Combining transfer learning and hyperspectral imaging to identify bruises of pears across different bruise types.

Mechanical bruise is one of the most crucial factors affecting the quality of pears, which has a huge influence on postharvest transportation, storage, and sale of pears. To rapidly detect early bruises of pears across different bruise types, hyperspectral imaging technology coupled with transfer learning methods was performed in this study. Two transfer learning methods, that is, transfer component analysis (TCA) and manifold embedded distribution alignment (MEDA), were applied for two tasks (impact bruise â†’ crush bruise, crush bruise â†’ impact bruise). Supporting vector machine (SVM) was set as a baseline to conduct analysis and comparison of the transferability of the models. The result showed that, for task 1 (impact bruise â†’ crush bruise), MEDA and TCA-SVM model achieved a classification accuracy of 93.33% and 91.11% in target domain, individually. For task 2 (crush bruise â†’impact bruise), MEDA and TCA-SVM model achieved an accuracy of 88.89% and 85.19% in target domain, respectively. Both the two models improved the accuracy compared with SVM models (84.44% for task 1; 77.04% for task 2). Overall, the results indicated that transfer learning approaches could perform pear bruise detection across different bruise types. Hyperspectral imaging in combination with transfer learning methods is a promising possibility for the efficient and cost-saving field detection of fruit bruises among different bruise types. PRACTICAL APPLICATION: The production and export of pears are faced with problems of mechanical damage due to vibration, collision, impact, and other factors, which cause chemical changes in color, odor, and taste. Sometimes the bruise was too slight to be ignored which would infect with other fruits in the future. In this study, we used hyperspectral imaging combined with transfer learning method could detect these slight bruises caused by different factors. Distinguishing different types of damage can provide a reference for quick judgment of the process causing damage and take prompt measures to reduce economic losses.

Classification of early mechanical damage over time in pears based on hyperspectral imaging and transfer learning.

Mechanical damage of fresh fruit caused by compression and collision during harvesting and transportation is an urgent problem in the agricultural industry. The purpose of this work was to detect early mechanical damage of pears using hyperspectral imaging technology and advanced modeling techniques of transfer learning and convolutional neural networks. The visible/near-infrared hyperspectral imaging system was applied to obtain the intact and damaged pears at three time points (2, 12, and 24 h) after compression or collision damage. After the hyperspectral images were preprocessed and feature-extracted, ImageNet was used to pre-train ConvNeXt network, and then, transfer learning strategy was applied from compression damage to collision damage to build the T_ConvNeXt model for classification. The results showed that the test set accuracy of fine-tuned ConvNeXt model was 96.88% for compression damage time. For the classification of collision damage time, the test set accuracy of T_ConvNeXt network reached 96.61% and was 3.64% higher than the fine-tuned ConvNeXt network. The number of training samples was proportionally reduced to verify the superiority of the T_ConvNeXt model, and the model was compared with conventional machine learning algorithms. This study achieved the classification of mechanical damage over time and achieved a generalized model for different damage types. The accurate prediction of pear damage time is crucial for determining proper storage conditions and shelf-life time. PRACTICAL APPLICATION: The T_ConvNeXt model proposed in this paper transferred from compression damage to collision damage effectively promoted the generality of the damage time classification model. Guidelines for choosing an effective shelf life from a commercial aspect were presented.

Respiratory exposure to graphene oxide induces pulmonary fibrosis and organ damages in rats involving caspase-1/p38MAPK/TGF-ß1 signaling pathways.

Numerous studies have shown that graphene oxide (GO) respiratory exposure led to severe lung injury, but whether pulmonary fibrosis caused by GO respiratory exposure is related to the activation of the caspase-1/p38MAPK/TGF-ß1 remains unclear. In this study, rats were administrated GO by intratracheal instillation and fed for three months, and the molecular mechanisms of GO on the pulmonary fibrosis and other organ damage caused by GO respiratory exposure were examined. The results showed that the expression of caspase-1/p38MAPK/TGF-ß1 pathway-related factors were significantly elevated with the increase of exposure concentrations of GO. Those data proved that the caspase-1/p38MAPK/TGF-ß1 signaling pathway was involved in the pulmonary fibrosis caused by GO respiratory exposure. The trends of related factors also proved that the caspase-1/p38MAPK/TGF-ß1 pathway was likely to play a dominant role in the sub-acute and sub-chronic stages. The other organ damage examination found that the liver and spleen were damaged initially by the GO respiratory exposure. Meanwhile for the testicle, although the acute injury was severe, signs of recovery were found during the three-month trial period.

Non-destructive sugar content assessment of multiple cultivars of melons by dielectric properties.

