Agricultural Engineering International (E-Journal, CIGR - International Commission of Agricultural Engineering)
Not a member yet
1914 research outputs found
Sort by
Development of an image-based android application for quality inference of tomato
Full text linkAbstract
The objective of this study is to develop real-time quality evaluation tool of tomato from image input. Recent advancements in deep learning tools such as Tensorflow Lite, have assisted in building a light weight real-time android-based application for tomato quality inference. Availability of smart phones and its developmental prospects can meet the growing concern of consumers for quality foods from image. Deep learning has significant potential on image identification and hence an image-based application is thus opted. This work is an effort to develop an image-based AI tool for quality inference of tomatoes. To execute the task of application development, an extensive study on the quality attributes of tomato is done and different state-of-the-art CNN models are trained on tomato images for quality prediction. The proposed CNN models after being trained on tomato image dataset are then deployed in an android application for the following quality inferences: (a) prediction of current state of tomatoes as edible or spoilt, immature or partially mature, or fully mature (b) prediction of physico-chemical properties and (c) shelf-life estimation. Experimental results indicate high classification accuracy of 99% and 97% respectively for spoilage detection and maturity detection respectively from tomato images. In addition to the high recognition rate, the tflite models in android application consumes very less computation time and is able to make prediction in real-time (<0.67 sec). Thus, this application can be considered as a viable solution in tomato quality inference.
Keywords: Tomato, quality, app development
 
The Suitability evaluation of circular economics models for sweet potato in Binh Tan district, Vinh Long province, Viet Nam
No full textThe study was conducted to assess the current production status and natural land potential for the development of circular sweet potato plants in Binh Tan district, Vinh Long province, to propose solutions to increase the economic, social, and environmental value of sweet potatoes. The following methods carry it out: collecting primary and secondary data; synthetic, descriptive statistics; analysis of variance T-test; adaptive assessment; and proposed methods. According to research findings, the sweet potato varieties of purple, white, milk, and red are distributed throughout most study areas. The low economic efficiency due to the complicated situation of the epidemic in the past year caused the price of sweet potatoes to drop significantly. The export of sweet potatoes to foreign countries was limited. Meanwhile, the district has suitable adaptive conditions for sweet potato plants, such as texture, pH, humidity, rainfall, irrigation capacity, etc. The recommended models increase income from growing sweet potatoes and raising livestock, bringing higher economic efficiency to people, more labor needed for people to have jobs, and making full use of agricultural and livestock by-products (unused animal manure, leaves, stems, and roots of sweet potato plants), which limiting environmental pollution when handling improper waste products. The study has proposed solutions to increase the circulation of products, thereby increasing the efficiency of sweet potato production. However, people need to learn the proper use and handling of plant by-products
PERFORMANCE EVALUATION OF A SMALL-SCALE IRISH POTATO (SOLANUM TUBEROSUM L.) HARVESTER
No full textAbstract
Irish potato is the most important non-cereal food crop in Kenya, contributing significantly to food security and the livelihoods of small-scale farmers. However, the labor-intensive nature of potato harvesting poses persistent drudgery, operational inefficiencies, and substantial on-harvest potato damage and post-harvest losses. This study presents design, development and performance evaluation of a small-scale Irish potato harvester for small-scale farmers in Kenya. The harvester incorporates mechanical and automated components for digging, soil-potato separation, and collecting potatoes efficiently, while allowing for adjustments to accommodate various potato varieties and sizes. Field trials have demonstrated substantial time and labor savings without compromising crop quality. The potato harvester has a demonstrated field capacity of 0.45 ha/hr at 0.5 m/s and 1.10 ha/hr at 1.5 m/s. After testing, it was found that it uses 4 hours less during harvesting compared to the manual method, saving the farmer significant amounts of time and labor. Farmers have responded with enthusiasm, about 85% of all who used the harvester expressed satisfaction with the harvester. There has also been a 50% improvement in net profitability associated with using the machine. The collaborative approach with local stakeholders has ensured that the harvester aligns with the specific needs of Kenyan farmers, taking into account limited resources and technical expertise. This research underscores the potential for mechanization to transform potato farming in Kenya, fostering industry growth and enhancing the livelihoods of small-scale farmers.
