• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.123-125
• /
• 2023

As deep learning has become an essential part of human lives, the requirement for Deep Learning as a Service (DLaaS) is growing. Since using remote cloud servers induces privacy concerns for users, a Fully Homomorphic Encryption (FHE) arises to protect users' sensitive data from a malicious attack in the cloud environment. However, the FHE cannot support several computations, including the most popular activation function, Rectified Linear Unit (ReLU). This paper analyzes several polynomial approximation methods for ReLU to utilize FHE in DLaaS.

• Atmosphere
• /
• v.33 no.5
• /
• pp.457-475
• /
• 2023

Accurately predicting localized heavy rainfall is challenging without high-resolution mesoscale cloud information in the numerical model's initial field, as precipitation intensity and amount vary significantly across regions. In the Korean Peninsula, the radar observation network covers the entire country, providing high-resolution data on hydrometeors which is suitable for data assimilation (DA). During the pre-processing stage, radar reflectivity is classified into hydrometeors (e.g., rain, snow, graupel) using the background temperature field. The mixing ratio of each hydrometeor is converted and inputted into a numerical model. Moreover, assimilating saturated water vapor mixing ratio and decomposing radar radial velocity into a three-dimensional wind vector improves the atmospheric dynamic field. This study presents radar DA experiments using a numerical prediction model to enhance the wind, water vapor, and hydrometeor mixing ratio information. The impact of radar DA on precipitation prediction is analyzed separately for each radar component. Assimilating radial velocity improves the dynamic field, while assimilating hydrometeor mixing ratio reduces the spin-up period in cloud microphysical processes, simulating initial precipitation growth. Assimilating water vapor mixing ratio further captures a moist atmospheric environment, maintaining continuous growth of hydrometeors, resulting in concentrated heavy rainfall. Overall, the radar DA experiment showed a 32.78% improvement in precipitation forecast accuracy compared to experiments without DA across four cases. Further research in related fields is necessary to improve predictions of mesoscale heavy rainfall in South Korea, mitigating its impact on human life and property.

• Journal of Information Technology Services
• /
• v.19 no.5
• /
• pp.1-14
• /
• 2020

Mankind has been attempting to live a happy and safe family life in a residential space. Due to the advent of the mobile phone in the 1990s and the smart phone in the 2000s, when the information and communication age came, human life has been innovatively changed. The revolution of human civilization led to the Neolithic Revolution and the Iron Age, followed by a smart phone revolutionizing human life, and the revolution faces with the era of info-communication, smart phones became a daily life and the fourth industrial revolution. The fourth industrial revolution is an era of info-communication technology (ICT), creating a new paradigm across human life through technological developments such as artificial intelligence (AI), IoT, big data, mobile, and cloud. The smart home is actively researched in a direction to support the overall human life as a representative future residential culture paradigm. However, the study considering the needs according to the lifestyle, functional characteristics of each living space and human lifestyle of the Phono Sapiens era where smart phones live like daily life was relatively insufficient. In addition, research on smart home service design should be considered from the apartment residential space planning stage. Therefore, this study has significance in suggesting the direction of research on human-centered smart home service design considering the characteristics of each living space and resident's life-style in the smart phone era.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.37 no.5
• /
• pp.486-493
• /
• 2024

Lighting has been used for a long time as a medium to convey brightness from darkness, and through incandescent lamps and fluorescent lamps, LED light sources have now become the standard in the lighting industry. Recently, the lighting equipment industry has been undergoing rapid digital transformation, starting with smart lighting, and is evolving into smart lighting customized for individuals and spaces through the development of IoT technology, cloud-based services, and data analysis. However, the blue light emitted from digital devices (computers, smartphones, tablets, etc.) or LED lights stimulates the melanopsin in the optic ganglion cells in the retina of the eye, which in turn stimulates the secretion of melatonin through the pineal gland, which regulates the secretion of melatonin. This can reduce sleep quality or disrupt biological rhythms. This interaction between blue light and melatonin has such a significant impact on human sleep patterns and overall health that it is essential to reduce exposure to blue light, especially in the evening. Human-centered lighting refers to lighting that takes into account the effects of light on the physical and mental areas, such as human activity and awakening, improvement of sleep quality, and health management. Many research institutes study the effects in the visible area and the non-visible area. By studying the impact, it is expected to improve the quality of human life. In this study, we plan to study ways to implement human-centered lighting by collecting sunrise and sunset data and linking commercialized LED packages and control devices with open-source hardware.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.319-325
• /
• 2023

