• 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.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.9 no.3
• /
• pp.348-355
• /
• 2021

Asphalt, widely used for road pavement, has different required physical properties depending on the environment to which the road is exposed. Therefore, it is essential to maximize the life of asphalt roads by evaluating the physical properties of asphalt according to additives and selecting an appropriate formulation considering road traffic and climatic environment. Dynamic shear rheometer(DSR) test is mainly used to measure resistance to rutting among various physical properties of asphalt. However, the DSR test has limitations in that the results are different depending on the experimental setting and can only be measured within a specific temperature range. Therefore, in this study, to overcome the limitations of the DSR test, the rheological characteristics were predicted by learning the images collected from atomic force microscopy. Images and rheology properties were trained through EfficientNet, one of the deep learning architectures, and transfer learning was used to overcome the limitation of the deep learning model, which require many data. The trained model predicted the rheological properties of the asphalt binder with high accuracy even though different types of additives were used. In particular, it was possible to train faster than when transfer learning was not used.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.4
• /
• pp.1-8
• /
• 2014

As cores in multi-core processors are integrated in a single chip, power density increased considerably, resulting in high temperature. For this reason, many research groups have focused on the techniques to solve thermal problems. In general, the approaches using mechanical cooling system or DTM(Dynamic Thermal Management) have been used to reduce the temperature in the microprocessors. However, existing approaches cannot solve thermal problems due to high cost and performance degradation. However, floorplan scheme does not require extra cooling cost and performance degradation. In this paper, we propose the diverse floorplan schemes in order to alleviate the thermal problem caused by the hottest unit in multi-core processors. Simulation results show that the peak temperature can be reduced efficiently when the hottest unit is located near to L2 cache. Compared to baseline floorplan, the peak temperature of core-central and core-edge are decreased by $8.04^{\circ}C$, $8.05^{\circ}C$ on average, respectively.

• International Journal of Highway Engineering
• /
• v.14 no.4
• /
• pp.29-36
• /
• 2012

PURPOSES : Plastic deformation is frequently made in intersection asphalt pavement at its early age due to deceleration and stoppage of vehicles. This study has been performed to provide a mechanistic basis for reasonable selection of paving method to minimize the plastic deformation at intersection. METHODS : Pavement layer, temperature, traffic volume of the intersections managed by the Daejeon Regional Construction and Management Administration were collected to calculate asphalt dynamic modulus with pavement depth by using a prediction equation suggested by the Korean pavement design guide. Performance of ordinary dense-graded asphalt pavement, polymer modified asphalt pavement, and fiber reinforced asphalt pavement was analyzed by finite element method and the results were used in a performance model to predict the plastic deformation. RESULTS : In aspect of performance, the three paving methods were usable under low traffic while the fiber reinforced asphalt pavement was the most suitable under heavy traffic. CONCLUSIONS : Reasonable paving method suitable for traffic characteristics in the intersection might be decided by considering economic feasibility.

• Journal of Korean Society on Water Environment
• /
• v.23 no.1
• /
• pp.52-63
• /
• 2007

The objectives of this study were to setup a laterally-averaged two-dimensional eutrophication model in Daecheong Reservoir, and to validate the model under two different hydrological conditions; drought year (2001) and wet year (2004). The suggested modeling approach was found to be very effective to simulate the dynamic variations of water temperature, nutrients, dissolved oxygen, and algae in the reservoir. The model satisfactorily replicated the algal bloom that happened between Janggae (Sta.4) and Haenam (Sta.5) during summer of 2001, although the peak concentration was slightly underestimated due to the laterally averaged assumption. The allochthonous phosphorus and algae induced from upstream and So-oak stream during several rainfall events were found to be most significant sources of algal bloom in 2001. In contrast to draught year, the flood events happened during summer months of 2004 tended to remove the hypolimnetic anaerobic conditions and dilute the dissolved phosphorus in the upper reach of the reservoir, and in turn mitigated algal bloom. It implies that the impact of hydrological and hydrodynamic conditions on the reservoir water quality is highly significant, and a drought year may be more vulnerable to algal bloom in the reservoir.

• Steel and Composite Structures
• /
• v.19 no.2
• /
• pp.309-325
• /
• 2015

A convenient procedure for seismic retrofit of existing buildings is to use passive control methods, like using friction dampers in steel frames with bracing systems. In this method, reduction of seismic demand and increase of ductility generally improve seismic performance of the structures. Some of its advantages are development of a stable rectangular hysteresis loop and independence on environmental conditions such as temperature and loading rate. In addition to friction dampers, masonry-infill panels improve the seismic resistance of steel structures by increasing lateral strength and stiffness and reducing story drifts. In this study, the effect of masonry-infill panels on seismic performance of a three-span four-story steel frame with Pall friction dampers is investigated. The results show that friction dampers in the steel frame increase the ductility and decrease the drift (to less than 1%). The infill panels fulfill their function during the imposed drift and increase structural strength. It can be concluded that infill panels together with friction dampers, reduced structural dynamic response. These infill panels dissipated input earthquake energy from 4% to 10%, depending on their thickness.

