• Korean Journal of Materials Research
• /
• v.32 no.8
• /
• pp.345-353
• /
• 2022

In this study, using deep learning, super-resolution images of transmission electron microscope (TEM) images were generated for nanomaterial analysis. 1169 paired images with 256 × 256 pixels (high resolution: HR) from TEM measurements and 32 × 32 pixels (low resolution: LR) produced using the python module openCV were trained with deep learning models. The TEM images were related to DyVO₄ nanomaterials synthesized by hydrothermal methods. Mean-absolute-error (MAE), peak-signal-to-noise-ratio (PSNR), and structural similarity (SSIM) were used as metrics to evaluate the performance of the models. First, a super-resolution image (SR) was obtained using the traditional interpolation method used in computer vision. In the SR image at low magnification, the shape of the nanomaterial improved. However, the SR images at medium and high magnification failed to show the characteristics of the lattice of the nanomaterials. Second, to obtain a SR image, the deep learning model includes a residual network which reduces the loss of spatial information in the convolutional process of obtaining a feature map. In the process of optimizing the deep learning model, it was confirmed that the performance of the model improved as the number of data increased. In addition, by optimizing the deep learning model using the loss function, including MAE and SSIM at the same time, improved results of the nanomaterial lattice in SR images were achieved at medium and high magnifications. The final proposed deep learning model used four residual blocks to obtain the characteristic map of the low-resolution image, and the super-resolution image was completed using Upsampling2D and the residual block three times.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.335-349
• /
• 2023

Bridges constantly undergo deterioration and damage, the most common ones being concrete damage and exposed rebar. Periodic inspection of bridges to identify damages can aid in their quick remediation. Likewise, identifying components can provide context for damage assessment and help gauge a bridge's state of interaction with its surroundings. Current inspection techniques rely on manual site visits, which can be time-consuming and costly. More recently, robotic inspection assisted by autonomous data analytics based on Computer Vision (CV) and Artificial Intelligence (AI) has been viewed as a suitable alternative to manual inspection because of its efficiency and accuracy. To aid research in this avenue, this study performs a comparative assessment of different architectures, loss functions, and ensembling strategies for the autonomous segmentation of bridge components and damages. The experiments lead to several interesting discoveries. Nested Reg-UNet architecture is found to outperform five other state-of-the-art architectures in both damage and component segmentation tasks. The architecture is built by combining a Nested UNet style dense configuration with a pretrained RegNet encoder. In terms of the mean Intersection over Union (mIoU) metric, the Nested Reg-UNet architecture provides an improvement of 2.86% on the damage segmentation task and 1.66% on the component segmentation task compared to the state-of-the-art UNet architecture. Furthermore, it is demonstrated that incorporating the Lovasz-Softmax loss function to counter class imbalance can boost performance by 3.44% in the component segmentation task over the most employed alternative, weighted Cross Entropy (wCE). Finally, weighted softmax ensembling is found to be quite effective when used synchronously with the Nested Reg-UNet architecture by providing mIoU improvement of 0.74% in the component segmentation task and 1.14% in the damage segmentation task over a single-architecture baseline. Overall, the best mIoU of 92.50% for the component segmentation task and 84.19% for the damage segmentation task validate the feasibility of these techniques for autonomous bridge component and damage segmentation using RGB images.

• BMB Reports
• /
• v.49 no.2
• /
• pp.69-70
• /
• 2016

Mutations of orthodentricle homeobox 2 (OTX2) in human and mice often cause retinal dystrophy and nyctalopia, suggesting a role of OTX2 in mature retina, in addition to its functions in the development of the eye and retina. In support of this, the number of bipolar cells in Otx2^+/− post-natal mouse retina was found to be significantly lower than normal. Degeneration of the cells becomes greater as the mice age, leading to the loss of vision. Especially, the type-2 OFF-cone bipolar cells, which do not express Otx2 mRNA but carry Otx2 protein, are most sensitive to Otx2 haplodeficiency. Interestingly, this bipolar cell subpopulation imports Otx2 protein from photoreceptors to protect itself from glutamate excitotoxicity in the dark. Moreover, in the bipolar cells, the exogenous Otx2 relocates to the mitochondria to support mitochondrial ATP synthesis. This novel mitochondrial activity of exogenous Otx2 highlights the therapeutic potential of Otx2 protein transduction in retinal dystrophy.

