Virtual Scenarios of Earthquake Early Warning to Disaster Management in Smart Cities Based on Auxiliary Classifier Generative Adversarial Networks.

Effective response strategies to earthquake disasters are crucial for disaster management in smart cities. However, in regions where earthquakes do not occur frequently, model construction may be difficult due to a lack of training data. To address this issue, there is a need for technology that can generate earthquake scenarios for response training at any location. We proposed a model for generating earthquake scenarios using an auxiliary classifier Generative Adversarial Network (AC-GAN)-based data synthesis. The proposed ACGAN model generates various earthquake scenarios by incorporating an auxiliary classifier learning process into the discriminator of GAN. Our results at borehole sensors showed that the seismic data generated by the proposed model had similar characteristics to actual data. To further validate our results, we compared the generated IM (such as PGA, PGV, and SA) with Ground Motion Prediction Equations (GMPE). Furthermore, we evaluated the potential of using the generated scenarios for earthquake early warning training. The proposed model and algorithm have significant potential in advancing seismic analysis and detection management systems, and also contribute to disaster management.

Seismic Data Augmentation Based on Conditional Generative Adversarial Networks.

Realistic synthetic data can be useful for data augmentation when training deep learning models to improve seismological detection and classification performance. In recent years, various deep learning techniques have been successfully applied in modern seismology. Due to the performance of deep learning depends on a sufficient volume of data, the data augmentation technique as a data-space solution is widely utilized. In this paper, we propose a Generative Adversarial Networks (GANs) based model that uses conditional knowledge to generate high-quality seismic waveforms. Unlike the existing method of generating samples directly from noise, the proposed method generates synthetic samples based on the statistical characteristics of real seismic waveforms in embedding space. Moreover, a content loss is added to relate high-level features extracted by a pre-trained model to the objective function to enhance the quality of the synthetic data. The classification accuracy is increased from 96.84% to 97.92% after mixing a certain amount of synthetic seismic waveforms, and results of the quality of seismic characteristics derived from the representative experiment show that the proposed model provides an effective structure for generating high-quality synthetic seismic waveforms. Thus, the proposed model is experimentally validated as a promising approach to realistic high-quality seismic waveform data augmentation.

Precipitable Water Vapor Retrieval from Shipborne GNSS Observations on the Korean Research Vessel ISABU.

We estimate precipitable water vapor (PWV) from data collected by the low-cost Global Navigation Satellite System (GNSS) receiver at a vessel. The dual-frequency GNSS receiver that the vessel ISABU is equipped with that is operated by the Korea Institute of Ocean Science and Technology. The ISABU served in the Pacific Ocean for scientific research during a period from August 30 to September 21, 2018. It also performs radiosonde observations to obtain a vertical profile of troposphere on the vessel's path. The GNSS-derived PWV is compared to radiosonde observations and the Atmospheric Infrared Sounder (AIRS) on NASA's Aqua satellite output. A bias and root-mean-square (RMS) error between shipborne GNSS-PWV and radiosonde-PWV were -1.48 and 5.22 mm, respectively. When compared to the ground GNSS-PWV, shipborne GNSS-PWV has a relatively large RMS error in comparison with radiosonde-PWV. However, the GNSS observations on the vessel are still in good agreement with radiosonde observations. On the other hand, the GNSS-PWV is not well linearly correlated with AIRS-PWV. The RMS error between the two observations was approximately 8.97 mm. In addition, we showed that the vessel on the sea surface has significantly larger carrier phase multipath error compared to the ground-based GNSS observations. This also can result in reducing the accuracy of shipborne GNSS-PWV. However, we suggest that the shipborne GNSS has sufficient potential to derive PWV with the kinematic precise point positioning (PPP) solution on the vessel.

Anti-osteoporotic effects of mixed compositions of extracellular polymers isolated from Aureobasidium pullulans and Textoria morbifera in ovariectomized mice.

