• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1212-1223
• /
• 2022

Skin lesions are common diseases that range from skin rashes to skin cancer, which can lead to death. Note that early diagnosis of skin diseases can be important because early diagnosis of skin diseases considerably can reduce the course of treatment and the harmful effect of the disease. Recently, the development of computer-aided diagnosis (CAD) systems based on artificial intelligence has been actively made for the early diagnosis of skin diseases. In a typical CAD system, the accurate classification of skin lesion types is of great importance for improving the diagnosis performance. Motivated by this, we propose a novel deep ensemble classification with multi-scale attention networks. The proposed deep ensemble networks are jointly trained using a single loss function in an end-to-end manner. In addition, the proposed deep ensemble network is equipped with a multi-scale attention mechanism and segmentation information of the original skin input image, which improves the classification performance. To demonstrate our method, the publicly available human skin disease dataset (HAM 10000) and the private animal skin lesion dataset were used for the evaluation. Experiment results showed that the proposed methods can achieve 97.8% and 81% accuracy on each HAM10000 and animal skin lesion dataset. This research work would be useful for developing a more reliable CAD system which helps doctors early diagnose skin diseases.

• Nuclear Engineering and Technology
• /
• v.54 no.12
• /
• pp.4751-4758
• /
• 2022

Two-phase flow may almost exist in every branch of the energy industry. For the corresponding engineering design, it is very essential and crucial to monitor flow patterns and their transitions accurately. With the high-speed development and success of deep learning based on convolutional neural network (CNN), the study of flow pattern identification recently almost focused on this methodology. Additionally, the photographing technique has attractive implementation features as well, since it is normally considerably less expensive than other techniques. The development of such a two-phase flow pattern online monitoring system is the objective of this work, which seldom studied before. The ongoing preliminary engineering design (including hardware and software) of the system are introduced. The flow pattern identification method based on CNNs and transfer learning was discussed in detail. Several potential CNN candidates such as ALexNet, VggNet16 and ResNets were introduced and compared with each other based on a flow pattern dataset. According to the results, ResNet50 is the most promising CNN network for the system owing to its high precision, fast classification and strong robustness. This work can be a reference for the online monitoring system design in the energy system.

• International Journal of Computer Science & Network Security
• /
• v.23 no.5
• /
• pp.148-162
• /
• 2023

Classification systems can significantly assist the medical sector by allowing for the precise and quick diagnosis of diseases. As a result, both doctors and patients will save time. A possible way for identifying risk variables is to use machine learning algorithms. Non-surgical technologies, such as machine learning, are trustworthy and effective in categorizing healthy and heart-disease patients, and they save time and effort. The goal of this study is to create a medical intelligent decision support system based on machine learning for the diagnosis of heart disease. We have used a mixed feature creation (MFC) technique to generate new features from the UCI Cleveland Cardiology dataset. We select the most suitable features by using Least Absolute Shrinkage and Selection Operator (LASSO), Recursive Feature Elimination with Random Forest feature selection (RFE-RF) and the best features of both LASSO RFE-RF (BLR) techniques. Cross-validated and grid-search methods are used to optimize the parameters of the estimator used in applying these algorithms. and classifier performance assessment metrics including classification accuracy, specificity, sensitivity, precision, and F1-Score, of each classification model, along with execution time and RMSE the results are presented independently for comparison. Our proposed work finds the best potential outcome across all available prediction models and improves the system's performance, allowing physicians to diagnose heart patients more accurately.

• Journal of Practical Engineering Education
• /
• v.16 no.1_spc
• /
• pp.59-64
• /
• 2024

As the aging population grows, the incidence of cancer is increasing. Skin cancer appears externally, but people often don't notice it or simply overlook it. As a result, if the early detection period is missed, the survival rate in the case of late stage cancer is only 7.5-11%. However, the disadvantage of diagnosing, serious skin cancer is that it requires a lot of time and money, such as a detailed examination and cell tests, rather than simple visual diagnosis. To overcome these challenges, we propose an Attention-based CNN model skin cancer classification system. If skin cancer can be detected early, it can be treated quickly, and the proposed system can greatly help the work of a specialist. To mitigate the problem of image data imbalance according to skin cancer type, this skin cancer classification model applies the Over Sampling, technique to data with a high distribution ratio, and adds a pre-learning model without an Attention layer. This model is then compared to the model without the Attention layer. We also plan to solve the data imbalance problem by strengthening data augmentation techniques for specific classes.

