• Convergence Security Journal
• /
• v.21 no.1
• /
• pp.191-200
• /
• 2021

Artificial intelligence technology is developing in an environment where a lot of data is produced due to the development of computing technology, a cloud environment that can store data, and the spread of personal mobile phones. Among these artificial intelligence technologies, the deep neural network provides excellent performance in image recognition and image classification. There have been many studies on image detection for forest fires and fire prevention using such a deep neural network, but studies on detection of cigarette smoking were insufficient. Meanwhile, military units are establishing surveillance systems for various facilities through CCTV, and it is necessary to detect smoking near ammunition stores or non-smoking areas to prevent fires and explosions. In this paper, by reflecting experimentally optimized numerical values such as activation function and learning rate, we did the detection of smoking pictures and non-smoking pictures in two cases. As experimental data, data was constructed by crawling using pictures of smoking and non-smoking published on the Internet, and a machine learning library was used. As a result of the experiment, when the learning rate is 0.004 and the optimization algorithm Adam is used, it can be seen that the accuracy of 93% and F1-score of 94% are obtained.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.9
• /
• pp.721-736
• /
• 2019

In this paper, the behavior of the fire smoke due to the operation of the ventilation systems when the fire occurred in the underground station (6 basement floors) and the tunnel at the great depth was measured. Fire smoke was generated by using a smoke generator which realized heat buoyancy effect by using hot air blower. The two locations of the fire were selected on the platform and on the platform of the tunnel located outside the screen door. A ventilation mode is generally used in which smoke is exhausted through a vent hole provided in a platform when a platform fire occurs. The tests were performed by operating the exhaust through the ventilation holes of the tunnel part located at both ends of the platform. The smoke density and the wind speed/velocity were measured at various positions, and the videos were taken to analyze the movement and smoke of the smoke. In both cases for fire inside the platform and in the railway tunnel, due to the ventilation mode operation of the fan for the platform and the exhaust of the fans in the tunnel smoke were well exhausted and the smoke propagation to the area near the smoke zone was suppressed. The smoke-control mode, which is applied to both fans for the platform and fans for in the tunnel at both ends of the platform, can provide a safer evacuation environment to the passengers from the fire smoke when the platform fire or fire train stops.

• Food Engineering Progress
• /
• v.15 no.1
• /
• pp.75-79
• /
• 2011

Analytical methods for food antioxidants including ascorbic acid, erythorbic acid, ascorbyl palmitate (AP), and ascorbyl stearate (AS), were validated using high performance liquid chromatography. Validation parameters such as linearity, limit of detection (LOD), limit of quantification (LOQ), and recovery were tested using lard and cider as food model systems. Linearity of ascorbic acid and erythorbic acid were both higher than ($R^2$> 0.99), LOD of these compounds were 0.46 and 0.48 ${\mu}g/mL$, respectively and LOQ were 1.39 and 1.45 ${\mu}g/mL$, respectively. The recovery rates of these compounds were 86.35-94.78% and 84.76-95.02%, respectively. However, the concentration of AP and AS decreased in methanol stock solution. Four other solvents including ethanol, acetonitrile, mixture of methanol and acetonitrile, and mixture of ethanol and acetonitrile were tested to increase the stability of AP and AS under room temperature and refrigerated temperature. Ethanol provided better stability of AP and AS under both room and refrigerated temperature. This study can help to accurately analyze the content of ascorbic acid and its derivatives in processed foods.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.20 no.6
• /
• pp.1161-1175
• /
• 2018

An unexpected event could be easily followed by a large secondary accident due to the limitation in sight of drivers in road tunnels. Therefore, a series of automated incident detection systems have been under operation, which, however, appear in very low detection rates due to very low image qualities on CCTVs in tunnels. In order to overcome that limit, deep learning based tunnel incident detection system was developed, which already showed high detection rates in November of 2017. However, since the object detection process could deal with only still images, moving direction and speed of moving vehicles could not be identified. Furthermore it was hard to detect stopping and reverse the status of moving vehicles. Therefore, apart from the object detection, an object tracking method has been introduced and combined with the detection algorithm to track the moving vehicles. Also, stopping-reverse discrimination algorithm was proposed, thereby implementing into the combined incident detection processes. Each performance on detection of stopping, reverse driving and fire incident state were evaluated with showing 100% detection rate. But the detection for 'person' object appears relatively low success rate to 78.5%. Nevertheless, it is believed that the enlarged richness of image big-data could dramatically enhance the detection capacity of the automatic incident detection system.

