• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1478-1499
• /
• 2024

Coronavirus disease (COVID-19) is an infectious disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus. COVID-19 become an active epidemic disease due to its spread around the globe. The main causes of the spread are through interaction and transmission of the droplets through coughing and sneezing. The spread can be minimized by isolating the susceptible patients. However, it necessitates remote monitoring to check the breathing issues of the patient remotely to minimize the interactions for spread minimization. Thus, in this article, we offer a wearable-IoTs-centered framework for remote monitoring and recognition of the breathing pattern and abnormal breath detection for timely providing the proper oxygen level required. We propose wearable sensors accelerometer and gyroscope-based breathing time-series data acquisition, temporal features extraction, and machine learning algorithms for pattern detection and abnormality identification. The sensors provide the data through Bluetooth and receive it at the server for further processing and recognition. We collect the six breathing patterns from the twenty subjects and each pattern is recorded for about five minutes. We match prediction accuracies of all machine learning models under study (i.e. Random forest, Gradient boosting tree, Decision tree, and K-nearest neighbor. Our results show that normal breathing and Bradypnea are the most correctly recognized breathing patterns. However, in some cases, algorithm recognizes kussmaul well also. Collectively, the classification outcomes of Random Forest and Gradient Boost Trees are better than the other two algorithms.

• Asia Pacific Journal of Corpus Research
• /
• v.5 no.1
• /
• pp.23-36
• /
• 2024

This research centers on the Taiwan Eye-Movement Corpus of Spanish (TECS), a specially created corpus comprising eye-tracking data from Chinese-speaking learners of Spanish as a third language in Taiwan. Its primary purpose is to explore the broad utility of TECS in understanding language learning processes, particularly the initial stages of language learning. Constructing this corpus involves gathering data on eye-tracking, reading comprehension, and language proficiency to develop a machine-learning model that predicts learner behaviors, and subsequently undergoes a predictability test for validation. The focus is on examining attention in input processing and their relationship to language learning outcomes. The TECS eye-tracking data consists of indicators derived from eye movement recordings while reading Spanish sentences with temporal references. These indicators are obtained from eye movement experiments focusing on tense verbal inflections and temporal adverbs. Chinese expresses tense using aspect markers, lexical references, and contextual cues, differing significantly from inflectional languages like Spanish. Chinese-speaking learners of Spanish face particular challenges in learning verbal morphology and tenses. The data from eye movement experiments were structured into feature vectors, with learner behaviors serving as class labels. After categorizing the collected data, we used two types of machine learning methods for classification and regression: Random Forests and the k-nearest neighbors algorithm (KNN). By leveraging these algorithms, we predicted learner behaviors and conducted performance evaluations to enhance our understanding of the nexus between learner behaviors and language learning process. Future research may further enrich TECS by gathering data from subsequent eye-movement experiments, specifically targeting various Spanish tenses and temporal lexical references during text reading. These endeavors promise to broaden and refine the corpus, advancing our understanding of language processing.

• Progress in Medical Physics
• /
• v.28 no.2
• /
• pp.54-60
• /
• 2017

This study was designed to measure transit dose with an electronic portal imaging device (EPID) in eight patients treated with intensity modulated radiotherapy (IMRT), and to verify the accuracy of dose delivery to patients. The calculated dose map of the treatment planning system (TPS) was compared with the EPID based dose measured on the same plane with a gamma index method. The plan for each patient was verified prior to treatment with a diode array (MapCHECK) and portal dose image prediction (PDIP). To simulate possible patient positioning errors during treatment, outcomes were evaluated after an anthropomorphic phantom was displaced 5 and 10 mm in various directions. Based on 3%/3 mm criteria, the $mean{\pm}SD$ passing rates of MapCHECK, PDIP (pre-treatment QA) for 47 IMRT were $99.8{\pm}0.1%$, $99.0{\pm}0.7%$, and, respectively. Besides, passing rates using transit dosimetry was $90.0{\pm}1.5%$ for the same condition. Setup errors of 5 and 10 mm reduced the mean passing rates by 1.3% and 3.0% (inferior to superior), 2.2% and 4.3% (superior to inferior), 5.9% and 10.9% (left to right), and 8.9% and 16.3% (right to left), respectively. These findings suggest that the transit dose-based IMRT verification method using EPID, in which the transit dose from patients is compared with the dose map calculated from the TPS, may be useful in verifying various errors including setup and/or patient positioning error, inhomogeneity and target motions.