BACKGROUND: Non-destructive determination of the internal quality of fruit with a thick rind and of a large size is always difficult and challenging. To investigate the feasibility of the dielectric spectroscopy technique with respect to determining the sugar content of melons during the postharvest stage, three cultivars of melon samples (160 melons for each cultivar) were used to acquire dielectric spectra over the frequency range 20-4500 MHz. The three cultivars of melons were divided separately into a calibration set and a prediction set in a ratio of 3:1 by a joint x-y distance algorithm. Partial least squares (PLS) and extreme learning machine (ELM) methods were applied to develop individual-cultivar and multi-cultivar models based on full frequencies (FFs) and effective dielectric frequencies (EDFs) selected by the successive projection algorithm (SPA). RESULTS: The results showed that ELM models demonstrated a better performance than PLS models for the same input dielectric variables. Most of the models built based on the EDFs selected by SPA had a slightly worse performance compared to those based on FFs. For both PLS and ELM methods, the models for multi-cultivars demonstrated a worse calibration and prediction performance compared to those for individual cultivars. When individual-cultivar and multi-cultivar samples were used to build sugar content determination models, the best model was FFs-ELM (Rp  = 0.887, RMSEP = 0.986), FFs-ELM (Rp  = 0.870, RMSEP = 1.028), FFs-PLS (Rp  = 0.882, RMSEP = 1.010) and FFs-ELM (Rp  = 0.849, RMSEP = 1.085) for 'Hongyanliang', 'Xinzaomi', 'Manao' and multi-cultivar melons, respectively. CONCLUSION: The present study indicates that it is possible to develop both individual-cultivar and multi-cultivar models for determining the sugar content of melons based on the dielectric spectroscopy technique. © 2021 Society of Chemical Industry.

Effect of CPPU on bulk optical properties of kiwifruit during storage in near-infrared range.

BACKGROUND: Investigating the effect of N-(2-chloro-4-pyridyl)-N'-phenylurea (CPPU) on the bulk optical properties of postharvest kiwifruit is helpful in understanding the mechanism of identification of CPPU-treated kiwifruit using spectroscopy and to develop effective optical sensing techniques. In this study, the absorption coefficient µa and reduced scattering coefficient µ s ' of flesh and skin of kiwifruit treated with CPPU solutions at CPPU concentration levels (CCLs) of 0, 5, 10 and 15 mg L-1 were measured by using a single integrating sphere setup over the range 950-1650 nm during 12 weeks' storage. RESULTS: Generally, at the same storage period, there was no significant difference (P ≤ 0.05) on flesh's µa among the kiwifruit treated with different CCLs at absorption peaks of 970, 1190, and 1390 nm. The average flesh's µ s ' of kiwifruit treated with higher CCLs at 1190 nm were larger than those treated with lower CCLs, and there was a significant difference (P ≤ 0.05) between the kiwifruit treated with 0, 5 and 15 mg L-1 CPPU solutions except for week 6. Contrasted with the µa and µ s ' of kiwifruit flesh, the µa and µ s ' of skin had bigger standard deviations and larger fluctuations with storage time. Additionally, the CPPU-treated kiwifruit had higher moisture content, lower firmness, and larger cells than CPPU-untreated kiwifruit. CONCLUSIONS: This study indicates that the µ s ' of flesh has potential in identifying kiwifruit treated with different CCLs during storage. © 2020 Society of Chemical Industry.

Polymorphisms in gene MMP-2 modify the association of cadmium exposure with hypertension risk.

BACKGROUND: Cadmium exposure has been inconsistently related with hypertension. However, epidemiologic data on the genetic susceptibility to the hypertensive effect of cadmium exposure are limited. OBJECTIVES: We investigated whether the associations between cadmium exposure and hypertension risk differed by genetic polymorphisms in MMPs genes. METHODS: The present study of 497 hypertension cases and 497 healthy controls was conducted in a Chinese population. Urinary cadmium levels were measured with inductively coupled plasma-mass spectrometer (ICP-MS). Multivariable logistic regression models were analyzed after controlling major confounders. RESULTS: Within the multivariable logistic regression models, compared with the lowest tertile, the highest tertile of urinary cadmium had a 1.33-fold (95% CI: 1.01, 1.93) increased risk of hypertension. Carriers of rs243865 T allele and rs243866 A allele in MMP-2 were suggested to have increased risks of hypertension. The associations of urinary cadmium with hypertension risk were modified by rs14070 (P-value for interaction = 0.022) and rs7201 (P-value for interaction = 0.009) in gene MMP-2. Positively significant trends for increasing odds of hypertension with cadmium levels were observed among the wild types of rs14070 and rs7201, respectively. CONCLUSIONS: Increasing urinary cadmium concentrations were positively associated with hypertension risk in a Chinese population, and the associations were modified by polymorphism of rs14070 and rs7201 in gene MMP-2.

