Search

Background Children's motor development is a crucial tool for assessing developmental levels, identifying developmental disorders early, and taking appropriate action. Although the Korean Developmental Screening Test for Infants and Children (K-DST) can accurately assess childhood development, its dependence on parental surveys rather than reliable, professional observation limits it. This study constructed a dataset based on a skeleton of recordings of K-DST behaviors in children aged between 20 and 71 months, with and without developmental disorders. The dataset was validated using a child behavior artificial intelligence (AI) learning model to highlight its possibilities. Results The 339 participating children were divided into 3 groups by age. We collected videos of 4 behaviors by age group from 3 different angles and extracted skeletons from them. The raw data were used to annotate labels for each image, denoting whether each child performed the behavior properly. Behaviors were selected from the K-DST's gross motor section. The number of images collected differed by age group. The original dataset underwent additional processing to improve its quality. Finally, we confirmed that our dataset can be used in the AI model with 93.94%, 87.50%, and 96.31% test accuracy for the 3 age groups in an action recognition model. Additionally, the models trained with data including multiple views showed the best performance. Conclusion Ours is the first publicly available dataset that constitutes skeleton-based action recognition in young children according to the standardized criteria (K-DST). This dataset will enable the development of various models for developmental tests and screenings.

Background: Bystander cardiopulmonary resuscitation (CPR) is associated with a better survival outcome in patients with out-of-hospital cardiac arrest (OHCA). However, there may be cultural barriers in performing high-quality bystander CPR in women in some non-Western countries and the effect of bystander CPR on survival outcomes may differ by patients’ sex. Methods: Using data between 2012-2018 from a national OHCA registry from the Republic of Korea, we identified adult patients with OHCA of presumed cardiac etiology. The main exposures were bystander CPR and patients’ sex. The primary outcome was survival discharge and the secondary outcome was favorable neurological survival. Multivariable logistic regression evaluated the association between bystander CPR and survival, adjusted for patients’ age, sex, socio-economic status, year of arrest, witnessed arrest status, initial OHCA rhythm, location of arrest, urbanization level of arrest location, and type of bystander. The interaction between bystander CPR and sex was explicitly evaluated in the models. Results: Of 101,505 patients with OHCA in the cohort, 34,124 (33.6 %) were women and 67,381 (64.4 %) were men. Bystander CPR was performed on 18,481 (54.2%) women and 35,904 (53.3%) men (p=0.07). Unadjusted rates of survival discharge were 4.5% in women and 9.5 % in men (p Conclusions: In a national registry of OHCA from the Republic of Korea, men who received bystander CPR were more likely to survive whereas women who received bystander CPR were not.

The quality of digital content has become increasingly significant in the digitalized broadcasting world. These days, consumers react even to subtle defects in media content, which in turn, influence consumer satisfaction about the entire content. The development of digital broadcasting technology has replaced tape-based content with file-based content. Nonetheless, in the process of generating file-based content, people are often confronted with different types of errors. Detecting such errors and fixing them requires a substantial amount of time and human labor, while being unable to fix them might lead to broadcast failure. Therefore in this paper, we introduce an automated restoration system that reduces intensive human labor in fixing the errors in the content generation process. Our automated video restoration system can be applied to different types of classical errors. We developed several algorithms to restore each error in the digital content derived from the KBS video archive. Implementing our method using a tool already familiar to content producers has also been one of our considerations. We are developing the restoration system as a plug-in to a well-known NLE (Non-linear editing system).

Automatic facial expression recognition has many potential applications in different areas of human computer interaction. However, they are not yet fully realized due to the lack of an effective facial feature descriptor. In this paper, we present a new appearancebased feature descriptor, the local directional pattern (LDP), to represent facial geometry and analyze its performance in expression recognition. An LDP feature is obtained by computing the edge response values in 8 directions at each pixel and encoding them into an 8 bit binary number using the relative strength of these edge responses. The LDP descriptor, a distribution of LDP codes within an image or image patch, is used to describe each expression image. The effectiveness of dimensionality reduction techniques, such as principal component analysis and AdaBoost, is also analyzed in terms of computational cost saving and classification accuracy. Two well-known machine learning methods, template matching and support vector machine, are used for classification using the Cohn-Kanade and Japanese female facial expression databases. Better classification accuracy shows the superiority of LDP descriptor against other appearance-based feature descriptors.

