Integrating deep learning with non-destructive thermal imaging for precision guava ripeness determination.

BACKGROUND: To mitigate post-harvest losses and inform harvesting decisions at the same time as ensuring fruit quality, precise ripeness determination is essential. The complexity arises in assessing guava ripeness as a result of subtle alterations in some varieties during the ripening process, making visual assessment less reliable. The present study proposes a non-destructive method employing thermal imaging for guava ripeness assessment, involving obtaining thermal images of guava samples at different ripeness stages, followed by data pre-processing. Five deep learning models (AlexNet, Inception-v3, GoogLeNet, ResNet-50 and VGGNet-16) were applied, and their performances were systematically evaluated and compared. RESULTS: VGGNet-16 demonstrated outstanding performance, achieving average precision of 0.92, average sensitivity of 0.93, average specificity of 0.96, average F1-score of 0.92 and accuracy of 0.92 within a training duration of 484 s. CONCLUSION: The present study presents a scalable and non-destructive approach for guava ripeness determination, contributing to waste reduction and enhancing efficiency in supply chains and fruit production. These initiatives align with environmentally friendly practices in agriculture. © 2024 Society of Chemical Industry.

Fast Recognition and Counting Method of Dragon Fruit Flowers and Fruits Based on Video Stream.

Dragon fruit (Hylocereus undatus) is a tropical and subtropical fruit that undergoes multiple ripening cycles throughout the year. Accurate monitoring of the flower and fruit quantities at various stages is crucial for growers to estimate yields, plan orders, and implement effective management strategies. However, traditional manual counting methods are labor-intensive and inefficient. Deep learning techniques have proven effective for object recognition tasks but limited research has been conducted on dragon fruit due to its unique stem morphology and the coexistence of flowers and fruits. Additionally, the challenge lies in developing a lightweight recognition and tracking model that can be seamlessly integrated into mobile platforms, enabling on-site quantity counting. In this study, a video stream inspection method was proposed to classify and count dragon fruit flowers, immature fruits (green fruits), and mature fruits (red fruits) in a dragon fruit plantation. The approach involves three key steps: (1) utilizing the YOLOv5 network for the identification of different dragon fruit categories, (2) employing the improved ByteTrack object tracking algorithm to assign unique IDs to each target and track their movement, and (3) defining a region of interest area for precise classification and counting of dragon fruit across categories. Experimental results demonstrate recognition accuracies of 94.1%, 94.8%, and 96.1% for dragon fruit flowers, green fruits, and red fruits, respectively, with an overall average recognition accuracy of 95.0%. Furthermore, the counting accuracy for each category is measured at 97.68%, 93.97%, and 91.89%, respectively. The proposed method achieves a counting speed of 56 frames per second on a 1080ti GPU. The findings establish the efficacy and practicality of this method for accurate counting of dragon fruit or other fruit varieties.

Evaluation of convolutional neural network for non-destructive detection of imidacloprid and acetamiprid residues in chili pepper (Capsicum frutescens L.) based on visible near-infrared spectroscopy.

Consumption of agricultural products with pesticide residue is risky and can negatively affect health. This study proposed a nondestructive method of detecting pesticide residues in chili pepper based on the combination of visible and near-infrared (VIS/NIR) spectroscopy (400-2498 nm) and deep learning modeling. The obtained spectra of chili peppers with two types of pesticide residues (acetamiprid and imidacloprid) were analyzed using a one-dimensional convolutional neural network (1D-CNN). Compared with the commonly used partial least squares regression model, the 1D-CNN approach yielded higher prediction accuracy, with a root mean square error of calibration of 0.23 and 0.28 mg/kg and a root mean square error of prediction of 0.55 and 0.49 mg/kg for the acetamiprid and imidacloprid data sets, respectively. Overall, the results indicate that the combination of the 1D-CNN model and VIS/NIR spectroscopy is a promising nondestructive method of identifying pesticide residues in chili pepper.

Characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm.

Wavelength selection is crucial to the success of near-infrared (NIR) spectroscopy analysis as it considerably improves the generalization of the multivariate model and reduces model complexity. This study proposes a new wavelength selection method, interval flower pollination algorithm (iFPA), for spectral variable selection in the partial least squares regression (PLSR) model. The proposed iFPA consists of three phases. First, the flower pollination algorithm is applied to search for informative spectral variables, followed by variable elimination. Subsequently, the iFPA performs a local search to determine the best continuous interval spectral variables. The interpretability of the selected variables is assessed on three public NIR datasets (corn, diesel and soil datasets). Performance comparison with other competing wavelength selection methods shows that the iFPA used in conjunction with the PLSR model gives better prediction performance, with the root mean square error of prediction values of 0.0096-0.0727, 0.0015-3.9717 and 1.3388-29.1144 are obtained for various responses in corn, diesel and soil datasets, respectively.

New approach for sugarcane disease recognition through visible and near-infrared spectroscopy and a modified wavelength selection method using machine learning models.

