• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.20-27
• /
• 2020

Sound event detection in real-world environments suffers from the interference of non-stationary and time-varying noise. This paper presents an adaptive noise reduction method for sound event detection based on non-negative matrix factorization (NMF). In this paper, we proposed a deep learning model that integrates Convolution Neural Network (CNN) with Non-Negative Matrix Factorization (NMF). To improve the separation quality of the NMF, it includes noise update technique that learns and adapts the characteristics of the current noise in real time. The noise update technique analyzes the sparsity and activity of the noise bias at the present time and decides the update training based on the noise candidate group obtained every frame in the previous noise reduction stage. Noise bias ranks selected as candidates for update training are updated in real time with discrimination NMF training. This NMF was applied to CNN and Hidden Markov Model(HMM) to achieve improvement for performance of sound event detection. Since CNN has a more obvious performance improvement effect, it can be widely used in sound source based CNN algorithm.

• 의학교육논단
• /
• 제26권2호
• /
• pp.155-166
• /
• 2024

This study utilized cohort data, student lifestyle surveys, and mental health examination results from a medical school to investigate the impact of factors such as hometown, alcohol use, smoking, university life adaptation, and aptitude on academic failure, with mental health serving as a mediator. We analyzed data from 409 of the 549 incoming students at Keimyung University School of Medicine, excluding 140 individuals with missing data, from the academic years 2015 to 2021. Significant differences were found according to hometown in feelings of depression, suicidal tendencies, and internet addiction. There were also significant differences based on university life adaptation in feelings of depression, suicidal tendencies, and internet addiction, as well as significant differences according to academic aptitude in feelings of depression and internet addiction. Academic failure showed significant differences based on hometown, university life adaptation, and academic aptitude. Furthermore, students' hometown had a complete mediating effect on academic failure together with feelings of depression, suicidal tendencies, and internet addiction. University life adaptation exhibited a complete mediating effect with suicidal tendencies and a partial mediating effect with feelings of depression and internet addiction. Academic aptitude demonstrated partial mediating effects on feelings of depression, suicidal tendencies, and internet addiction. Based on these results, we suggest establishing counseling programs tailored to the characteristics of medical students, and various programs for university life adaptation are necessary. There is also a need for diverse programs not only for clinical training, but also for different career paths.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• 제26권6호
• /
• pp.291-300
• /
• 2023

Purpose: The impact of coronavirus 2019 (COVID-19) on gastrointestinal (GI) endoscopy procedures in adults has been reported, with a drastic reduction in the number of procedures. However, there are no sufficient data regarding the impact on pediatric GI endoscopy. Here, we aimed to report that impact in the Asia-Pacific region. Methods: A questionnaire-based internet survey was conducted from June to November 2021 among pediatric endoscopy institutions in the Asia-Pacific region, with each institution providing a single response. Overall, 25 questions focused on the impact of the number of procedures conducted, the usage of personal protective equipment (PPE), and endoscopy training programs during the pandemic. Results: A total of 162 institutions across 13 countries in the Asia-Pacific region participated in the study, and 133 (82.1%) institutions underwent procedure changes since the emergence of COVID-19. The number of esophagogastroduodenoscopy and ileocolonoscopy procedures decreased in 118/133 (88.7%) and 112/133 (84.2%) institutions, respectively. Endoscopy for patient with positive COVID-19 in an emergency or urgent cases still carried out in 102/162 (62.9%) institutions. Screening of COVID-19 for all patients before endoscopy was done across 110/162 (67.9%) institutions. PPE recommendations varied among institutions. Pediatric gastrointestinal endoscopy training programs were discontinued in 127/162 (78.4%) institutions. Conclusion: This study reports the impact of the COVID-19 pandemic on pediatric gastrointestinal endoscopy in the Asia-Pacific region. There has been a significant reduction in the number of endoscopic procedures and relevant training programs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권5호
• /
• pp.1433-1449
• /
• 2023

In recent years, the rapid development of social networks has led to a rapid increase in the amount of information available on the Internet, which contains a large amount of sensitive information related to pornography, politics, and terrorism. In the aspect of sensitive image detection, the existing machine learning algorithms are confronted with problems such as large model size, long training time, and slow detection speed when auditing and supervising. In order to detect sensitive images more accurately and quickly, this paper proposes a multiclassification sensitive image detection method based on lightweight Convolutional Neural Network. On the basis of the EfficientNet model, this method combines the Ghost Module idea of the GhostNet model and adds the SE channel attention mechanism in the Ghost Module for feature extraction training. The experimental results on the sensitive image data set constructed in this paper show that the accuracy of the proposed method in sensitive information detection is 94.46% higher than that of the similar methods. Then, the model is pruned through an ablation experiment, and the activation function is replaced by Hard-Swish, which reduces the parameters of the original model by 54.67%. Under the condition of ensuring accuracy, the detection time of a single image is reduced from 8.88ms to 6.37ms. The results of the experiment demonstrate that the method put forward has successfully enhanced the precision of identifying multi-class sensitive images, significantly decreased the number of parameters in the model, and achieved higher accuracy than comparable algorithms while using a more lightweight model design.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권5호
• /
• pp.2590-2606
• /
• 2017

Generally, research of classical image classification algorithms assume that training data and testing data are derived from the same domain with the same distribution. Unfortunately, in practical applications, this assumption is rarely met. Aiming at the problem, a domain adaption image classification approach based on multi-sparse representation is proposed in this paper. The existences of intermediate domains are hypothesized between the source and target domains. And each intermediate subspace is modeled through online dictionary learning with target data updating. On the one hand, the reconstruction error of the target data is guaranteed, on the other, the transition from the source domain to the target domain is as smooth as possible. An augmented feature representation produced by invariant sparse codes across the source, intermediate and target domain dictionaries is employed for across domain recognition. Experimental results verify the effectiveness of the proposed algorithm.

