• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.628-629
• /
• 2018

Recently, residential spaces in urban areas have changed into multi - family residential spaces. There is a feature that smoke is charged when a fire occurs here. Also, the evacuation route and the direction of the outflow of smoke are the same, and the possibility of inhaling the smoke of the evacuees is very high. When fighting fire in a narrow residential space such as a dwelling in a downtown area, exploration is the most important. For this purpose, we implement EO / IR sensor which can be mounted on firefighter 's helmet and can be used for fire detection. By using the EO / IR operation test, we can derive the results that can be used for research and development of the fire search sensor.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.25-30
• /
• 2020

The purpose of this paper is to implement a deep learning-based real-time video analysis algorithm that monitors safety of workers in industrial facilities. The worker's clothes were divided into six classes according to whether workers are wearing a helmet, safety vest, and safety belt, and a total of 5,307 images were used as learning data. The experiment was performed by comparing the mAP when weight was applied according to the number of learning iterations for 645 images, using YOLO v4. It was confirmed that the mAP was the highest with 60.13% when the number of learning iterations was 6,000, and the AP with the most test sets was the highest. In the future, we plan to improve accuracy and speed by optimizing datasets and object detection model.

• Smart Media Journal
• /
• v.12 no.3
• /
• pp.120-128
• /
• 2023

There are various ICT technologies continuously being developed to reduce damage by industrial accidents. And research is being conducted to minimize damage in case of industrial accidents by utilizing sensors, IoT, big data, machine learning and artificial intelligence. In this paper, we propose a design method for a smart device capable of multilateral communication between devices and smart repeater in the communication shaded Areas such as closed areas of industrial sites, mountains, oceans, and coal mines. The proposed device collects worker's information such as worker location and movement speed, and environmental information such as terrain, wind direction, temperature, and humidity, and secures a safe distance between workers to warn in case of a dangerous situation and is designed to be attached to a helmet. For this, we proposed functional requirements for smart devices and design methods for implementing each requirement using sensors and modules in smart device. And we derived evaluation items for performance evaluation of the smart device and proposed an evaluation environment for performance evaluation in mountainous area.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.8 no.2
• /
• pp.209-223
• /
• 1998

The aim of this study was to evaluate welders' exposure to hexavalent chromium (Cr(VI)) and nickel (Ni) during welding operations in a Korean shipyard. The airborne Cr(VI) and Ni concentrations were measured during metal inert gas (MIG) welding on mild and stainless steel, and manual metal arc (MMA) welding on mild steel. The geometric mean (GM) of Cr(VI) concentrations inside the welding helmet during MIG welding on mild steel were $0.0018mg/m^3$ inside a ship section, and $0.0015-0.0026mg/m^3$ at the welding shops. All of the personal breathing zone air samples were below the American Conference of Governmental Industrial Hygienists (ACGIH) Threshold Limit Value ($TLV^{(R)}$) of $0.01mg/m^3$. Conversely, eighty-eight percent(21 of 24) of the personal breathing zone air samples exceeded the National Institute for Occupational Safety and Health (NIOSH) recommended exposure limit of $0.001mg/m^3$. Ni was not detected on 20 of 23 air samples collected during MIG welding on mild steel. The three Ni samples above the limit of detection ranged from 0.015 to $0.044mg/m^3$. The GM of Cr(VI) concentrations during MMA welding on mild steel were $0.0013mg/m^3$, but Ni was not detected in the air samples during this operation. It is assumed that the airborne Cr(VI) and Ni during mild steel welding were derived from the base metals which contained about 0.03% Cr and 0.03% Ni. The GM of airborne total Cr, Cr(VI) and Ni concentrations during MIG welding on stainless steel were 4.02, 0.13 and $0.86mg/m^3$, respectively, and the levels of Cr(VI) and Ni were above the ACGIH-$TLV^{(R)}$. Cr(VI) comprised about 35.5% of the total chromium(Cr) from MIG welding on mild steel, and about 8.4% of total Cr from MIG welding on stainless steel. The ratios of Cr(VI) to total Cr were significantly different among welding shops. It was concluded that welders were exposed to high levels of Cr(VI) and Ni during welding on stainless steel, and were exposed to low levels of Cr(VI) even during welding on mild steel.