The proliferation of pathogenic fungi in sugarcane crops poses a significant threat to agricultural productivity and economic sustainability. Early identification and management of sugarcane diseases are therefore crucial to mitigate the adverse impacts of these pathogens. In this study, visible and near-infrared spectroscopy (380-1400 nm) combined with a novel wavelength selection method, referred to as modified flower pollination algorithm (MFPA), was utilized for sugarcane disease recognition. The selected wavelengths were incorporated into machine learning models, including Naïve Bayes, random forest, and support vector machine (SVM). The developed simplified SVM model, which utilized the MFPA wavelength selection method yielded the best performances, achieving a precision value of 0.9753, a sensitivity value of 0.9259, a specificity value of 0.9524, and an accuracy of 0.9487. These results outperformed those obtained by other wavelength selection approaches, including the selectivity ratio, variable importance in projection, and the baseline method of the flower pollination algorithm.

A non-destructive methodology for determination of cantaloupe sugar content using machine vision and deep learning.

BACKGROUND: To determine the maturity of cantaloupe, measuring the soluble solid content (SSC) as the indicator of sugar content based on the refractometric index is commonly practised. This method, however, is destructive and limited to a small number of samples. In this study, the coupling of a convolutional neural network (CNN) with machine vision was proposed in detecting the SSC of cantaloupe. The cantaloupe images were first acquired under controlled and uncontrolled conditions and subsequently fed to the CNN to predict the class to which each cantaloupe belonged. Four hand-crafted classical machine-learning classifiers were used to compare against the performance of the CNN. RESULTS: Experimental results showed that the CNN method significantly outperformed others, with an improvement of >100% being achieved in terms of classification accuracy, considering the data acquired under the uncontrolled environment. CONCLUSION: The results demonstrated the potential benefit to operationalize CNNs in practice for SSC determination of cantaloupe before harvesting. © 2022 Society of Chemical Industry.

Prediction of tea theanine content using near-infrared spectroscopy and flower pollination algorithm.

In this study, near-infrared (NIR) spectroscopy was exploited for non-destructive determination of theanine content of oolong tea. The NIR spectral data (400-2500 nm) were correlated with the theanine level of 161 tea samples using partial least squares regression (PLSR) with different wavelengths selection methods, including the regression coefficient-based selection, uninformative variable elimination, variable importance in projection, selectivity ratio and flower pollination algorithm (FPA). The potential of using the FPA to select the discriminative wavelengths for PLSR was examined for the first time. The analysis showed that the PLSR with FPA method achieved better predictive results than the PLSR with full spectrum (PLSR-full). The developed simplified model using on FPA based on 12 latent variables and 89 selected wavelengths produced R-squared (R2) value and root mean squared error (RMSE) of 0.9542, 0.8794 and 0.2045, 0.3219 for calibration and prediction, respectively. For PLSR-full, the R2 values of 0.9068, 0.8412 and RMSEs of 0.2916, 0.3693, were achieved for calibration and prediction. Also, the optimized model using FPA outperformed other wavelengths selection methods considered in this study. The obtained results indicated the feasibility of FPA to improve the predictability of the PLSR and reduce the model complexity. The nonlinear regression models of support vector machine regression and Gaussian process regression (GPR) were further utilized to evaluate the superiority of using the FPA in the wavelength selection. The results demonstrated that utilizing the wavelength selection method of FPA and nonlinear regression model of GPR could improve the predictive performance.

Loss of tumor suppressor KDM6A amplifies PRC2-regulated transcriptional repression in bladder cancer and can be targeted through inhibition of EZH2.

Trithorax-like group complex containing KDM6A acts antagonistically to Polycomb-repressive complex 2 (PRC2) containing EZH2 in maintaining the dynamics of the repression and activation of gene expression through H3K27 methylation. In urothelial bladder carcinoma, KDM6A (a H3K27 demethylase) is frequently mutated, but its functional consequences and therapeutic targetability remain unknown. About 70% of KDM6A mutations resulted in a total loss of expression and a consequent loss of demethylase function in this cancer type. Further transcriptome analysis found multiple deregulated pathways, especially PRC2/EZH2, in KDM6A-mutated urothelial bladder carcinoma. Chromatin immunoprecipitation sequencing analysis revealed enrichment of H3K27me3 at specific loci in KDM6A-null cells, including PRC2/EZH2 and their downstream targets. Consequently, we targeted EZH2 (an H3K27 methylase) and demonstrated that KDM6A-null urothelial bladder carcinoma cell lines were sensitive to EZH2 inhibition. Loss- and gain-of-function assays confirmed that cells with loss of KDM6A are vulnerable to EZH2. IGFBP3, a direct KDM6A/EZH2/H3K27me3 target, was up-regulated by EZH2 inhibition and contributed to the observed EZH2-dependent growth suppression in KDM6A-null cell lines. EZH2 inhibition delayed tumor onset in KDM6A-null cells and caused regression of KDM6A-null bladder tumors in both patient-derived and cell line xenograft models. In summary, our study demonstrates that inactivating mutations of KDM6A, which are common in urothelial bladder carcinoma, are potentially targetable by inhibiting EZH2.

