• Proceeding of KASS Symposium
• /
• 2008.05a
• /
• pp.101-106
• /
• 2008

This paper describes a comparative study of genetic algorithm and mathematical programming technique applied in the design optimization of geodesic dome. In particular, the genetic algorithm adopted in this study uses the so-called re-birthing technique together with the standard GA operations such as fitness, selection, crossover and mutation to accelerate the searching process. The finite difference method is used to calculate the design sensitivity required in mathematical programming techniques and three different techniques such as sequential linear programming (SLP), sequential quadratic programming(SQP) and modified feasible direction method(MFDM) are consistently used in the design optimization of geodesic dome. The optimum member sizes of geodesic dome against several external loads is evaluated by the codes $ISADO-GA{\alpha}$ and ISADO-OPT. From a numerical example, we found that both optimization techniques such as GA and mathematical programming technique are very effective to calculate the optimum member sizes of three dimensional discrete structures and it can provide a very useful information on the existing structural system and it also has a great potential to produce new structural system for large spatial structures.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.2
• /
• pp.111-120
• /
• 2017

This paper proposes an improved standard genetic algorithm (GA) of making a near optimal schedule for integrated process planning and scheduling problem (IPPS) considering tool flexibility and tool related constraints. Process planning involves the selection of operations and the allocation of resources. Scheduling, meanwhile, determines the sequence order in which operations are executed on each machine. Due to the high degree of complexity, traditionally, a sequential approach has been preferred, which determines process planning firstly and then performs scheduling independently based on the results. The two sub-problems, however, are complicatedly interrelated to each other, so the IPPS tend to solve the two problems simultaneously. Although many studies for IPPS have been conducted in the past, tool flexibility and capacity constraints are rarely considered. Various meta-heuristics, especially GA, have been applied for IPPS, but the performance is yet satisfactory. To improve solution quality against computation time in GA, we adopted three methods. First, we used a random circular queue during generation of an initial population. It can provide sufficient diversity of individuals at the beginning of GA. Second, we adopted an inferior selection to choose the parents for the crossover and mutation operations. It helps to maintain exploitation capability throughout the evolution process. Third, we employed a modification of the hybrid scheduling algorithm to decode the chromosome of the individual into a schedule, which can generate an active and non-delay schedule. The experimental results show that our proposed algorithm is superior to the current best evolutionary algorithms at most benchmark problems.

• Journal of Chest Surgery
• /
• v.55 no.3
• /
• pp.225-232
• /
• 2022

Background: Pulmonary lobectomy is the standard of care for the treatment of early-stage non-small cell lung cancer. This study investigated the rate of utilization of supplemental anesthesia in patients undergoing video-assisted thoracoscopic surgery (VATS) or open lobectomy using a national database and assessed the effect of regional block (RB) on postoperative outcomes. Methods: Patients who underwent lobectomy for lung cancer between 2014-2019 were identified in the American College of Surgeons National Surgical Quality Improvement Program. The patients' primary mode of anesthesia and supplemental anesthesia were recorded. Preoperative characteristics and postoperative outcomes were compared between 2 surgical groups: those who underwent general anesthesia (GA) alone versus GA with RB. Multivariable regression analyses were performed on the outcomes of interest. Results: In total, 13,578 patients met the study criteria, with 87% undergoing GA and the remaining 13% receiving GA and RB. The use of neuraxial anesthesia decreased over the years, while RB use increased up to 20% in 2019. Age, body mass index, and preoperative comorbidities were comparable between groups. Patients who underwent VATS were more likely to receive RB than those who underwent thoracotomy. RB was most often utilized by thoracic surgeons. An adjusted analysis showed that RB use was associated with shorter hospital stays and a reduced likelihood of prolonged length of stay, but a higher rate of surgical site infections (SSIs). Conclusion: In a large surgical database, there was underutilization of supplemental anesthesia in patients undergoing lobectomy for lung cancer. RB utilization was associated with a shorter length of hospital stay and an increase in SSI incidence.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.49-56
• /
• 2023

