Automatic Environmental Sensor Data Collection System Using Raspberry Pi

( Bhola Paudel ),( Anil Bhujel ),( Hyeon Tae Kim ) 한국농업기계학회 2021 한국농업기계학회 학술발표논문집 Vol.26 No.2

Precision agriculture is gaining its popularity because of the controlled environments which significantly improves the quality and quantity production of crops. To maintain a suitable environment for the plant, continuous monitoring of greenhouse inside environmental conditions is indispensable. However, manual monitoring of such parameters is impractical. A sensor-based data collection system is inherently implemented in the greenhouse monitoring system. In this experiment, a Raspberry Pi-based programmable data collection system was designed to collect the greenhouse indoor temperature, humidity and CO2 using two DHT22 sensors. The DHT22 and MH-Z19 sensors spatially hung on two locations inside a greenhouse were connected to a Raspberry Pi via cables. A Python script is run in the Raspberry Pi to acquire the sensing digital data from the sensors and logged it into the micro SD card. Raspberry Pi is a miniature version of a computer, which offers a high-level language platform. Therefore, a user-interactive program written in Python language was implemented that allows configuring parameters like sensor numbers and sensing intervals in every time while restarting the program. The system was tested by installing it in a greenhouse with a user-defined logging interval. It concludes that a flexible data collection system can be designed by using Raspberry Pi.

Properties of paper-based biodegradable pots for growing seedlings

PAUDEL BHOLA,Basak Jayanta Kumar,Kaushalya Madhavi Bolappa Gamage,김나은,Lee Gun-Ho,최경문,Choi Young-Woo,김현태 한국원예학회 2022 Horticulture, Environment, and Biotechnology Vol.63 No.6

The disadvantageous properties of plastic and plastic wastes have resulted in biodegradable products and seedling pots gain- ing popularity. Agents of diff erent strengths and sizes agents are usually mixed in the paper pulp to enhance the strength of paper-based seedlings pots. In this study, three types of paper-based seedling pots, with 0%, 3% and 5% of additives, named N0, N3, and N5, respectively, were tested to determine their physical, mechanical and biodegradation properties. Water absorption test results showed that the absorption rate was higher in N0, followed by N3 and N5; a similar pattern was observed in the maximum water absorption, thickness and solubility tests. The tensile test showed the highest strength in N3 (3.9 MPa), followed by N0 (3.8 MPa) and N5 (3.1 MPa) at 0% moisture absorption. However, at 100% moisture absorption, tensile strength dropped the most for N0 (82%), followed by N3 (67%) and N5 (65%). Hybrid broccoli seeds germinated inside the plant factory showed that 95% germinated within 13 days. Temporal data showed that germination time was most delayed in N5. No signifi cant diff erence was found in seedling height; however, a signifi cant diff erence was found in the root to shoot height ratio. N0 showed maximum weight and tensile strength loss on the biodegradation test, followed by N3 and N5. At the end of the fourth week, the tensile strength of N0, N3 and N5 was found to be 0.25 MPa, 0.69 MPa and 0.79 MPa, respectively, which was reduced by 94%, 81%, and 79%, respectively, compared to their initial strength. In conclusion, pots containing water repellent additives showed diff erent properties than those without additives, except for germination and seedling growth. This experiment confi rms that using additives will increase the strength of paper-based seedling pots in wet conditions without aff ecting the germination and growth of seedlings.

