• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.190-201
• /
• 2023

Securing transportation safety infrastructure technology for Lv.4 connected autonomous driving is very important for the spread of autonomous vehicles, and the safe operation of level 4 autonomous vehicles in adverse weather has limitations due to the development of vehicle-only technology. We developed the radar-enabled AI convergence transportation entities detection system. This system is mounted on fixed and mobile supports on the road, and provides excellent autonomous driving situation recognition/determination results by converging transportation entities information collected from various monitoring sensors such as 60GHz radar and EO/IR based on artificial intelligence. By installing such a radar-enabled AI convergence transportation entities detection system on an autonomous road, it is possible to increase driving efficiency and ensure safety in adverse weather. To secure competitive technologies in the global market, the development of four key technologies such as ① AI-enabled transportation situation recognition/determination algorithm, ② 60GHz radar development technology, ③ multi-sensor data convergence technology, and ④ AI data framework technology is required.

• Publications of The Korean Astronomical Society
• /
• v.27 no.4
• /
• pp.301-303
• /
• 2012

We present the result of our near infrared J- (${\lambda}=1.25{\mu}m$), H- (${\lambda}=1.63{\mu}m$), and $K_s$-band (${\lambda}=2.14{\mu}m$) imaging of ultraluminous ($L_{IR}$ > $10^{12}L_{\odot}$) and luminous ($L_{IR}=10^{11-12}L_{\odot}$) infrared galaxies (ULIRGs and LIRGs), to investigate their relationship through properties of their host galaxies. We find that (1) for single-nucleus ULIRGs and LIRGs, their spheroidal host galaxies have similar properties, but ULIRGs display a substantially higher level of nuclear activity than LIRGs, suggesting that their infrared luminosity difference comes primarily from the different level of current nuclear activity. We infer that LIRGs and ULIRGs have similar progenitor galaxies, follow similar evolutionary processes, and may evolve into optically-selected QSOs. (2) Largely-separated multiple-nuclei ULIRGs have significantly brighter host galaxies than single-nucleus ULIRGs and LIRGs in $K_s$-band, indicating that multiple-nuclei ULIRGs have a bias towards mergers of intrinsically large progenitor galaxies, in order to produce high infrared luminosity ($L_{IR}$ > $10^{12}L_{\odot}$) even at the early merging stage. (3) We derive dust extinction of host galaxies of ULIRGs and LIRGs to be $A_V$ ~ 14 mag in the optical or equivalently $A_K$ ~ 0.8 mag in the near-infrared $K_s$-band, based on the comparison of host galaxy's luminosities in the J-, H-, and $K_s$-bands.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.5
• /
• pp.354-365
• /
• 2015

This work presents an Internet of Things (IoT) system for home energy management based on a custom-designed Impulse Radio Ultra-Wideband (IR-UWB) transceiver that targets a generic and multi-standard control system. This control system enables the interoperability of heterogeneous devices: it integrates various sensor nodes based on ZigBee, EnOcean and UWB in the same middleware by utilizing an ad-hoc layer as an interface between the hardware and software. The paper presents as a first the design of the IR-UWB transceiver for a portable sensor node integrated with the middleware layer, and also describes the receiver connected to the control system. The custom-designed low-power transmitter on the sensor node is fabricated with 130 nm CMOS technology. It generates a signal with a 1.1 ns pulse width while consuming $39{\mu}W$ at 1 Mbps. The UWB sensor node with a temperature measurement capability consumes 5.31 mW, which is lower than the power level of state-of-the-art solutions for smart-home applications. The UWB hardware and software layers necessary to interface with the control system are verified in over-the-air measurements in an actual office environment. With the implementation of the presented sensor node and its integration in the energy management system, we demonstrate achievement of the broad flexibility demanded for IoT.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.9
• /
• pp.745-752
• /
• 2016

In the era of the Internet of Things, where all physical objects are connected to the Internet, we suggest a remote control system using a Raspberry Pi single-board computer with ZigBee, which can turn an indoor light-emitting diode (LED) and a multiple-tap on and off, and with a smart phone can control the brightness of the LED as well as an electronic door lock. By connecting an infrared (IR) transmitter module to the Raspberry Pi, we can control home appliances, such as an air conditioner, and we can also monitor indoor images, indoor temperatures, and illumination by using a smart phone app. We developed a method of finding out IR transmission codes required for remote-controllable appliances with an AVR micro-controller. We suggest a method to remotely open and shut an office door by novating the door lock. The brightness level of an LED (between 0 and 10) can be controlled through a PWM signal generated by an ATmega88 microcontroller. A mutiple-tap is controlled using an ATmega32, a photo-coupler, and a TRIAC. The signals for measured temperature and illumination are converted from analog to digital by using the ATtiny44A microcontroller transmitting to a Raspberry Pi through SPI communication. Then, we connect a camera to the CSI head of the Raspberry Pi. We can turn on the smart multiple-tap for a certain period of time, or we can schedule the multi-tap to turn on at a specific time. To reduce standby power, people usually pull out a power code from multiple-taps or turn off a switch. Our method helps people do the same thing with a smart phone, if they are away from home.

