The classification of germinated pole sitao (Vigna unguiculata (L.) Walp.) seeds is important in seed germination tests. The automation of this process has been explored for different grain and legume seeds but is only limited to binary classification. This study aimed to develop a classifier system that can recognize three classes: normal, abnormal, and ungerminated. SSD MobileNet and Faster R-CNN models were trained to perform the classification. Both were trained using 1500 images of germinated seeds at fifth- and eighth-day observations. Each class had 500 images. The trained models were evaluated using 150 images per class. The SSD MobileNet model had an accuracy of 0.79 while the Faster R-CNN model had an accuracy of 0.75. The results showed that the average accuracies for the classes were significantly different from one another based on one-way ANOVA at a 95% confidence level with an F-critical value of 3.0159. The SSD MobileNet model outperformed the Faster R-CNN model in classifying pole sitao seeds, with improved precision in identifying abnormal and ungerminated seeds on the fifth day and normal and ungerminated seeds on the eighth day. The results confirm the potential of the SSD MobileNet model as a more reliable classifier in germination tests.

Peanut harvesting remains labor-intensive and costly due to the limited availability of locally developed mechanized harvesting technologies. Thus, this study presents the design, optimization, and evaluation of a four-wheel tractor peanut digger to advance harvesting. Structural integrity was evaluated using Finite Element Analysis (FEA) in ANSYS under a draft load of 2008.2 N, yielding a maximum von Mises stress of 33.012 MPa, a peak strain of 0.00015, a maximum deformation of 1.72 mm, and a factor of safety of 5.74, confirming adequate structural reliability. Field performance was optimized using a Box–Behnken Design (BBD) with tractor speed, digger blade lift angle, and clearance angle as factors, while material capacity and digging efficiency served as response variables. Regression analysis showed that the main effects significantly influenced both responses, whereas interaction effects were insignificant. Response Surface Methodology (RSM) optimization identified optimal operating conditions of a 14.95° lift angle, 15.70° clearance angle, and 1.74 km·h⁻¹ forward speed, achieving a predicted material capacity of 0.56 t·h⁻¹ and digging efficiency of 96.69%. Validation tests improved these values to 0.59 t·h⁻¹ and 97.42%, demonstrating that integrating numerical methods provides an effective approach for developing adoptable and structurally reliable peanut harvesting machinery.

Biochar’s potential value as a soil amendment is in continuous demand. However, as-produced biochar comes in different forms and sizes making its application and distribution challenging. Because there is a limited commercialized biochar pelletizer machine in the Philippines, a biochar pelletizer was developed to meet the requirements of the end-user and to produce a relatively efficient and comparatively inexpensive machine. The developed pelletizer was fabricated in local shops. The pelleting mechanism was composed of a horizontal die and two rollers. Pellet rollers were designed to press the biochar against the die. As the mixture passed the holes, pellets were formed and then fell to the catchment. The developed pelletizer was tested using three (3) different feedstocks, namely: carbonized rice hull (CRH), carbonized coconut shell (CCS), and carbonized wood chips (CWC). Cassava paste was utilized as the binder in levels of 10%, 15%, and 20%, respectively. The pellets produced in the study were 13 mm long with a range of 6.60 to 7.79% moisture content. Particle and bulk densities were highest with CRH at 764.22 and 343.67 kg-m3, respectively. The hardness and durability were highest with CWC with 1272.75 Pa and 87.48%, respectively. The highest actual capacity was observed with the CRH at 678.22 kg/day. An analysis of variance showed that the mean machine efficiency ranged from 67.86% to 71.02%, irrespective of the binder level. On the other hand, the binder level had a significant effect on the pelleting recovery with the highest recovery of 98.50%was achieved with a binder level of 20%. CCS and CWC could hold water up to 101 to 104% of their weight and could resist up to 806.66 to 1559.6 Pa of pressure. The study recommends the testing of pellets with other feedstock materials and other binder types and formulations.

Saba bananas are widely produced in the Philippines, mainly for food production. The peel of saba was characterized, and some physical properties of it were measured. The heating value, fixed carbon, volatile matter, ash, and moisture content of the peel were also determined. In predicting the elemental composition, the equation of Parikh et al. (2007) was used, yielding an air-to-fuel ratio of 6.92 kgair/ kgbiomass for combustion. A laboratory-scale prototype updraft gasifier was fabricated and tested for efficiency by boiling water on it. The size of the peel affects the ignition time of the syngas and the burning rate of the biomass. Flow rate affects the amount of heat produced and the equivalence ratio during gasification. Thermal efficiencies in different settings are less than 20% due to system heat loss. The highest efficiency was obtained with a low airflow setting, while the lowest efficiency was yielded at a high airflow setting. At an equivalence ratio of 0.208, about 500g of saba peel produced around 1562.63 kJ of heat with a thermal efficiency of 17.46%. For higher efficiency of the peel, it is recommended to design a gasifier that would decrease the system heat loss and process the biomass into briquettes or pellets for a more uniform mass and size distribution.