• Journal of the Korean Applied Science and Technology
• /
• v.35 no.4
• /
• pp.1260-1268
• /
• 2018

To improve fuel performance and specific characteristics of long storage and moving through fuel systems additives should be added in kerosene type aviation turbine fuel (AVTUR) such as antioxidant, fuel system icing inhibitor (FSII), electric conductivity improvers and so on. The dosage of additives has to be analyzed qualitatively and quantitatively due to inspect the quality of abnormal fuel and distinguish other petroleum products. Multi-dimensional GC-MS (MDGC-MS) with Deans switching technique are applied the determination of antioxidant and FSII, which are added with AVTUR containing complex mixture of hydrocarbons. Antioxidant and FSII in the range of 2.5-20 mg/L was quantitatively and qualitatively analyzed using MDGC-MS and the detection limit was about twice as low as that of the 1-dimensional GC-MS results. The method in this study has been higher peak resolution compared with GC-MS and could be simultaneously analyzed different two additives without sample pre-treatment.

• Journal of Korean Society on Water Environment
• /
• v.35 no.4
• /
• pp.316-331
• /
• 2019

Carbon dioxide($CO_2$) emission from rivers to the atmosphere is a key component in the global carbon cycle. Most of the rivers are supersaturated with $CO_2$. At a global scale, the amount of $CO_2$ emission from rivers is reported to be five-fold greater than that from lakes and reservoirs, but relevant data are rare in Korea. The objectives of this study is to estimate the $CO_2$ net atmospheric flux(NAF) from the upstream of Gangjeong-Goryeong Weir(GGW), Dalseong Weir(DSW), Hapcheon-Changnyeong Weir(HCW), and Changnyeong-Haman Weir(CHW) located in Nakdong River South Korea) using field and laboratory experiments and to apply data mining techniques to develop parsimonious prediction models that can be used to estimate $CO_2$ NAF with physical and water quality variables that can be collected easily. As a result, the study sites were all heterotrophic systems that often released $CO_2$ to the atmosphere, except when the algal photosynthesis was active.The median $CO_2$ NAF was minimum $391.5mg-CO_2/m^2$ day at GGW and maximum $1472.7mg-CO_2/m^2$ day at DSW. The $CO_2$ NAF showed a negative correlation with pH and Chl-a since the overgrowth of the algae consumed $CO_2$ in the water and increased the pH. As the parsimonious multiple regression model and random forest model developed, this study showed an excellent performance with the $Adj.R^2$ value higher than 0.77 in all weirs. Thus, these methods can be used to estimate $CO_2$ NAF in the river even if there is no $pCO_2$ measurement data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2060-2077
• /
• 2019

