• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.705-708
• /
• 2023

다중밀집 사고를 사전에 방지하기 위해 군중 밀집도를 정확하게 파악하는 것은 중요하다. 기존 방법 중 일부는 군중 계수를 기반으로 군중 밀집도를 추정하거나 원근 왜곡이 있는 데이터를 그대로 학습한다. 이 방식은 물체의 거리에 따라 크기가 달라지는 원근 왜곡에 큰 영향을 받는다. 본 연구는 보행자 깊이 정보를 이용한 군중 밀집도 알고리즘을 제안한다. 보행자의 깊이 정보를 계산하기 위해 편차가 적은 머리 크기를 이용한다. 머리를 탐지하기 위해 OC-Sort를 학습모델로 사용한다. 탐지된 머리의 경계박스 좌표, 실제 머리 크기, 카메라 파라미터 등을 이용하여 보행자의 깊이 정보를 추정한다. 이후 깊이 정보를 기반으로 밀도 맵을 추정한다. 제안 알고리즘은 혼잡한 환경에서 객체의 위치와 밀집도를 정확하게 분석하여 군중밀집 사고를 사전에 방지하는 지능형 CCTV시스템의 기반 기술로 활용될 수 있으며, 더불어 보안 및 교통 관리 시스템의 효율성을 향상하는 데 중요한 역할을 할 것으로 기대한다.

• Journal of Korean Society of Transportation
• /
• v.35 no.3
• /
• pp.247-259
• /
• 2017

This study analyzed the network of low cost carriers (LCCs) to investigate the structural characteristics of airport networks. 71 LCCs in Asian major airports from January 2010 to January 2016 were queried from the SRS Analyzer Schedule Database of IATA's Airport Intelligence Service, and analyzed international routes excluding domestic flights. We analyzed the network connection mechanism focusing on Incheon International Airport, Hong Kong, Singapore, Narita, Kansai, Pudong, Kaohsiung, Gimpo and Jeju airports as well as structural changes in the LCC network using four centrality analysis concepts. The outcomes showed that the LCC network is formed in these airports and the density of connectivity to other airports increased. In recent years, LCC has launched LCCs-Alliances and would be considered to operate a hub-and-spoke network.

• Journal of Radiation Protection and Research
• /
• v.46 no.4
• /
• pp.204-212
• /
• 2021

Background: Identification of radioisotopes for plastic scintillation detectors is challenging because their spectra have poor energy resolutions and lack photo peaks. To overcome this weakness, many researchers have conducted radioisotope identification studies using machine learning algorithms; however, the effect of data normalization on radioisotope identification has not been addressed yet. Furthermore, studies on machine learning-based radioisotope identifiers for plastic scintillation detectors are limited. Materials and Methods: In this study, machine learning-based radioisotope identifiers were implemented, and their performances according to data normalization methods were compared. Eight classes of radioisotopes consisting of combinations of ²²Na, ⁶⁰Co, and ¹³⁷Cs, and the background, were defined. The training set was generated by the random sampling technique based on probabilistic density functions acquired by experiments and simulations, and test set was acquired by experiments. Support vector machine (SVM), artificial neural network (ANN), and convolutional neural network (CNN) were implemented as radioisotope identifiers with six data normalization methods, and trained using the generated training set. Results and Discussion: The implemented identifiers were evaluated by test sets acquired by experiments with and without gain shifts to confirm the robustness of the identifiers against the gain shift effect. Among the three machine learning-based radioisotope identifiers, prediction accuracy followed the order SVM > ANN > CNN, while the training time followed the order SVM > ANN > CNN. Conclusion: The prediction accuracy for the combined test sets was highest with the SVM. The CNN exhibited a minimum variation in prediction accuracy for each class, even though it had the lowest prediction accuracy for the combined test sets among three identifiers. The SVM exhibited the highest prediction accuracy for the combined test sets, and its training time was the shortest among three identifiers.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.11-20
• /
• 2024

Among the generative models in Artificial Intelligence (AI), especially Generative Adversarial Network (GAN) has been successful in various applications such as image processing, density estimation, and style transfer. While the GAN models including Conditional GAN (CGAN), CycleGAN, BigGAN, have been extended and improved, researchers face challenges in real-world applications in specific domains such as disaster simulation, healthcare, and urban planning due to data scarcity and unstable learning causing Image distortion. This paper proposes a new progressive learning methodology called Progressive Step Training (PST) based on the Auxiliary Classifier GAN (ACGAN) that discriminates class labels, leveraging the progressive learning approach of the Progressive Growing of GAN (PGGAN). The PST model achieves 70.82% faster stabilization, 51.3% lower standard deviation, stable convergence of loss values in the later high resolution stages, and a 94.6% faster loss reduction compared to conventional methods.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.22 no.3
• /
• pp.303-309
• /
• 2004

In this paper, an adaptive Bayesian approach to image segmentation was developed for boundary detection. Both image intensities and texture information were used for obtaining better quality of the image segmentation by using the C programming language. Fuzzy c-mean clustering was applied fer the conditional probability density function, and Gibbs random field model was used for the prior probability density function. To simply test the algorithm, a synthetic image (256$\times$256) with a set of low gray values (50, 100, 150 and 200) was created and normalized between 0 and 1 n double precision. Results have been presented that demonstrate the effectiveness of the algorithm in segmenting the synthetic image, resulting in more than 99% accuracy when noise characteristics are correctly modeled. The algorithm was applied to the Antarctic mosaic that was generated using 1963 Declassified Intelligence Satellite Photographs. The accuracy of the resulting vector map was estimated about 300-m.

