Thanakorn Yarnguy

Dr. Thanakorn Yarnguy

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 September 2025 in IEEE Access
Verified
Journal Article
Open access
PCPhoori Chantima
Phoori Chantima
TYThanakorn Yarnguy
Thanakorn Yarnguy
KSKamthorn Sarawan
Kamthorn Sarawan
RSRonnachai Sangmuenmao
Ronnachai Sangmuenmao
WSWorapot Sommool
Worapot Sommool
SGSarayut Gonwirat
Sarayut Gonwirat
This work provides the design and development of a portable soil testing system utilising artificial intelligence (AI) and machine learning (ML) capabilities for real-time soil analysis and crop suggestion. It uses a series of sensors to measure the essential soil parameters of pH, moisture, temperature, electrical conductivity, and macronutrients-nitrogen (N), phosphorus (P), and potassium (K). These sensor data are processed in a microcontroller-based system and analyzed by applying ML algorithms in order to assess the fertility and categorize the soil. A rule-based system integrated with a Random Forest Regressor provides dynamic, explainable crop recommendation using soil condition, environmental conditions, and past data trends. Users can view real-time sensor data in a web-based visualization, monitor history, and receive AI-driven crop advisory support through a web-based dashboard. This field-friendly device is rugged, low in cost, and oriented towards the requirements of smallholder producers. Field experiments using 500 soil samples also exhibit high conformity to a commercial soil tester, as the respective RMSEs are 2.26 mg/kg for nitrogen, 1.90 mg/kg for phosphorus, 1.97 mg/kg for potassium, and 0.60 for pH. The deployed MLmodel had an R² value of 0.978 in test data. These findings validate the system’s accuracy, dependability, and potential to facilitate sustainable, data-based decision-making in precision agriculture.

16 March 2025 in Computers
Verified
Journal Article
Open access
PDF file
ACAtchara Choompol
Atchara Choompol
SGSarayut Gonwirat
Sarayut Gonwirat
NWNarong Wichapa
Narong Wichapa
ASAnucha Sriburum
Anucha Sriburum
STSARAYUT THITAPARS
SARAYUT THITAPARS
RSRonnachai Sangmuenmao
Ronnachai Sangmuenmao
Automating fish freshness assessment is crucial for ensuring quality control and operational efficiency in large-scale fish processing. This study evaluates deep learning models for classifying the freshness of Barbonymus gonionotus (Silver Barb) and optimizing their deployment in an automated fish quality sorting system. Three lightweight deep learning architectures, MobileNetV2, MobileNetV3, and EfficientNet Lite2, were analyzed across 18 different configurations, varying model size (Small, Medium, Large) and preprocessing methods (With and Without Preprocessing). A dataset comprising 1200 images, categorized into three freshness levels, was collected from the Lam Pao Dam in Thailand. To enhance classification performance, You Only Look Once version 8 (YOLOv8) was utilized for object detection and image preprocessing. The models were evaluated based on classification accuracy, inference speed, and computational efficiency, with Technique for Order Preference by Similarity to Ideal Solution with Linear Programming (TOPSIS-LP) applied as a multi-criteria decision-making approach. The results indicated that the MobileNetV3 model with a large parameter size and preprocessing (M2-PL-P) achieved the highest closeness coefficient (CC) score, with an accuracy of 98.33% and an inference speed of 6.95 frames per second (fps). This study establishes a structured framework for integrating AI-driven fish quality assessment into fishery-based community enterprises, improving productivity and reducing reliance on manual sorting processes.