• International Journal of Contents
• /
• v.18 no.1
• /
• pp.17-26
• /
• 2022

With the acceleration of urbanization and industrialization, air pollution has become increasingly serious, and the pollution control situation is not optimistic. Climate change has become a major global challenge faced by mankind. To actively respond to climate change, China has proposed carbon peak and carbon neutral goals. However, atmospheric pollutants and meteorological factors that affect air quality are complex and changeable, and the complex relationship and correlation between them must be further clarified. This paper uses China's 2013-2018 high-resolution air pollution reanalysis open data set, as well as statistical methods of the Pearson Correlation Coefficient (PCC) to calculate and visualize the design and analysis of environmental monitoring big data, which is intuitive and it quickly demonstrated the correlation between pollutants and meteorological factors in the temporal and spatial sequence, and provided convenience for environmental management departments to use air quality routine monitoring data to enable dynamic decision-making, and promote global climate governance. The experimental results show that, apart from ozone, which is negatively correlated, the other pollutants are positively correlated; meteorological factors have a greater impact on pollutants, temperature and pollutants are negatively correlated, air pressure is positively correlated, and the correlation between humidity is insignificant. The wind speed has a significant negative correlation with the six pollutants, which has a greater impact on the diffusion of pollutants.

• Korean Journal of Environmental Biology
• /
• v.34 no.1
• /
• pp.56-62
• /
• 2016

Pest population density models are very important to monitor the initial occurrence and to understand the continuous fluctuation pattern of pest in pest management. This is one of the major issues in agriculture because these predictions make pesticides more effective and environmental impact of pesticides less. In this study, we combined and predicted the mortality change of pest caused by pesticides with temperature change and population dynamic model. Sensitive strain of two-spotted spider mite (Tetranychus urticae Koch) with kidney bean leaf as host was exposed to mixed acaricide, Acrinathrin-Spiromesifen and organotin acaricide, Azocyclotin, at 20, 25, 30, and $35^{\circ}C$, respectively. There was significant difference in mortality of T. urticae among pesticides and temperatures. We used DYMEX to simulate population density of T. urticae and predicted that the initial management time and number of chemical control would be changed in the future with climate change. There would be implications for strategies for pest management and selection process of pesticide in the future corresponding climate change.

• KIPS Transactions on Computer and Communication Systems
• /
• v.3 no.11
• /
• pp.419-426
• /
• 2014

The recent trend of performance increase in the smart mobile devices demands more power consumption and lower batter life time. Among three battery models of mathematical model, electrochemical model and electric model, the Thevenin's equivalent circuit with non-linear function model of SOC in the electrical model is widely used. However, the OCV results have only limited accuracy because of the characteristic shift caused by temperature and age and atypical impedance property that cannot expressed by electrical components. In this paper, the new battery model that improves the accuracy of the existing models is proposed. In the proposed simulator the mathematical model for SOC characteristic is improved and the adjustment for the temperature, the age of battery and atypical electrical characteristics. In the experimental results of predicting of the battery in the static and dynamic state, the proposed simulator shows improved MSE comparing to the results of the existing methods.

• The KIPS Transactions:PartA
• /
• v.17A no.6
• /
• pp.265-274
• /
• 2010

As the process technology scales down and integration densities continue to increase, interconnection has become one of the most important factors in performance of recent multi-core processors. Recently, to reduce the delay due to interconnection, 3D architecture has been adopted in designing multi-core processors. In 3D multi-core processors, multiple cores are stacked vertically and each core on different layers are connected by direct vertical TSVs(through-silicon vias). Compared to 2D multi-core architecture, 3D multi-core architecture reduces wire length significantly, leading to decreased interconnection delay and lower power consumption. Despite the benefits mentioned above, 3D design technique cannot be practical without proper solutions for hotspots due to high temperature. In this paper, we propose three floorplan schemes for reducing the peak temperature in 3D multi-core processors. According to our simulation results, the proposed floorplan schemes are expected to mitigate the thermal problems of 3D multi-core processors efficiently, resulting in improved reliability. Moreover, processor performance improves by reducing the performance degradation due to DTM techniques. Power consumption also can be reduced by decreased temperature and reduced execution time.