• Korean Journal of Labor Studies
• /
• v.24 no.2
• /
• pp.1-28
• /
• 2018

Now labour policy of Moon Jae-in Administration is very different from the labour reform politics of the past ages in its structural conditions. Especially the difference is in the fact that the new labour policy is originated from the Candlelight Revolution in 2016 which has resisted to the 20years-long neoliberal domination. This kind of change in the political situation made a optimistic prediction with regard to the possibility of successful labour reform. However the future is in many points so uncertain that we could not confirm the success of labour reform at all. The uncertainty always resides in the structural unbalance between labour movement power and capitalist state power bloc in Korea. In this sense strategical orientation and practices of the democratic labour movement(KCTU) are very critical to produce some positive outcomes.

• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.37-52
• /
• 2015

The recent global trends display expansion and growing solidity in both cooperative collaboration between industry, education, and research and R&D network systems. A greater support for the network and cooperative research sector would open greater possibilities for the evolution of new scholar and industrial fields and the development of new theories evoked from synergized educational research. Similarly, the national need for a strategy that can most efficiently and effectively support R&D network that are established through the government's R&D project research is on the rise. Despite the growing urgency, due to the habitual dependency on simple individual personal information data regarding R&D industry participants and generalized statistical data references, the policies concerning network system are disappointing and inadequate. Accordingly, analyses of the relationships involved for each subject who is participating in the R&D industry was conducted and on the foundation of an educational-industrial-research network system, possible changes within and of the network that may arise were predicted. To predict the R&D network transitions, Common Neighbor and Jaccard's Coefficient models were designated as the basic foundational models, upon which a new prediction model was proposed to address the limitations of the two aforementioned former models and to increase the accuracy of Link Prediction, with which a comparative analysis was made between the two models. Through the effective predictions regarding R&D network changes and transitions, such study result serves as a stepping-stone for an establishment of a prospective strategy that supports a desirable educational-industrial-research network and proposes a measure to promote the national policy to one that can effectively and efficiently sponsor integrated R&D industries. Though both weighted applications of Common Neighbor and Jaccard's Coefficient models provided positive outcomes, improved accuracy was comparatively more prevalent in the weighted Common Neighbor. An un-weighted Common Neighbor model predicted 650 out of 4,136 whereas a weighted Common Neighbor model predicted 50 more results at a total of 700 predictions. While the Jaccard's model demonstrated slight performance improvements in numeric terms, the differences were found to be insignificant.

• Clinical and Experimental Reproductive Medicine
• /
• v.23 no.1
• /
• pp.51-59
• /
• 1996