 
Improving Irrigation Water Use and Management in Large Paddy Rice Fields Using SWAT Model
Full text linkPaddy fields are designed with water impoundments in which their ecohydrological processes are affected by water management practices, the case in the Doho rice scheme, Butaleja District, Uganda, with large paddy fields and farmers facing water management challenges. The water source for this Ugandan scheme originates from Manafwa River, which experiences floods due to climate change, poor drainage, and land use change, affecting paddy production. Flooding deposits silt in the channels. The Soil and Water Assessment Tool (SWAT) simulates and simplifies hydrological processes in large paddy fields. The SWAT Model was used in this study to assess irrigation water use and sustainable water management strategies by simulating hydrologic processes within the catchment for a period of 35 years (2015 to 2050) using hydrological data from the Manafwa catchment and assessing future water-use demand. The SWAT output viewer was also applied to analyse water-use scenarios in the catchment. Model calibrations by SWAT-CUP were performed using the data from 2002 to 2008 and then validated with data from 2009 to 2013. The calibration was successfully performed in the SWAT model with Nash-Sutcliffe Efficiency (NSE) of 0.77 and a coefficient of determination (R2) of 0.79. On the other hand, NSE and R2 values for validation were 0.55 and 0.7 respectively. Calibration data was used to check model performance, which produced reliable results. Average annual available water in the Manafwa River was 949.5192 m3/s and the crop water requirement of the paddy rice in the Doho rice scheme was 11.053 M Similarly, the SWAT output viewer showed that the pothole impoundment module improved irrigation water in times of competitive demands and dry seasons. Therefore, implementing desiltation and grassed waterways minimizes soil erosion, a reliable approach for reducing sedimentation in the river and the channels, significantly contributing to water management in such large irrigation schemes
Role of phenyalanine as elicitor to promote some physiological and biochemical attributes of two wheat cultivars grown under sandy soil conditions
Full text linkPhenylalanine is considered as an effective elicitor and bio-stimulant with positive influence on photosynthesis, plant growth, and yield of different crop species. So, a field experiment was carried out to investigate the role of phenylalanine at 0, 50, 75, 100 mg/L in inducing quality and quantity of two wheat cultivars. Results indicate that plant growth and yield of Gemiza 7 cultivar was more pronounced than that of Sakha 94 cultivar because of its higher significant vegetative growth parameters, total photosynthetic pigments, IAA, phenolic content, activities of both PAL and TAL enzymes, number of grains/spike, grains weight/spike, and weight of 1000 grains. The results also revealed that 100mg/L phenylalanine was the most effective treatment followed by 75mg/L phenylalanine. It was noted that phenylalanine at 100mg/L significantly increased shoot dry weight, total photosynthetic pigments, IAA, phenolic content, PAL, TAL of both cultivars relative to corresponding controls. Likewise, 100mg/L phenylalanine significantly increased grains yield (ardab/fed) by 22.27% in Gemiza 7 cultivar and by 14.93% in Sakha 94 cultivar. On the other hand, 75mg/L phenylalanine significantly increased grains yield (ardab/fed) by 19.52% in Gemiza 7 cultivar and by 16.55% in Sakha 94 cultivar. Hence, the highest significant increase in grains yield (ardab/fed) in Gemiza 7 cultivar was recorded due to 100mg/L phenylalanine. Whereas, the highest significant increase in grains yield (ardab/fed) in Sakha 94 cultivar was recorded due to 75mg/L phenylalanine. So, suggesting using phenylalanine as a biofertilizer as an alternative to chemical fertilizers
Comprehensive Analysis of Soil Physical Properties and their Relationships: Recommendations for Optimized Irrigation Strategies
Full text linkThis study aims to evaluate the soil physical properties in the Zobe Irrigation Area of Katsina State to determine the most suitable irrigation method for enhancing water use efficiency and crop yield. Soil samples were collected from six different locations and analysed for texture, bulk density, porosity, and water holding capacity. The results indicated that the soils are predominantly sandy loam, with an average sand content of 60.17%, silt 24.17%, and clay 15.7%. The mean bulk density was found to be 1.38 g/cm³, while the mean porosity was 47.67%. A strong negative correlation was observed between sand content and field capacity (-0.72), and a strong positive correlation between porosity and field capacity (0.983). Additionally, a strong negative correlation between bulk density and field capacity (-0.962) was identified, indicating that denser soils have lower water retention. Analysis within the soil profile revealed a decrease in sand content and bulk density with depth, and an increase in silt content and porosity. Based on these findings, drip irrigation is recommended as the most effective technique for the study area due to its ability to deliver water directly to the root zone, thus ensuring efficient water use and optimal moisture levels. Supporting studies confirm that drip irrigation maintains consistent soil moisture levels, crucial for maximizing plant available water capacity and promoting healthy plant growth. This research provides essential insights for developing climate-resilient irrigation strategies to support sustainable agriculture in semi-arid regions
Development of Heat Storage-based Greenhouse Dryer - A Comprehensive Assessment of the Dryer
