• Korean Journal of Artificial Intelligence
• /
• v.12 no.3
• /
• pp.1-7
• /
• 2024

In this paper, we propose an innovative super-resolution technique to address the issue of reduced accuracy in license plate recognition caused by low-resolution images. Conventional vehicle license plate recognition systems have relied on images obtained from fixed surveillance cameras for traffic detection to perform vehicle detection, tracking, and license plate recognition. However, during this process, image quality degradation occurred due to the physical distance between the camera and the vehicle, vehicle movement, and external environmental factors such as weather and lighting conditions. In particular, the acquisition of low-resolution images due to camera performance limitations has been a major cause of significantly reduced accuracy in license plate recognition. To solve this problem, we propose a Single Image Super-Resolution (SISR) model with a parallel structure that combines Multi-Scale and Attention Mechanism. This model is capable of effectively extracting features at various scales and focusing on important areas. Specifically, it generates feature maps of various sizes through a multi-branch structure and emphasizes the key features of license plates using an Attention Mechanism. Experimental results show that the proposed model demonstrates significantly improved recognition accuracy compared to existing vehicle license plate super-resolution methods using Bicubic Interpolation.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.10
• /
• pp.513-519
• /
• 2024

Advancements in artificial intelligence(AI) have significantly improved deep learning-based audio deepfake technology, which has been exploited for criminal activities. To detect audio deepfake, we propose CoNSIST, an advanced audio deepfake detection model. CoNSIST builds on AASIST, which a graph-based end-to-end model, by integrating three key components: Squeeze and Excitation, Positional Encoding, and Reformulated HS-GAL. These additions aim to enhance feature extraction, eliminate unnecessary operations, and incorporate diverse information. Our experimental results demonstrate that CoNSIST significantly outperforms existing models in detecting audio deepfakes, offering a more robust solution to combat the misuse of this technology.

• BMB Reports
• /
• v.39 no.1
• /
• pp.9-15
• /
• 2006

To prove whether error catastrophe /lethal mutagenesis is the primary antiviral mechanism of action of ribavirin against foot-and-mouth disease virus (FMDV). Ribavirin passage experiments were performed and supernatants of $Rp_1$ to $Rp_5$ were harvested. Morphological alterations as well as the levels of viral RNAs, proteins, and infectious particles in the BHK-21 cells infected using the supernatants of $Rp_1$ to $Rp_5$ and control were measured by microscope, real-time RT-PCR, western-blotting and plaque assays, respectively. The mutation frequency was measured by sequencing the complete P1- and 3D-encoding region of FMDV after a single round of virus infection from ribavirin-treated or untreated FMDV-infected cells. Ribavirin treatment for FMDV caused dramatically inhibition of multiplication in cell cultures. The levels of viral RNAs, proteins, and infectious particles in the BHK-21 cells infected were more greatly reduced along with the passage from $Rp_1$ to $Rp_5$, moreover, nucleocapsid protein could not be detected and no recovery of infectious virus in the supernatant or detection of intracellular viral RNA was observed at the $Rp_5$-infected cells. A high mutation rate, giving rise to an 8-and 11-fold increase in mutagenesis and resulting in some amino acid substitutions, was found in viral RNA synthesized at a single round of virus infection in the presence of ribavirin of $1000\;{\mu}M$ and caused a 99.7% loss in viral infectivity in contrast with parallel untreated control virus. These results suggest that the antiviral molecular mechanism of ribavirin is based on the lethal mutagenesis/error catastrophe, that is, the ribavirin is not merely an antiviral reagent but also an effective mutagen.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.11
• /
• pp.6697-6701
• /
• 2013