Recently, mobile healthcare services have attracted significant attention because of the emerging development and supply of diverse wearable devices. Smartwatches and health bands are the most common type of mobile-based wearable devices and their market size is increasing considerably. However, simple value comparisons based on accumulated data have revealed certain problems, such as the standardized nature of health management and the lack of personalized health management service models. The convergence of information technology (IT) and biotechnology (BT) has shifted the medical paradigm from continuous health management and disease prevention to the development of a system that can be used to provide ground-based medical services regardless of the user's location. Moreover, the IT-BT convergence has necessitated the development of lifestyle improvement models and services that utilize big data analysis and machine learning to provide mobile healthcare-based personal health management and disease prevention information. Users' health data, which are specific as they change over time, are collected by different means according to the users' lifestyle and surrounding circumstances. In this paper, we propose a prediction model of user physical activity that uses data characteristics-based long short-term memory (DC-LSTM) recurrent neural networks (RNNs). To provide personalized services, the characteristics and surrounding circumstances of data collectable from mobile host devices were considered in the selection of variables for the model. The data characteristics considered were ease of collection, which represents whether or not variables are collectable, and frequency of occurrence, which represents whether or not changes made to input values constitute significant variables in terms of activity. The variables selected for providing personalized services were activity, weather, temperature, mean daily temperature, humidity, UV, fine dust, asthma and lung disease probability index, skin disease probability index, cadence, travel distance, mean heart rate, and sleep hours. The selected variables were classified according to the data characteristics. To predict activity, an LSTM RNN was built that uses the classified variables as input data and learns the dynamic characteristics of time series data. LSTM RNNs resolve the vanishing gradient problem that occurs in existing RNNs. They are classified into three different types according to data characteristics and constructed through connections among the LSTMs. The constructed neural network learns training data and predicts user activity. To evaluate the proposed model, the root mean square error (RMSE) was used in the performance evaluation of the user physical activity prediction method for which an autoregressive integrated moving average (ARIMA) model, a convolutional neural network (CNN), and an RNN were used. The results show that the proposed DC-LSTM RNN method yields an excellent mean RMSE value of 0.616. The proposed method is used for predicting significant activity considering the surrounding circumstances and user status utilizing the existing standardized activity prediction services. It can also be used to predict user physical activity and provide personalized healthcare based on the data collectable from mobile host devices.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.1
• /
• pp.17-28
• /
• 2019

In the financial investment management strategy, the distributed investment selecting and combining various financial assets is called portfolio management theory. In recent years, the blockchain based financial assets, such as cryptocurrencies, have been traded on several well-known exchanges, and an efficient portfolio management approach is required in order for investors to steadily raise their return on investment in cryptocurrencies. On the other hand, deep learning has shown remarkable results in various fields, and research on application of deep reinforcement learning algorithm to portfolio management has begun. In this paper, we propose an efficient financial portfolio investment management method based on Asynchronous Advantage Actor-Critic (A3C), which is a representative asynchronous reinforcement learning algorithm. In addition, since the conventional cross-entropy function can not be applied to portfolio management, we propose a proper method where the existing cross-entropy is modified to fit the portfolio investment method. Finally, we compare the proposed A3C model with the existing reinforcement learning based cryptography portfolio investment algorithm, and prove that the performance of the proposed A3C model is better than the existing one.

• Journal of Convergence for Information Technology
• /
• v.9 no.3
• /
• pp.140-145
• /
• 2019

With the development of IT technology, many changes are taking place in the health service environment over the past. However, even if medical technology is converged with IT technology, the problem of medical costs and management of health services are still one of the things that needs to be addressed. In this paper, we propose a model for hospitals that have established the IoT system to efficiently analyze and manage the personal information of users who receive medical services. The proposed model aims to efficiently check and manage users' medical information through an in-house IoT system. The proposed model can be used in a variety of heterogeneous cloud environments, and users' medical information can be managed efficiently and quickly without additional human and physical resources. In particular, because users' medical information collected in the proposed model is stored on servers through the IoT gateway, medical staff can analyze users' medical information accurately regardless of time and place. As a result of performance evaluation, the proposed model achieved 19.6% improvement in the efficiency of health care services for occupational health care staff over traditional medical system models that did not use the IoT system, and 22.1% improvement in post-health care for users who received medical services. In addition, the burden on medical staff was 17.6 percent lower on average than the existing medical system models.

• Journal of Climate Change Research
• /
• v.3 no.4
• /
• pp.281-291
• /
• 2012

Forests act as carbon sinks and also improve water resources and biodiversity to climate change. Secure funding, administrative support, and sustainable management systems are essential to conserve forests and to implement international forestry related projects to climate change. Public private partnership (PPP) could be an effective way for forestry sector in developing countries. Awareness analysis should be preceded in order to encourage participation of enterprises for the diversification of funding and the enhancing quality of projects. We conducted a survey targeting more than 129 private enterprises for awareness analysis. As a result, lack of information, complexity of processes and low profit resulted in low interest on forest projects from private enterprises. Improving awareness of recipient countries on forest resources, financial and institutional supports from the public sector, information sharing, performance management and equal partnership between sectors were suggested to encourage PPP in international forestry related projects to climate change.