Research in Agricultural Engineering - In Press
The Auto Sprinkler Rover: An Innovative Fertilizer Applicator for Sustainable Agriculture Original Paper
Wan khaima azira Wan mat khalir, ISMAIL AZIMAH, Nur Maizatul Akma Abdul Aziz (email: nurmaizatulakma011@ gmail.com)
Fertilizers are essential to agriculture since they provide crucial nutrients that stimulate crop growth, increase yield and improve yield quality. However, this practice requires the use of manual labour, which consumes energy and time as well as limits the effectiveness of fertilization methods and is environmentally harmful. These factors have led to the development of an innovative product based on the Internet of Things (IoT) called the Auto Sprinkler Rover, which is a remote controlled machine that operates automatically. It contains a 12 L water barrel that serves as a storage tank for liquid fertilizer. This study had designed a liquid sensor and light emitting diode to alert the user to the amount of liquid in the tank. The water pump facilitates the smooth spraying of liquid fertilizer from the pipe’s nozzle. Auto Sprinkler Rover differs from conventional methods because it integrates real-time monitoring via Wi-Fi, an automatic liquid level sensor as well as an automatic spraying system and ergonomic design that is manually operated. The Auto Sprinkler Rover was designed to be a cutting-edge technology that benefits sustainable crop cultivation for households, communities and the global agriculture industry.
Effect of probe diameter, cultivar and postharvest storage on cocoa pod firmness and deformation energyOriginal Paper
Amuaku Randy, Francis Kumi, Godwin K. Amanor, Enoch Asante, Gladys Pepertual Awudi
Mechanical characterization of cocoa pods is essential for improving postharvest handling, mechanized processing, and objective quality assessment. This study investigated the effects of probe diameter, cultivar, and postharvest storage duration on cocoa pod firmness, deformation energy, and yield stress using penetration testing. Three cultivars (Amazonia, Forastero, and Amelonado) were evaluated under controlled conditions (27 ± 2°C; 70 ± 5% RH) over 8 days using probe diameters of 3.5, 8, and 11 mm. Results showed that probe diameter significantly influenced measured firmness, with smaller probes producing higher values due to stress concentration effects. Firmness and deformation energy decreased significantly during storage, particularly within the first 2-4 days, indicating rapid structural degradation. Cultivar-specific responses were observed, with Forastero exhibiting the highest mechanical strength and slowest softening, while Amazonia showed the fastest degradation, losing approximately 60% of firmness by Day 6. A strong positive correlation between firmness and deformation energy (r = 0.9478-0.9999; p < 0.05) confirms deformation energy as a reliable substitute for mechanical integrity. Partial Least Squares Regression models improved with increasing probe diameter, with optimal performance observed in Forastero (R² = 0.8118; RMSE = 1.4036 MPa).
Chacracteristics of tiger nut milk pretreated with magnetic fieldShort Communication
M.M Odewole, T.O Abodunrin, G.O Ajayi, S.O Yusuf
Thermal pretreatment of tiger nut milk (TNM) via pasteurization may have adverse effect on its quality characteristics. The use of magnetic field (MF) to pretreat TNM is a promising non-thermal method. This study investigated the effects of MF pretreatment on three (3) selected quality characteristics of TNM. Fresh TNM samples were pretreated at 0.25 - 15.37 mT MF strength under static and pulse MFs for 10 min. All samples were analyzed for calcium, vitamin E and microbial load, using standard procedures. Results showed that, MF pretreatment led to an average 10% increment in the calcium of TNM; vitamin E reduced by 2.28%, but the reduction was not significantly different from that of pasteurized TNM. Partial reduction in microbial load of TNM was achieved with MF pretreatment. MF is a viable quality-enhancing pretreatment alternative for TNM. Studies should be done on more quality characteristics of MF pretreated TNM.
A semi-automatic prototype machine for splitting and endosperm extraction of Nypa fruticans: design and experimental evaluationOriginal Paper
Huynh Thanh Thuong, Dinh Dao Khanh Danh, Bui Van Huu
Nypa fruticans is a mangrove palm whose immature fruit endosperm is widely consumed, yet harvesting and extraction are still largely manual, resulting in low productivity and inconsistent quality. This study presents the design, fabrication, and experimental evaluation of a semi-automatic prototype machine for splitting Nypa palm fruit and extracting endosperm. The proposed machine integrates a roller–blade mechanism for longitudinal fruit splitting with a suction-based system for immediate endosperm extraction. To identify suitable operating conditions under practical experimental constraints, the Taguchi design of experiments approach was employed. Two independent L9 orthogonal arrays were used to optimise the fruit splitting and endosperm extraction functions, accounting for key mechanical and suction-related parameters. Performance was evaluated using mean response and signal-to-noise analyses. Experimental results show that the splitting mechanism achieves consistently high splitting efficiency, while extraction performance is mainly governed by suction flow rate and airflow-related parameters. Integrated machine tests conducted on 180 fruits under optimised conditions confirmed stable splitting and a practical level of extraction efficiency. Unsuccessful extraction cases were primarily associated with natural variability in fruit morphology and maturity. The results demonstrate the technical feasibility of the proposed prototype and provide a foundation for further improvements toward higher robustness and throughput.
