A Flexible Multi-Ion Detection System Based on Organic Electrochemical Transistors for Physiological Monitoring

Electronics, Journal Year: 2025, Volume and Issue: 14(5), P. 1023 - 1023

Published: March 4, 2025

The continuous and real-time monitoring of physiological indicators is essential for early disease detection, prevention, clinical diagnosis. In response to the growing demand precise parameter assessment, this study presents a flexible, organic electrochemical transistor (OECT)-based multi-ion sensing system designed monitor key electrolyte concentrations—sodium (Na+), potassium (K+), calcium (Ca2+)—in human biofluids. features highly adaptable sensor array with detection range tailored conditions, ensuring high selectivity stability in complex biological environments. Our demonstrated sensitivity exceeding 1 mA/decade. To enhance measurement accuracy mitigate cross-interference among ions, we integrate advanced machine learning algorithms, which optimize signal processing significantly improve system’s reliability. Additionally, have developed fully integrated hardware–software platform comprising customized acquisition circuitry dedicated data analysis software, specifically OECT-based applications. This comprehensive framework not only refines ion but also paves way broader translation OECT technology. proposed holds great promise point-of-care diagnostics, offering potential paradigm shift non-invasive, on-demand health assessment.

Language: Английский

---

Artificial Intelligence and IoT for Water Saving in Agriculture: A Systematic Review

Smart Agricultural Technology, Journal Year: 2025, Volume and Issue: unknown, P. 101008 - 101008

Published: May 1, 2025

Language: Английский

---

Agro-Technological Systems in Traditional Agriculture Assistance: A Systematic Review

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 123047 - 123069

Published: Jan. 1, 2023

Guaranteeing food security from agriculture in an uncertain context, derived the effects of multiple factors, is a challenge. Traditional agricultural production one that faces greatest challenges, scarce evolution practices, despite being contributes most to availability food, at 80%. This systematic review aims identify and analyze agrotechnological systems belonging precision agriculture, which may be potentially adaptable traditional rural agriculture. Contributions improved crop yields scientific technological studies were analyzed. The PRISMA statement was used as formal outline collect 114 period 2018-2023. From review, it identified there growing trend adoption intelligent help producers management crops, accentuated increase yield, determination product quality, water resources, mainly. Likewise, preponderant approach monitoring control development. achieved through emerging technologies, such Internet Things, artificial intelligence, machine learning, with information mainly collected by sensors embedded drones, algorithms, decision support systems, sensors, Arduino technology systems. Finally, this shows are five viable can adapted strengthen production. Therefore, scientific-technological contributions ensuring security.

Language: Английский

---

Machine Learning Based Water Requirement Prediction for Agriculture Before a Rainfall

2021 International Conference on Emerging Smart Computing and Informatics (ESCI), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 7

Published: March 5, 2024

Enhancing crop output and streamlining irrigation techniques can be achieved through the potential application of artificial intelligence (AI) in agriculture. The use approaches to forecast needs before notable rainfall occurrences are examined this work. goal is develop a predictive model that precisely estimate agricultural demands based on expected precipitation by using machine learning algorithms weather data. To provide accurate suggestions, suggested AI system takes into account past patterns, soil moisture levels, traits, other pertinent parameters. By taking proactive stance, farmers may minimize water waste, save important resources, make well-informed decisions about management.

Language: Английский

---

Kiwi 4.0: In Vivo Real-Time Monitoring to Improve Water Use Efficiency in Yellow Flesh Actinidia chinensis

Biosensors, Journal Year: 2024, Volume and Issue: 14(5), P. 226 - 226

Published: May 3, 2024

This manuscript reports the application of sensors for water use efficiency with a focus on an in vivo OECT biosensor. In two distinct experimental trials, sensor bioristor was applied yellow kiwi plants to monitor, real-time and continuously, changes composition concentration plant sap open field during growth development. The response physiological data, together other fruit monitoring were acquired combined both giving complete picture biosphere conditions. A high correlation observed between index (ΔIgs), canopy cover expressed as fraction intercepted PAR (fi_PAR), soil content (SWC). addition, confirmed be good proxy occurrence drought plants; fact, period stress identified within month July. novelty measurements their ability detect advance defoliation, thereby reducing yield quality losses. plant-based irrigation protocol can achieved tailored based real needs, increasing sustainability preserving high-quality standards.