• Parasites, Hosts and Diseases
• /
• v.57 no.6
• /
• pp.681-690
• /
• 2019

The infection status of digenetic trematode metacercariae (DTM) was investigated in fishes from coastal lakes in Gangwon-do, the Republic of Korea (Korea). All fishes collected in 5 lakes were examined with the artificial digestion method. More than 10 species, i.e., Metagonimus spp., Pygidiopsis summa, Centrocestus armatus, Metorchis orientalis, M. taiwanensis, Clinostomum complanatum, Echinostoma spp., Stictodora spp., Diplostomum sp. and Diplostomid No. 1. by Morita (1960), of DTM were detected in fishes from 5 coastal lakes in Gangwon-do. Metagonimus spp. metacercariae were found in 52 (41.3%) out of 126 sea rundace, Tribolodon hakonensis, from 5 lakes, and their density was 14.6 per fish infected. P. summa metacercariae were detected in 48 (84.2%) out of 57 mullets from 5 lakes, and their density was 316 per fish infected. C. armatus metacercariae were detected in 7 (14.6%) T. hakonensis and 3 (15.0%) Tridentiger brevispinis from Hyang-ho, and 5 (19.2%) Acanthogobius flavimanus from Gyeongpo-ho. Stictodora spp. metacercariae were found in 4 fish species, i.e., Tridentiger obscurus, Tridentiger trigonocephalus, Chelon haematocheilus, and Acanthogobius lactipes, from Gyeongpo-ho. Total 15 C. complanatum metacercariae were detected in 2 (9.1%) crucian carp, Carassius auratus, from Songji-ho. M. taiwanensis metacercariae were found in T. hakonensis from Hyang-ho and Gyeongpo-ho and in Pseudorasbora parva from Gyeongpo-ho. Total 11 M. orientalis metacercariae were detected in 3 (6.3%) T. hakonensis from Hyang-ho. From the above results, it was confirmed that various species of DTM are infected in fishes from coastal lakes in Gangwon-do, Korea.

• Journal of Internet Computing and Services
• /
• v.14 no.2
• /
• pp.25-34
• /
• 2013

In this paper, we propose an activity-performer bipartite matrix generation algorithm for analyzing workflow-supported human-resource affiliations in a workflow model. The workflow-supported human-resource means that all performers of the organization managed by a workflow management system have to be affiliated with a certain set of activities in enacting the corresponding workflow model. We define an activity-performer affiliation network model that is a special type of social networks representing affiliation relationships between a group of performers and a group of activities in workflow models. The algorithm proposed in this paper generates a bipartite matrix from the activity-performer affiliation network model(APANM). Eventually, the generated activity-performer bipartite matrix can be used to analyze social network properties such as, centrality, density, and correlation, and to enable the organization to obtain the workflow-supported human-resource affiliations knowledge.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.15-21
• /
• 2018

In this study, we try to detect anomalies on the network intrusion detection system by learning only one class. We use KDD CUP 1999 dataset, an intrusion detection dataset, which is used to evaluate classification performance. One class classification is one of unsupervised learning methods that classifies attack class by learning only normal class. When using unsupervised learning, it difficult to achieve relatively high classification efficiency because it does not use negative instances for learning. However, unsupervised learning has the advantage for classifying unlabeled data. In this study, we use one class classifiers based on support vector machines and density estimation to detect new unknown attacks. The test using the classifier based on density estimation has shown relatively better performance and has a detection rate of about 96% while maintaining a low FPR for the new attacks.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.905-912
• /
• 2022

Virtual reality, one of the core technologies of the 4th industrial revolution, is entering a new phase with the spread of low-cost wearable devices represented by Oculus. In the case of disaster evacuation drills, where practical training is almost impossible due to the risk of accidents, virtual reality is becoming a new alternative that enables effective training. In this paper, we propose a smoke modeling method that can be applied to fire evacuation drills implemented with virtual reality technology. In the event of a fire, smoke spreads along the aisle, and the density of the smoke changes over time. The proposed method models the smoke by applying a procedural function that can reflect the density of smoke calculated through simulation to the model in real-time. Implementation results in the background of the factory show that the proposed method produces models that can express the smoke according to the user's movement.

• Imaging Science in Dentistry
• /
• v.52 no.4
• /
• pp.393-398
• /
• 2022

Purpose: This study proposed a generative adversarial network (GAN) model for T2-weighted image (WI) synthesis from proton density (PD)-WI in a temporomandibular joint(TMJ) magnetic resonance imaging (MRI) protocol. Materials and Methods: From January to November 2019, MRI scans for TMJ were reviewed and 308 imaging sets were collected. For training, 277 pairs of PD- and T2-WI sagittal TMJ images were used. Transfer learning of the pix2pix GAN model was utilized to generate T2-WI from PD-WI. Model performance was evaluated with the structural similarity index map (SSIM) and peak signal-to-noise ratio (PSNR) indices for 31 predicted T2-WI (pT2). The disc position was clinically diagnosed as anterior disc displacement with or without reduction, and joint effusion as present or absent. The true T2-WI-based diagnosis was regarded as the gold standard, to which pT2-based diagnoses were compared using Cohen's ĸ coefficient. Results: The mean SSIM and PSNR values were 0.4781(±0.0522) and 21.30(±1.51) dB, respectively. The pT2 protocol showed almost perfect agreement(ĸ=0.81) with the gold standard for disc position. The number of discordant cases was higher for normal disc position (17%) than for anterior displacement with reduction (2%) or without reduction (10%). The effusion diagnosis also showed almost perfect agreement(ĸ=0.88), with higher concordance for the presence (85%) than for the absence (77%) of effusion. Conclusion: The application of pT2 images for a TMJ MRI protocol useful for diagnosis, although the image quality of pT2 was not fully satisfactory. Further research is expected to enhance pT2 quality.