• The Transactions of the Korea Information Processing Society
• /
• v.4 no.11
• /
• pp.2780-2785
• /
• 1997

Although KBANN(knowledge-based artificial neural network) has been shown to be more effective than other machine learning algorithms, KBANN doesn't have the theory refinement capability because the topology of the network can't be altered dynamically. Although TopGen algorithm was proposed to extend the ability of KABNN in this respect, it also had some defects due to the connection of hidden nodes from all input nodes and the use of beam search. An algorithm, which could solve this TopGen's defects by adding the hidden nodes connected from only related input nodes and using hill-climbing search with backtracking, is proposed.

• The Journal of the Korea Contents Association
• /
• v.10 no.2
• /
• pp.268-276
• /
• 2010

This study was to investigate the knee joint flexion angle and the foot pressure during climbing with different slope. The 24 healthy subjects were participated. And foot pressure was investigated using Parotec system. The knee joint flexion angle were filmed to using a video camera on each slope($0^{\circ},\;3^{\circ},\;6{\circ},\;9^{\circ}$). And knee joint angle was investigated by Dartfish. The data were analyzed ANOVAs. In conclusion, there was significantly different that knee joint flexion angle related on each slope angle. In foot pressure, there was significantly different in lateral heel area(1 cell), medial midfoot area(9 cell), medial forefoot area(15, 16 cell) of left foot, and in lateral heel area(3 cell) of right foot. There was significantly different of foot pressure in lateral and medial heel when knee joint flexion angle is between $10^{\circ}$ and $20^{\circ}$. There was change of gait cycle according to walking slop angle increasing, and the initial contact phase was shorter, the foot pressure in lateral heel was lower.

• Journal of the Korean Society of Child Welfare
• /
• no.36
• /
• pp.197-230
• /
• 2011

This study is aimed to examine the emotional experiences of parents with children who have been sexually abused by others. Five mothers whose child was sexually abused participated in this study. They were first recruited through recommendations made by social welfare agencies that provided services to these children. We conducted two or more in-depth interviews for each mother to collect the data. The mothers' emotional experiences were analyzed using phenomenology. Mothers expressed that they felt like the whole world came crashing down around them, felt "totally lost", and felt deep pain together with their children, such that "my family and I were so devastated". Nevertheless, they gradually came to believe that they could overcome this tragedy by continuously making efforts to protect their children from the dangers outside. Despite their efforts, however, they kept the feeling of "hopelessness, neglect, and their children's wounds", deep inside them. The results indicate that it is necessary to have an intervention for mothers whose child has been sexually abused from a companions' perspective within 10 days after the sexual abuse incident.

• Journal of Korean Philosophical Society
• /
• v.129
• /
• pp.83-109
• /
• 2014

The aim of this study is to examine the limits and problems of researchers that appear in the papers of applied qualitative research by phenomenological methods. Using phenomenological methods in the field of Pedagogy, pedagogical phenomenology is not to approach pedagogical issues that are closely related to human life through scientism or positivism, but to explain them in things themselves. The problem, however, is that cases misunderstood and distorted in the essential meaning of phenomenology are happening as domestic researchers are applying pure phenomenology(the philosophical phenomenology) to the field of phenomenology of practice(the pedagogical phenomenology). Especially, these researchers show some errors caused by lack of basic understanding about research logic and research techniques in qualitative research methodology. Thus if a researcher carry out a qualitative study by using phenomenological methods, she or he needs insights in analysing and interpreting the essence of the various phenomena appearing from the participants by comparing in with her or his own lives.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.9 no.4
• /
• pp.319-329
• /
• 2015

The purpose of this paper is to analyze lower extremities pattern of daily activities and walking on the treadmill with passive body support system. The experiments will be used for basic research of developing active harness system. The experimental procedure has been validated on 5 healthy male subjects and we measured foot pressure and 8 section of lower limb muscles activities. The EMG results of ADL indicate that there have specific muscle activity patterns followed by each activities. The vastus lateralis muscle activities were highly seems on the activities that requires flection and extension of knee joint. The foot pressure value of stair descent activity was the highest due to the fact that it is come down to the direction of gravity. The results with the passive body weight support percentages show that the EMG and foot pressure values were declined according to increasement of the body weight support percentages. Therefore the body weight support system could apply gait rehabilitation system for various patients by changing the percentages of the body weight support.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.42-47
• /
• 2010