• Safety and Health at Work
• /
• v.6 no.3
• /
• pp.184-191
• /
• 2015

Chemical mutagenicity is a major hazard that is important to workers' health. Despite the use of large amounts of allyl chloride, the available mutagenicity data for this chemical remains controversial. To clarify the mutagenicity of allyl chloride and because a micronucleus (MN) test had not yet been conducted, we screened for MN induction by using male ICR mice bone marrow cells. The test results indicated that this chemical is not mutagenic under the test conditions. In this paper, the regulatory test battery and several assay combinations used to determine the genotoxic potential of chemicals in the workplace have been described. Further application of these assays may prove useful in future development strategies of hazard evaluations of industrial chemicals. This study also should help to improve the testing of this chemical by commonly used mutagenicity testing methods and investigations on the underlying mechanisms and could be applicable for workers' health.

• Journal of Korean Society of Rural Planning
• /
• v.3 no.1
• /
• pp.54-67
• /
• 1997

Korean societies have been experiencing the wholesale structural changes in the rapid currents of recent openness, globalization and democratization, which effect much more heavily in rural areas than in urban areas, so rural recomposition works being an important national concern. In order to systematically reconstruct the rural structure, the decision makers, with a four step hierarchy of rural resident-residents group-community-region, should be endowed with the objective judgement on basic elements of resource potentialities under their control. In this process. rational resource evaluation works would be firstly necessiated from expert groups. Based on the view mentioned above, this study principally aimed at developing a rational evaluation framework for rural resources. For that objective, the first step of the study pigeonholed the total resources items identifiable in rural areas from the existing study results, spatial planning and field surveying data. After then, using the formalized classification criteria of resources items, a tentative goal system for rural resources evaluation was proposed and the final one determined through expert-group checking. The results obtained during the study are summarized as follows ; 1. Using the existing examples of resources identification/classification and the basic data list for county-level development planning as the principal reference ones, total rural resources elements were classified into 3 constituent units : land, natural environment and human resources, which correspond to places to work, to play and to live, respectively, as 3 constituent ones of life-supporting space. 2. Three characteristic areal types were adopted to represent the total rural areas : lowland, upland and seashore areas, and also 3 practical use types to represent the objectives of resources evaluation systems : for land use planning, natural conservation policy and village improvement planning. Thus 9 different types of goal system for resources evaluation were developed(each system by 3 areal typesX3 practical use types) 3. Each goal system has 3-tier classification steps from the higher, middle and lower one. The higher and middle steps should contain equally applicable components to all the rural areas, of which allowable number being around 3 and 4 respectively. However the lower step would contain detailed sub-components changeable to areal characteristics of which allowable number being around 7.

• Journal of Ocean Engineering and Technology
• /
• v.34 no.4
• /
• pp.277-284
• /
• 2020

Underwater acoustics, which is the study of phenomena related to sound waves in water, has been applied mainly in research on the use of sound navigation and range (SONAR) systems for communication, target detection, investigation of marine resources and environments, and noise measurement and analysis. The main objective of underwater acoustic remote sensing is to obtain information on a target object indirectly by using acoustic data. Presently, various types of machine learning techniques are being widely used to extract information from acoustic data. The machine learning techniques typically used in underwater acoustics and their applications in passive SONAR systems were reviewed in the first two parts of this work (Yang et al., 2020a; Yang et al., 2020b). As a follow-up, this paper reviews machine learning applications in SONAR signal processing with a focus on active target detection and classification.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 1995.11a
• /
• pp.125-152
• /
• 1995

An Integrated Bridge System (IBS) is not an officially defined term, but a concept of which integrates on a consol at bridge the primary functions of stand-alone navigational aids and communication instruments or of stand-alone units which are integrated i.e. ARPA ECDIS It aims to enable officers on navigational watch to perform their duty without impairing proper lookout. IBS has been taking shape through a rapid development of navigation and communication systems in relation with bridge configuration bridge work station and one man bridge operation system. IBS related matters have been considered for years and is on the agenda of the International Maritime Organization(IMO) for its technical details and safety aspect of possible one-man watchkeeping at night. However IMO has made it clear that human element should be the key factor in considering IBS and single watchkeeping issue. In the development of IBS ergonomic element and human psychological aspect have been more emphasized than technical requirements. This paper refers to documents presented to the IMO and its progress made in various IMO technical meetings on the development of IBS which is perceived as an effective aid to proper bridge lookout and those standards adopted by classification societies on the composition of workstation at bridge in order to identify the international trend on regulating required equipment function of workstation of IBS the regulatory review process and technical recommendations related thereto.