Enhancing the performance of lotus seed kernel and shell sorting after dehulling: A real-time approach based on deep learning and image processing (YOLOv8)Original Paper
Nguyen Dinh-Tu, Huu-Phat Tran, Duc-Tin Le, Nguyen Hoai-Tan, Thanh-Thuong Huynh
Lotus seeds represent a high-value agricultural commodity, widely utilized in food and pharmaceutical industries for their nutritional and medicinal benefits. However, post-harvest processing specifically the removal of shells often relies on manual labour or rudimentary equipment that results in low productivity. This study proposes a computer vision system based on the YOLOv8 deep learning framework to automate and enhance the efficiency of post-decortication sorting. The model is designed to detect and classify three distinct components: unshelled seeds, kernels, and shell fragments. Based on these predictions, the system controls pneumatic actuators to perform precise, real-time separation. Trained on a dataset of more than 30,000 images, the model achieved a mean average precision (mAP@0.5) of 92.6%. These results validate the model’s capability to accurately identify lotus seed components under high-speed processing conditions. Consequently, this research presents a feasible technological solution to mitigate labour dependence and optimize the shell residue removal stage in industrial lotus seed processing.
Quality Classification of Mangosteen using Image Processing and Machine LearningOriginal Paper
Usman Ahmad, Mardison Suhil
Mangosteen is one of important fruits for Indonesia with a good economic value both in domestic and international markets. Mangosteen has a soft and watery white flesh, consumed when the fruit is fully ripe, fresh with dark red color of peel and sometimes almost purple. For export quality grade, beside its tandard size and ripening stage, additional citeria are required by market such as the calyx with normal form and green color are necessary. Normal form and green color of calyx has no direct connection to internal quality of mangosteen, however it important for international market because they reflect the fruit freshness and esthetic value. The objective of this research is to develop quality classification of mangosteen into three classes; export, supermarket and others markets. Random Forest and Extreme Gradient Boosting models of machine learning were trained and validated using 300 samples using 26 image features, and then repeated using only 10 and 5 selected features for more robust classifier. The results of classification using all features were 90.0% and 86.7%, 86.7% and 85.0% using 10 selected features, and 86.7% and 75.0% using 5 selected features for Random Forest and Extreme Gradient Boosting respectively.
Experimental Study of the Haulm-Cutting Module of Root Crop Harvesting Machines
Viktor Baranovsky, Maria Pankiv, Roman Komar, Vitalii Pankiv, Yevhen Berezhenko
Reducing the energy consumption during the harvesting of large root crops (such as sugar and fodder beets, and chicory), which are used to produce food and industrial products, is a priority issue for improving the efficiency of production processes in agro-industrial enterprises. One approach to addressing this issue involves reducing energy expenditures by the working elements of the haulm removal module in root crop harvesters implementing a single-phase harvesting method. An improved method for haulm cutting is proposed, whereby the cut haulm is deposited in the field between two adjacent dividing discs located in the inter-row space of root crops. This eliminates the intermediate operation of unloading haulm onto the harvested field, which is a feature of the conventional method. Based on the results of planned factorial experiments, empirical models were obtained that describe the functional variation of the specific mass of haulm deposited in the protective row zone, depending on changes in module travel speed, haulm yield, and rotational speed of the rotary haulm cutter. Graphical analysis showed that the specific mass of deposited haulm ranges from 15 to 82 g m-2 at rotary cutter speeds of 400, 600 and 800 rpm.
