• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• Journal of the Society of Naval Architects of Korea
• /
• v.41 no.6
• /
• pp.120-125
• /
• 2004

There are very few numbers of 115K FPP (Fixed Pitch Propulsion) Tankers for the Baltic ice class IA because the minimum power requirement of FMA (Finish- Swedish Maritime Association) needs quite large engine power and the 40 m Beam is out of calculation range of FMA minimum power requirements. The shipyard has no choice except to increase the engine power to satisfy FMA minimum power requirement Rule. And the operation cost, efficiency of hullform and its building cost are not good from the ship owners' point of view To solve this problem, the experience of ice breaking tanker development and the ice tank test results were adopted. The main idea to reduce the ice resistance is by reducing waterline angle at design load waterline. The reason behind the main idea is to reduce the ice-clearing force. Two hull forms were developed to satisfy Baltic Ice class IA. Two ice tank tests and one towing tank test was performed at MARC (Kvaener-Masa Arctic Research Center) and SSMB (Samsung Ship Model Basin) facilities, respectively. The purpose of these tests was to verify the performance in ice and open water respectively The hull form 2 shows less speed loss compared to Hull form 1 in open water operation but hull form 2 shows very good ice clearing ability. finally the Hull Form 2 satisfying Baltic ice class IA. The merit of this hull form is to use the same engine capacity and no major design changes in hull form and other related designs But the hull structure has to be changed according to the ice class grade. The difference in two hull form development methods, ice model test methods and analysis methods of ice model test will be described in this paper.

• Structural Engineering and Mechanics
• /
• v.63 no.1
• /
• pp.55-64
• /
• 2017

The paper concerns concrete carbonation, the phenomena that occurs in every type of climate, especially in urban-industrial areas. In European Standards, including Eurocode (EC) for concrete structures the demanded durability of construction located in the conditions of the carbonation threat is mainly assured by the selection of suitable thickness of reinforcement cover. According to EC0 and EC2, the thickness of the cover in the particular class of exposure depends on the structural class/category and concrete compressive strength class which is determined by cement content and water-cement ratio (thus the quantitative composition) but it is not differentiated for various cements, nor additives (i.e., qualitative composition), nor technological types of concrete. As a consequence the selected thickness of concrete cover is in fact a far estimation - sometimes too exaggerated (too safe or too risky). The paper presents the elaborated "self-terminated carbonation model" that includes abovementioned factors and enables to indicate the maximal possible depth of carbonation. This is possible because presented model is a hyperbolic function of carbonation depth in time (the other models published in the literature use the parabolic function that theoretically assume the infinite increase of carbonation depth value). The paper discusses the presented model in comparison to other models published in the literature, moreover it contains the algorithm of concrete cover design with use of the model as well as an example of calculation of the cover thickness.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.10 no.3
• /
• pp.367-375
• /
• 2018

The present paper considers the contact between energy-saving device of ice-class vessel and ice block. The main objective of this study is to clarify the tendency of the ice impact force and the structural response as well as interaction effects of them. The contact analysis is performed by using LS-DYNA finite element code. The main collision scenario is based on Finnish-Swedish ice class rules and a stern duct model is used as an energy-saving device. For the contact force, two modelling approaches are adopted. One is dynamic indentation model of ice block based on the pressure-area curve. The other is numerical material modelling by LS-DYNA. The authors investigated the sensitivity of the structural response against the ice contact pressure, the interaction effect between structure and ice block, and the influence of eccentric collision. The results of these simulations are presented and discussed with respect to structural safety.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.3
• /
• pp.57-65
• /
• 1995

This paper presents a new classified vector quantization (VQ) technique using a neural network model in the transform domain. Prior to designing a codebook, the proposed approach extracts class features from a set of images using self-organizing feature map (SOFM) that has the pattern recognition characteristics and the same as VQ objective. Since we extract the class features from the training images unlike previous approaches, the reconstructed image quality is improved. Moreover, exploiting the adaptivity of the neural network model makes our approach be easily applied to designing a new vector quantizer when the processed image characteristics are changed. After the generalized BFOS algorithm allocates the given bits to each class, codebooks of each class are also generated using SOFM for the maximal reconstructed image quality. In experimental results using monochromatic images, we obtained a good visual quality in the reconstructed image. Also, PSNR is comparable to that of other classified VQ technique and is higher than that of JPEG baseline system.