• Proceedings of the Korean Environmental Health Society Conference
• /
• 2005.06a
• /
• pp.240-248
• /
• 2005

To implement a globally harmonized system of classification and labeling of chemicals (GHS) in Korea, an interminsterial GHS working group involving 6 ministries established an expert working group composed of 7 experts from relevant organizations and one private consultant to prepare an officialKorean GHS version by March, 2005. As such, the translation and review of the official Korean GHS version, including annexes, started in October, 2004 and was completed on March 15, 2005. The official Korean GHS version has now been posted on the websites of the relevant ministries and organizations to solicit public opinions. The official Korean GHS version will be finalized after a public hearing scheduled forMay, 2005. Collaborative efforts as regards implementing and disseminating the GHS in Korea will be continued to avoid any confusion or duplication and for effective use of resources. The globally harmonized system of classifying and labeling chemicals (GHS) was originally adopted in 1992 at the United Nations Conference on Environment and Development (UNCED), as subsequently reflected in Agenda 21 chapter 19. The work was coordinated and managed under the auspices of the Interorganization Programme for the Sound Management of Chemicals(IOMC) Coordinating Group for the Harmonization of Chemical Classification Systems (UNCEGHS). The technical focal points for completing the work were the International Labour Organization (ILO); Organization for Economic Cooperation and Development (OECD); and United Nations Economic and Social Council's Subcommittee of Experts on the Transport of Dangerous Goods (UNSCETDG). The work was finalized in October 2002, and the World Summit on Sustainable Development in Johannesburg on 4 September 2002 encouraged countries to implement the new GHS as soon as possible with a view to having the system fully operational by 2008 (UN, 2003). Implementation has already started with pilot countries introducing the system to their national practices in different regions of the world. The GHS text, called the purple book, becameavailable as a W publication in early 2003. The GHS text, called the purple book, becameavailable as a UN publication in early 2003. The GHS system will be kept dynamic, and regularly revised and made more efficient as experience is gained in its implementation. While national or regional governments are the primary audiences for this document, it also contains sufficient context and guidance for those in industry who will ultimately be implementing the national requirements that will be introduced (UN, 2003). The Japanese government published their official Japanese GHS version, the first in Asia, in April 2004 after starting work in January 2003 based on an interministerial chemical coordination committee involving 7 ministries, including the Ministry of Foreign Affairs, Ministry of Internal Affairs and Communications, Ministry of Health, Labour, and Welfare, Ministry of Agriculture, Forestry and Fisheries, Ministry of Economy, Trade and Industry, Ministry of Land, Infrastructure, and Transport, and Ministry of Environment (MOE, 2004). Accordingly, similar to the Japanese GHS efforts, this paper presents the interministerial efforts involved in publishing the official Korean GHS version.

• Journal of Biomedical Engineering Research
• /
• v.44 no.1
• /
• pp.73-79
• /
• 2023

The purpose of this study is to derive medical devices with different management systems through comparison of domestic and overseas medical device product classification systems and to propose management conversion measures for the products. The definitions of medical devices were compared and the scope of medical devices defined by each country was confirmed through surveys of the Medical Device Act, Federal Food, Drug & Cosmetics Act (FD&C) in the U.S., and Medical Device Regulations (MDR) in Europe. Using the Ministry of Food and Drug Safety's regulations on medical device products and grades, 21 CFR part 860-892 and product code classification files in U.S., and EMDN in Europe as basic data to compare medical device products and derive medical devices with different management systems. As a result of comparing the definition and product classification systems of medical devices in Korea, the U.S. and Europe, medical device accessories, prosthetic limbs and aids among assistive devices for persons with disabilities, drugs, quasi-drugs and industrial products that are not managed by medical devices in Korea are managed as medical devices in the U.S. and Europe. This study aims to improve public health by securing systematic product safety management and essential performance under medical device regulations. Management within a single medical device system will increase the efficiency of licensing work of domestic medical device manufacturers and related organizations. It is also expected to help advance the system according to the international harmony of the item classification system and enhance smooth import and export competitiveness.