• Journal of Internet Computing and Services
• /
• v.22 no.5
• /
• pp.27-33
• /
• 2021

With the broad adoption of the Internet of Things (IoT) in a variety of scenarios and application services, management and orchestration entities require upgrading the traditional architecture and develop intelligent models with ultra-reliable methods. In a heterogeneous network environment, mission-critical IoT applications are significant to consider. With erroneous priorities and high failure rates, catastrophic losses in terms of human lives, great business assets, and privacy leakage will occur in emergent scenarios. In this paper, an efficient resource slicing scheme for optimizing federated learning in software-defined IoT (SDIoT) is proposed. The decentralized support vector regression (SVR) based controllers predict the IoT slices via packet inspection data during peak hour central congestion to achieve a time-sensitive condition. In off-peak hour intervals, a centralized deep neural networks (DNN) model is used within computation-intensive aspects on fine-grained slicing and remodified decentralized controller outputs. With known slice and prioritization, federated learning communications iteratively process through the adjusted resources by virtual network functions forwarding graph (VNFFG) descriptor set up in software-defined networking (SDN) and network functions virtualization (NFV) enabled architecture. To demonstrate the theoretical approach, Mininet emulator was conducted to evaluate between reference and proposed schemes by capturing the key Quality of Service (QoS) performance metrics.

• Journal of Internet Computing and Services
• /
• v.22 no.3
• /
• pp.37-43
• /
• 2021

In this paper, we study how objects from front and back cameras can be recognized in real time in a mobile environment to segment regions of object pixels and synthesize them through image processing. To this work, we applied DeepLabV3 machine learning model to dual cameras provided by Apple's iOS. We also propose methods using Core Image and Core Graphics libraries from Apple for image synthesis and postprocessing. Furthermore, we improved CPU usage than previous works and compared the throughput rates and results of Depth and DeepLabV3. Finally, We also developed a camera application using these two methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.1
• /
• pp.280-294
• /
• 2023

Unmanned aerial vehicles (UAVs) and millimeter-wave frequencies play key roles in supporting 5G wireless communication systems. They expand the field of wireless communication by increasing the data capacities of communication systems and supporting high data rates. However, short wavelengths, owing to the high millimeter-wave frequencies can cause problems, such as signal attenuation and path loss. To address these limitations, research on high directional beamforming technologies continue to garner interest. Furthermore, owing to the mobility of the UAVs, it is essential to track the beam angle accurately to obtain full beamforming gain. This study presents a beam tracking method based on the unscented Kalman filter using hybrid beamforming. The simulation results reveal that the proposed beam tracking scheme improves the overall performance in terms of the mean-squared error and spectral efficiency. In addition, by expanding analog beamforming to hybrid beamforming, the proposed algorithm can be used even in multi-user and multi-stream environments to increase data capacity, thereby increasing utilization in new-radio multiple-input multiple-output orthogonal frequency-division multiplexing systems.

• ETRI Journal
• /
• v.45 no.1
• /
• pp.163-170
• /
• 2023

We report an electroabsorption modulator (EAM)-integrated distributed Bragg reflector laser diode (DBR-LD) capable of supporting a high data rate and a wide wavelength tuning. The DBR-LD contains two tuning elements, plasma and heater tunings, both of which are implemented in the DBR section, which have blue-shift and red-shift in the Bragg wavelength through a current injection, respectively. The light created from the DBR-LD is intensity-modulated through the EAM voltage, which is integrated monolithically with the DBRLD using a butt-joint coupling method. The fabricated chip shows a threshold current of approximately 8 mA, tuning range of greater than 30 nm, and static extinction ratio of higher than 20 dB while maintaining a side mode suppression ratio of greater than 40 dB under a window of 1550 nm. To evaluate its modulation properties, the chip was bonded onto a mount including a radiofrequency line and a load resistor showing clear eye openings at data rates of 25 Gb/s nonreturn-to-zero and 50 Gb/s pulse amplitude modulation 4-level, respectively.

• Korean Journal of Ecology and Environment
• /
• v.52 no.3
• /
• pp.202-209
• /
• 2019

The primary productivity and production rate of photosynthetic pigment of periphyton and phytoplankton were estimated using a $^{13}C$ stable labeling technique in May 2011, in the waterfront of Lake Paldang. Primary productivity of periphyton ($28.15mgC\;m^{-2}\;d^{-1}$) was higher than phytoplankton production ($0.14mgC\;m^{-2}\;d^{-1}$). The net production rates of photosynthetic pigments(Chl a and Fucoxanthin) of periphyton were $2.53ngC\;m^{-2}\;d^{-1}$ and $0.12ngC\;m^{-2}\;d^{-1}$, respectively. On the other hand, the net production rate of pigments on phytoplankton (Chl a : $0.023ngC\;m^{-2}\;d^{-1}$, Fucoxanthin: $0.002ngC\;m^{-2}\;d^{-1}$) was lower than that of periphyton. Specific production rates of individual pigments of phytoplankton to the total primary productivity indicate the predominance of diatom (Fucoxanthin) species in phytoplankton assemblage in Lake Paldang. The net individual production rate of pigments by $^{13}C$ tracer was a useful tool to estimate the contribution of each phytoplankton class for total primary productivity, and it is possible to calculate the seasonal contribution of each phytoplankton class to the total primary productivity in the aquatic ecosystems. This study is the first report on photosynthetic pigment production rates of periphyton and phytoplankton.