In this study, we proposed a method for hyperparameter optimization in the building and training of a deep learning model designed to process point cloud data collected by a millimeter-wave radar system. The primary aim of this study is to facilitate the deployment of a baseline model in resource-constrained IoT devices. We evaluated a RadHAR baseline deep learning model trained on a public dataset composed of point clouds representing five distinct human activities. Additionally, we introduced a coarse-to-fine hyperparameter optimization procedure, showing substantial potential to enhance model efficiency without compromising predictive performance. Experimental results show the feasibility of significantly reducing model size without adversely impacting performance. Specifically, the optimized model demonstrated a 3.3% improvement in classification accuracy despite a 16.8% reduction in number of parameters compared th the baseline model. In conclusion, this research offers valuable insights for the development of deep learning models for resource-constrained IoT devices, underscoring the potential of hyperparameter optimization and model size reduction strategies. This work contributes to enhancing the practicality and usability of deep learning models in real-world environments, where high levels of accuracy and efficiency in data processing and classification tasks are required.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.6
• /
• pp.427-434
• /
• 2019

In the present study, we assessed the parallel computing performance of Agisoft Metashape for orthomosaic generation, which can implement aerial triangulation, generate a three-dimensional point cloud, and make an orthomosaic based on SfM (Structure from Motion) technology. Due to the nature of SfM, most of the time is spent on Align photos, which runs as a relative orientation, and Build dense cloud, which generates a three-dimensional point cloud. Metashape can parallelize the two processes by using multi-cores of CPU (Central Processing Unit) and GPU (Graphics Processing Unit). An orthomosaic was created from large UAV (Unmanned Aerial Vehicle) images by six conditions combined by three parallel methods (CPU only, GPU only, and CPU + GPU) and two operating systems (Windows and Linux). To assess the consistency of the results of the conditions, RMSE (Root Mean Square Error) of aerial triangulation was measured using ground control points which were automatically detected on the images without human intervention. The results of orthomosaic generation from 521 UAV images of 42.2 million pixels showed that the combination of CPU and GPU showed the best performance using the present system, and Linux showed better performance than Windows in all conditions. However, the RMSE values of aerial triangulation revealed a slight difference within an error range among the combinations. Therefore, Metashape seems to leave things to be desired so that the consistency is obtained regardless of parallel methods and operating systems.

• Korean Journal of Food Science and Technology
• /
• v.27 no.5
• /
• pp.666-672
• /
• 1995

This study was carried out to characterize thermolabile pectinesterase (TLPE) and thermostable pectinesterase (TSPE) separated from crude PE of Valencia orange in order to investigate the preventive measures of cloudy juice clarification. The TLPE was observed to be mixture of several isoenzymes with the same molecular weight of 36 KD (37.5 KD) but different isoelectric point of pH 8.4, 8.7, 8.9, 9.8 and ${\geq}10$ which were unstable at $70^{\circ}C$, and the TSPE also was found to be mixture of two or three isoenzymes with the same molecular weight of 53 KD (50 KD) but different isoelectric point of pH 8.7, 9.2 and ${\geq}10$ which had slightly different stability from one another at $70^{\circ}C$. The TLPE and the TSPE had the optimum reaction pH of 7.0 and $7.0{\sim}8.5,\;appK_{M}$ of 1.1 and 1.7 mg/ml, appVmax of 0.53 and $1.01\;{\mu}mol/min/{\mu}g$, and the turnover number of 19.000 and 54,000 mol/mol/min toward Kodak pectin, respectively. The TSPE had higher storage stabiblity and cloud loss effect on orange juice than the TLPE. Above all, the crude PE was most effective on orange juice cloud loss among the PEs used.

• Journal of Digital Convergence
• /
• v.18 no.10
• /
• pp.233-238
• /
• 2020

In the cloud environment, IoT devices using sensors and wearable devices are being applied in various environments, and technologies that accurately determine the information generated by IoT devices are being actively studied. However, due to limitations in the IoT environment such as power and security, information generated by IoT devices is very weak, so financial damage and human casualties are increasing. To accurately collect and analyze IoT information, this paper proposes a topographic information-based key management technique that considers IoT information errors. The proposed technique allows IoT layout errors and groups topographic information into groups of dogs in order to secure connectivity of IoT devices in the event of arbitrary deployment of IoT devices in the cloud environment. In particular, each grouped terrain information is assigned random selected keys from the entire key pool, and the key of the terrain information contained in the IoT information and the probability-high key values are secured with the connectivity of the IoT device. In particular, the proposed technique can reduce information errors about IoT devices because the key of IoT terrain information is extracted by seed using probabilistic deep learning.

