Harnessing artificial intelligence for advancements in Rice / wheat functional food Research and Development

Food Research International, Год журнала: 2025, Номер unknown, С. 116306 - 116306

Опубликована: Март 1, 2025

Язык: Английский

---

DenseViT-XGB: A hybrid approach for dates varieties identification

Neurocomputing, Год журнала: 2024, Номер 596, С. 127976 - 127976

Опубликована: Май 31, 2024

Язык: Английский

---

An Effective Feature Extraction Method for Tomato Leafminer - Tuta Absoluta (Meyrick) (Lepidoptera: Gelechiidae) Classification

Brazilian Archives of Biology and Technology, Год журнала: 2025, Номер 68

Опубликована: Янв. 1, 2025

Abstract Global warming caused by climate change causes some problems in agricultural production. One of these is the increase various pest populations. This poses a serious threat to products and significantly negatively affects productivity quality. Insecticides are commonly used combat pests. However, most time, farmers' lack knowledge recognizing pests understanding their effects results incorrect excessive spray applications. While use insecticides harms human health environmental pollution, it also increases production costs, changes genetic structures pests, causing them become more resistant, makes control difficult. Therefore, early detection damage plant extremely important. study aims develop an accurate efficient method detect tomato leaf miner, Tuta absoluta, on leaves. A dataset comprising healthy damaged leaves was created. Using hybrid approach, features were extracted through Convolutional Neural Networks (CNNs) with transfer learning classified using traditional machine techniques. Among methods evaluated, SVM-Linear achieved highest accuracy 97.83%, outperforming other classifiers such as Random Forest 96.14%, Rotation 95.89%, SVM-RBF 90.70%. These highlight potential combining deep learning-based feature extraction conventional for detection. approach offers practical solution reduce misuse improve management strategies, contributing sustainable agriculture.

Язык: Английский

---

Classification of hazelnut varieties based on bigtransfer deep learning model

European Food Research and Technology, Год журнала: 2024, Номер 250(5), С. 1433 - 1442

Опубликована: Фев. 27, 2024

Abstract Hazelnut is an agricultural product that contributes greatly to the economy of countries where it grown. The human factor plays a major role in hazelnut classification. typical approach involves manual inspection each sample by experts, process both labor-intensive and time-consuming, often suffers from limited sensitivity. deep learning techniques are extremely important classification detection products. Deep has great potential sector. This technology can improve quality, increase productivity, offer farmers ability classify detect their produce more effectively. for sustainability efficiency industry. In this paper aims application algorithms streamline classification, reducing need labor, time, cost sorting process. study utilized images three different varieties: Giresun, Ordu, Van, comprising dataset 1165 1324 1138 Van hazelnuts. open-access dataset. study, experiments were carried out on determination varieties with BigTransfer (BiT)-M R50 × 1, BiT-M R101 3 R152 4 models. models, including big transfer was employed task involved 3627 nut resulted remarkable accuracy 99.49% model. These innovative methods also lead patentable products devices various industries, thereby boosting economic value country.

Язык: Английский

---

Ensemble and optimization algorithm in support vector machines for classification of wheat genotypes

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Сен. 30, 2024

Язык: Английский

---

Fusion of machine learning and explainable AI for enhanced rice classification: a case study on Cammeo and Osmancik species

European Food Research and Technology, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 13, 2024

Язык: Английский

---

Hybrid convolutional neural network and multilayer perceptron vision transformer model for wheat species classification task: E-ResMLP+

European Food Research and Technology, Год журнала: 2024, Номер 250(5), С. 1379 - 1388

Опубликована: Фев. 20, 2024

Abstract Wheat plant is one of the most basic food sources for whole world. There are many species wheat that differ according to conditions region where they grown. In this context, can exhibit different characteristics. Issues such as resistance geographical and productivity at forefront in all other plants. The should be correctly distinguished correct agricultural practice. study, a hybrid model based on Vision Transformer (VT) approach Convolutional Neural Network (CNN) was developed classify species. For purpose, ResMLP architecture modified EfficientNetV2b0 fine-tuned improved. A transformer has been by combining these two methods. As result experiments, overall accuracy performance determined 98.33%. potential power proposed method computer-aided analysis systems demonstrated.

Язык: Английский

---

Prediction of air compressor faults with feature fusion and machine learning

Knowledge-Based Systems, Год журнала: 2024, Номер 304, С. 112519 - 112519

Опубликована: Сен. 13, 2024

Язык: Английский

---

Integrated approach to assessing strength in slag-based geopolymer mortars: experimental study and modeling with advanced techniques

Journal of Materials Science, Год журнала: 2024, Номер 59(17), С. 7258 - 7272

Опубликована: Апрель 21, 2024

Abstract The study consists of two main parts. In the initial phase, a variety slag-based geopolymer mortars with different activator concentrations were prepared. These underwent curing in both water and air environments for periods 3, 7, 28, 90 days, after which their compressive strength was evaluated at conclusion each interval. second phase is dedicated to development innovative models estimating based on data gathered. To achieve this, range techniques including multi-gene genetic programming (MGGP), artificial neural networks (ANN), XGBoost, SVM-Gauss, long short-term memory (LSTM), convolutional (CNN) employed formulate model capable accurately. made use various performance evaluation metrics such as mean squared error (MSE), root (RMSE), R-squared, absolute (MAE), scatter index (SI) assess precision MGGP method evaluating under conditions. findings indicate that equations generated by exhibit high level when juxtaposed experimental outcomes. This research endeavors enhance prediction mortars, subject has garnered significant interest scholarly literature.

Язык: Английский

---

A Deep Learning Model-Based Feature Extraction Method for Architectural Space and Color Connection in Interior Design

Scalable Computing Practice and Experience, Год журнала: 2024, Номер 25(4), С. 2948 - 2959

Опубликована: Июнь 16, 2024

In architectural interior design, color is one of the important design elements. Through reasonable combination various elements, it can effectively improve environment and create an atmosphere that meets preferences needs users. And with continuous development social economy, application in becoming more widespread. Using different colors to harmonize not only relieve people’s visual fatigue, but also bring people a pleasant mood. Different have meanings, therefore, use should be flexible matching innovative. The warm cold, near far, expansion contraction make space most dynamic key element design. grasp scale will directly affect quality Color strengthen form or destroy its form. order accurately connection between this paper proposes deep learning model-based feature extraction method for First, we construct product sentiment imagery dataset; then, build model generating layout schemes based on dataset conditional convolutional generation adversarial network, innovatively generate schemes. This algorithm better balance chromaticity, saturation, clarity images. When determining similarity indoor colors, depth features are superior point-to-point pixel distance aesthetic colors. Finally, effectiveness applicability proposed verified relevant experiments.

Язык: Английский

---