• Parasites, Hosts and Diseases
• /
• v.52 no.2
• /
• pp.125-129
• /
• 2014

Several reports on taeniasis and cysticercosis in Vietnam show that they are distributed in over 50 of 63 provinces. In some endemic areas, the prevalence of taeniasis was 0.2-12.0% and that of cysticercosis was 1.0-7.2%. The major symptoms of taeniasis included fidgeted anus, proglottids moving out of the anus, and proglottids in the feces. Clinical manifestations of cysticercosis in humans included subcutaneous nodules, epileptic seizures, severe headach, impaired vision, and memory loss. The species identification of Taenia in Vietnam included Taenia asiatica, Taenia saginata, and Taenia solium based on combined morphology and molecular methods. Only T. solium caused cysticercosis in humans. Praziquantel was chosen for treatment of taeniasis and albendazole for treatment of cysticercosis. The infection rate of cysticercus cellulosae in pigs was 0.04% at Hanoi slaughterhouses, 0.03-0.31% at provincial slaughterhouses in the north, and 0.9% in provincial slaughterhouses in the southern region of Vietnam. The infection rate of cysticercus bovis in cattle was 0.03-2.17% at Hanoi slaughterhouses. Risk factors investigated with regard to transmission of Taenia suggested that consumption of raw meat (eating raw meat 4.5-74.3%), inadequate or absent meat inspection and control, poor sanitation in some endemic areas, and use of untreated human waste as a fertilizer for crops may play important roles in Vietnam, although this remains to be validated.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.10
• /
• pp.4929-4947
• /
• 2017

In visual object tracking, Correlation Filter-based Tracking (CFT) systems have arouse recently to be the most accurate and efficient methods. The CFT's circularly shifts the larger search window to find most likely position of the target. The need of larger search window to cover both background and object make an algorithm sensitive to the background and the target occlusions. Further, the use of fixed-sized windows for training makes them incapable to handle scale variations during tracking. To address these problems, we propose two layer target representation in which both global and local appearances of the target is considered. Multiple local patches in the local layer provide robustness to the background changes and the target occlusion. The target representation is enhanced by employing additional reversed RGB channels to prevent the loss of black objects in background during tracking. The final target position is obtained by the adaptive weighted average of confidence maps from global and local layers. Furthermore, the target scale variation in tracking is handled by the statistical model, which is governed by adaptive constraints to ensure reliability and accuracy in scale estimation. The proposed structural enhancement is tested on VTBv1.0 benchmark for its accuracy and robustness.

• Archives of Plastic Surgery
• /
• v.37 no.3
• /
• pp.271-276
• /
• 2010

Purpose: The purpose is to present an useful and simple surgical method to improve the aging of upper third face in patients with high frontal hairline as well as low frontal hairline. Methods: Forty eight female patients were treated with subcutaneous forehead lift using an anterior hairline incision over 14 years. This surgical technique is performed under direct vision utilizing a beveled incision made 4 to 5 mm into the anterior hairline with subcutaneous dissection, which is continued near to eyebrow, sometimes extended to supraorbital rim to remove corrugator and procerus muscles. In patients with high frontal hairline, excess forehead skin anterior to incision line is removed. On the contrary in the patients with low frontal hairline, scalp posterior to incision line is removed. Results: This technique provided constant and good results with the forty six patients, who were satisfied with eyebrow elevation and removal of wrinkles in forehead and glabellar region. However two patients were undercorrected, and focal alopecia developed in another two patients. One patient complained of pruritus over one year, but subsided spontaneously without any treatment. Temporary paresthesia developed in the forehead and frontal scalp of all cases after operation but permanent sensory loss never occurred in all the patients. Conclusion: Subcutaneous forehead lift using an anterior hairline incision is suggested to be one of the effective surgical methods to improve the aging of upper third face in the patients with high frontal hairline as well as low frontal hairline.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.5
• /
• pp.513-519
• /
• 2013