• Analyses & Alternatives
• /
• v.3 no.1
• /
• pp.29-61
• /
• 2019

Within the discipline of International Relations (IR), the literatures on global governance (GG) and great power management (GPM) at best ignore each other, and at worst treat the other as a rival or enemy. On the one hand, the GPM literature, like both realism in all its forms, and neoliberalism, takes for granted the ongoing, disproportionate influence of the great powers in the management of the international system/society, and does not look much beyond that. On the other hand, the GG literature emphasizes the roles of smaller states, non-state actors and intergovernmental organizations (IGOs), and tends to see great powers more as part of the problem than as part of the solution. This paper argues that the rise to prominence of a non-traditional security agenda, and particularly of human security, has triggered a de facto merger of GPM and GG that the IR literature usually treated as separate and often opposed theories. We use the Ebola crisis of 2014-15 to show how an issue framed as human security brought about a multi-actor response that combined the key elements of GPM and GG. The security framing overrode many of the usual inhibitions between great powers and non-state actors in humanitarian crises, including even the involvement of great power military forces. Through examining broadly the way in which the Ebola crisis is tackled, we argue that in an age of growing human security challenges, GPM and GG are necessarily and fruitfully merging. The role of great powers in this new human security environment is moving away from the simple means and ends of traditional GPM. Now, great powers require the ability to cooperate and coordinate with multiple-level actors to make the GG/GPM nexus more effective and sustainable. In doing so they can both provide crucial resources quickly, and earn respect and status as responsible great powers. IGOs provide legitimation and coordination to the GPM/GG package, and non-state actors (NSAs) provide information, specialist knowledge and personnel, and links into public engagement. In this way, the unique features of the Ebola crisis provide a model for how the merger of GPM and GG might be taken forward on other shared-fate threats facing global international society.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.12
• /
• pp.1207-1215
• /
• 2013

This paper proposes the location estimation techniques of distributed targets with the multi-sensor data perceived through IR sensors of the military robots in consideration of obstacles. In order to match up targets with measured azimuths, to add to the depth-first search (DFS) algorithms in free-obstacle environment, we suggest the expanded DFS (EDS) algorithm including bypass path search, partial path search, middle level ending, and the supplementation of decision metric. After matching up targets with azimuths, we estimate the coordinate of each target by obtaining the intersection point of the azimuths with the least square error (LSE) algorithm. The experimental results show the error rate of estimated location, mean number of calculating nodes, and mean distance between real coordinates and estimated coordinates of the proposed algorithms.

• Proceedings of the KSRS Conference
• /
• 2006.03a
• /
• pp.117-120
• /
• 2006

Heavy rainfall events are occurred exceedingly various forms by a complex interaction between synoptic, dynamic and atmospheric stability. As the results, quantitative precipitation forecast is extraordinary difficult because it happens locally in a short time and has a strong spatial and temporal variations. GOES-9 imagery data provides continuous observations of the clouds in time and space at the right resolution. In this study, an power-law type algorithm(KAE: Korea auto estimator) for estimating rainfall based on the rainfall type was developed using geostationary meteorological satellite data. GOES-9 imagery and automatic weather station(AWS) measurements data were used for the classification of rainfall types and the development of estimation algorithm. Subjective and objective classification of rainfall types using GOES-9 imagery data and AWS measurements data showed that most of heavy rainfalls are occurred by the convective and mired type. Statistical analysis between AWS rainfall and GOES-IR data according to the rainfall types showed that estimation of rainfall amount using satellite data could be possible only for the convective and mixed type rainfall. The quality of KAE in estimating the rainfall amount and rainfall area is similar or slightly superior to the National Environmental Satellite Data and Information Service's auto-estimator(NESDIS AE), especially for the multi cell convective and mixed type heavy rainfalls. Also the high estimated level is denoted on the mature stage as well as decaying stages of rainfall system.

• Korean Journal of Remote Sensing
• /
• v.22 no.3
• /
• pp.175-182
• /
• 2006

Because of the phenological variation of vegetation growth in temperate region, it is often difficult to accurately assess the surface conditions of agricultural croplands, grasslands, and disturbed forests by multi-spectral remote sensor data. In particular, the spectral similarity between soil and dry vegetation has been a primary problem to correctly appraise the surface conditions during the non-growing seasons in temperature region. This study analyzes the spectral characteristics of the mixture of dry vegetation and soil. The reflectance spectra were obtained from laboratory spectroradiometer measurement (GER-2600) and from EO-1 Hyperion image data. The reflectance spectra of several samples having different level of dry vegetation fractions show similar pattern from both lab measurement and hyperspectral image. Red-edge near 700nm and shortwave IR near 2,200nm are more sensitive to the fraction of dry vegetation. The use of hyperspectral data would allow us for better separation between bare soils and other surfaces covered by dry vegetation during the leaf-off season.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.23-45
• /
• 2020