• Journal of the Ergonomics Society of Korea
• /
• v.31 no.3
• /
• pp.437-444
• /
• 2012

The purpose of this study was to suggest appropriate human model for ergonomic evaluation considering working postures on 3D space. Background: Traditionally extreme design rules have been widely utilized at the stage of designing products. Body size of 5th percentile and 95th percentile in stature has been generally selected for controllability and clearance evaluation, respectively. However, these rules had limitations in reflecting working posture in ergonomic evaluation. Method: In order to define working posture on 3D space, not only sagittal plane but also lateral plane was considered. Kinematic linkage body model was utilized for representation of working posture. By utilizing the anthropometric data of 2,836 South Korean male populations, the point cloud for end points of linkage models was derived. The individuals who were lacking in certain controllability were selected as human models for the evaluation. Result: In case of standing posture it was found that conventional approach is proper for all controllability evaluations. Contrary to standing posture, tall people had less controllability on control location below shoulder point in sitting posture. Conclusion: From the derived proper range on controllability, ergonomic evaluation rule was suggested according to working posture especially in standing and sitting. Application: The results of the study are expected to aid in selection of appropriate human model for ergonomic evaluation and to improve the usability of products and work space.

• Journal of Internet Computing and Services
• /
• v.15 no.3
• /
• pp.45-52
• /
• 2014

The Ubiquitous-City (U-City) is a smart or intelligent city to satisfy human beings' desire to enjoy IT services with any device, anytime, anywhere. It is a future city model based on Internet of everything or things (IoE or IoT). It includes a lot of video cameras which are networked together. The networked video cameras support a lot of U-City services as one of the main input data together with sensors. They generate huge amount of video information, real big data for the U-City all the time. It is usually required that the U-City manipulates the big data in real-time. And it is not easy at all. Also, many times, it is required that the accumulated video data are analyzed to detect an event or find a figure among them. It requires a lot of computational power and usually takes a lot of time. Currently we can find researches which try to reduce the processing time of the big video data. Cloud computing can be a good solution to address this matter. There are many cloud computing methodologies which can be used to address the matter. MapReduce is an interesting and attractive methodology for it. It has many advantages and is getting popularity in many areas. Video cameras evolve day by day so that the resolution improves sharply. It leads to the exponential growth of the produced data by the networked video cameras. We are coping with real big data when we have to deal with video image data which are produced by the good quality video cameras. A video surveillance system was not useful until we find the cloud computing. But it is now being widely spread in U-Cities since we find some useful methodologies. Video data are unstructured data thus it is not easy to find a good research result of analyzing the data with MapReduce. This paper presents an analyzing system for the video surveillance system, which is a cloud-computing based video data management system. It is easy to deploy, flexible and reliable. It consists of the video manager, the video monitors, the storage for the video images, the storage client and streaming IN component. The "video monitor" for the video images consists of "video translater" and "protocol manager". The "storage" contains MapReduce analyzer. All components were designed according to the functional requirement of video surveillance system. The "streaming IN" component receives the video data from the networked video cameras and delivers them to the "storage client". It also manages the bottleneck of the network to smooth the data stream. The "storage client" receives the video data from the "streaming IN" component and stores them to the storage. It also helps other components to access the storage. The "video monitor" component transfers the video data by smoothly streaming and manages the protocol. The "video translator" sub-component enables users to manage the resolution, the codec and the frame rate of the video image. The "protocol" sub-component manages the Real Time Streaming Protocol (RTSP) and Real Time Messaging Protocol (RTMP). We use Hadoop Distributed File System(HDFS) for the storage of cloud computing. Hadoop stores the data in HDFS and provides the platform that can process data with simple MapReduce programming model. We suggest our own methodology to analyze the video images using MapReduce in this paper. That is, the workflow of video analysis is presented and detailed explanation is given in this paper. The performance evaluation was experiment and we found that our proposed system worked well. The performance evaluation results are presented in this paper with analysis. With our cluster system, we used compressed $1920{\times}1080(FHD)$ resolution video data, H.264 codec and HDFS as video storage. We measured the processing time according to the number of frame per mapper. Tracing the optimal splitting size of input data and the processing time according to the number of node, we found the linearity of the system performance.