Plug-trays cutting mechanism for fully automated vegetable seedling transplanter

( Bhola Paudel ),( Jayanta Kumar Basak ),( Seong Woo Jeon ),( Hyeon Tae Kim ) 한국농업기계학회 2023 한국농업기계학회 학술발표논문집 Vol.28 No.1

Transplanting seedlings from plastic trays to the field can cause transplanting shock, which negatively impacts their growth and development. Biodegradable seedling plug-trays are a potential solution, but their large-scale implementation is challenging due to a lack of machinery. In this study, we propose and develop a fully automated vegetable seedling transplanter that separates the seedling plug-cell from the biodegradable plug-tray for transplanting. The biodegradable plug-trays are prepared from the paper and cardboard waste mixed with strength enhancing additives. The plug-trays mechanism comprises two sub-mechanisms: a plug-trays aligning mechanism and a plug-trays separating mechanism. The former moves the plug-trays laterally and longitudinally to align each plug-cell at the seedling discharge point using a double helical grooved screw and a five-bar mechanism. The latter uses a blade assembly to separate the plug-cell from the tray, which falls through a seedling discharge tube to the hopper of the planter unit. Experimental trials showed that the system successfully separated 70% of the plug-cells from 35-day-old pepper and cabbage seedlings. The proposed mechanism has potential as a practical solution for the transplanting shock issue and can be optimized for larger-scale farming by reducing the stagnation count and developing a support system for separating the last two rows of the plug-tray.

Working speed optimization for the existing four-bar linkage-based transplanter

( Bhola Paudel ),( Jayanta Kumar Basak ),( Seong Woo Jeon ),( Gun Ho Lee ),( Hyeon Tae Kim ) 한국농업기계학회 2022 한국농업기계학회 학술발표논문집 Vol.27 No.2

The increasing demand for vegetable products can be fulfilled by increasing productivity, which could be achieved through effective mechanization. However, compared to the harvesting and threshing machinery, the development in the transplanter machine sector is still limited. There is a lack of automated seedling transplanters which could transplant multiple seedlings crops, as most of the existing transplanters are designed to work at a single speed, which results in a single plant spacing not suitable for different crops. Therefore, this study tried to optimize the existing transplanter, which works at a single and relatively low speed, to work at multiple speeds corresponding to other commercial transplanters. Firstly, the existing planter unit's design features were extracted and designed in the commercial simulation software. The real trajectory of the planter was extracted from highspeed camera video and compared with the simulated result to ensure the accuracy of the design. Next, the planter design was simulated at a different working speed (150 - 350 mm/s) similar to commercial transplanters and extracted the working trajectories. The working trajectories were compared, and the speeds whose trajectories tend to meet the requirement for ideal trajectories were selected. The selected speeds were tested for the planter in the soil bin test experiment, and it found that the planter unit can be operated at the speed of 200mm/s, 250 mm/s and 300 mm/s with crank rotation of 30, 40 and 50 rpm. The selected speed combinations are similar to that of other commercially available transplanters, and the test bin result showed that the planting performance of the planters was within the permissible range

Properties of biodegradable seedling plug trays made up of recycled paper pulp mixed with different proportions of strength-enhancing additives.

( Bhola Paudel ),( Jayanta Kumar Basak ),( Bolappa Gamage Kaushalya Madhavi ),( Na-eun Kim ),( Gun-ho Lee ),( Gyeong-mun Choi ),( Young-woo Choi ),( Hyeon Tae Kim ) 한국농업기계학회 2022 한국농업기계학회 학술발표논문집 Vol.27 No.1

The harmful effects of plastic and their product increase the attention of researchers and farmers toward the development and use of biodegradable products. Biodegradable products have several advantages over the plastics, but one of the major concerns is strength. Several researchers found that the strength of the biodegradable product will reduce significantly with the addition of water. To overcome this problem, biodegradable products made from paper waste are mixed with different wet strength agents and surface sizing agents at various proportions to increase their strength against the effect of water. In this study, three types of biodegradable seedling pot, made from waste paper pulp, mixed with wet strength and surface sizing agent in aratio of 0%, 3% and 5%, namely B0, B3 and B5, were tested for their physical, mechanical, germination and degradation properties. In the moisture absorption test, pot with additives showed significantly different properties than pot without additives. The absorption was lower for B0 while the highest for B5. Mechanical properties of pots were tested in dry and wet conditions, where the strength in wet conditions was significantly lower compared to dry conditions. The strength in wet conditions was higher for the pot with additives than the pot without additives; however, no significant difference was found. When comparing the seedlings' total germination percentage and height, no difference was found during the germination and growing test of Broccoli seeds in each pot. In the biodegradation test, all the pots loosed around half of their weight when placed in the soil for a month; however, around 90% of the strength of all the pots was loosed during the same period. Overall, the additives do not show any effect on the germination and growth of broccoli seeds in the seedling tray. However, differences were found among the pots with and without additives for other properties.