Big data is creating in a wide variety of fields such as medical care, manufacturing, logistics, sales site, SNS, and the dataset characteristics are also diverse. In order to secure the competitiveness of companies, it is necessary to improve decision-making capacity using a classification algorithm. However, most of them do not have sufficient knowledge on what kind of classification algorithm is appropriate for a specific problem area. In other words, determining which classification algorithm is appropriate depending on the characteristics of the dataset was has been a task that required expertise and effort. This is because the relationship between the characteristics of datasets (called meta-features) and the performance of classification algorithms has not been fully understood. Moreover, there has been little research on meta-features reflecting the characteristics of multi-class. Therefore, the purpose of this study is to empirically analyze whether meta-features of multi-class datasets have a significant effect on the performance of classification algorithms. In this study, meta-features of multi-class datasets were identified into two factors, (the data structure and the data complexity,) and seven representative meta-features were selected. Among those, we included the Herfindahl-Hirschman Index (HHI), originally a market concentration measurement index, in the meta-features to replace IR(Imbalanced Ratio). Also, we developed a new index called Reverse ReLU Silhouette Score into the meta-feature set. Among the UCI Machine Learning Repository data, six representative datasets (Balance Scale, PageBlocks, Car Evaluation, User Knowledge-Modeling, Wine Quality(red), Contraceptive Method Choice) were selected. The class of each dataset was classified by using the classification algorithms (KNN, Logistic Regression, Nave Bayes, Random Forest, and SVM) selected in the study. For each dataset, we applied 10-fold cross validation method. 10% to 100% oversampling method is applied for each fold and meta-features of the dataset is measured. The meta-features selected are HHI, Number of Classes, Number of Features, Entropy, Reverse ReLU Silhouette Score, Nonlinearity of Linear Classifier, Hub Score. F1-score was selected as the dependent variable. As a result, the results of this study showed that the six meta-features including Reverse ReLU Silhouette Score and HHI proposed in this study have a significant effect on the classification performance. (1) The meta-features HHI proposed in this study was significant in the classification performance. (2) The number of variables has a significant effect on the classification performance, unlike the number of classes, but it has a positive effect. (3) The number of classes has a negative effect on the performance of classification. (4) Entropy has a significant effect on the performance of classification. (5) The Reverse ReLU Silhouette Score also significantly affects the classification performance at a significant level of 0.01. (6) The nonlinearity of linear classifiers has a significant negative effect on classification performance. In addition, the results of the analysis by the classification algorithms were also consistent. In the regression analysis by classification algorithm, Naïve Bayes algorithm does not have a significant effect on the number of variables unlike other classification algorithms. This study has two theoretical contributions: (1) two new meta-features (HHI, Reverse ReLU Silhouette score) was proved to be significant. (2) The effects of data characteristics on the performance of classification were investigated using meta-features. The practical contribution points (1) can be utilized in the development of classification algorithm recommendation system according to the characteristics of datasets. (2) Many data scientists are often testing by adjusting the parameters of the algorithm to find the optimal algorithm for the situation because the characteristics of the data are different. In this process, excessive waste of resources occurs due to hardware, cost, time, and manpower. This study is expected to be useful for machine learning, data mining researchers, practitioners, and machine learning-based system developers. The composition of this study consists of introduction, related research, research model, experiment, conclusion and discussion.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.2
• /
• pp.1-9
• /
• 2008

As the security requirements of mobile phones have been increasing, there have been extensive researches using one biometric feature (e.g., an iris, a fingerprint, or a face image) for authentication. Due to the limitation of uni-modal biometrics, we propose a method that combines face and iris images in order to improve accuracy in mobile environments. This paper presents four advantages and contributions over previous research. First, in order to capture both face and iris image at fast speed and simultaneously, we use a built-in conventional mega pixel camera in mobile phone, which is revised to capture the NIR (Near-InfraRed) face and iris image. Second, in order to increase the authentication accuracy of face and iris, we propose a score level fusion method based on SVM (Support Vector Machine). Third, to reduce the classification complexities of SVM and intra-variation of face and iris data, we normalize the input face and iris data, respectively. For face, a NIR illuminator and NIR passing filter on camera are used to reduce the illumination variance caused by environmental visible lighting and the consequent saturated region in face by the NIR illuminator is normalized by low processing logarithmic algorithm considering mobile phone. For iris, image transform into polar coordinate and iris code shifting are used for obtaining robust identification accuracy irrespective of image capturing condition. Fourth, to increase the processing speed on mobile phone, we use integer based face and iris authentication algorithms. Experimental results were tested with face and iris images by mega-pixel camera of mobile phone. It showed that the authentication accuracy using SVM was better than those of uni-modal (face or iris), SUM, MAX, NIN and weighted SUM rules.