Artificial Intelligence in Agriculture, Год журнала: 2024, Номер 12, С. 72 - 84
Опубликована: Апрель 30, 2024
The issue of food security continues to be a prominent global concern, affecting significant number individuals who experience the adverse effects hunger and malnutrition. finding solution this intricate necessitates implementation novel paradigm-shifting methodologies in agriculture sector. In recent times, domain artificial intelligence (AI) has emerged as potent tool capable instigating profound influence on sectors. AI technologies provide advantages by optimizing crop cultivation practices, enabling use predictive modelling precision techniques, aiding efficient monitoring disease identification. Additionally, potential optimize supply chain operations, storage management, transportation systems, quality assurance processes. It also tackles problem loss waste through post-harvest reduction, analytics, smart inventory management. This study highlights that how utilizing power AI, we could transform way produce, distribute, manage food, ultimately creating more secure sustainable future for all.
Язык: Английский
Процитировано
42Streamlit-based enhancing crop recommendation systems with advanced explainable artificial intelligence for smart farming
Neural Computing and Applications, Год журнала: 2024, Номер 36(32), С. 20011 - 20025
Опубликована: Авг. 10, 2024
Язык: Английский
Процитировано
15Interpretability Research of Deep Learning: A Literature Survey
Information Fusion, Год журнала: 2024, Номер 115, С. 102721 - 102721
Опубликована: Окт. 9, 2024
Язык: Английский
Процитировано
13A Decision Support System for Crop Recommendation Using Machine Learning Classification Algorithms
Agriculture, Год журнала: 2024, Номер 14(8), С. 1256 - 1256
Опубликована: Июль 30, 2024
Today, crop suggestions and necessary guidance have become a regular need for farmer. Farmers generally depend on their local agriculture officers regarding this, it may be difficult to obtain the right at time. Nowadays, datasets are available different websites in sector, they play crucial role suggesting suitable crops. So, decision support system that analyzes dataset using machine learning techniques can assist farmers making better choices selections. The main objective of this research is provide quick with more accurate effective recommendations by utilizing methods, global positioning coordinates, cloud data. Here, recommendation personalized, which enables predict crops specific geographical context, taking into account factors like climate, soil composition, water availability, conditions. In regard, an existing historical contains state, district, year, area-wise production rate, name, season was collected 246,091 sample records from Dataworld website, holds data 37 areas India. Also, analysis, offices Rayagada, Koraput, Gajapati districts Odisha Both these were combined stored Firebase service. Thirteen algorithms been applied identify dependencies within To facilitate process, Android application developed Studio (Electric Eel | 2023.1.1) Emulator (Version 32.1.14), Software Development Kit (SDK, SDK 33), Tools. A model has proposed implements SMOTE (Synthetic Minority Oversampling Technique) balance dataset, then allows implementation 13 classifiers, such as logistic regression, tree (DT), K-Nearest Neighbor (KNN), SVC (Support Vector Classifier), random forest (RF), Gradient Boost (GB), Bagged Tree, extreme gradient boosting (XGB classifier), Ada Classifier, Cat Boost, HGB (Histogram-based Boosting), SGDC (Stochastic Descent), MNB (Multinomial Naive Bayes) dataset. It observed performance method 1.00 accuracy, precision, recall, F1-score, ROC AUC (Receiver Operating Characteristics–Area Under Curve) 0.91 sensitivity 0.54 specificity after applying SMOTE. Overall, compared all other classifiers implemented predictions.
Язык: Английский
Процитировано
10Challenges in Achieving Artificial Intelligence in Agriculture
Опубликована: Янв. 1, 2024
Язык: Английский
Процитировано
9Customization of health insurance premiums using machine learning and explainable AI
International Journal of Information Management Data Insights, Год журнала: 2025, Номер 5(1), С. 100328 - 100328
Опубликована: Фев. 7, 2025
Язык: Английский
Процитировано
1DeepLeaf: an optimized deep learning approach for automated recognition of grapevine leaf diseases
Neural Computing and Applications, Год журнала: 2025, Номер unknown
Опубликована: Фев. 28, 2025
Язык: Английский
Процитировано
1Artificial Intelligence Tools for the Agriculture Value Chain: Status and Prospects
Electronics, Год журнала: 2024, Номер 13(22), С. 4362 - 4362
Опубликована: Ноя. 7, 2024
This article explores the transformative potential of artificial intelligence (AI) tools across agricultural value chain, highlighting their applications, benefits, challenges, and future prospects. With global food demand projected to increase by 70% 2050, AI technologies—including machine learning, big data analytics, Internet things (IoT)—offer critical solutions for enhancing productivity, sustainability, resource efficiency. The study provides a comprehensive review applications at multiple stages including land use planning, crop selection, management, disease detection, yield prediction, market integration. It also discusses significant challenges adoption, such as accessibility, technological infrastructure, need specialized skills. By examining case studies empirical evidence, demonstrates how AI-driven can optimize decision-making operational efficiency in agriculture. findings underscore AI’s pivotal role addressing with implications farmers, agribusinesses, policymakers, researchers. aims advance evolving research discussions on sustainable agriculture, contributing insights that promote adoption technologies influence farming.
Язык: Английский
Процитировано
5YOLOv7-Based Intelligent Weed Detection and Laser Weeding System Research: Targeting Veronica didyma in Winter Rapeseed Fields
Agriculture, Год журнала: 2024, Номер 14(6), С. 910 - 910
Опубликована: Июнь 8, 2024
In recent years, rapeseed oil has received considerable attention in the agricultural sector, experiencing appreciable growth. However, weed-related challenges are hindering expansion of production. This paper outlines development an intelligent weed detection and laser weeding system—a non-chemical precision protection method Veronica didyma winter fields Yangtze River Basin. A total 234 images were obtained to compile a database for deep-learning model, YOLOv7 was used as model training. The effectiveness demonstrated, with final accuracy 94.94%, recall 95.65%, [email protected] 0.972 obtained. Subsequently, parallel-axis binocular cameras selected image acquisition platform, calibration semi-global block matching locate within cultivation box, yielding minimum confidence camera height values 70% 30 cm, respectively. system then built, experimental results indicated that practicable 100 W power 80 mm/s scanning speed, resulting visibly lost activity no resprouting 15 days weeding. successful execution provides new reference holds promise its practical application settings.
Язык: Английский
Процитировано
4A Multi‐Objective Decision‐Making Neural Network: Effective Structure and Learning Method
Concurrency and Computation Practice and Experience, Год журнала: 2025, Номер 37(4-5)
Опубликована: Фев. 19, 2025
ABSTRACT Decision Neural Networks significantly improve the performance of complex models and create more transparent accountable decision‐making systems that can be trusted in critical applications. However, their strongly depends on amount data learning algorithm. This article describes development a simplified structure training algorithm based Levenberg–Marquardt to enhance decision neural network's assess utility function's efficacy multi‐objective issues. The suggested converges faster than traditional algorithms. Also, designed scheme combines gradient descent with Gauss‐Newton method, allowing it escape shallow local minima effectively other similar techniques. Numerical examples demonstrate how well method estimates linear functions, even complicated nonlinear ones. Additionally, findings applying enhanced network issues show this instructional technique produces responses higher quality convergence. By problem seven primary answers, is shown accuracy improved by 20%.
Язык: Английский
Процитировано
0