• Proceedings of the KSPS conference
• /
• 2000.07a
• /
• pp.117-134
• /
• 2000

Kim, Key-Seop(2000). English Restructuring and A Use of Music in Teaching English Pronunciation. JSEP 2000 voU This study has two-fold aims: one is to clarify the restructuring of English in utterance, and the other is to relate it to teaching English pronunciation for listening and speaking with a use of music and song by suggesting a model of 10-15 minute pronunciation class syllabus for every period in class. Generally, English utterances are restructured by stress-timed rhythm, irrespective of syntactic boundaries. So the rhythmic units are arranged in isochronous groups, of which the making is to attach clitic(s) to a host or head often leftwards and sometimes rightwards, which results in linking, contraction, reduction, sound change and rhythm adjustment in utterance, just as in music and song. With English restructuring focused on, a model of English pronunciation class syllabus is proposed to be put forward in class for every period of a lesson or unit. It tries to relate the focused factor(s) in pronunciation to the integrated, with teaching techniques and music made use of.

• The Mathematical Education
• /
• v.38 no.1
• /
• pp.61-75
• /
• 1999

This study has its purpose to develop an optimal teaching model in math class leading to an effective device of open education in mathematics being transformed from the current teacher-centered teaching to the individually specified student-centered one on the basis of the definitions and methods of open education learned from sundry literature references. Accordingly, this paper established several patterns of effective open math class for teaching specific math's contents, followed by developing applicable teaching-learning models for class situation rested on each math lesson's features. Unit learning models for open education in mathematics, which were made step by step according to each unit's contents were also presented to be applied to real class situations.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.105-107
• /
• 2019

최근 몇 년간 소량의 데이터를 송수신하는 Massive IoT 네트워크에 많은 관심을 가지고 있다. 이러한 환경을 구축하기 위해서 저전력 광역 네트워크(LPWAN) 기술 중 LoRa(Long Range) 네트워크를 사용하고 있다. 대부분의 IoT 응용 서비스는 디바이스가 장시간 안정적으로 작동해야 하므로 에너지 효율성을 중점으로 두고 LoRa 디바이스의 수명을 최대화하기 위한 디바이스의 여러 동작들을 설계하는 에너지 소비 모델링이 중요하다. 따라서 본 논문에서는 LoRa Class B 통신 방식의 에너지 소비 모델을 정의하고 성능을 평가한다.

• Journal of Digital Convergence
• /
• v.12 no.10
• /
• pp.405-414
• /
• 2014

This research aims to strengthen the ethical decision-making capability of nursing students, and involves 82 fourth-year undergraduate nursing students in a nonequivalent control group pre-post quasi experimental research design from March 4 to June 3, 2013. Experimental group took a discussion-based class and control group took a traditional lecture-based class and we identified the differences in ethical knowledge, class satisfaction and ethical values between the two groups. Experimental group had higher scores for ethical knowledge after the class. There was no significant change in ethical values after the class in the two groups. The experimental group achieved significantly higher scores for the comprehension of class contents and practical application within the class satisfaction criteria. So we propose to use this model as an effect teaching method to apply ethical principles in nursing practice.

• Communications for Statistical Applications and Methods
• /
• v.14 no.2
• /
• pp.377-388
• /
• 2007

As one of multi-class classification methods, ECOC (Error Correcting Output Coding) method is known to have low classification error rate. This paper aims at suggesting effective multi-class classification method (1) by comparing various encoding methods and decoding methods in ECOC method and (2) by comparing ECOC method and direct classification method. Both SVM (Support Vector Machine) and logistic regression model were used as binary classifiers in comparison.