Estimation of CO₂ emissions in a swine barn based on age, body weight gain and different activities of swine

( Nibas Chandra Deb ),( Jayanta Kumar Basak ),( Bhola Paudel ),( Sijan Karki ),( Daeyeong Kang ),( Junghoo Kook ),( Myeongyong Kang ),( Seongwoo Jeon ),( Hyeon Tae Kim ) 한국농업기계학회 2023 한국농업기계학회 학술발표논문집 Vol.28 No.1

In the modern world, global warming is a serious problem that is predominantly caused by greenhouse gases (GHGs). However, due to the demand of pork, carbon dioxide (CO₂) emissions are increasing dramatically from swine burns, which have a significant impact on increasing GHGs in the atmosphere. Therefore, the objectives of this study were to measure the CO₂ emissions based on age, body weight gain and different activities of swine. The experiment was conducted in an experimental swine barn from September to December, 2022. A load cell and a livestock environment management system (LEMS) were used to measure the body weight of swine’s and CO₂ emissions level inside the barn, respectively. A 2d camera was used to record the swine’s different activities on a daily basis. The findings of the study showed that the CO₂ emissions were strongly correlated with body weight (r = 0.83) and age of swine (r = 0.86). In this study, we also found that the CO₂ emissions were highest at sleeping time (1-2 PM) and lowest at feeding time (5-6 PM). Moreover, the CO₂ emissions during sleeping (1-2 PM) and feeding (5-6 PM) time were significantly different from other activities (P < 0.05). In conclusion, this study recommends additional research need to be conducted in the different seasons to estimate the CO₂ emissions in concern to swine’s age, body weight and different activities by providing different additives of diets.

Applicability of Deep Learning Network on Gray Mold Disease Detection on Strawberry Leaves

( Sijan Karki ),( Jayanta Kumar Basak ),( Bhola Paudel ),( Na Eun Kim ),( Nibas Chandra Deb ),( Hyeon Tae Kim ) 한국농업기계학회 2022 한국농업기계학회 학술발표논문집 Vol.27 No.2

Early and accurate disease detection in the plant is crucial to mitigate its effect and maximize the yield. Gray mold is considered the most devastating strawberry disease, leading to complete plant death. Various machine learning and deep learning-based models were developed in the past. However, most studies used a controlled environment to capture the images and trained a model whose performance decreased when the models were tested images captured in the field. Therefore, there has been a need for a model that can detect and quantify plant disease accurately, especially in the natural environment. Therefore, this study developed an image segmentation model based on deep learning to distinguish the gray mold disease in strawberry plants. Three groups of strawberry plants (ten plants in each group) were inoculated with different concentrations of necrotrophic fungus pathogen (Botrytis cinerea) and observed the resulting disease. The deep learning model (Unet) was trained with images captured in a natural environment non-destructively. Model performance was assessed using evaluation metrics like intersection over union (IoU), pixel accuracy, and dice accuracy. Furthermore, two machine learning-based models (K-means and XGBoost) were also trained with the same images, and the performance of these models was compared. The deep learning-based model had an average IoU accuracy of 82.12%, dice accuracy of 89.71%, and pixel accuracy of 98.24%, surpassing both machine learning models in multiple aspects. The XGBoost model had an average IoU accuracy of 80.89%, dice accuracy of 85.40%, and pixel accuracy of 98.16%, which performed consistently well in identifying the disease following the deep learning-based model. In conclusion, the developed model could be a valuable tool for strawberry farmers with a simple computational setup in gray mold disease detection.

