• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.2
• /
• pp.119-125
• /
• 2023

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1049-1050
• /
• 2008

It is difficult to measure the pulse wave in a short time because radial artery position and located depth are different depending on the person. In this paper, the pulse wave measurement system was developed using 3 channel piezoresistive sensor array to detect the most significant pulse wave. Augmentation Index(AI) and Heart Rate(HR) analysis are also available for predicting cardiovascular risks. The developed system is small and easy to use. And it is promising to be used as home healthcare device.

• Journal of information and communication convergence engineering
• /
• v.22 no.3
• /
• pp.256-266
• /
• 2024

Sasang constitutional medicine (SCM) is one of the best traditional therapeutic approaches used in Korea. SCM prioritizes personalized treatment that considers the unique constitution of an individual and encompasses their physical characteristics, personality traits, and susceptibility to specific diseases. Facial features are essential for diagnosing Sasang constitutional types (SCTs). This study aimed to develop a real-time artificial intelligence-based model for diagnosing SCTs using facial images, building an SCTs prediction model based on a machine learning method. Facial features from all images were extracted to develop this model using feature engineering and machine learning techniques. The fusion of these features was used to train the AI model. We used four machine learning algorithms, namely, random forest (RF), multilayer perceptron (MLP), gradient boosting machine (GBM), and extreme gradient boosting (XGB), to investigate SCTs. The GBM outperformed all the other models. The highest accuracy achieved in the experiment was 81%, indicating the robustness of the proposed model and suitability for real-time applications.

• Journal of Web Engineering
• /
• v.21 no.5
• /
• pp.1671-1690
• /
• 2022

Human activity recognition (HAR) is a key technology in many applications, such as smart signage, smart healthcare, smart home, etc. In HAR, deep learning-based methods have been proposed to recognize activity data effectively from video streams. In this paper, the end-to-end model based on convolutional long short-term memory (LSTM) is proposed to recognize human activities. Convolutional LSTM can learn features of spatial and temporal simultaneously from video stream data. Also, the number of learning weights can be diminished by employing convolutional LSTM with an end-to-end model. The proposed HAR model was optimized with various simulation environments using activities data from the AI hub. From simulation results, it can be confirmed that the proposed model can be outperformed compared with the conventional model.

• Journal of Preventive Medicine and Public Health
• /
• v.56 no.4
• /
• pp.319-326
• /
• 2023

Objectives: The coronavirus disease 2019 (COVID-19) pandemic has increased the workload of healthcare workers (HCWs), impacting their health. This study aimed to assess sleep quality using the Pittsburgh Sleep Quality Index (PSQI) and identify factors associated with poor sleep among HCWs in Vietnam during the COVID-19 pandemic. Methods: In this cross-sectional study, 1000 frontline HCWs were recruited from various healthcare facilities in Vietnam between October 2021 and November 2021. Data were collected using a 3-part self-administered questionnaire, which covered demographics, sleep quality, and factors related to poor sleep. Poor sleep quality was defined as a total PSQI score of 5 or higher. Results: Participants' mean age was 33.20±6.81 years (range, 20.0-61.0), and 63.0% were women. The median work experience was 8.54±6.30 years. Approximately 6.3% had chronic comorbidities, such as hypertension and diabetes mellitus. About 59.5% were directly responsible for patient care and treatment, while 7.1% worked in tracing and sampling. A total of 73.8% reported poor sleep quality. Multivariate logistic regression revealed significant associations between poor sleep quality and the presence of chronic comorbidities (odds ratio [OR], 2.34; 95% confidence interval [CI], 1.17 to 5.24), being a frontline HCW directly involved in patient care and treatment (OR, 1.59; 95% CI, 1.16 to 2.16), increased working hours (OR, 1.84; 95% CI,1.37 to 2.48), and a higher frequency of encountering critically ill and dying patients (OR, 1.42; 95% CI, 1.03 to 1.95). Conclusions: The high prevalence of poor sleep among HCWs in Vietnam during the COVID-19 pandemic was similar to that in other countries. Working conditions should be adjusted to improve sleep quality among this population.

• Phonetics and Speech Sciences
• /
• v.14 no.4
• /
• pp.45-56
• /
• 2022

This paper proposes an optimal methodology for automatically diagnosing and predicting the severity of the chronic kidney disease (CKD) using patients' utterances. In patients with CKD, the voice changes due to the weakening of respiratory and laryngeal muscles and vocal fold edema. Previous studies have phonetically analyzed the voices of patients with CKD, but no studies have been conducted to classify the voices of patients. In this paper, the utterances of patients with CKD were classified using the variety of utterance types (sustained vowel, sentence, general sentence), the feature sets [handcrafted features, extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS), CNN extracted features], and the classifiers (SVM, XGBoost). Total of 1,523 utterances which are 3 hours, 26 minutes, and 25 seconds long, are used. F1-score of 0.93 for automatically diagnosing a disease, 0.89 for a 3-classes problem, and 0.84 for a 5-classes problem were achieved. The highest performance was obtained when the combination of general sentence utterances, handcrafted feature set, and XGBoost was used. The result suggests that a general sentence utterance that can reflect all speakers' speech characteristics and an appropriate feature set extracted from there are adequate for the automatic classification of CKD patients' utterances.