Association of co-exposure to heavy metals with renal function in a hypertensive population.

BACKGROUND: Chronic kidney disease (CKD) is an increasing health problem worldwide. Recent studies have suggested the potential associations between exposure to metals and CKD events, particularly in participants with hypertension. However, relevant studies are limited. OBJECTIVES: We aimed to explore the associations of metal exposure with renal function in participants with essential hypertension. METHODS: Nine hundred and thirty-four participants with essential hypertension were recruited at the Department of Cardiology, Union Hospital, Wuhan, China. We measured the levels of chromium, cadmium, thallium and uranium in urine and calculated the estimated glomerular filtration rate (eGFR) for renal function. Multivariable linear regression models adjusted for potential confounders were applied. RESULTS: After adjusting for potential confounders and other metals, doubling of urinary chromium or uranium levels decreased eGFR by 2.90 (95% confidence interval, 2.04 to 3.76) and 1.87 (0.58 to 3.15) mL/min per 1.73m2, respectively. Co-exposure to chromium and uranium was found to greatly decrease eGFR, particularly in women. Compared with those in the low exposure group, women with high exposure to chromium and uranium had a 11.36 (3.66 to 19.07) mL/min per 1.73m2 adjusted decline in eGFR. Higher urinary thallium levels were positively related to elevated eGFR in men. The adjusted increase in eGFR with doubling of thallium levels was 3.12 (1.14 to 5.10) mL/min per 1.73m2. Sex-difference in the associations of exposure to heavy metals with eGFR was also suggested. CONCLUSIONS: Our findings suggest that environmental exposure to chromium and uranium might contribute to a decline in eGFR in individuals with hypertension. The associations of exposure to heavy metals with eGFR might be sex-different. Further studies are warranted to confirm our findings and clarify the underlying mechanisms.

Environmental exposure to metals and the risk of hypertension: A cross-sectional study in China.

Metal pollution is a severe environmental issue in China, which has been recently linked with the risk of hypertension. However, relevant epidemiological studies are limited. The present exploratory study was conducted to assess the associations of environmental exposure to metals with the odds of hypertension as well as blood pressure (BP) levels using urine samples in a Chinese general population. From May 2016 to April 2017, a total of 823 eligible participants were consecutively enrolled in our study in Wuhan, China. Hypertension was defined as systolic BP (SBP) of ≥140 mmHg or diastolic BP (DBP) of ≥90 mmHg, a self-reported physician diagnosis, or current use of antihypertensive medication. We used urine samples as biomarkers to reflect the levels of environmental exposure to 20 metals. Multivariable regression models were applied to assess the potential association. Multi-metal models were conducted to investigate the impacts of co-exposure to various metals. Based on the results from various models, positive trends for increased odds of hypertension with increasing quartiles of vanadium (V), iron (Fe), zinc (Zn) and selenium (Se) were suggested. Compared with those in the lowest quartiles, participants in the highest quartiles of V, Fe, Zn and Se had a 4.4-fold, 4.9-fold, 4.2-fold and 2.5-fold increased odds of having hypertension, respectively. High urinary Hg level was found to increase the levels of DBP. Individuals in the highest group of Hg were found to have a 4.3 mmHg higher level of DBP. Our findings suggest that environmental exposure to V, Fe, Zn, Se and Hg might increase the risk of hypertension or elevate the levels of BP. These findings warrant further prospective studies in a larger population.

Associations of environmental exposure to metals with the risk of hypertension in China.

Hypertension contributes largely to the global burden of disease and mortality. Environmental exposure to metals might be a causative factor for hypertension, but the association remains unclear. The present case-control study of 502 hypertension patients and 502 healthy participants aimed to evaluate the potential relationships between the concentrations of 20 metal in urine and the risk of hypertension in a Chinese population. Multivariate logistic analyses adjusted for potential confounders were performed separately considering the effects of single and multi-metal. We found the increasing trends of urinary Fe, Co, Ni, Cu, Zn and Sr quartiles and the decreasing trends of urinary V and Rb quartiles with the ORs for hypertension. These dose-response associations were confirmed in the RCS models and remained robust in the multi-metal model. Urinary Hg quartiles were positively associated with the risk of hypertension in the models of single-metal and multi-metal. Urinary Cd quartiles were inversely associated with the risk of hypertension in the multi-metal model. Besides, modification effects of gender, BMI and smoking status on the associations of the exposure to various metals with the risk of hypertension were also suggested in the subgroup analysis. Our findings suggest that environmental exposure to V, Fe, Co, Ni, Cu, Zn, Rb, Sr, Cd and Hg might be related with the prevalence of hypertension. Further studies with prospective design should be conducted to confirm these findings.