BACKGROUND: Extracellular polymeric substances isolated from Aureobasidium pullulans (EAP), containing specifically 13% ß-1,3/1,6-glucan, have shown various favorable bone-preserving effects. Textoria morbifera Nakai (TM) tree has been used as an ingredient in traditional medicine and tea for various pharmacological purposes. Thus, the present study was aimed to examine the synergistic anti-osteoporotic potential of mixtures containing different proportions of EAP and TM compared with that of the single formulations of each herbal extract using bilateral ovariectomized (OVX) mice, a renowned rodent model for studying human osteoporosis. METHODS: Thirty five days after bilateral-OVX surgery, 9 combinations of EAP:TM (ratios = 1:1, 1:3, 1:5, 1:7, 1:9, 3:1, 5:1, 7:1, 9:1) and single separate formulations of EAP or TM were supplied orally, once a day for 35 days at a final concentration of 200 mg/kg. Variations in body weight gains during the experimental periods, as well as femur weights, bone mineral density (BMD), bone strength (failure load), and mineral content (calcium [Ca] and inorganic phosphorus [IP]) following sacrifice were measured. Furthermore, histomorphometric and histological profile analyses of serum biochemical parameters (osteocalcin content and bone specific alkaline phosphatase [bALP] activity) were conducted following sacrifice. Femurs histomorphometric analyses were also conducted for bone resorption, structure and mass. The results for the mixed formulations of EAP:TM and separate formulations were compared with those of risedronate sodium (RES). RESULTS: The EAP:TM (3:1) formulation synergistically enhanced the anti-osteoporotic potential of individual EAP or TM formulations, possibly due to enhanced variety of the active ingredients. Furthermore, the effects of EAP:TM were comparable to those of RES (2.5 mg/kg) treatment. CONCLUSION: The results of this study suggest that, the EAP:TM (3:1) combination might act as a new pharmaceutical agent and/or health functional food substance for curing osteoporosis in menopausal women.

Robust Target Tracking with Multi-Static Sensors under Insufficient TDOA Information.

This paper focuses on underwater target tracking based on a multi-static sonar network composed of passive sonobuoys and an active ping. In the multi-static sonar network, the location of the target can be estimated using TDOA (Time Difference of Arrival) measurements. However, since the sensor network may obtain insufficient and inaccurate TDOA measurements due to ambient noise and other harsh underwater conditions, target tracking performance can be significantly degraded. We propose a robust target tracking algorithm designed to operate in such a scenario. First, track management with track splitting is applied to reduce performance degradation caused by insufficient measurements. Second, a target location is estimated by a fusion of multiple TDOA measurements using a Gaussian Mixture Model (GMM). In addition, the target trajectory is refined by conducting a stack-based data association method based on multiple-frames measurements in order to more accurately estimate target trajectory. The effectiveness of the proposed method is verified through simulations.

Online multi-object tracking with efficient track drift and fragmentation handling.

This paper addresses the problem of multi-object tracking in complex scenes by a single, static, uncalibrated camera. Tracking-by-detection is a widely used approach for multi-object tracking. Challenges still remain in complex scenes, however, when this approach has to deal with occlusions, unreliable detections (e.g., inaccurate position/size, false positives, or false negatives), and sudden object motion/appearance changes, among other issues. To handle these problems, this paper presents a novel online multi-object tracking method, which can be fully applied to real-time applications. First, an object tracking process based on frame-by-frame association with a novel affinity model and an appearance update that does not rely on online learning is proposed to effectively and rapidly assign detections to tracks. Second, a two-stage drift handling method with novel track confidence is proposed to correct drifting tracks caused by the abrupt motion change of objects under occlusion and prolonged inaccurate detections. In addition, a fragmentation handling method based on a track-to-track association is proposed to solve the problem in which an object trajectory is broken into several tracks due to long-term occlusions. Based on experimental results derived from challenging public data sets, the proposed method delivers an impressive performance compared with other state-of-the-art methods. Furthermore, additional performance analysis demonstrates the effect and usefulness of each component of the proposed method.