A Comparison of Recurrent Neural Network for Forecasting Short Term Solar Irradiance

( Niraj Tamrakar ),( Jayanta Kumar Basak ),( Bhola Paudel ),( Nibas Chandra Deb ),( Hyeon Tae Kim ) 한국농업기계학회 2023 한국농업기계학회 학술발표논문집 Vol.28 No.1

Efficient and timely supply of renewable energy relies heavily on accurate solar irradiance forecasting. The study aims to develop reliable short-term solar irradiance prediction models with a 5-minute time interval, using five different variants of recurrent neural networks (RNN). These models include long-short term memory (LSTM), gated recurrent unit (GRU), simple RNN, bidirectional LSTM (Bi-LSTM), and bidirectional GRU (Bi-GRU). The first three models are unidirectional, while the last two are bidirectional RNNs. The dataset used in this study spans 26 months of highly volatile weather conditions in Jinju city, South Korea. To achieve effective results, careful experimentation and selection of five hyper-parameters for each model were conducted. Additionally, the models were tested with varying levels of depth and width, and evaluated using a 9-fold cross-validation method to account for the high variability in the seasonal time-series dataset. Notably, the Bi-GRU model produced the lowest root mean square error (RMSE) and the highest R2 values of 46.1 and 0.958, respectively, and also incurred the lowest computational cost at 5.25*105 seconds per trainable parameter per epoch. In the 9-fold cross-validation test, all five models showed different performances across the four seasons, but on average, the bidirectional RNNs and the simple RNN model demonstrated high robustness with less data and high temporal data variability. However, the stronger architectures of the bidirectional models make their results more reliable.

Colour space selection for enhanced machine learning model performance in classifying strawberry ripeness

( Sijan Karki ),( Jayanta Kumar Basak ),( Bhola Paudel ),( Nibas Chandra Dev ),( Hyeon Tae Kim ) 한국농업기계학회 2023 한국농업기계학회 학술발표논문집 Vol.28 No.1

Color space is a fundamental concept in image processing and machine learning, as it plays a crucial role in determining how an image is represented and processed by the computer. The choice of color space can have a significant impact on the performance of machine learning algorithms, as different color spaces have different properties and emphasize different features. Therefore, this study aimed to evaluate the efficacy of machine learning models in classifying strawberry ripeness stages using color spaces: RGB, HLS, HSV, CIELab*, and YCbCr. The study results indicate that the four ripeness stages: unripe, semi-ripe, ripe and over-ripe exhibited significant differences in biochemical and color features. While the Unripe stage was the most correctly classified stage, the Semi-ripe stage was the most challenging. The Feed Forward Artificial Neural Network using the CIELab* colour space was the most successful in classifying ripeness stages with an average accuracy of 96.7%. This combination with other features, which indicate fruit ripeness, may be utilized in the automatic detection of strawberry ripeness.

Assessment of Load on Threshing Bar During Soybean Pod Threshing

이건호,문병은,Basak Jayanta Kumar,김나은,Paudel Bhola,전성우,국정후,강명용,고한종,김현태 한국농업기계학회 2023 바이오시스템공학 Vol.48 No.4

Purpose This study investigated the threshing load experienced by the threshing bar when it collides with soybean pods during the threshing process. Methods The threshing machine was designed and modeled in the commercial design software, Solidworks, referring to the threshing compartment of a commercial thresher available in Korea. The threshing load was simulated using a commercial simulation software and was recorded for each rotating speed. The actual load experienced by the threshing bar during soybean pod threshing was measured by a strain gauge attached to the threshing bar. Load data from the strain gauge was collected at each microsecond interval. Results The results of the field test and simulations showed that the load gap range varied from about 0.15 N at 250 rpm to about 1.00 N at 400 rpm rotational speed. It was observed that stress increases with an increase in rotational speed, which was similar in both simulation and field experiment. The probable reasons for this difference were the lack of consideration for the joint characteristics between the threshing bar and drum, the properties of the soybean pods, and the influence of gravity and pressure on the field test results.