Objective: To explore the inhibiting effect and mechanism of Endostar injection concomitant with cryoablation on lung adenocarcinoma A549 xenografts in nude mice. Materials and Methods: A total of 24 nude mice with subcutaneous xenografts of the A549 cell line were established and divided into 4 groups when the maximal diameters of tumors became 1 cm: control group, Endostar group, cryoablation group and combination group (Endostar concomitant with cryoablation). The nude mice were sacrificed after 21-days treatment, tumour tissues were removed to measure their volume, in situ test of TdT-mediated dUTP nick end labeling (TUNEL) was adopted to determine the cellular apoptosis around freezing injury zones, and immunohistochemical SP test was applied for the detection of micro-vessel density (MVD) and vascular endothelial growth factor (VEGF) expression levels. Results: At 21-days after treatment, the growth velocities of control group, Endostar group, cryoablation group and combination group were $236.7{\pm}51.2%$, $220.0{\pm}30.6%$, $159.5{\pm}29.3%$ and $103.3{\pm}25.5%$ (P<0.01), while cellular apoptosis rates of tumors were $21.7{\pm}2.34%$, ($22.17{\pm}1.47$)%, $38.3{\pm}1.37%$ and $49.2{\pm}1.72%$, (P<0.01), respectively, according to the immunohistochemical test. MVD and VEGF expression levels in the combination group were both lower than in other groups (P<0.01), also being positively related (r=0.925, P<0.01). Conclusions: Endostar can significantly improve the inhibitory effects of cryoablation on xenografts of lung adenocarcinoma A549, and the mechanism is probably associated with its function as an inhibitor of tumour neo-angiogenesis through down-regulating VEGF expression.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.24
• /
• pp.10937-10941
• /
• 2015

Pathogenesis of lung cancer is a complicated biological process including multiple genetic and epigenetic changes. Since cigarette smoking is confirmed as the most main risk factor of non-small cell lung cancer (NSCLC), the aim of this study was to determine whether tobacco exposure plays a role in gene methylation. Methylation of the RAR-${\beta}$ gene were detected using methylation-specific polymerase chain reaction in DNA from 167 newly diagnosed cases with NSCLC and corresponding 105 controls. A significant statistical association was found in the detection rate of the promoter methylation of RAR-${\beta}$ gene between NSCLC and controls ($x^2$=166.01; p<0.01), and hypermethylation of the RAR-${\beta}$ gene was significantly associated with smoking status (p=0.038, p<0.05). No relationship was found between RAR-${\beta}$ gene methylation and pathologic staging including clinical stage, cell type, gender and drinking (p>0.05), and the methylation of RAR-${\beta}$ gene rate of NSCLC was slightly higher in stages III+IV (80.0%) than in I+II (70.8%). Similar results were obtained for methylation of the RAR-${\beta}$ gene between squamous cell carcinoma (77.9%) and other cell type lung cancer (73.9%). These results showed that the frequency of methylation increased gradually with the development of clinical stage in smoking-associated lung cancer patients, and tobacco smoke may be play a potential role in RAR-${\beta}$ gene methylation in the early pathogenesis and process in lung cancer, particularly squamous cell carcinoma. Aberrant promoter methylation is considered to be a promising marker of previous carcinogen exposure and cancer risk.

• Journal of KIISE:Software and Applications
• /
• v.28 no.5
• /
• pp.389-401
• /
• 2001

This paper proposes an abstraction mechanism of the low-level digital video features for the automatic retrievals of the explosion scenes from the digital video library. In the proposed abstraction mechanism, the regional dominant colors of the key frame and the motion energy of the shot are defined as the primary abstractions of the shot for the explosion scene retrievals. It is because an explosion shot usually consists of the frames with a yellow-tone pixel and the objects in the shot are moved rapidly. The regional dominant colors of shot are selected by dividing its key frame image into several regions and extracting their regional dominant colors, and the motion energy of the shot is defined as the edge image differences between key frame and its neighboring frame. The edge image of the key frame makes the retrieval of the explosion scene more precisely, because the flames usually veils all other objects in the shot so that the edge image of the key frame comes to be simple enough in the explosion shot. The proposed automatic retrieval algorithm declares an explosion scene if it has a shot with a yellow regional dominant color and its motion energy is several times higher than the average motion energy of the shots in that scene. The edge image of the key frame is also used to filter out the false detection. Upon the extensive exporimental results, we could argue that the recall and precision of the proposed abstraction and detecting algorithm are about 0.8, and also found that they are not sensitive to the thresholds. This abstraction mechanism could be used to summarize the long action videos, and extract a high level semantic information from digital video archive.