Controlled Ovarian hyperstimulation(COH) is generally used to obtain synchronous high quality oocytes in in vitro fertilization-embryo transfer(IVF-ET). Many investigators have studied the relationship between serum hormone levels and outcomes of IVF-ET because there is no accurate estimation method of oocyte quality. Early premature luteinization of follicles before oocyte retrieval is the most troublesome problem in COH for IVF-ET. Gonadotropin-releasing hormone agonists(GnRH-a) are used as adjuncts with gonadotropins for COH in patients undergoing in IVF. The possible benefits of GnRH-a pretreatment include improving oocyte quality, allowing a more synchronous cohort of follicles to be recruited, and preventing premature lueinization hormone surges. In COH of IVF cycles, we investigated whether an elevated progesterone(P4) level on the day of human chorionic gonadotropin(hCG) administration indicates premature luteinization and is associated with a lower fertilization rate. Many investigators have studied that the lower fertilization rates seen in patients with elevated P4 levels might result from an adverse effect of P4 on the oocytes. We hypothesizes that serum P4 levels around the day of hCG may be helpful prediction of out come in IVF-ET cycles. Success rates after COH of IVF-ET cycles are dependent upon many variable factors. Follicular factors including the number of follicles, follicular diameters and especially serum estradiol(E2) levels as an indirect measurement of follicular function and guality have been thought to influence the outcomes of IVF-ET. To assess whether serum P4 and E2 levels affect the fertilization and pregnancy rate, we reviewed the stimulation cycles of 113 patients (119 cycles) undergoing IVF-ET with short protocol with GnRH-a, from March 1993 to August 1994 retrospectively. The serum P4 and E2 levels were compared on the day of hCG in the pregnant group, 45 patients(47 cycles) and in the non-pregnant group, 68 patients (72 cycles) respectively. The serum E2 level in non-pregnant group was $1367{\pm}875.8$ pg/ml which was significantly lower than that of pregnant group, $1643{\pm}987.9$ pg/ml( p< 0.01 ). And the serum P4 level in non-pregnant group was $2.1{\pm}1.4$ ng/ml which was significantly higher than that of pregnant group, $1.0{\pm}0.7$ ng/ml( p< 0.001 ). The fertilization rate was $61.3{\pm}21.3%$ in pregnant group which was higher than that of non-pregnant group, $41.1{\pm}20.2%$ (p< 0.01). We suggest that the serum levels of P4 and E2 on the day of hCG administration are additional parameters that predict the outcomes of IVF-ET cycles.

• Clinical and Experimental Reproductive Medicine
• /
• v.34 no.3
• /
• pp.189-196
• /
• 2007

Objectives: The purpose of this study is to investigate the clinical significance of age and basal serum FSH in predicting the outcomes of in vitro fertilization (IVF) in patients with poor-ovarian response. Methods: From January 2000 to December 2004, 85 second IVF cycles of 85 poor-ovarian response patients under the age of 42 with a back-ground of the first IVF cycles at our infertility center and 5 or less oocytes were retrieved and their basal serum FSH levels of 15$\sim$25 mIU/ml were enrolled in this study. Exclusion criteria were patients with a male factor for the etiology of infertility and undergoing genetic diagnosis of embryo such as PGD. Flare-up protocol was used for ovarian stimulation in all cases. Results: When we stratified the study groups by patient's age, the younger age group (age<35, n=35) showed significantly higher implantation rate (19.0% versus 4.0%, p<0.05) and higher ongoing pregnancy rate (100% versus 14.3%, p<0.05) than the older age group (age$\geq$35, n=50). And then, when we stratified the study populations by basal serum FSH level, the lower FSH group (basal serum FSH<20 mIU/ml, n=58) showed significantly higher number of retrieved oocytes (4.6$\pm$0.7 versus 2.2$\pm$0.5, p<0.05) and lower cancellation rate (19.0% versus 55.6%, p<0.05) than higher FSH group (basal serum FSH$\geq$20 mIU/ml, n=27). Conclusions: In conclusion, it was suggested that the patient's age could predict the IVF outcomes in respect to its potency of pregnancy and ongoing pregnancy. Serum basal FSH levels could predict more accurately the ovarian response of cycle, but not clinical outcomes.

• Clinical and Experimental Pediatrics
• /
• v.50 no.3
• /
• pp.241-247
• /
• 2007

