CURRENT CHALLENGES, AND FUTURE OPPORTUNITIES FOR FERMENTED TEA LEAF SEGMENTATION, CLASSIFICATION, AND OPTIMIZATION DOI

C.M. Sulaikha,

Aditya Somasundaram

ShodhKosh Journal of Visual and Performing Arts, Год журнала: 2024, Номер 5(1)

Опубликована: Июнь 30, 2024

Fermented tea leaves emerged as a significant agricultural commodity on the global scene. This type of product experiences segmentation, classification, and optimization due to different textures, stages fermentation, environmental influences. The article reviews progresses limitations made by automatic systems in realm image-based analysis fermented leaves, machine learning algorithms, methods. challenges high segmentation accuracy heterogeneous samples, robust classification among diverse varieties, scaling strategies for quality enhancement are some key challenges. Apart from hybrid algorithms designed interpret gap, future areas opportunities that utilize deep multimodal fusion. Highlights hyperspectral imaging approaches AI-driven models providing quick solutions with cost-effectiveness.

Язык: Английский

NMR spectroscopy combined with chemometrics for quality assessment of common vegetable oils: A review DOI
Tao Shi,

Tenghui Dai,

Tao Zhang

и другие.

Trends in Food Science & Technology, Год журнала: 2025, Номер unknown, С. 104889 - 104889

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

1

A novel lightweight model for tea disease classification based on feature reuse and channel focus attention mechanism DOI Creative Commons
Junjie Liang, Renjie Liang, Dongxia Wang

и другие.

Engineering Science and Technology an International Journal, Год журнала: 2025, Номер 61, С. 101940 - 101940

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0

China’s Rural Revitalization Policy: A PRISMA 2020 Systematic Review of Poverty Alleviation, Food Security, and Sustainable Development Initiatives DOI Open Access
Y Wang, R. B. Radin Firdaus, Jiaqing Xu

и другие.

Sustainability, Год журнала: 2025, Номер 17(2), С. 569 - 569

Опубликована: Янв. 13, 2025

This systematic review evaluates China’s Rural Revitalization Policy, focusing on sustainable agriculture, food security, and poverty alleviation initiatives from 2010 to 2024. The study addresses critical gaps in understanding how these combined efforts impact long-term security ecological sustainability impoverished areas, moving beyond the short-term outcomes often emphasized existing literature. Following PRISMA 2020 guidelines, we reviewed 33 peer-reviewed publications Web of Science Scopus databases, employing bibliometric analyses RStudio assess citation patterns, collaboration networks, thematic evolution. Our analysis reveals significant progress across three interconnected domains. First, achieved a 12.3% reduction rural through integrated agricultural modernization targeted support programs. Second, productivity increased by 9.8% technological integration farming practices, strengthening outcomes. Third, environmental improved notably, with 15.7% increase clean water access, demonstrating successful balance between economic growth protection. China emerged as largest contributor (15.2%) research this field, substantial international (42.4% involving cross-border co-authorship). Despite achievements, regional disparities persist, particularly eastern western regions, where interventions are needed. findings highlight need for regionally tailored approaches: regions require focus intensification, fundamental infrastructure development, central would benefit strengthened urban–rural linkages. provides valuable insights policymakers researchers working development while identifying areas requiring further research, assessments climate resilience strategies.

Язык: Английский

Процитировано

0

TBF-YOLOv8n: A Lightweight Tea Bud Detection Model Based on YOLOv8n Improvements DOI Creative Commons
Wen-Hui Fang, Weizhen Chen

Sensors, Год журнала: 2025, Номер 25(2), С. 547 - 547

Опубликована: Янв. 18, 2025

Tea bud localization detection not only ensures tea quality, improves picking efficiency, and advances intelligent harvesting, but also fosters industry upgrades enhances economic benefits. To solve the problem of high computational complexity deep learning models, we developed Bud DSCF-YOLOv8n (TBF-YOLOv8n)lightweight model. Improvement Cross Stage Partial Bottleneck Module with Two Convolutions(C2f) module via efficient Distributed Shift Convolution (DSConv) yields C2f DSConv(DSCf)module, which reduces model’s size. Additionally, coordinate attention (CA) mechanism is incorporated to mitigate interference from irrelevant factors, thereby improving mean accuracy. Furthermore, SIOU_Loss (SCYLLA-IOU_Loss) function Dynamic Sample(DySample)up-sampling operator are implemented accelerate convergence enhance both average precision The experimental results show that compared YOLOv8n model, TBF-YOLOv8n model has a 3.7% increase in accuracy, 1.1% 44.4% reduction gigabit floating point operations (GFLOPs), 13.4% total number parameters included In comparison experiments variety lightweight still performs well terms accuracy while remaining more lightweight. conclusion, achieves commendable balance between efficiency precision, offering valuable insights for advancing harvesting technologies.