• Journal of Convergence for Information Technology
• /
• v.10 no.6
• /
• pp.35-40
• /
• 2020

As we enter the society of the future, efforts to increase healthy living are a major area of concern for modern people. In particular, the development of technology for a healthy life that combines ICT technology with a competitive healthcare industry environment is becoming the next growth engine. Therefore, in this paper, artificial intelligence-based data analysis of the examination results was applied in the health examination process. Through this, a research was conducted to build a knowledge base modeling that can improve the reliability of the overall judgment. To this end, an algorithm was designed through deep learning analysis to calculate and verify the test result index. Then, the modeling that provides comprehensive examination information through judgment knowledge was studied. Through the application of the proposed modeling, it is possible to analyze and utilize big data on national health, so it can be expected to reduce medical expenses and increase health.

• Advanced Industrial SCIence
• /
• v.2 no.2
• /
• pp.31-41
• /
• 2023

The study aims to identify unmet needs, barriers, and constraints in reproductive health education for adolescent girls in Luwero, Uganda. The study included a survey of 55 young women (aged 14-26) in the region and interviews with 40 stakeholders, including teachers and healthcare workers. Results showed that the majority of respondents (87%) rely on schools for reproductive health information, preferring health institutions (58%) for reproductive health services. Over half of respondents encountered obstacles accessing relevant information due to limited resources and cultural barriers and emphasized the significance of schools and health institutions as essential health information sources. Schools and health institutions need to collaborate to enhance reproductive health education for young women's accessibility.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.826-842
• /
• 2024

As 5G and AI continue to develop, there has been a significant surge in the healthcare industry. The COVID-19 pandemic has posed immense challenges to the global health system. This study proposes an FL-supported edge computing model based on federated learning (FL) for predicting clinical outcomes of COVID-19 patients during hospitalization. The model aims to address the challenges posed by the pandemic, such as the need for sophisticated predictive models, privacy concerns, and the non-IID nature of COVID-19 data. The model utilizes the FATE framework, known for its privacy-preserving technologies, to enhance predictive precision while ensuring data privacy and effectively managing data heterogeneity. The model's ability to generalize across diverse datasets and its adaptability in real-world clinical settings are highlighted by the use of SHAP values, which streamline the training process by identifying influential features, thus reducing computational overhead without compromising predictive precision. The study demonstrates that the proposed model achieves comparable precision to specific machine learning models when dataset sizes are identical and surpasses traditional models when larger training data volumes are employed. The model's performance is further improved when trained on datasets from diverse nodes, leading to superior generalization and overall performance, especially in scenarios with insufficient node features. The integration of FL with edge computing contributes significantly to the reliable prediction of COVID-19 patient outcomes with greater privacy. The research contributes to healthcare technology by providing a practical solution for early intervention and personalized treatment plans, leading to improved patient outcomes and efficient resource allocation during public health crises.

• Advances in Computational Design
• /
• v.3 no.4
• /
• pp.339-366
• /
• 2018

Parametric design systems serve as powerful assistive tools in the design process by providing a flexible approach for the generation of a vast number of design alternatives. However, contemporary parametric design systems focus primarily on low-level engineering and structural forms, without an explicit means to also take into account high-level, cognitively motivated people-centred design goals. We present a precedent-based parametric design method that integrates people-centred design "precedents" rooted in empirical evidence directly within state of the art parametric design systems. As a use-case, we illustrate the general method in the context of an empirical study focusing on the multi-modal analysis of wayfinding behaviour in two large-scale healthcare environments. With this use-case, we demonstrate the manner in which: (1). a range of empirically established design precedents -e.g., pertaining to visibility and navigation- may be articulated as design constraints to be embedded directly within state of the art parametric design tools (e.g., Grasshopper); and (2). embedded design precedents lead to the (parametric) generation of a number of morphologies that satisfy people-centred design criteria (in this case, pertaining to wayfinding). Our research presents an exemplar for the integration of cognitively motivated design goals with parametric design-space exploration methods. We posit that this opens-up a range of technological challenges for the engineering and development of next-generation computer aided architecture design systems.