We propose a pixel similarity based Betacam dropout detection method. Proposed method aims at detecting errors, having vertically similar pattern without considering sequential frame when archiving a tape-based content to a file-based system. Moreover, this method works along with a real-time instant Quality Control(QC) system with less false-alarm.

A spatial detection technique, based on the extrema of current pixel's neighborhood, is proposed for Digital Dropout error, evident in the archived media. Digital dropout is a major type of damage occurred due to the physical error in original tape and tends to occur in block by block basis. As long as the presence of fast moving object is observed in video sequences where current state-of-the-art methods fail to detect accurate error information, such spatial detection offers a much better solution in terms of quality and complexity. Experiments are performed on video archives to evaluate the efficacy of the proposed technique.

A spatial concealment technique, based on the concept of the strength of an edge, is proposed for 'digital dropout' error, evident in old archived media. As long as the presence of pathological motion is observed in video sequences where current state-of-the-art methods fail to reproduce correct information, such spatial restoration offers a much better solution in terms of quality and complexity. Furthermore, relevant edge-based weighted interpolation is able to restore complicated edges and complex textures from the available neighbourhood. An experiment is performed on real video archives to evaluate the efficacy of the proposed technique. Refereed/Peer-reviewed

Now-a-days, recent trend is to represent high quality images or videos by using less bit representation. To represent high quality videos or images with low bit rate, an effective compression algorithm removes the redundancy because of statistical correlation and also the insignificant component of image signal. This paper represents a new algorithm to measure the blocking artifacts of videos by analyzing the distortions of local properties of image signals like dominant edge magnitude and direction. For this purpose sobel convolution mask is used rather than kirsch mask to make the detection process faster and to model video noises that occur in broadcasting systems. Extensive experiments on various videos show that the new algorithm is very much efficient to measure the blocking artifacts in real time video error detection applications. © 2011 IEEE. Refereed/Peer-reviewed

To represent high quality videos or images with low bit rate, an effective compression algorithm removes the redundancy because of statistical correlation and also the insignificant component of image signal. This paper represents a new algorithm to measure the blocking artifacts of videos by analyzing the distortions of local properties of image signals like dominant edge magnitude and direction. Extensive experiments on various videos show that the new algorithm is very much efficient and faster to measure the blocking artifacts in real time video error detection applications.

The initial base deficit (BD) is an important indicator of shock in adult trauma patients, but its value is unclear in pediatric trauma patients. This study assessed the ability of the initial BD to predict mortality and blood transfusion requirements in children except severe brain injury patients.This study was a retrospective review of pediatric patients with severe trauma arriving at the emergency department of a university hospital from January 1998 to June 2005. Blood pressure, the initial BD, and the Injury Severity Score were assessed as independent predictors of mortality and the blood transfusion requirement using multiple regression analysis.The study group constituted 102 patients. According to the multiple regression analysis results, the initial systolic blood pressure, Injury Severity Score, and blood transfusion requirement were not independent predictors of mortality (P = 0.104, 0.959, 0.386, respectively). By contrast, the initial BD was an independent predictor, with an odds ratio of 13.6 for BD of -8 mEq/L or less (confidence interval [CI], 3.51-35.23, P = 0.037), and systolic blood pressure and BD were independent predictors of blood transfusion requirement; the odds ratio for hypotension was 3.2 (CI, 0.51-8.32, P = 0.044), and the odds ratio was 15.3 for BD values of -8 or less (CI, 2.24-51.43, P = 0.003).The initial BD in pediatric trauma patients except severe brain injury was an independent predictor of mortality and blood transfusion requirement within 24 hours. Mortality and blood transfusion requirement were significantly high when initial BD was less than -8 mEq/L.