• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.126-146
• /
• 2024

Caladium bicolor is one of the most popular plants in Thailand. The original species of Caladium bicolor was found a hundred years ago. Until now, there are more than 500 species through multiplication. The classification of Caladium bicolor can be done by using its color and shape. This study aims to develop a model to classify Caladium bicolor using a transfer learning technique. This work also presents a proof of concept, GUI design, and web application deployment using the user-design-center method. We also evaluated the performance of the following pre-trained models in this work, and the results are as follow: 87.29% for AlexNet, 90.68% for GoogleNet, 93.59% for XceptionNet, 93.22% for MobileNetV2, 89.83% for RestNet18, 88.98% for RestNet50, 97.46% for RestNet101, and 94.92% for InceptionResNetV2. This work was implemented using MATLAB R2023a.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1224-1232
• /
• 2022

Whole body bone scan is the most frequently performed nuclear medicine imaging to evaluate bone metastasis in cancer patients. We evaluated the performance of a VGG16-based transfer learning classifier for bone scan images in which metastatic bone lesion was present. A total of 1,000 bone scans in 1,000 cancer patients (500 patients with bone metastasis, 500 patients without bone metastasis) were evaluated. Bone scans were labeled with abnormal/normal for bone metastasis using medical reports and image review. Subsequently, gradient-weighted class activation maps (Grad-CAMs) were generated for explainable AI. The proposed model showed AUROC 0.96 and F1-Score 0.90, indicating that it outperforms to VGG16, ResNet50, Xception, DenseNet121 and InceptionV3. Grad-CAM visualized that the proposed model focuses on hot uptakes, which are indicating active bone lesions, for classification of whole body bone scan images with bone metastases.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.1
• /
• pp.48-63
• /
• 2015

In this study, we introduce various hyperspectral data processing techniques for the monitoring of shallow and coastal waters to enlarge the application range and to improve the accuracy of the end results in Korea. Unlike land, more accurate atmospheric correction is needed in coastal region showing relatively low reflectance in visible wavelengths. Sun-glint which occurs due to a geometry of sun-sea surface-sensor is another issue for the data processing in the ocean application of hyperspectal imagery. After the preprocessing of the hyperspectral data, a semi-analytical algorithm based on a radiative transfer model and a spectral library can be used for bathymetry mapping in coastal area, type classification and status monitoring of benthos or substrate classification. In general, semi-analytical algorithms using spectral information obtained from hyperspectral imagey shows higher accuracy than an empirical method using multispectral data. The water depth and quality are constraint factors in the ocean application of optical data. Although a radiative transfer model suggests the theoretical limit of about 25m in depth for bathymetry and bottom classification, hyperspectral data have been used practically at depths of up to 10 m in shallow and coastal waters. It means we have to focus on the maximum depth of water and water quality conditions that affect the coastal applicability of hyperspectral data, and to define the spectral library of coastal waters to classify the types of benthos and substrates.

• Journal of Korean Clinical Nursing Research
• /
• v.18 no.3
• /
• pp.354-367
• /
• 2012

Purpose: This study was done to verify validity and reliability of a neonatal patient classification system (NeoPCS-1). Methods: An expert group of 8 nurse managers and 40 nurses from 8 Neonatal Intensive Care Units in Korea, verified content validity of the measurement using item level content validity index (I-CVI). The participants were nurses caring for 469 neonates. Data were collected from November 11 to December 14, 2011 and analyzed using descriptive statistics, ANOVA, intraclass correlation coefficient, and K-cluster analysis with PASW 18.0 program. Results: Nursing domains and activities included 8 items with 91 activities. I-CVI was above .80 in all areas. Interrater reliability was significant between two raters (r=.95, p<.001). Classification scores for participants according to patient types and nurses' intuition were significantly higher for the following patients; gestational age (${\leq}29$ weeks), body weight (<1,000 gm), and transfer from hospital. Six groups were classified using cluster analysis method based on nursing needs. Patient classification scores were significantly different for the groups. Conclusion: These results show adequate validity and reliability for the NeoPCS-1 based on nursing needs. Study is needed to refine the measurement and develop index scores to estimate number of nurses needed for adequate neonatal care.