Many contests by micro mouse was celebrated of which maze search algorithms performance are compared. That is used in various forms based on left(right) weight method, euclidean algorithm method, hill climbing method. However we feel uncomfortable to test algorithms performance through direct development of programs or hardwares as no software platform to test in maze search algorithms. In this research we develop of a platform for maze search algorithms that is easily to produce various forms of maze that are hard to be realized by hardware, to apply algorithms, and evaluate the seek time, operation count, steps and performance. The platform is consist of main layer, interface layer, user layer which has merit to apply and replace easily algorithms. We verified that the maze search algorithm can be applied even in the development and experiment of algorithm by evaluating and analyzing its performance through the experiment of platform.

• Journal of KIISE
• /
• v.43 no.4
• /
• pp.480-488
• /
• 2016

Search-Based Software Testing (SBST) is an effective technique for test data generation on large domain size. Although the performance of SBST seems to be affected by the structural characteristics of Software Under Test (SUT), studies for the comparison of SBST techniques considering structural characteristics are rare. In addition to the comparison study for SBST, we analyzed the best algorithm with different structural characteristics of SUT. For the generalization of experimental results, we automatically generated 19,800 SUTs by combining four metrics, which are expected to affect the performance of SBST. According to the experiment results, Genetic algorithm showed the best performance for SUTs with high complexity and test data evaluation with count ${\leq}20,000$. On the other hand, the genetic simulated annealing and the simulated annealing showed relatively better performance for SUTs with high complexity and test data evaluation with count ${\geq}50,000$. Genetic simulated annealing, simulated annealing and hill climbing showed better performance for SUTs with low complexity.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.9
• /
• pp.47-55
• /
• 2010

Linear constraint satisfaction optimization problem is a kind of combinatorial optimization problem involving linearly expressed objective function and complex constraints. Integer programming is known as a very effective technique for such problem but require very much time and memory until finding a suboptimal solution. In this paper, we propose a method to improve the search performance by integrating local search and integer programming. Basically, simple hill-climbing search, which is the simplest form of local search, is used to solve the given problem and integer programming is applied to generate a neighbor solution. In addition, constraint programming is used to generate an initial solution. Through the experimental results using N-Queens maximization problems, we confirmed that the proposed method can produce far better solutions than any other search methods.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.69-76
• /
• 2022

The traveling salesman problem(TSP) is one of the most famous combinatorial optimization problem. So far, many metaheuristic search algorithms have been proposed to solve the problem, and one of them is local search. One of the very important factors in local search is neighbor generation method, and random-based neighbor generation methods such as inversion have been mainly used. This paper proposes 4 new greedy-based neighbor generation methods. Three of them are based on greedy insertion heuristic which insert selected cities one by one into the current best position. The other one is based on greedy rotation. The proposed methods are applied to first-choice hill-climbing search and simulated annealing which are representative local search algorithms. Through the experiment, we confirmed that the proposed greedy-based methods outperform the existing random-based methods. In addition, we confirmed that some greedy-based methods are superior to the existing local search methods.

• 한국노년학
• /
• v.25 no.2
• /
• pp.143-154
• /
• 2005

This study was conducted to examine the environmental status, FIM(Function Independence Measure), Illness intrusiveness of home stayed stroke patients. Data were collected on 145 patients living in K city and the neighborhood located in southern part of Korea. The data were analyzed by means of SPSS program. Results : In assessment of environmental safety, 46.2%(67) felt unsafe around their residential area. The most dangerous facilities in their residence was stairs(58.2%), gas/electric facilities(14.9%). For sanitary problems, 28.2%(41) felt they have problems at their home. The most important problems were outdoor polluted toilet(22.0%) and scattered and dirty residential circumstances(22.0%). The average FIM score was 74.52(4.14) of total score 126(7). In motor area FIM was lowest at stair walking(3.01) and bathing(3.16). In cognitive area FIM was lowest at social activities(3.36). The mean score of Illness intrusiveness was 58.86(4.52) of total score 91(7). The major area largely impacted by stroke were health(5.61), working(5.68), active leisure activities(5.56). There was significant reverse correlation between FIM and illness intrusiveness(r=-0.66, p=0.00). Conclusion : It was needed environmental improvement and rehabilitation program for stroke patients, and repeated follow up study.