Potatoes are a food source that is beneficial for humans in various aspects, such as having nutritional and economic value. However, potato plants are susceptible to many diseases. To address this issue, various resea...
详细信息
In indoor vertical farming systems, managing dynamic and complex environments poses significant challenges. Traditional control strategies often fall short in adapting to rapid changes in critical parameters such as n...
详细信息
In this research, the Human Following Robot (HFR) prototype has been designed and implemented using YOLO v3-Tiny and Tensor Flow Lite on Raspberry Pi hardware named Rewang. The HFR Rewang is designed to assist aircraf...
详细信息
Molten salt has attracted the attention of researchers, especially as a coolant because of its characteristics. This study aimed to analyse the transient and steady-state of the natural circulation system in the molte...
详细信息
Potatoes are a food source that is beneficial for humans in various aspects, such as having nutritional and economic value. However, potato plants are susceptible to many diseases. To address this issue, various resea...
详细信息
ISBN:
(数字)9798350364750
ISBN:
(纸本)9798350364767
Potatoes are a food source that is beneficial for humans in various aspects, such as having nutritional and economic value. However, potato plants are susceptible to many diseases. To address this issue, various researchers have suggested methods utilizing machine learning and image processing for automatic disease type detection. This paper introduces a disease detection model for potato leaf images, employing two computer vision techniques: Vision Transformer (ViT) and CoAtNet. The dataset used in this paper consisted of 30,760 augmented images divided into seven classes. The ViT model had a test accuracy of 99.32% and a validation accuracy of99.12%. Meanwhile, the CoAtNEt model had a test accuracy of 99.58 % and a validation accuracy of 99.48 %. These results show that both models can be used in the detection of potato leaf diseases.
In indoor vertical farming systems, managing dynamic and complex environments poses significant challenges. Traditional control strategies often fall short in adapting to rapid changes in critical parameters such as n...
详细信息
ISBN:
(数字)9798350364750
ISBN:
(纸本)9798350364767
In indoor vertical farming systems, managing dynamic and complex environments poses significant challenges. Traditional control strategies often fall short in adapting to rapid changes in critical parameters such as nutrient levels, climate conditions, and plant health indicators. To address these challenges, this paper presents a novel approach for optimizing indoor vertical farming using Deep Deterministic Policy Gradient (DDPG), a reinforcement learning algorithm well-suited for environments with continuous action spaces. Our study focused on the control and monitoring of key parameters, including nutrient levels (pH and EC), climate conditions (temperature, humidity, light, and CO2 levels), and plant health indicators (biomass accumulation and leaf size structure). By defining a comprehensive state and action space, we simulated an indoor farming environment and trained the DDPG model to maximize crop yield and health.
In this research, the Human Following Robot (HFR) prototype has been designed and implemented using YOLO v3-Tiny and Tensor Flow Lite on Raspberry Pi hardware named Rewang. The HFR Rewang is designed to assist aircraf...
详细信息
ISBN:
(数字)9798331507930
ISBN:
(纸本)9798331507947
In this research, the Human Following Robot (HFR) prototype has been designed and implemented using YOLO v3-Tiny and Tensor Flow Lite on Raspberry Pi hardware named Rewang. The HFR Rewang is designed to assist aircraft technicians by bringing maintenance tool kits to aircraft shelters. Rewang's movement is based on a camera as a vision sensor following the movement of human entities. Image input is processed by YOLO v3-Tiny through the determination of the bounding box, the calculation of Euclidean Distance, and the determination of the pixel value of the camera as the basis of Rewang's movement which is regulated by an L298N driver motor that controls two Direct Current (DC) motors for the left and right wheels. The test results show that Rewang can move at an average speed of 0.18 m/s at 2 m with a travel time of 11 seconds with a light intensity of more than 250 lux. The minimum and maximum distance of object detection is as far as 120 cm and 400 cm, with an object detection accuracy of 95.8%. Rewang allows the HFR to have a larger carrying capacity to bring more complete aircraft maintenance tools and is prospective for other aerospace and general applications.
暂无评论