Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 8 de 8
Filter
1.
13th International Workshop on Machine Learning in Medical Imaging, MLMI 2022, held in conjunction with 25th International Conference on Medical Image Computing and Computer_Assisted Intervention, MICCAI 2022 ; 13583 LNCS:210-219, 2022.
Article in English | Scopus | ID: covidwho-2173784

ABSTRACT

Chest X-ray (CXR) is a common imaging modality for examination of pneumonia. However, some pneumonia signs which are visible in CT may not be clearly identifiable in CXR. It is challenging to create a good ground truth for positive pneumonia cases based on CXR images especially for cases with small pneumonia lesions. In this paper, we propose a novel CT-based CXR synthesis framework, called ct2cxr, to perform data augmentation for pneumonia classification. Generative Adversarial Networks (GANs) were exploited and a customized loss function was proposed for model training to preserve the target pathology and maintain high image fidelity. Our results show that CXR images generated through style mixing can enhance the performance of general pneumonia classification models. Testing the models on a Covid-19 dataset shows similar improvements over the baseline models. © 2022, Springer Nature Switzerland AG.

2.
International Journal of Mental Health Promotion ; 25(1):99-126, 2023.
Article in English | Scopus | ID: covidwho-2156180

ABSTRACT

The prevalence of mental health problems in both Malaysian and global workplaces has significantly increased due to the presence of the coronavirus disease (COVID-19) pandemic, globalization, technology advancement in Industry 4.0, and other contributing factors. The pervasiveness of the issue poses a huge challenge to improving the occupational safety and health (OSH) of workers in various industries, especially in the digital industry. The emergence of the innovative industry is evident mainly due to the rapid development of Industry 4.0 and the rele-vant demands of multiple businesses in the digital transformation. Nonetheless, limited studies and academic dis-cussions were conducted on the OSH topic of digital employees. Hence, the current study serves to fill the existing gap and provide academic contributions by scrutinising the perceptions of digital workers regarding their workplace well-being, mental health literacy, and the impression of employing e-mental health. The objectives of this study are: 1) To examine the mental health literacy and workplace wellness of digital workers, 2) to explore the e-mental health usage intention and actual e-mental health utilization, and 3) to identify digital workers’ feedback on e-mental health. In the current context, e-mental health focuses on three dimensions, namely, 1) “health in our hand (HIOH)”, 2) “interacting for health (IFH)”, and 3) “data enabling health (DEH)”. The present study employed an online cross-sectional survey and received 326 digital workers’ completed responses. Variables, such as “mental health literacy (MHL)”, “workplace wellness (WW)”, and e-mental health intention and usage were explicated by analysing the data through descriptive statistics. The study results indicated a moderate to a high level of the MHL and the WW. More than half of the workers possessed a high intention level to employ e-mental health, with the HIOH dimension being the most prevalent domain. Nevertheless, the actual e-mental health usage was very low, owing to the online resources being a new concept amongst digital employees. Numerous confounding factors also existed in affecting the low usage, such as privacy concerns, data security levels, and health verification issues. In addition, the mental health issue has not been openly and widely discussed in Malaysian workplaces due to stigmatisation. As such, the current findings could provide additional insights into the OSH literature;it could serve as a guideline for the OSH decision-makers, employers, and eHealth developers when establishing a feasible framework for the practical adoption of e-mental health services by digital workers. © 2023, Tech Science Press. All rights reserved.

3.
Annals of the Academy of Medicine Singapore ; 49(7):456-461, 2020.
Article in English | EMBASE | ID: covidwho-2115576

ABSTRACT

Coronavirus disease 2019 (COVID-19) is caused by the severe acute respiratory syndrome coronavirus 2 and was declared a global pandemic by the World Health Organization on 11 March 2020. A definitive diagnosis of COVID-19 is made after a positive result is obtained on reverse transcription-polymerase chain reaction assay. In Singapore, rigorous contact tracing was practised to contain the spread of the virus. Nasal swabs and chest radiographs (CXR) were also taken from individuals who were suspected to be infected by COVID-19 upon their arrival at a centralised screening centre. From our experience, about 40% of patients who tested positive for COVID-19 had initial CXR that appeared "normal". In this case series, we described the temporal evolution of COVID-19 in patients with an initial "normal" CXR. Since CXR has limited sensitivity and specificity in COVID-19, it is not suitable as a first-line diagnostic tool. However, when CXR changes become unequivocally abnormal, close monitoring is recommended to manage potentially severe COVID-19 pneumonia. Copyright © 2020 Annals, Academy of Medicine, Singapore.

