• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.57-66
• /
• 2011

In this paper, it is proposed for algorithm to detect human efficiently using a edge symmetry and gradient directional characteristics in realtime by the feature extraction in a single input image. Proposed algorithm is composed of three stages, preprocessing, region partition of human candidates, verification of candidate regions. Here, preprocessing stage is strong the image regardless of the intensity and brightness of surrounding environment, also detects a contour with characteristics of human as considering the shape features size and the condition of human for characteristic of human. And stage for region partition of human candidates has separated the region with edge symmetry for human and size in the detected contour, also divided 1st candidates region with applying the adaboost algorithm. Finally, the candidate region verification stage makes excellent the performance for the false detection by verifying the candidate region using feature vector of a gradient for divided local area and classifier. The results of the simulations, which is applying the proposed algorithm, the processing speed of the proposed algorithms is improved approximately 1.7 times, also, the FNR(False Negative Rate) is confirmed to be better 3% than the conventional algorithm which is a single structure algorithm.

• Korean Journal of Radiology
• /
• v.22 no.6
• /
• pp.912-921
• /
• 2021

Objective: To compare the performance of the deep learning-based lesion detection algorithm (DLLD) in detecting liver metastasis with that of radiologists. Materials and Methods: This clinical retrospective study used 4386-slice computed tomography (CT) images and labels from a training cohort (502 patients with colorectal cancer [CRC] from November 2005 to December 2010) to train the DLLD for detecting liver metastasis, and used CT images of a validation cohort (40 patients with 99 liver metastatic lesions and 45 patients without liver metastasis from January 2011 to December 2011) for comparing the performance of the DLLD with that of readers (three abdominal radiologists and three radiology residents). For per-lesion binary classification, the sensitivity and false positives per patient were measured. Results: A total of 85 patients with CRC were included in the validation cohort. In the comparison based on per-lesion binary classification, the sensitivity of DLLD (81.82%, [81/99]) was comparable to that of abdominal radiologists (80.81%, p = 0.80) and radiology residents (79.46%, p = 0.57). However, the false positives per patient with DLLD (1.330) was higher than that of abdominal radiologists (0.357, p < 0.001) and radiology residents (0.667, p < 0.001). Conclusion: DLLD showed a sensitivity comparable to that of radiologists when detecting liver metastasis in patients initially diagnosed with CRC. However, the false positives of DLLD were higher than those of radiologists. Therefore, DLLD could serve as an assistant tool for detecting liver metastasis instead of a standalone diagnostic tool.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.1
• /
• pp.69-75
• /
• 2022

Due to the increase in the demand for anomaly detection according to the ageing of power generation facilities, the need for developing an anomaly detection method that can provide high-reliability turbine blade anomaly detection performance has been continuously raised. Additionally, the false detection results caused by a human error accelerates the increase of the need. In this paper, we propose an anomaly detection technique for turbine blades in power plants using deep neural networks. Experimental results prove that the proposed technique achieves stable anomaly detection performance while minimizing human factor intervention.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.193-196
• /
• 2009

Most of studies adopt a fixed skin color model to segment skin color region in a single image. The methods, however, result in low detection rates or high false positive error rates since the distribution of skin color is varies depending on the characteristics of input image. For the effective skin color segmentation, therefore, we need a adaptive skin color model which changes the model depending on the color distribution of input image. In this paper, we propose a novel adaptive skin color segmentation algorithm consisting of 2 stages which results in both high detection rate and low false positive error rate.

• Journal of Astronomy and Space Sciences
• /
• v.27 no.3
• /
• pp.245-252
• /
• 2010

Korea Astronomy and Space Science Institute (KASI) has developed a mobile satellite laser ranging (SLR) system called ARGO-M since 2008 for space geodesy research and precise orbit determination technologies using SLR with mm level accuracy. ARGO-M is capable of night tracking and daylight tracking for which requires spatial, spectral and time filters due to high background noises. In this study, characteristics and specifications of ARGO-M are discussed and its tracking capabilities of night and daylight tracking are analyzed for STSAT-2B and KOMPSAT-5 through link budget. Additionally false alarm and signal detection probabilities are also analyzed depending on spectral and time filters for daylight tracking for these satellites.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.9A
• /
• pp.714-721
• /
• 2005