No full textDifferent agricultural produce is dried using various drying sources and processes. Fossil fuel based dryers are more efficient but polluting and costly. In third world countries primary processing systems are scarce in all production catchment. Present study develops heat storage-based greenhouse solar bulk drying system for process standardization and value addition of produce.Among several cost-effective bulk drying systems, the Poly-house heat storage-based greenhouse dryer stands out because it considers meteorological conditions and physico-chemical characteristics of harvested agricultural produce. This dryer is suitable for spices like ginger and turmeric and minor fruit like elephant apple and Indian gooseberry. Structural design dimensions are improvised and the system is smart to achieve improved hot air circulation, thermal efficiency, and economic return.The structural system of the dryer is standardized into hemi-cylindrical section ofspan 10.2m and radius 2m of capacity 1000 kg (with racks), flat plate collectors in inlets, insulated heat storage base and improvised forced convection system.Under no load test, the system generates hot air ranging from 42.70 to 54.32˚C at an ambient temperature of 28.50 to 34.60˚C.The primary drying is predominantly natural convection with an air residence time of 36 seconds, supplemented by humidity sensor-induced forced convection. Initial and final moisture content of 640 kg turmeric dried in one batch range from 85 - 89% to below 11% respectively. At average solar radiation 521.46 watt/m2, thermal efficiency of the dryer is 28.49%
Development and Evaluation of a Machine Vision System for Assessing the Quality of Wheat Seeds: Technical and economical evaluation of the machine vision system
No full textIn this research, a machine vision system was built and evaluated for two cultivars, Torabi and Azar wheat. This system consisted of three parts: suction box, sampling box and imaging box. In each type of wheat, the performance of the suction device was evaluated with two seed plates and four suction values. A completely randomized design with five replications was used for statistical analysis of data and Duncan test was used to compare means. In each amount of suction, the total number of seeds of sticked to the seed plate, the number of singled seeds and the seeds of sticked together on each hole were counted and their percentage was calculated. The image prepared by the digital camera was transferred to the MATLAB software and the algorithm for determining the percentage of breakage, impurity and the number of wheat seeds was coded and validated. The results obtained from the research showed that the most suitable treatment for Turabi variety wheat was the seed plate with 1 mm holes and -100 mm Hg suction. For Azar variety wheat, the seed plate with 1 mm holes and suction of -120 mm Hg was the most suitable treatment. The validation results of the algorithm showed that its accuracy was close to 100%. The results of the economic study also showed that the decision to replace the machine vision system with the usual method has an economic justification in terms of the costs incurred
Drying and tempering effect on milling process of paddy in unparboiled condition: Drying and tempering effect on milling process of paddy
No full textThis research was conducted during the Aman season to assess the impact of drying and tempering on the milling performance of unparboiled rice (BRRI dhan49). Five treatments were tested, with temperatures ranging from 24.1 to 42.7 °C. Drying over three days at different time intervals led to reduced moisture content (from 23.42% to 9.24%), resulting in increased kernel hardness for reduced breakage during milling. The strongest kernel strength recorded was 34.933 N/m. Varying conditions like relative humidity, temperature, air flow, and solar radiation influenced the drying process. Treatment T4 (5 hours sun drying with 1-hour drying and 1-hour tempering) and T1 (4 hours drying with 1-hour drying and ½-hour tempering) exhibited the highest milling yield (19.03 kg) and head rice recovery (17.05 kg) respectively, with T1 having the minimum loss (1.9 kg). These treatments increased milling yield, head rice recovery, and reduced losses, showcasing their effectiveness in maximizing rice output.
 
Predictive Regression Model for Crop Biomass in Clayey Soil Amended with Bamboo Biochar
Full text linkBy employing Multiple Linear Regression (MLR) and Random Forest (RF) algorithms, we delve into the intricate interactions of clay soil amended with bamboo biochar, aiming to introduce innovative strategies in precision crop management. The performance of two machine learning-based statistical models were assessed to predict maize biomass following a single application of biochar to clay soil at doses of 25 and 50 tons per hectare, respectively, either alone or in combination with vermicompost, across two cropping cycles. A total of 34 soil input variables, comprising chemical, physical, and hydraulic soil parameters, including pore size distribution, infiltration rate, and hydraulic conductivity, and one target crop biomass, were subjected to correlation analysis. The process of refining model parameters involved assessing feature importance and redundancy to optimize selection. Three models were chosen based on a dataset encompassing the 100th, 50th, and 75th percentiles. Among them, the Random Forest (RF) model using the 50th percentile data demonstrated the best fit explaining 60% of the variability of the target crop biomass variable while yielding the smallest Root Mean Square Error (RMSE). Notably, all RF models identified potassium (K), phosphorus (P), and the magnesium-to-potassium (Mg/K) ratio as the most influential soil properties for biomass prediction. The RF models represent a valuable tool for predicting crop biomass yield in clay soils amended with biochar