• Journal of Biomedical Engineering Research
• /
• v.34 no.3
• /
• pp.141-147
• /
• 2013

Ultrasonic shears is currently in wide use as an energy device for minimal invasive surgery. There is an advantage of minimizing the carbonization behavior of the tissue due to the vibrational energy transfer system of the transducer by applying a piezoelectric ceramic. However, the vibrational energy transfer system has a pitfall in energy consumption. When the movement of the forceps is interrupted by the tissue, the horn which transfers the vibrational energy of the transducer will be affected. A study was performed to recognize different tissues by measuring the impedance of the transducer of the ultrasonic shears in order to find the factor of energy consumption according to the tissue. In the first stage of the study, the voltage and current of the transducer connecting portion were measured, along with the phase changes. Subsequently, in the second stage, the impedance of the transducer was directly measured. In the final stage, using the handpiece, we grasped the tissue and observed the impedance differences appeared in the transducer To verify the proposed tissue distinguishing method, we used the handpiece to apply a force between 5N and 10N to pork while increasing the value of the impedance of the transducer from 400 ${\Omega}$.. It was found that fat and skin tissue, tendon, liver and protein all have different impedance values of 420 ${\Omega}$, 490 ${\Omega}$, 530 ${\Omega}$, and 580 ${\Omega}$, respectively. Thus, the impedance value can be used to distinguish the type of tissues grasped by the forceps. In the future study, this relationship will be used to improve the energy efficiency of ultrasonic shears.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.293-301
• /
• 2023

Unstandardized medical data collection and management are still being conducted manually, and studies are being conducted to classify CT data using deep learning to solve this problem. However, most studies are developing models based only on the axial plane, which is a basic CT slice. Because CT images depict only human structures unlike general images, reconstructing CT scans alone can provide richer physical features. This study seeks to find ways to achieve higher performance through various methods of converting CT scan to 2D as well as axial planes. The training used 1042 CT scans from five body parts and collected 179 test sets and 448 with external datasets for model evaluation. To develop a deep learning model, we used InceptionResNetV2 pre-trained with ImageNet as a backbone and re-trained the entire layer of the model. As a result of the experiment, the reconstruction data model achieved 99.33% in body part classification, 1.12% higher than the axial model, and the axial model was higher only in brain and neck in contrast classification. In conclusion, it was possible to achieve more accurate performance when learning with data that shows better anatomical features than when trained with axial slice alone.

• The korean journal of orthodontics
• /
• v.52 no.2
• /
• pp.112-122
• /
• 2022

Objective: This study aimed to present and evaluate a new deep learning model for determining cervical vertebral maturation (CVM) degree and growth spurts by analyzing lateral cephalometric radiographs. Methods: The study sample included 890 cephalograms. The images were classified into six cervical stages independently by two orthodontists. The images were also categorized into three degrees on the basis of the growth spurt: pre-pubertal, growth spurt, and post-pubertal. Subsequently, the samples were fed to a transfer learning model implemented using the Python programming language and PyTorch library. In the last step, the test set of cephalograms was randomly coded and provided to two new orthodontists in order to compare their diagnosis to the artificial intelligence (AI) model's performance using weighted kappa and Cohen's kappa statistical analyses. Results: The model's validation and test accuracy for the six-class CVM diagnosis were 62.63% and 61.62%, respectively. Moreover, the model's validation and test accuracy for the three-class classification were 75.76% and 82.83%, respectively. Furthermore, substantial agreements were observed between the two orthodontists as well as one of them and the AI model. Conclusions: The newly developed AI model had reasonable accuracy in detecting the CVM stage and high reliability in detecting the pubertal stage. However, its accuracy was still less than that of human observers. With further improvements in data quality, this model should be able to provide practical assistance to practicing dentists in the future.

