Differentiation of Yeast-Inoculated and Uninoculated Tomatoes Using Fluorescence Spectroscopy Combined with Machine Learning

Ropelewska, Ewa; Slavova, Vanya; Sabancı, Kadir; Aslan, Muhammet Fatih; Masheva, Veselina; Petkova, Mariana

doi:10.3390/agriculture12111887

Cited by 3 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because machine learning uses data to feed an algorithm that can understand the relationship between input and output, it requires little human intervention after deployment [ 31 ]. Machine learning models can provide their own predictions based on the received amount of data input [ 32 ]. Moreover, they can also increase their predictive capacity as they learn more about the information they are processing.…”

Section: Methodsmentioning

confidence: 99%

Beef Quality Classification with Reduced E-Nose Data Features According to Beef Cut Types

Feyzioğlu

Taşpınar

2023

Sensors

View full text Add to dashboard Cite

Ensuring safe food supplies has recently become a serious problem all over the world. Controlling the quality, spoilage, and standing time for products with a short shelf life is a quite difficult problem. However, electronic noses can make all these controls possible. In this study, which aims to develop a different approach to the solution of this problem, electronic nose data obtained from 12 different beef cuts were classified. In the dataset, there are four classes (1: excellent, 2: good, 3: acceptable, and 4: spoiled) indicating beef quality. The classifications were performed separately for each cut and all cut shapes. The ANOVA method was used to determine the active features in the dataset with data for 12 features. The same classification processes were carried out by using the three active features selected by the ANOVA method. Three different machine learning methods, Artificial Neural Network, K Nearest Neighbor, and Logistic Regression, which are frequently used in the literature, were used in classifications. In the experimental studies, a classification accuracy of 100% was obtained as a result of the classification performed with ANN using the data obtained by combining all the tables in the dataset.

show abstract

Section: Methodsmentioning

confidence: 99%

Beef Quality Classification with Reduced E-Nose Data Features According to Beef Cut Types

Feyzioğlu

Taşpınar

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The measurement scheme is shown in fig. 2, and the measurement methodology is the same as Ropelewska et al [24].…”

Section: Fluorescence Spectroscopymentioning

confidence: 99%

Physical parameters of chocolate with the addition of Arthrospira platensis

Gavrailov,

Pehlivanov,

Gentscheva

et al. 2023

Proceedings of 11th International Conference of the Balkan Physical Union — PoS(BPU11)

View full text Add to dashboard Cite

The physicochemical properties of chocolate mass with 85% cocoa content and 3%, 5%, and 10% of Arthrospira platensis have been studied. The algae were grown into a bioreactor in Varvara, Bulgaria. The present work aims to create an innovative chocolate product with appropriate physicochemical properties and organoleptic characteristics, contributing to the healthy nutrition of consumers. To achieve this goal, a technological scheme was developed for obtaining chocolate mass with Arthrospira platensis. Rheological, X-ray structural, and sensory analyses were performed. Data from reflective microscopy and fluorescence spectroscopy were also obtained. X-ray analysis shows peaks of crystalline sucrose and cocoa. In addition to these peaks in the X-ray diffraction pattern of the sample with 10% Arthrospira platensis content, some peaks may be due to complex crystals of the protein structure of freshwater algae. The rheological curves of the samples show that the studied systems are non-Newtonian fluids. Increasing the concentration of Arthrospira platensis does not affect the stickiness, softness, and hardness. According to sensory analysis, the samples with 5% Arthrospira platensis have a pronounced sweet taste, and those with 3% -a cocoa taste. Reflective microscope images were taken to examine the fracture section.

show abstract

“…To investigate the optimized manual threshold of the MLFA block, we reconstructed the low-frequency sample as Equation (2). The size of the original image was 224 × 224, thus when the value of K equaled 112, the sample was reconstructed by a quarter of the feature spectrum.…”

Section: Experiments For Optimized Manual Thresholdsmentioning

confidence: 99%

“…Ropelewska et al [1] extracted the texture parameters to discriminate the cultivars of tomatoes. Several classical machine learning methods, such as HoeffdingTree and BayesNet, were also proved to be effective in classification [2]. The limitation of manual feature extraction methods is the dependence of a reasonable feature-design algorithm.…”

Section: Introductionmentioning

confidence: 99%

MLFAnet: A Tomato Disease Classification Method Focusing on OOD Generalization

Yin

Zhao

et al. 2023

Agriculture

View full text Add to dashboard Cite

Tomato disease classification based on images of leaves has received wide attention recently. As one of the best tomato disease classification methods, the convolutional neural network (CNN) has an immense impact due to its impressive performance. However, better performance is verified by independent identical distribution (IID) samples of tomato disease, which breaks down dramatically on out-of-distribution (OOD) classification tasks. In this paper, we investigated the corruption shifts, which was a vital component of OOD, and proposed a tomato disease classification method to improve the performance of corruption shift generalization. We first adopted discrete cosine transform (DCT) to obtain the low-frequency components. Then, the weight of the feature map was calculated by multiple low-frequency components, in order to reduce the influence of high-frequency variation caused by corrupted perturbation. The proposed method, termed as a multiple low-frequency attention network (MLFAnet), was verified by the benchmarking of ImageNet-C. The accuracy result and generalization performance confirmed the effectiveness of MLFAnet. The satisfactory generalization performance of our proposed classification method provides a reliable tool for the diagnosis of tomato disease.

show abstract

Differentiation of Yeast-Inoculated and Uninoculated Tomatoes Using Fluorescence Spectroscopy Combined with Machine Learning

Cited by 3 publications

References 44 publications

Beef Quality Classification with Reduced E-Nose Data Features According to Beef Cut Types

Beef Quality Classification with Reduced E-Nose Data Features According to Beef Cut Types

Physical parameters of chocolate with the addition of Arthrospira platensis

MLFAnet: A Tomato Disease Classification Method Focusing on OOD Generalization

Contact Info

Product

Resources

About