• Journal of Ginseng Research
• /
• v.45 no.6
• /
• pp.642-653
• /
• 2021

Background: Effective strategies are dramatically needed to prevent and improve the recovery from myocardial ischemia and reperfusion (I/R) injury. Direct interactions between the mitochondria and endoplasmic reticulum (ER) during heart diseases have been recently investigated. This study was designed to explore the cardioprotective effects of gypenoside XVII (GP-17) against I/R injury. The roles of ER stress, mitochondrial injury, and their crosstalk within I/R injury and in GP-17einduced cardioprotection are also explored. Methods: Cardiac contractility function was recorded in Langendorff-perfused rat hearts. The effects of GP-17 on mitochondrial function including mitochondrial permeability transition pore opening, reactive oxygen species production, and respiratory function were determined using fluorescence detection kits on mitochondria isolated from the rat hearts. H9c2 cardiomyocytes were used to explore the effects of GP-17 on hypoxia/reoxygenation. Results: We found that GP-17 inhibits myocardial apoptosis, reduces cardiac dysfunction, and improves contractile recovery in rat hearts. Our results also demonstrate that apoptosis induced by I/R is predominantly mediated by ER stress and associated with mitochondrial injury. Moreover, the cardioprotective effects of GP-17 are controlled by the PI3K/AKT and P38 signaling pathways. Conclusion: GP-17 inhibits I/R-induced mitochondrial injury by delaying the onset of ER stress through the PI3K/AKT and P38 signaling pathways.

• Journal of Korea Water Resources Association
• /
• v.47 no.8
• /
• pp.671-684
• /
• 2014

Change point analysis is a efficient tool to understand the fundamental information in hydro-meteorological data such as rainfall, discharge, temperature etc. Especially, this fundamental information to change points to future rainfall data identified by reasonable detection skills can affect the prediction of flood and drought occurrence because well detected change points provide a key to resolve the non-stationary or inhomogeneous problem by climate change. Therefore, in this study, the comparative study to assess the performance of the 3 change point detection skills, cumulative sum (CUSUM) method, Bayesian change point (BCP) method, and segmentation by dynamic programming (DP) was performed. After assessment of the performance of the proposed detection skills using the 3 types of the synthetic series, the 2 reasonable detection skills were applied to the observed and future rainfall data at the 5 rainfall gauges in South Korea. Finally, it was suggested that BCP (with 0.9 posterior probability) could be best detection skill and DP could be reasonably recommended through the comparative study. Also it was suggested that BCP (with 0.9 posterior probability) and DP detection skills to find some change points could be reasonable at the North-eastern part in South Korea. In future, the results in this study can be efficiently used to resolve the non-stationary problems in hydrological modeling considering inhomogeneity or nonstationarity.

• Journal of Korean Society of Transportation
• /
• v.19 no.6
• /
• pp.105-118
• /
• 2001

Incident detection rate and false alarm rate are the key measures tot estimating the performance of automatic incident detection algorithms. It is, however inherently very difficult to improve the two measures simultaneously. The main purpose of this study is to present some methods for solving the problem. For this, an incident detection algorithm has been designed in this study. The algorithm is consisted of two functions, one for detecting incident and another for detecting congestion. A logic for distinguishing non-recurrent congestion from recurrent congestion was employed in the algorithm. The new algorithm basically requires speed, flow, and occupancy data for defining incident situation, but the algorithm is able to perform this task without one of the three parameters. The performance of the algorithm has been evaluated by using the field data collected from Interstate Highway 880 in Bay Area, California. The empirical analysis results are very promising and thus, the algorithm proposed may be very useful for the analysts. This paper presents some empirical test results for the performance of California incident detection algorithm, only for the reference purpose.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.12
• /
• pp.363-370
• /
• 2023

Object detection technology that accurately recognizes the road and surrounding conditions is a key technology in the field of autonomous driving. In the field of autonomous driving, object detection technology requires real-time performance as well as accuracy of inference services. Task offloading technology should be utilized to apply object detection technology for accuracy and real-time on resource-constrained devices rather than high-performance machines. In this paper, experiments such as performance comparison of task offloading, performance comparison according to input image resolution, and performance comparison according to camera object resolution were conducted and the results were analyzed in relation to the application of task offloading for real-time object detection of autonomous driving in resource-constrained devices. In this experiment, the low-resolution image could derive performance improvement through the application of the task offloading structure, which met the real-time requirements of autonomous driving. The high-resolution image did not meet the real-time requirements for autonomous driving due to the increase in communication time, although there was an improvement in performance. Through these experiments, it was confirmed that object recognition in autonomous driving affects various conditions such as input images and communication environments along with the object recognition model used.