In this parer, we analyze the preamble model in the OFDMA/TDD(OFDM-FDMA/Time Division Duplexing). Besides, under AWGN, ITU-R M.1225 Ped-B and Veh-A channel environments, we analyze capabilities of symbol timing & carrier frequency offset and performance of cell searching capabilities applied to OFDM/TDD system through computer simulation. The performance using Detection Probability, False Alarm Probability, Missing Probability, Mean Acquisition Time and MSE(Mean Square Error) is analyzed. Especially, in the case of symbol timing offset estimation, the preamble structure and its algorithm with enhanced performance are proposed and then compared with existing ones.

• The Bulletin of The Korean Astronomical Society
• /
• v.39 no.2
• /
• pp.107.1-107.1
• /
• 2014

We apply a machine learning algorithm, artificial neural network, to the search for gravitational-wave signals associated with short gamma-ray bursts. The multi-dimensional samples consisting of data corresponding to the statistical and physical quantities from the coherent search pipeline are fed into the artificial neural network to distinguish simulated gravitational-wave signals from background noise artifacts. Our result shows that the data classification efficiency at a fixed false alarm probability is improved by the artificial neural network in comparison to the conventional detection statistic. Therefore, this algorithm increases the distance at which a gravitational-wave signal could be observed in coincidence with a gamma-ray burst. We also evaluate the gravitational-wave data within a few seconds of the selected short gamma-ray bursts' event times using the trained networks and obtain the false alarm probability. We suggest that artificial neural network can be a complementary method to the conventional detection statistic for identifying gravitational-wave signals related to the short gamma-ray bursts.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.39 no.4
• /
• pp.403-408
• /
• 2002

In this paper, the performance on the PN code acquisition of DS/CDMA system was analyzed using the Nakagami-m probability density function considered fading environment. The equations on detection probability, $P_D$ and false alarm probability, ($P_{FA}$, decision variables affecting the PN code acquisition time were derived and proved using simulation in order to analyze the performance. In conclusion, It was necessary increasing the gain of PLL for correcting phase errors and improving the acquisition performance of PN code in apply to the rake receiver.

• Journal of the Optical Society of Korea
• /
• v.20 no.1
• /
• pp.150-155
• /
• 2016

To evaluate the autofocusing performance of recent mobile phone cameras, it is necessary to determine the peak position of the center field MTF (Modulation Transfer Function), -known as the through focus MTF- of the module. However, the MTF peak position found by conventional methods deviates from the ideal position due to the focus scanning resolution of mobile phone cameras. This inaccurate peak position results in false judgements of the optical performance, leading to yield losses or customer complaints. An increase in the focus scanning resolution can address this problem, but the manufacturing UPH (Unit per Hour) level will also unfortunately increase as well, resulting in a loss of manufacturing capabilities. In this paper, several fitting models are studied to find an accurate MTF peak position within a short period of time. With an analysis of a large amount of manufacturing data, it is demonstrated that the fitting methods can reduce false judgements and simultaneously increase the capabilities of the manufacturing system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.12
• /
• pp.5249-5267
• /
• 2016

Cognitive radio is an efficient technique to improve spectrum efficiency and relieve the pressure of spectrum resources. In this paper, we investigate the spectrum sensing period in cooperative relay cognitive radio networks; analyze the relationship between the available capacity and the signal-to-noise ratio of the received signal of second users, the target probability of detection and the active probability of primary users. Finally, we derive the closed form expression of the optimal spectrum sensing period in terms of maximum throughput. We simulate the probability of false alarm and available capacity of cognitive radio networks and compare optimal spectrum sensing period scheme with fixed sensing period one in these performance. Simulation results show that the optimal sensing period makes the cognitive networks achieve the higher throughput and better spectrum sensing performance than the fixed sensing period does. Cooperative relay cognitive radio networks with optimal spectrum sensing period can achieve the high capacity and steady probability of false alarm in different target probability of detection. It provides a valuable reference for choosing the optimal spectrum sensing period in cooperative relay cognitive radio networks.