Purpose : Congenital muscular torticollis (CMT) is a common and benign congenital disorder of the musculoskeletal system in neonates and infants. The pathophysiology is that the sternocleidomastoid muscle (SCM) is shortened on the involved side by fibrosis, leading to ipsilateral tilt and contralateral rotation of the face and chin. In this study, we investigated the clinical features of CMT, the role of ultrasonography (USG) in prediction of prognoses and the clinical significance of early detection and treatment. Methods : Forty seven patients (M:F=31:16) were diagnosed as a CMT between March 2003 and May 2006. We reviewed age at diagnosis, physical findings, USG findings, treatment and therapeutic outcome from their medical records. Results : The median age at diagnosis was 90 days (18 days-9 years, 7 months) and the right side of neck was affected in more patients (right : left=26:21). Of 24 patients with a palpable neck mass, 21 had USG; 19 cases showed sternocleidomastoid tumor (SMT). In cases with no neck mass, USG was performed in 11 patients; seven had postural torticollis (POST), three had SMT and one had muscular torticollis (MT). Among 40 patients with follow-up, 36 had total resolution. There was negative correlation between the age at diagnosis and the recovery time, whereas the final outcome was not correlated with USG findings. However, the patients without positive findings in USG had earlier resolution (1 month vs 2.6 months, P=0.0008). The patients with SMT had earlier diagnosis and excellent outcomes. The patients with MT were delayed to diagnosis and had the longest time to resolve. Lastly, the patients with POST had delayed diagnoses, but they had excellent outcomes. Conclusion : Since the patients with delayed diagnoses, in despite of benign courses, may take a long time to resolve and rarely need surgical treatment, it is important to diagnose and treat early. This study showed that USG findings of the SCM may be used as predictive factors.

• Journal of Trauma and Injury
• /
• v.25 no.4
• /
• pp.196-202
• /
• 2012

Purpose: This study aimed to recognize the frequency of near-hanging patients with elevated Troponin-I (Tn-I), to obtain information necessary for treatment and prediction of prognosis by analyzing the clinical feature of near-hanging patients, and to evaluate the relevance of elevated Tn-I to abnormal result of other cardiac-related examinations. Methods: A retrospective review for the near-hanging patients, clinical record was conducted at two urban training hospitals between April, 2001 and December, 2011. We divided included patients into two groups, which one with elevated Tn-I level ($Tn-I{\geq}0.1ng/dL$) and one without it, and compared the differences in initial vital signs, cardiac enzyme tests, an electrocardiogram, echocardiography, chest X-ray, and the clinical outcomes. Results: A total of 39 patients were included, out of them, 14 patients showed rise in Tn-I level. The length of hospital stay and ICU hospitalization was more prolonged in the patient group with elevated Tn-I level than non-elevated group. As well as the incidence of endotracheal intubation and abnormal findings in echocardiography or chest X-ray was higher in the Tn-I elevated group, which is statistically significant. Conclusion: The rising of serum Tn-I level in near-hanging patients were not uncommonly observed. We believe that the cardiac-related test including Tn-I is necessary for near-hanging patients, and those who are shown abnormal result in cardiac-related test may need close observation and intensive care.

• Journal of Cardiovascular Imaging
• /
• v.30 no.3
• /
• pp.185-196
• /
• 2022

BACKGROUND: Two-dimensional (2D) strain provides more predictive power than ejection fraction (EF) in patients with ST-elevation myocardial infarction (STEMI). 3D strain and EF are also expected to have better clinical usefulness and overcome several inherent limitations of 2D strain. We aimed to clarify the prognostic significance of 3D strain analysis in patients with STEMI. METHODS: Patients who underwent successful revascularization for STEMI were retrospectively recruited. In addition to conventional parameters, 3D EF, global longitudinal strain (GLS), global area strain (GAS), as well as 2D GLS were obtained. We constructed a composite outcome consisting of all-cause death or re-hospitalization for acute heart failure or ventricular arrhythmia. RESULTS: Of 632 STEMI patients, 545 patients (86.2%) had a reliable 3D strain analysis. During median follow-up of 49.5 months, 55 (10.1%) patients experienced the adverse outcome. Left ventricle EF, 2D GLS, 3D EF, 3D GLS, and 3D GAS were significantly associated with poor outcomes. (all, p < 0.001) The maximum likelihood-ratio test was performed to evaluate the additional prognostic value of 2D GLS or 3D GLS over the prognostic model consisting of clinical characteristics and EF, and the likelihood ratio was 15.9 for 2D GLS (p < 0.001) and 1.49 for 3D GLS (p = 0.22). CONCLUSIONS: The predictive power of 3D strain was slightly lower than the 2D strain. Although we can obtain 3D strains, volume, and EF simultaneously in same cycle, the clinical implications of 3D strains in STEMI need to be investigated further.