• 혜화의학회지
• /
• 제22권2호
• /
• pp.47-56
• /
• 2014

Objectives : The purpose of this study is to raise the proper recognition of Qigong and expand the area of Medical Qigong in the korean Medicine by investigating and analyzing the current state of Javaldonggong training which has a high medical value but there has not been little research on. Method : The survey of this study was conducted by doing a search on the internet - Naver(www.naver.com) and Daum(www.daum.net), Nate(www.nate.com), trying question-and-answer on the websites and over the phone, visiting the organizations and reading their publications. Results : None of the teachers of these selected organizations are doctors. One thing all these organizations have in common is that they are, ultimately, aiming to gain the individual enlightenment and to contribute to public welfare although the terms they use are different. As for training contents, most of these organizations use breathing, meditation, gymnastics, circuit training in addition to Javaldonggong training and they work on Javaldonggong training programs to prevent problems that Qigong training can result in. 7 organizations have published the books of the theories, which are based on their own Javaldonggong training experience. Conclusions : Applying Javaldonggong training to the therapy for the diseases is the role of a doctor of Korean medicine. A further study of and a great interest in Javaldonggong training are required for Korean medical doctors to gain a firm foothold in using it as the medical Qigong therapy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권2호
• /
• pp.520-541
• /
• 2023

In CRNs, SS is of utmost significance. Every CR user generates a sensing report during the training phase beneath various circumstances, and depending on a collective process, either communicates or remains silent. In the training stage, the fusion centre combines the local judgments made by CR users by a majority vote, and then returns a final conclusion to every CR user. Enough data regarding the environment, including the activity of PU and every CR's response to that activity, is acquired and sensing classes are created during the training stage. Every CR user compares their most recent sensing report to the previous sensing classes during the classification stage, and distance vectors are generated. The posterior probability of every sensing class is derived on the basis of quantitative data, and the sensing report is then classified as either signifying the presence or absence of PU. The ISVM technique is utilized to compute the quantitative variables necessary to compute the posterior probability. Here, the iterations of SVM are tuned by novel GO-PSA by combining GOA and PSO. Novel GO-PSA is developed since it overcomes the problem of computational complexity, returns minimum error, and also saves time when compared with various state-of-the-art algorithms. The dependability of every CR user is taken into consideration as these local choices are then integrated at the fusion centre utilizing an innovative decision combination technique. Depending on the collective choice, the CR users will then communicate or remain silent.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권10호
• /
• pp.2650-2662
• /
• 2012

Due to the semantic gap issue, the performance of automatic image annotation is still far from satisfactory. Active learning approaches provide a possible solution to cope with this problem by selecting most effective samples to ask users to label for training. One of the key research points in active learning is how to select the most effective samples. In this paper, we propose a novel active learning approach based on sparse graph. Comparing with the existing active learning approaches, the proposed method selects the samples based on two criteria: uncertainty and representativeness. The representativeness indicates the contribution of a sample's label propagating to the other samples, while the existing approaches did not take the representativeness into consideration. Extensive experiments show that bringing the representativeness criterion into the sample selection process can significantly improve the active learning effectiveness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4270-4284
• /
• 2019

This study presents a reference model (RM) and the architecture of a cognitive health advisor (CHA) that integrates information with ambient intelligence. By controlling the information using the CHA platform, the reference model can provide various ambient intelligent solutions to a user. Herein, a novel approach to a CHA RM based on evolutional cyber-physical systems is proposed. The objective of the CHA RM is to improve personal health by managing data integration from many devices as well as conduct a new feedback cycle, which includes training and consulting to improve quality of life. The RM can provide an overview of the basis for implementing concrete software architectures. The proposed RM provides a standardized clarification for developers and service designers in the design and implementation process. The CHA RM provides a new approach to developing a digital healthcare model that includes integrated systems, subsystems, and components. New features for chatbots and feedback functions set the position of the conversational interface system to improve human health by integrating information, analytics, and decisions and feedback as an advisor on the CHA platform.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권11호
• /
• pp.2784-2799
• /
• 2012

Biological data have been increased exponentially in recent years, and analyzing these data using data mining tools has become one of the major issues in the bioinformatics research community. This paper focuses on the protein construction process in higher organisms where the deoxyribonucleic acid, or DNA, sequence is filtered. In the process, "unmeaningful" DNA sub-sequences (called introns) are removed, and their meaningful counterparts (called exons) are retained. Accurate recognition of the boundaries between these two classes of sub-sequences, however, is known to be a difficult problem. Conventional approaches for recognizing these boundaries have sought for solely enhancing machine learning techniques, while inherent nature of the data themselves has been overlooked. In this paper we present an approach which makes use of the data attributes inherent to species in order to increase the accuracy of the boundary recognition. For experimentation, we have taken the data sets for four different species from the University of California Santa Cruz (UCSC) data repository, divided the data sets based on the species types, then trained a preprocessed version of the data sets on neural network(NN)-based and support vector machine(SVM)-based classifiers. As a result, we have observed that each species has its own specific features related to the splice sites, and that it implies there are related distances among species. To conclude, dividing the training data set based on species would increase the accuracy of predicting splicing junction and propose new insight to the biological research.