Язык: Английский

Процитировано

0

Machine learning-based classification and prediction of typical Chinese green tea taste profiles DOI
Yingbin Zhang, Xuwei Chen, Dingding Chen

и другие.

Food Research International, Год журнала: 2025, Номер unknown, С. 115796 - 115796

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0

Advances of Vis/NIRS and imaging techniques assisted by AI for tea processing DOI
Dengshan Li, Quansheng Chen, Qin Ouyang

и другие.

Critical Reviews in Food Science and Nutrition, Год журнала: 2025, Номер unknown, С. 1 - 19

Опубликована: Март 7, 2025

Tea is one of the most popular drinks due to its distinct flavor and numerous health benefits. The quality tea closely related production processing. Human sensory evaluation conventional method for monitoring in However, this subjective susceptible environmental influences. Therefore, visible/near-infrared spectroscopy (Vis/NIRS) hyperspectral imaging (HSI) techniques offer great potential their rapid detection speed, nondestructive, low cost, simple operations. Artificial intelligence (AI) promising methodological approaches spectral analysis decision-making automated production. Vis/NIRS HSI assisted by AI further promote progress This paper reviewed updated applications processing from 2019 2025. In particular, process, theories techniques, algorithms are briefly introduced. Furthermore, recent summarized discussed. Finally, challenges future trends associated with practical application industry presented.

Язык: Английский

Процитировано

0

Data integrity of food and machine learning: Strategies, advances and prospective DOI
Chenming Li, Jieqing Li,

Yuanzhong Wang

и другие.

Food Chemistry, Год журнала: 2025, Номер unknown, С. 143831 - 143831

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0

LCLN-CA: A Survival Regression Analysis-Based Prediction Method for Catechin Content in Yunnan Sun-Dried Tea DOI Creative Commons

Hongxu Li,

Qiaomei Wang,

Houqiao Wang

и другие.

Horticulturae, Год журнала: 2024, Номер 10(12), С. 1321 - 1321

Опубликована: Дек. 11, 2024

Catechins are pivotal determinants of tea quality, with soil environmental factors playing a crucial role in the synthesis and accumulation these compounds. To investigate impact changes garden environments on catechin content sun-dried tea, this study measured samples corresponding leaves from Nanhua, Yunnan, China. By integrating variations those 17 employing COX regression factor analysis, it was found that pH, organic matter (OM), fluoride, arsenic (As), chromium (Cr) were significantly correlated (p < 0.05). Further, using LASSO for variable selection, model named LCLN-CA constructed four variables including OM, As. The demonstrated high fitting accuracy AUC values 0.674, 0.784, 0.749 intervals CA ≤ 10%, 10% 20%, 20% 30% training set, respectively. validation set showed 0.630, 0.756, 0.723, respectively, indicating well-calibrated curve. Based DynNom framework, visual prediction system Yunnan developed. External test dataset achieved an Accuracy 0.870. This explored relationship between soil-related content, paving new way enhancing practical application value artificial intelligence technology agricultural production.

Язык: Английский

Процитировано

1

CURRENT CHALLENGES, AND FUTURE OPPORTUNITIES FOR FERMENTED TEA LEAF SEGMENTATION, CLASSIFICATION, AND OPTIMIZATION DOI

C.M. Sulaikha,

Aditya Somasundaram

ShodhKosh Journal of Visual and Performing Arts, Год журнала: 2024, Номер 5(1)

Опубликована: Июнь 30, 2024

Fermented tea leaves emerged as a significant agricultural commodity on the global scene. This type of product experiences segmentation, classification, and optimization due to different textures, stages fermentation, environmental influences. The article reviews progresses limitations made by automatic systems in realm image-based analysis fermented leaves, machine learning algorithms, methods. challenges high segmentation accuracy heterogeneous samples, robust classification among diverse varieties, scaling strategies for quality enhancement are some key challenges. Apart from hybrid algorithms designed interpret gap, future areas opportunities that utilize deep multimodal fusion. Highlights hyperspectral imaging approaches AI-driven models providing quick solutions with cost-effectiveness.

Язык: Английский

Процитировано

0