Effect of maturity and colour parameters on cocoa opening force using the existing mechanical systemOriginal Paper
Amuaku Randy, Eric Amoah Asante, Emmanuel Y.H Bobobee, Jerry Oppong Adutwum, Godwin Amanor
The study assessed the mechanical and colourimetric properties of cocoa (Theobroma cacao L.) pods at various maturity stages to improve mechanised pod-opening efficiency. Thirty pods, each replicated three times, underwent compressive loading and colour analysis using the CIE Lab* colour space to correlate colour attributes with mechanical resistance. Pod maturity significantly (p < 0.05) influenced the opening force and compressive strength: unripe pods required the highest mean force (1,222 N) and strength (0.316 N.mm-2), while aged pods needed only 346 N and 0.094 N.mm-2. Transverse orientation yielded higher and more consistent force responses than longitudinal orientation, with ANOVA confirming significant differences (p < 0.05). Colour parameters, especially b* (yellowness), chroma (C), and hue angle (H°), were strongly and negatively correlated with mechanical properties (r ≥ –0.99, p ≤ 0.05), making them reliable non-destructive indicators of maturity. Partial Least Squares Regression (PLSR) models validated the predictive power of combined colour and mechanical data, with longitudinal orientation producing the highest model accuracy across all maturity levels. Combining colour-based maturity assessment with mechanical testing provides a robust framework for designing automated, maturity-sensitive cocoa pod-opening systems that optimise efficiency and reduce bean damage during postharvest handling. The research approach provided an excellent outstanding quantitative assessment.
Vetiver Grass for Road Slope Protection through Soil Erosion and Runoff Reduction in a Haor Area of Sunamganj DistrictOriginal Paper
Tahmina Akter, Saumik Acharya, Sayed Jaber Al-Hossain, Golam Kibria Robbani
Erosion control on slopes and embankments is a global concern, with vetiver planting emerging as an effective solution. This study investigated vetiver grass as a potential alternative for reducing runoff and soil erosion in protecting road embankments. In a small-scale model on a 1V:2H slope, simulated rainfall was applied through a perforated sheet. Runoff was collected, and eroded soil samples were dried using the sand bath method. Runoff and soil loss were compared with and without vetiver grass. Results showed that vetiver grass significantly reduced soil erosion, preventing about 87% more soil loss than bare soil. During 60 minutes of simulated rainfall, the bare soil plot lost per unit area is 27.196 kg.m-2, whereas the vetiver-covered plot lost only 3.606 kg.m-2. This soil retention is due to vetiver’s strong, deep root system and hedge-like structure that effectively holds the soil. Additionally, the runoff was reduced by 14% in plots covered with vetiver. For the 60 minutes of cumulative rainfall, the total runoff in the bare soil micro-plot was 81.45 cm, compared to 70.35 cm in the vetiver micro-plot. Therefore, vetivers are expected to be a sustainable and eco-friendly solution for runoff and erosion control within the lowland haor context.
Comparative study of Portable Vis-NIR Spectrometers for Corn Moisture Content Prediction Using Machine LearningOriginal Paper
Harki Himawan, Muhammad Dzakky Alghifari, Rut Juniar Nainggolan, Mochamad Bagus Hermanto, Nazmi Mat Nawi, Ken Abamba Omwange, Dimas Firmanda Al Riza
Non-destructive estimation of corn kernel moisture content is essential for determining the optimal harvest period. Although various spectrometer sensors are currently available, their predictive performance differs due to variations in spectral resolution and wavelength coverage. This study compared the performance of several portable spectrometer sensors with different wavelength ranges for predicting corn moisture content. Spectral data and reference moisture content were used to develop prediction models using Partial Least Squares Regression (PLSR) and Artificial Neural Network (ANN). Based on PLSR modelling, the AS7265X and C12880MA sensors produced the best performance, with coefficients of determination (R²) for training and testing reaching up to 0.90. Furthermore, ANN modelling yielded improved predictive accuracy, with the highest R² value of 0.95 obtained using the same sensor combination. These results demonstrate that portable spectrometers show strong potential for non-destructive field-based prediction of corn moisture content and can serve as a reliable indicator for determining optimal harvest timing.
Automated analysis of lettuce seed primary root protrusion using computer visionOriginal Paper
Heiber Andres Trujillo, Rafael Mateus Alves, Robson Campos de Lima, Francisco Guilhien Gomes-Junior
Despite high germination rates in lettuce seeds, seedling emergence often varies in terms of speed and percentage, highlighting the need for vigor assessment during the early stages of seedling development. This study employed transillumination imaging and Machine Learning to determine the optimal time intervals for assessing seed vigor in the Roxa and Vanda genotypes. Morphological parameters such as Area, Perimeter, Circularity, and Solidity were extracted from the images using computer vision and analysed through multiple linear regressions applying the ordinary least squares (OLS) model. The results demonstrated that the proposed model effectively identified morphological traits associated with seed vigor. By identifying Circularity and Solidity as reliable early indicators of physiological performance, the study established 21 hours for the Roxa genotype and 16 hours for the Vanda genotype as the most suitable evaluation periods, showing the strongest agreement with conventional vigor assessment methods. In particular, Circularity and Solidity exhibited a strong association with seed vigor and primary root protrusion dynamics. These findings highlight the potential of automated image processing and Machine Learning as rapid, objective and non-destructive tools for seed vigor assessment, contributing to significant advances in seed technology and quality assessment systems.