Nondestructive Eggshell Thickness Measurement Technique Using Terahertz Waves

Interval Partial Least Squares (iPLS) Regression Approach to Predict Hatching Time of Chick

Nondestructive sex-specific monitoring of early embryonic development rate in white layer chicken eggs using visible light transmission

Contact Info

Product

Resources

About