• Journal of Korea Water Resources Association
• /
• v.55 no.8
• /
• pp.565-575
• /
• 2022

Recently, in the field of water resource engineering, interest in predicting time series water levels and flow rates using deep learning technology that has rapidly developed along with the Fourth Industrial Revolution is increasing. In addition, although water-level and flow-rate prediction have been performed using the Long Short-Term Memory (LSTM) model and Gated Recurrent Unit (GRU) model that can predict time-series data, the accuracy of flow-rate prediction in rivers with rapid temporal fluctuations was predicted to be very low compared to that of water-level prediction. In this study, the Paldang Bridge Station of the Han River, which has a large flow-rate fluctuation and little influence from tidal waves in the estuary, was selected. In addition, time-series data with large flow fluctuations were selected to collect water-level and flow-rate data for 2 years and 7 months, which are relatively short in data length, to be used as training and prediction data for the LSTM and GRU models. When learning time-series water levels with very high time fluctuation in two models, the predicted water-level results in both models secured appropriate accuracy compared to observation water levels, but when training rapidly temporal fluctuation flow rates directly in two models, the predicted flow rates deteriorated significantly. Therefore, in this study, in order to accurately predict the rapidly changing flow rate, the water-level data predicted by the two models could be used as input data for the rating curve to significantly improve the prediction accuracy of the flow rates. Finally, the results of this study are expected to be sufficiently used as the data of flood warning system in urban rivers where the observation length of hydrological data is not relatively long and the flow-rate changes rapidly.

• Journal of the Korea Convergence Society
• /
• v.7 no.6
• /
• pp.7-11
• /
• 2016

Voice recognition systems which use a white noise and voice recognition environment are not correct voice recognition with variable voice mixture. Therefore in this paper, we propose a method using the convergence of Bayesian technique and selecting voice for effective voice recognition. we make use of bank frequency response coefficient for selective voice extraction, Using variables observed for the combination of all the possible two observations for this purpose, and has an voice signal noise information to the speech characteristic extraction selectively is obtained by the energy ratio on the output. It provide a noise elimination and recognition rates are improved with combine voice recognition of bayesian methode. The result which we confirmed that the recognition rate of 2.3% is higher than HMM and CHMM methods in vocabulary recognition, respectively.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.10
• /
• pp.7189-7195
• /
• 2015

The method of moments (MoM) is implemented to simulate scattering from a PEC (perfectly electric conductor) cylinder in the TE(transversw electric) EFIE (Electric Field Integral Equation) approach. The procedure expresses the singularity integral and the hypersingularity integral in terms of an analytic function and employs a singularity isolation process coupled with numerical technique along the discretized segment to evaluate the self terms. It is known that, in the MoM technique, the choice of base functions and test functions is very important for the accuracy and convergence of the numerical analysis. Thus, in this paper, three conditions, obtained from the combination of basis functions and test functions, are adopted to get the induced currents on the PEC surface. These currents are compared to the analytical one in the relative rms current error to get the condition that shows fast convergence rate. The fast order of convergence of the current error, 2.528, is obtained under the combination of pulse basis function/delta test function.

• Journal of Digital Convergence
• /
• v.13 no.9
• /
• pp.323-332
• /
• 2015

This paper examines the level of the primary care continuity for patients with high blood pressure and the effects of the primary care continuity on their convergence health outcomes. We conducted a retrospective cohort study. A total of 315,791 patients who had received new diagnoses of hypertension. We determined standard indices of continuity of care-MFPC, MMCI, and COC and evaluated their association with study outcomes over three years of follow-up. Outcome measures included hospitalization and emergency room visits. The result of the primary care continuity levels and hazard ratios of health outcome showed that, comparing continuity group, non-continuity group had higher rates of hospitalization by 1.655(95% CI: 1.547-1.771) and emergency room visits by 1.669(95% CI: 1.465-1.903). This paper argues that medical costs of chronic diseases will reduce if low continuity of care turns into high continuity of care.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.24 no.5
• /
• pp.15-23
• /
• 2021

This study was carried out to suggest an appropriate plant combination by evaluating the growth of flowering ground-cover plants planted with Festuca glauca 'Eljiah Blue' on the roof-top environment. As for the plant materials, Allium senescens and Chrysanthemum coreanum which are shorter than Festuca glauca 'Eljiah Blue' and Sedum takesimense and Agastache rugosa which are taller than Festuca glauca 'Eljiah Blue' were selected. Festuca glauca 'Eljiah Blue' was planted on Conrol, and Festuca glauca 'Eljiah Blue' with Allium senescens (T1), Festuca glauca 'Eljiah Blue' with Sedum takesimense (T2), Festuca glauca 'Eljiah Blue' with Agastache rugosa(T3), and Festuca glauca 'Eljiah Blue' with Chrysanthemum coreanum (T4) were planted in each experimental plot. Plant height and covering rate were measured to evaluate the growth of Festuca glauca 'Eljiah Blue'. Also, relative growth rate (RGR) of plant height, RGR of plant width, and mortality rate of the flowering ground-cover plants were estimated. Plant height and cover rate of Festuca glauca 'Eljiah Blue' was greatest in T3. RGR of plant height was greater in the order of Agastache rugosa, Allium senescens, Chrysanthemum coreanum, and Sedum takesimense. In particular, RGR of plant width was also greatest for Agastache rugosa. Mortality rates of Agastache rugosa and Allium senescens were lowest at 11%. Therefore, based on good growth of Festuca glauca 'Eljiah Blue' planted with Agastache rugosa, these results were suggested as a desirable combination of plant species for rooftop gardening.