• The Korean Journal of Emergency Medical Services
• /
• v.3 no.1
• /
• pp.20-32
• /
• 1999

The purpose of this retrospective research of 603 patients who were transferred to the emergency medical center of university hospital from 1 Jan, 1998 to 31 Jan, 1998 was making of basic data for emergency medical transfer system improvement countermeasure and the point at issue of overlapping reexamination ststus of patients transfered to emergency medical center of university hospital from 1,2 level hospital. The data analysis was done by SPSS, t-test, ANOVA, Pearson correlation. The results were as follows: 1. Male to female ratio was 1.7:1 and peak age group was patients over forties and under nine years of age(70.5%) 2. Traumatic patients were 17.8%, motor vehicle accident patients were 16.7% and Non-traumatic patients were 65.3%. Transferring hospital was divided into 2groups: primary hospital, secondary hospital. The majority was secondary hospital(73.3%). The result of symptom severity classification of patients transferred to 3rd emergency medical center was urgent patients 32.5%, emergency patients 33.58%, non-emergency patients 34.0% 3. Most highest score items amoung overlapping reexamination of patients transfered to emergency medical center of university hospital from 1,2 level hospital were CBC test, simple X-ray (0.93점), CBC test(0.97점), urin test(0.88점), chemistry test(0.94점), simple X-ray(0.98점), CT(0.42점), EKG(0.89점) amoung overlapping reexamination of motor vehicle accident patients were more higher reexamination score than traumatic patients and non-traumatic patients 4. CBC test(P<0.001), urin test(P<0.001), chemistry test(P<0.001), simple X-ray(P<0.001), CT(P<0.01), EKG(P<0.001) amoung overlapping reexamination of patients in 2 level hospital were more higher reexamination score than 1 level hospital patients 5. About symptom severity classification of patients transferred to 3rd emergency medical center, CBC test(P<0.001), urin test(P<0.001), chemistry test(P<0.001), simple X-ray(P<0.01), CT(P<0.001), EKG(P<0.001) amoung overlapping reexamination items in urgent patients were more higher reexamination score than other patients 6. Influencing variation for overlapping reexamination in hospital was CBC test(P<0.001), CT (P<0.001), MRI (P<0.05).

• The Korean Journal of Emergency Medical Services
• /
• v.25 no.3
• /
• pp.63-70
• /
• 2021

Purpose: The study aimed to collect data from patients who were rejected by emergency requests for transfer to a tertiary hospital through 119 EMT and to analyze the data in the hospital to improve the plan. Methods: We analyzed 4,702 cases of emergency requests made by patients who were rejected by 119 emergency assistance out of the 22,568 patients who visited the emergency medical center in the C area of G metropolitan city from January 2018 through December 2020. The collected data were analyzed using IBM SPSS Statistics Version XX (IBM Corp., Armonk, N.Y., USA). Results: The major medical department with the largest number of such cases was the department of emergency medicine, with 2,519 cases (53.6%). Simple bruises were the most common diagnosis, with 2,819 cases (61.2%). KTAS classification was the highest with 3,562 patients (75.8%) in grade 4. As for the results, 4,084 patients (86.9%) were discharged from the hospital. Conclusion: Most of the patients who were rejected by emergency requests were non-emergency patients and were discharged from the hospital. emergency requests must be rejected at public relations and sites. In addition, the law should be amended to specifically present the reasons for refusal of emergency requests.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.112-120
• /
• 2021

Recently, the number of consumers using digital online distribution platforms is increasing. This caused the rapid growth of the e-commerce market and increased delivery volume in urban areas. The logistics system, designed ar006Fund the city center to handle the delivery volume, operates a delivery system from the outskirts of the city to the urban area using cargo trucks. This maintains an ecosystem of high-cost and inefficient structures that increase social costs such as road traffic congestion and environmental problems. To solve this problem, research is being conducted worldwide to establish a high-efficiency urban joint logistics system using urban railway facilities and underground space infrastructure existing in existing cities. The joint logistics system begins with linking unmanned delivery automation services that link terminal delivery such as cargo classification and stacking, infrastructure construction that performs cargo transfer function by separating from passengers such as using cargo platform. To this end, it is necessary to apply the device to the vertical and horizontal transportation machine supporting the vertical transfer in the flat space of the joint logistics terminal, which is the base technology for transporting cargo using the transfer robot to the destination designated as a freight-only urban railway vehicle. Therefore, this paper aims to derive holistic viewpoints needs for design requirements for vertical and vertical transportation machines and freight transportation standard containers, which are underground railway logistics transport devices to be constructed by urban logistics ecosystem changes.