Multi-item Prediction Using LSTM with Single Data for Plant Growth DOI Open Access

Masahiro Ogawa,

Takeshi Kumaki

Journal of Signal Processing, Journal Year: 2024, Volume and Issue: 28(6), P. 293 - 299

Published: Oct. 31, 2024

In recent years, food problems have arisen due to population changes. To solve this problem, Advanced technologies such as robots and artificial intelligence are increasingly being used improve the efficiency of agriculture. particular, plant factories attracting attention because they a high affinity for advanced can be produced regardless cultivation location climate. However, production in exhibits higher management costs lower profitability than traditional methods. It is thought that problem solved by predicting growth notifying farm manager. research, we will use data measured at create machine learning model which predicts, both size weight an agricultural product from single piece data. As result, were able predict multiple items using relatively lightweight model. The overall error was small, with average rate about 15%. Although 30%, behaves close actual values.

Language: Английский

Algorithms for Plant Monitoring Applications: A Comprehensive Review DOI Creative Commons
Giovanni Paolo Colucci, Paola Battilani, Marco Camardo Leggieri

et al.

Algorithms, Journal Year: 2025, Volume and Issue: 18(2), P. 84 - 84

Published: Feb. 5, 2025

Many sciences exploit algorithms in a large variety of applications. In agronomy, amounts agricultural data are handled by adopting procedures for optimization, clustering, or automatic learning. this particular field, the number scientific papers has significantly increased recent years, triggered scientists using artificial intelligence, comprising deep learning and machine methods bots, to process crop, plant, leaf images. Moreover, many other examples can be found, with different applied plant diseases phenology. This paper reviews publications which have appeared past three analyzing used classifying agronomic aims crops applied. Starting from broad selection 6060 papers, we subsequently refined search, reducing 358 research articles 30 comprehensive reviews. By summarizing advantages applying analyses, propose guide farming practitioners, agronomists, researchers, policymakers regarding best practices, challenges, visions counteract effects climate change, promoting transition towards more sustainable, productive, cost-effective encouraging introduction smart technologies.

Language: Английский

Citations

0
Wearable Plant Sensing Devices for Health Monitoring DOI Creative Commons

Shihao Wu,

Yiheng Li,

Qiannian Wang

et al.

Wearable electronics., Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0
Biocompatible, biodegradable, and high-performance flexible pressure sensors for severity grading and rehabilitation assessment in Parkinson's disease management DOI

X. L. Zheng,

Yuanlong Li, Qihui Zhou

et al.

Nano Energy, Journal Year: 2025, Volume and Issue: unknown, P. 111030 - 111030

Published: April 1, 2025

Language: Английский

Citations

0
Unlocking the Secrets: Structure-Function Dynamics of Plant Proteins DOI
Tanweer Haider, Wasim Akram, Ramakant Joshi

et al.

Colloids and Surfaces B Biointerfaces, Journal Year: 2025, Volume and Issue: 254, P. 114791 - 114791

Published: May 15, 2025

Language: Английский

Citations

0
PSDNet: Plant Status Detection Network Utilized in an Intelligent Bougainvillea Glabra Sensing and Watering System DOI
Kai Cui, Yuling Huang, Xuanfeng Li

et al.

IEEE Sensors Journal, Journal Year: 2024, Volume and Issue: 24(11), P. 18685 - 18698

Published: April 24, 2024

Bougainvillea glabra, commonly planted landscape flowers in Macau, requires the precise water management during whole growing process. Conventional timed irrigation systems, however, fail to offer required level of precision. Sensor-based watering systems have been employed, utilizing soil moisture and temperature sensors monitor plant conditions. Nonetheless, these are proved be unreliable due various factors, such as presence stones. Thus, plants still require botanical experts judge status based on photos. To address this challenge provide a dependable evaluation plant's status, study proposes novel approach: Plant Status Detection Net (PSDNet) for sensing, which uses computer vision technology replace decision-making. Different from directly using image classification, paper combines object detection extract leaves, then makes decisions leaves. By Regions Interest (RoI) structure pre-trained module called Leaf with CNN Features (Leaf-RCNN), proposed PSDNet effectively extracts leaf regions their corresponding feature maps captured images. further improve accuracy, specialized decoupling head position embedding integrated into network enable extraction relative information between Finally, pilot project at Macau Keang Peng Middle School (MKPMS), an automated system was implemented PSDNet, leading substantial increase flowering rate. The anticipated adoption is projected significantly advance landscaping practices beyond.

Language: Английский

Citations

0
Multi-item Prediction Using LSTM with Single Data for Plant Growth DOI Open Access

Masahiro Ogawa,

Takeshi Kumaki

Journal of Signal Processing, Journal Year: 2024, Volume and Issue: 28(6), P. 293 - 299

Published: Oct. 31, 2024

In recent years, food problems have arisen due to population changes. To solve this problem, Advanced technologies such as robots and artificial intelligence are increasingly being used improve the efficiency of agriculture. particular, plant factories attracting attention because they a high affinity for advanced can be produced regardless cultivation location climate. However, production in exhibits higher management costs lower profitability than traditional methods. It is thought that problem solved by predicting growth notifying farm manager. research, we will use data measured at create machine learning model which predicts, both size weight an agricultural product from single piece data. As result, were able predict multiple items using relatively lightweight model. The overall error was small, with average rate about 15%. Although 30%, behaves close actual values.

Language: Английский

Citations

0