Language: Английский

---

From Pixels to Phenotypes: Quest of Machine Vision for Drought Tolerance Traits in Plants

Russian Journal of Plant Physiology, Journal Year: 2024, Volume and Issue: 71(3)

Published: June 1, 2024

Language: Английский

---

Machine Learning Models Comparison for Water Stress Detection Based on Stem Electrical Impedance Measurements

Published: Sept. 25, 2023

Smart agriculture is a promising solution to improve food production and reduce waste of resources. The idea adopt electronics sensors monitor key parameters the crops integrate these data with farmer knowledge. Sensors both environment plant itself, generating huge amount data. Data processing aspect smart agriculture, machine learning can help understand extract needed feature. In this paper, we present performance comparison several models trained detect water stress condition plants. dataset used for study includes stem electrical impedance, novel parameter directly measured on are compared based three different metrics, average accuracy higher than 85%. effect removing impedance results in worse models, indicating its impact application.

Language: Английский

---

Crop Yield Prediction Using Optimized Convolutional Neural Network Model Based on Environmental and Phenological Data

EAI/Springer Innovations in Communication and Computing, Journal Year: 2024, Volume and Issue: unknown, P. 27 - 54

Published: Jan. 1, 2024

Language: Английский

---

Leveraging Incremental Decision Trees and In-Vivo Biosensors for an Explainable Plant Health Monitoring System

Published: May 23, 2024

Among the factors concerning plant development and agricultural yield, water stress drought emerge as pivotal factors. Indeed, ability to know in advance imminent crops based on measurable biochemical metrics is priceless, it offers opportunity for rapid interventions aimed at restoring optimal growth conditions before plants show clear visible symptoms.In this work, we present an explainable system smart agriculture focused continuous monitoring of condition tomato plants, achieved through a new in-vivo biosensor, named bioristor. The proposed embeds incremental by design classifier. Specifically, experimented with traditional Hoeffding decision tree its fuzzy version. This analyzes data received from bioristors assess health status classifies into four classes. also leverages learning technique, which allows classification model be updated during period, maintain adequate performance. In way, are monitored continuously effective model, allowing timely countermeasures taken if situation detected. We preliminary results real dataset, using features related ionic currents within sap, measured bioristors. assessed performance both terms complexity, obtaining promising generation interesting rules that could allow implementation keep healthy long possible.

Language: Английский

---

Transformer-Based Water Stress Estimation Using Leaf Wilting Computed from Leaf Images and Unsupervised Domain Adaptation for Tomato Crops

Technologies, Journal Year: 2024, Volume and Issue: 12(7), P. 94 - 94

Published: June 25, 2024

Modern agriculture faces the dual challenge of ensuring sustainability while meeting growing global demand for food. Smart agriculture, which uses data from environment and plants to deliver water exactly when how it is needed, has attracted significant attention. This approach requires precise management highly accurate real-time monitoring crop stress. Existing methods pose challenges such as risk plant damage, costly sensors, need expert adjustments. Therefore, a low-cost, stress estimation model was developed that deep learning commercially available sensors. The relative stem diameter index incorporates environmental sensors an RGB camera, are processed by proposed daily normalization. In addition, domain adaptation in our Transformer implemented enable robust different areas. accuracy evaluated using real cultivation tomato crops, achieving coefficient determination (R2) 0.79 estimation. Furthermore, maintained high level applied areas, with R2 0.76, demonstrating its adaptability under conditions.

Language: Английский

---