This page has only limited features, please log in for full access.
Mosquito control is important as mosquitoes are extremely harmful pests that spread various infectious diseases. In this research, we present the preliminary results of an automated system that detects the presence of mosquitoes via image processing using multiple deep learning networks. The Fully Convolutional Network (FCN) and neural network-based regression demonstrated an accuracy of 84%. Meanwhile, the single image classifier demonstrated an accuracy of only 52%. The overall processing time also decreased from 4.64 to 2.47 s compared to the conventional classifying network. After detection, a larvicide made from toxic protein crystals of the Bacillus thuringiensis serotype israelensis bacteria was injected into static water to stop the proliferation of mosquitoes. This system demonstrates a higher efficiency than hunting adult mosquitos while avoiding damage to other insects.
Kyukwang Kim; Jieum Hyun; Hyeongkeun Kim; Hwijoon Lim; Hyun Myung. A Deep Learning-Based Automatic Mosquito Sensing and Control System for Urban Mosquito Habitats. Sensors 2019, 19, 2785 .
AMA StyleKyukwang Kim, Jieum Hyun, Hyeongkeun Kim, Hwijoon Lim, Hyun Myung. A Deep Learning-Based Automatic Mosquito Sensing and Control System for Urban Mosquito Habitats. Sensors. 2019; 19 (12):2785.
Chicago/Turabian StyleKyukwang Kim; Jieum Hyun; Hyeongkeun Kim; Hwijoon Lim; Hyun Myung. 2019. "A Deep Learning-Based Automatic Mosquito Sensing and Control System for Urban Mosquito Habitats." Sensors 19, no. 12: 2785.
The detection of bacterial growth in liquid media is an essential process in determining antibiotic susceptibility or the level of bacterial presence for clinical or research purposes. We have developed a system, which enables simplified and automated detection using a camera and a striped pattern marker. The quantification of bacterial growth is possible as the bacterial growth in the culturing vessel blurs the marker image, which is placed on the back of the vessel, and the blurring results in a decrease in the high-frequency spectrum region of the marker image. The experiment results show that the FFT (fast Fourier transform)-based growth detection method is robust to the variations in the type of bacterial carrier and vessels ranging from the culture tubes to the microfluidic devices. Moreover, the automated incubator and image acquisition system are developed to be used as a comprehensive in situ detection system. We expect that this result can be applied in the automation of biological experiments, such as the Antibiotics Susceptibility Test or toxicity measurement. Furthermore, the simple framework of the proposed growth measurement method may be further utilized as an effective and convenient method for building point-of-care devices for developing countries.
Kyukwang Kim; Duckyu Choi; Hwijoon Lim; Hyeongkeun Kim; Jessie S. Jeon. Vision Marker-Based In Situ Examination of Bacterial Growth in Liquid Culture Media. Sensors 2016, 16, 2179 .
AMA StyleKyukwang Kim, Duckyu Choi, Hwijoon Lim, Hyeongkeun Kim, Jessie S. Jeon. Vision Marker-Based In Situ Examination of Bacterial Growth in Liquid Culture Media. Sensors. 2016; 16 (12):2179.
Chicago/Turabian StyleKyukwang Kim; Duckyu Choi; Hwijoon Lim; Hyeongkeun Kim; Jessie S. Jeon. 2016. "Vision Marker-Based In Situ Examination of Bacterial Growth in Liquid Culture Media." Sensors 16, no. 12: 2179.
In this research an open source, low power sensor node was developed to check the growth of mycobacteria in a culture bottle with a nitrate reductase assay method for a drug susceptibility test. The sensor system reports the temperature and color sensor output frequency change of the culture bottle when the device is triggered. After the culture process is finished, a nitrite ion detecting solution based on a commercial nitrite ion detection kit is injected into the culture bottle by a syringe pump to check bacterial growth by the formation of a pigment by the reaction between the solution and the color sensor. Sensor status and NRA results are broadcasted via a Bluetooth low energy beacon. An Android application was developed to collect the broadcasted data, classify the status of cultured samples from multiple devices, and visualize the data for the end users, circumventing the need to examine each culture bottle manually during a long culture period. The authors expect that usage of the developed sensor will decrease the cost and required labor for handling large amounts of patient samples in local health centers in developing countries. All 3D-printerable hardware parts, a circuit diagram, and software are available online.
Kyukwang Kim; Hyeong Keun Kim; Hwijoon Lim; Hyun Myung. A Low Cost/Low Power Open Source Sensor System for Automated Tuberculosis Drug Susceptibility Testing. Sensors 2016, 16, 942 .
AMA StyleKyukwang Kim, Hyeong Keun Kim, Hwijoon Lim, Hyun Myung. A Low Cost/Low Power Open Source Sensor System for Automated Tuberculosis Drug Susceptibility Testing. Sensors. 2016; 16 (6):942.
Chicago/Turabian StyleKyukwang Kim; Hyeong Keun Kim; Hwijoon Lim; Hyun Myung. 2016. "A Low Cost/Low Power Open Source Sensor System for Automated Tuberculosis Drug Susceptibility Testing." Sensors 16, no. 6: 942.