 หัวเรื่อง:ไม่มีชื่อไทย (ชื่ออังกฤษ : Automatic Screening Algorithm for Narrow Anterior Chamber Angle and Angle-Closure Glaucoma Based on Slit-Lamp Image Analysis) ผู้เขียน: Chonlada Theeraworn, Waree Kongprawechnon, Toshiaki Kondo, Pished Bunnun, Akinori Nishihara, Anita Manassakorn สื่อสิ่งพิมพ์:pdf AbstractTo perform a narrow anterior chamber angle (NACA) and angle-closure glaucoma (ACG) screening using the Van Herick’s method, the width of the peripheral anterior chamber depth (PACD) and corneal thickness have to be measured. These are the key parameters to identify a patient who may be suffering from ACG. Therefore, to develop an automatic screening algorithm for NACA and ACG based on slit-lamp image analysis, a width measurement algorithm has to be as accurate as possible in order to produce the best result. An algorithm was proposed to increase the screening accuracy and also to reduce the computational time. To overcome bright spot reflection on the cornea, the extraction of light reflected and the measurements of both the PACD and corneal thickness were improved. In order to remove unnecessary areas from the image and decrease the processing time, an improved algorithm was designed to automatically detect a region of interest (ROI). Then, only the ROI image was used in subsequent processes. Experimental results showed that the proposed algorithm is accurate and reliable. |
หัวเรื่อง:ไม่มีชื่อไทย (ชื่ออังกฤษ : Development of Robotic Platform for Swarm Robots in Fire Detection Application) ผู้เขียน:Sarun Chattunyakit, Toshiaki Kondo, Itthisek Nilkhamhang สื่อสิ่งพิมพ์:pdf AbstractIn recent years, a team of simple robots, so-called swarm robots, can perform the same level of difficult tasks as a more complicated robot. Due to their abilities, they can be applied to many situations. Fire detection is one application that can be combined with swarm intelligence to increase efficiency and effectiveness. This paper presents a new swarm robotic platform for a fire detection task called FiFiBot that has been developed for low cost and high performance. The average cost per FiFiBot is USD 140. Compared with conventional designs, they are better in terms of computational speed, cost and the number of included sensors. Moreover, two FiFiBots were programmed to perform a leader-follower routine with fire detection, and were successfully tested. Hence, FiFiBots are feasible robotic platforms to be used for research and educational purposes for swarm systems. |