Machine learning methods diversely applied to the Internet of Things (IoT) field have been successful due to the enhancement of computer processing power. They offer an effective way of detecting malicious intrusions in IoT because of their high-level feature extraction capabilities. In this paper, we proposed a novel feature selection method for malicious intrusion detection in IoT by using an evolutionary technique - Genetic Algorithm (GA) and Machine Learning (ML) algorithms. The proposed model is performing the classification of BoT-IoT dataset to evaluate its quality through the training and testing with classifiers. The data is reduced and several preprocessing steps are applied such as: unnecessary information removal, null value checking, label encoding, standard scaling and data balancing. GA has applied over the preprocessed data, to select the most relevant features and maintain model optimization. The selected features from GA are given to ML classifiers such as Logistic Regression (LR) and Support Vector Machine (SVM) and the results are evaluated using performance evaluation measures including recall, precision and f1-score. Two sets of experiments are conducted, and it is concluded that hyperparameter tuning has a significant consequence on the performance of both ML classifiers. Overall, SVM still remained the best model in both cases and overall results increased.

• Proceedings of the Korean Magnestics Society Conference
• /
• 2004.12a
• /
• pp.160-160
• /
• 2004

• Proceedings of the Korean Magnestics Society Conference
• /
• 2007.05a
• /
• pp.46.2-46.2
• /
• 2007

• MALSORI
• /
• no.33_34
• /
• pp.23-42
• /
• 1997

This study has two main purposes. One is to explore the relationship between syntactic aspects and prosodic aspects in Standard Korean. The other is to provide speech synthesis with the information about such relationship. This study will focus on the prosodic behavior of subjective particles'-i/-ga', '-eun/-neun'. The prosodic features of subjective particles are described respectively. How do the elements such as the position of particles in a sentence, the sentence constituents, the length of the sentence and the rhythmic boundaries influence on the prosodic behavior are also investigated.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1995.04a
• /
• pp.142-146
• /
• 1995

In the paper, Fuzzy Logic Controller(FLC) that determines its optimal coefficients using Genetic Algorithms is considered. It is also applied to the inverted pendulum problem known popularly as a standard plant. Flexibility of the inverted pendulum has been taken into account. In the results, Fuzzy Logic Controller under consideration successfully controls both rigid mode and flexible mode. The rule base of Fuzzy Logic Controller is automatically tuned using not only trial-error method but also Genetic Algorithms.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2001.10a
• /
• pp.228-235
• /
• 2001

For standard size of farmland in Korea is small, we have to consume huge labor for cultivation and efficiency of machine is low. We practice the project, which make size of farmland enlarge. For many factors have to consider in design process in case of large-scale farmland, there are difficulties for comparing alternatives if we design it manually. So we need to techniques for establishing various alternatives and choosing the optimum design by the computer. In this study, fixing the boundary of project using the RGIS (Rural Geographical Information System) which standard electronic map in Korea. In the boundary, we analysis the many characteristics of farm land, optimize the adjustment process of field unit of farmland. In this process, we develop automatic farmland division techniques. The results of adapting the developed system show the usefulness to enlarge the size of farmland about 200%.

• The Journal of Fisheries Business Administration
• /
• v.34 no.1
• /
• pp.45-67
• /
• 2003

Main target of fishing policy was enlargement of fishing catches in Korea after 1960s. This has caused sustainable decrease of the amount on the fisheries resource. In the result, fishing managements in Korea have suffered from aggravation of management. In this research, it is estimated the technical efficiency on Korean Off-shore Stow Nets Fishery that was made publication by Farrel in 1957. According to the analysis, Its were excessive to the gap of technical efficiency among Korean Off-shore Stow Nets Fishing boats. The gaps were excessive not only among each fishing managements but also by tonnage class and by region. Then we can recognize we need the change of Fishing Policy. That is, we should change for main target of fishing policy from enlargement of fishing catches to the policy of Price. And we should consider the supply of standard tonnage boats and specialization of fisheries by regions.