Excessive fatty acid oxidation induces muscle atrophy in cancer cachexia.

Cachexia is a devastating muscle-wasting syndrome that occurs in patients who have chronic diseases. It is most commonly observed in individuals with advanced cancer, presenting in 80% of these patients, and it is one of the primary causes of morbidity and mortality associated with cancer. Additionally, although many people with cachexia show hypermetabolism, the causative role of metabolism in muscle atrophy has been unclear. To understand the molecular basis of cachexia-associated muscle atrophy, it is necessary to develop accurate models of the condition. By using transcriptomics and cytokine profiling of human muscle stem cell-based models and human cancer-induced cachexia models in mice, we found that cachectic cancer cells secreted many inflammatory factors that rapidly led to high levels of fatty acid metabolism and to the activation of a p38 stress-response signature in skeletal muscles, before manifestation of cachectic muscle atrophy occurred. Metabolomics profiling revealed that factors secreted by cachectic cancer cells rapidly induce excessive fatty acid oxidation in human myotubes, which leads to oxidative stress, p38 activation and impaired muscle growth. Pharmacological blockade of fatty acid oxidation not only rescued human myotubes, but also improved muscle mass and body weight in cancer cachexia models in vivo. Therefore, fatty acid-induced oxidative stress could be targeted to prevent cancer-induced cachexia.

Fumarate Hydratase-deficient Cell Line NCCFH1 as a New In Vitro Model of Hereditary Papillary Renal Cell Carcinoma Type 2.

BACKGROUND/AIM: Hereditary leiomyomatosis and renal cell carcinoma (HLRCC) is a rare autosomal dominant disorder characterized by fumarate hydratase (FH) gene mutation. It is associated with the development of very aggressive kidney tumors, characterized by early onset and high metastatic potential, and has no effective therapy. The aim of the study was to establish a new preclinical platform for investigating morphogenetic and metabolic features, and alternative therapy of metastatic hereditary papillary renal cell carcinoma type 2 (PRCC2). MATERIALS AND METHODS: Fresh cells were collected from pleural fluid of a patient with metastatic hereditary PRCC2. Morphogenetic and functional characteristics were evaluated via microscopy, FH gene sequencing analysis, real-time polymerase chaine reaction and enzymatic activity measurement. We performed bioenergetic analysis, gene-expression profiling, and cell viability assay with 19 anti-neoplastic drugs. RESULTS: We established a new in vitro model of hereditary PRCC2 - the NCCFH1 cell line. The cell line possesses a c.1162 delA - p.Thr375fs frameshift mutation in the FH gene. Our findings indicate severe attenuation of oxidative phosphorylation and glucose-dependent growth of NCCFH1 cells that is consistent with the Warburg effect. Furthermore, gene-expression profiling identified that the most prominent molecular features reflected a high level of apoptosis, cell adhesion, and cell signaling. Drug screening revealed a marked sensitivity of FH(-/-) cells to mitoxantrone, epirubicin, topotecan and a high sensitivity to bortezomib. CONCLUSION: We demonstrated that the NCCFH1 cell line is a very interesting preclinical model for studying the metabolic features and testing new therapies for hereditary PRCC2, while bortezomib may be a potential efficient therapeutic option.

Adaptive cuckoo search algorithm for unconstrained optimization.

Modification of the intensification and diversification approaches in the recently developed cuckoo search algorithm (CSA) is performed. The alteration involves the implementation of adaptive step size adjustment strategy, and thus enabling faster convergence to the global optimal solutions. The feasibility of the proposed algorithm is validated against benchmark optimization functions, where the obtained results demonstrate a marked improvement over the standard CSA, in all the cases.

Exome sequencing of liver fluke-associated cholangiocarcinoma.

Opisthorchis viverrini-related cholangiocarcinoma (CCA), a fatal bile duct cancer, is a major public health concern in areas endemic for this parasite. We report here whole-exome sequencing of eight O. viverrini-related tumors and matched normal tissue. We identified and validated 206 somatic mutations in 187 genes using Sanger sequencing and selected 15 genes for mutation prevalence screening in an additional 46 individuals with CCA (cases). In addition to the known cancer-related genes TP53 (mutated in 44.4% of cases), KRAS (16.7%) and SMAD4 (16.7%), we identified somatic mutations in 10 newly implicated genes in 14.8-3.7% of cases. These included inactivating mutations in MLL3 (in 14.8% of cases), ROBO2 (9.3%), RNF43 (9.3%) and PEG3 (5.6%), and activating mutations in the GNAS oncogene (9.3%). These genes have functions that can be broadly grouped into three biological classes: (i) deactivation of histone modifiers, (ii) activation of G protein signaling and (iii) loss of genome stability. This study provides insight into the mutational landscape contributing to O. viverrini-related CCA.