Line scan camera has been widely used in the area of inspection of glass, film, fabric, iron, PCB and etc. due to the high resolution and the high speed. We developed the line scan based vision system to inspect tangled and cut-off status of yarn in the manufacturing process. The original image is binarized with a proper threshold, and the gap distances in the yarn are measured in real time, so finally the status of the process is decided by the maximum value of the gap distance. All procedures are executed in real time by realization of multi-processed threads. By implementation of this system, the error of the yarn in manufacturing process can be precedently monitored and the loss of the yarn is decreased efficiently.

• Parasites, Hosts and Diseases
• /
• v.51 no.6
• /
• pp.613-619
• /
• 2013

Angiostrongyliasis, caused by Angiostrongylus cantonensis infection, is a food-borne parasitic disease. Its larvae evoke eosinophilic inflammation in the central nervous system, but can also cause pathological changes in the eyes. Among ocular angiostrongyliasis cases, the incidence of optic neuritis is low and only few sporadic reports exist. Some patients with optic neuritis developed obvious hypopsia or even vision loss, which would seriously influence the quality of life of patients. Prompt treatment of optic neuritis caused by A. cantonensis is the key factor for minimizing the incidence of serious complications of this disease. In this review, we first provide a comprehensive overview of ocular angiostrongyliasis, and then focus on the clinical features of optic neuritis caused by A. cantonensis.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1899-1909
• /
• 2015

Glaucoma is one of the most common causes of blindness which is caused by increase of fluid pressure in the eye which damages the optic nerve and eventually causing vision loss. An automated technique to diagnose glaucoma disease can reduce the physicians’ effort in screening of Glaucoma in a person through the fundal retinal images. In this paper, optimal hyper analytic wavelet transform for Glaucoma detection technique from fundal retinal images is proposed. The optimal coefficients for transformation process are found out using the hybrid GSO-Cuckoo search algorithm. This technique consists of pre-processing module, optimal transformation module, feature extraction module and classification module. The implementation is carried out with MATLAB and the evaluation metrics employed are accuracy, sensitivity and specificity. Comparative analysis is carried out by comparing the hybrid GSO with the conventional GSO. The results reported in our paper show that the proposed technique has performed well and has achieved good evaluation metric values. Two 10- fold cross validated test runs are performed, yielding an average fitness of 91.13% and 96.2% accuracy with CGD-BPN (Conjugate Gradient Descent- Back Propagation Network) and Support Vector Machines (SVM) respectively. The techniques also gives high sensitivity and specificity values. The attained high evaluation metric values show the efficiency of detecting Glaucoma by the proposed technique.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.3
• /
• pp.1081-1083
• /
• 2014

Malignancy-associated mortality, decreased productivity, and spiritual, social and physical burden in cancer patients and their families impose heavy costs on communities. Therefore cancer prevention, early detection, rapid diagnosis and timely treatment are very important. Use of modern methods based on information technology in cancer can improve patient survival and increase patient and health care provider satisfaction. Robot technology is used in different areas of health care and applications in surgery have emerged affecting the cancer treatment domain. Computerized and robotic devices can offer enhanced dexterity by tremor abolition, motion scaling, high quality 3D vision for surgeons and decreased blood loss, significant reduction in narcotic use, and reduced hospital stay for patients. However, there are many challenges like lack of surgical community support, large size, high costs and absence of tactile and haptic feedback. A comprehensive view to identify all factors in different aspects such as technical, legal and ethical items that prevent robotic surgery adoption is thus very necessary. Also evidence must be presented to surgeons to achieve appropriate support from physicians. The aim of this review article is to survey applications, opportunities and barriers to this advanced technology in patients and surgeons as an approach to improve cancer care.