4.
Journal of Logistics, Informatics and Service Science ; 9(3):64-77, 2022.
Article in English | Scopus | ID: covidwho-2081526

ABSTRACT

The major impact of the COVID-19 pandemic on the shift of education norms from physical classroom learning to MOOCs (Massive Open Online Courses) could accelerate the big data era growth for the e-learning platform. This circumstance has provided an opportunity for a teacher to use MOOC data to help students learn and perform better. Moreover, this research study goal is to propose a combination of machine learning algorithms and the feature selection benefit with the SMOTE (Synthetic Minority Oversampling Technique) algorithm for balancing the output features number to predict student performance in a video-based learning platform. As a result, the proposed machine learning classifier, Naïve Bayes algorithm with the combination of chi-square test and SMOTE has shown the highest accuracy in prediction of more than 90%. Results by the proposed classifier with feature selection and SMOTE have outperformed the traditional machine learning classifiers. © 2022, Success Culture Press. All rights reserved.

5.
Estudios de Economia Aplicada ; 39(12), 2021.
Article in English | Scopus | ID: covidwho-1566956

ABSTRACT

When it comes to online fashion, this research focused on the interaction between three factors: preferences for online fashion goods, consumer buying choices for online fashion products, and brand image. A descriptive correlational approach was used. A total of 184 sampled active online purchasers of fashion items from a population of 350 online buyers in Thailand participated in the research. The study was carried out with the use of tools that had been adopted. Descriptive data showed that respondents had a high preference for online marketing, a positive attitude towards online fashion goods, a high degree of consumer buying choices towards online fashion products, and a high preference for favorable brand image in the research. There were significant variations in respondents' preferences for online shopping as well as attitudes toward fashion items and consumer purchase decisions based on age, civil status, education, monthly income, and profession, according to the results of a test of difference. A further connection test revealed that respondents' liking for online marketing tends to improve their attitude toward online fashion items and consumer buying choices. In the end, the results of multiple regression analysis revealed that age, civil status and education level, online marketing approach, attitude towards online fashion goods, and brand image and attitude are all predictors of buying choices. The study's practical consequences for an internet business are addressed. The study's practical consequences for an internet business are addressed. © 2021 Galenos Publishing House. All rights reserved.

6.
Estudios de Economia Aplicada ; 39(12), 2021.
Article in English | Scopus | ID: covidwho-1566951

ABSTRACT

In this context, the study explored the relationship between organizational climate and employee innovative work behaviour among food manufacturing industries in Malaysia. The study is a descriptive correlational survey research design where data is sourced out from a total of randomly sampled 260 employees. Results revealed that a favourable organizational climate on innovation, proactivity, and risk-taking is prevailing among the companies. A very high level of innovative work behaviour is emanating among the employees on idea exploration, generation, championing, and implementation. Test of differences showed that employee gender, position, unit, and years of service spelt significant differences in the perception of the employees on organizational climate and innovative work behaviour. A meaningful relationship surfaced between organizational climate and employee innovative work behaviour, suggesting that for food manufacturing industries to sustain innovative and competitive advantages, there is a need to promote a nurturing and encouraging entrepreneurial organizational climate. Finally, a congruency among the domains of organizational climate and employee innovative work behaviour emerged. It suggests that when higher positive organizational climate surfaces, the more likely the employee's manifest innovation work behaviour. This study addressed the gap by providing organizational climate and employee innovative work behaviour among food manufacturing industries in Malaysia. © 2021 Ascociacion Internacional de Economia Aplicada. All Rights Reserved.

7.
Int. Conf. Inf. Syst., ICIS - Mak. Digit. Incl.: Blending Local Glob. ; 2021.
Article in English | Scopus | ID: covidwho-1172196
SELECTION OF CITATIONS
SEARCH DETAIL