• Geomechanics and Engineering
• /
• 제32권3호
• /
• pp.271-291
• /
• 2023

Settlement estimation in cohesion materials is a crucial topic to tackle because of the complexity of the cohesion soil texture, which could be solved roughly by substituted solutions. The goal of this research was to implement recently developed machine learning features as effective methods to predict settlement (S_m) of shallow foundations over cohesion soil properties. These models include hybridized support vector regression (SVR), random forests (RF), and coot optimization algorithm (COM), and black widow optimization algorithm (BWOA). The results indicate that all created systems accurately simulated the S_m, with an R² of better than 0.979 and 0.9765 for the train and test data phases, respectively. This indicates extraordinary efficiency and a good correlation between the experimental and simulated S_m. The model's results outperformed those of ANFIS - PSO, and COM - RF findings were much outstanding to those of the literature. By analyzing established designs utilizing different analysis aspects, such as various error criteria, Taylor diagrams, uncertainty analyses, and error distribution, it was feasible to arrive at the final result that the recommended COM - RF was the outperformed approach in the forecasting process of S_m of shallow foundation, while other techniques were also reliable.

• Geomechanics and Engineering
• /
• 제34권1호
• /
• pp.43-49
• /
• 2023

Knowledge of minimum horizontal stress (S_hmin) is a significant step in determining full stress tensor. It provides crucial information for the production of sand, hydraulic fracturing, determination of safe mud weight window, reservoir production behavior, and wellbore stability. Calculating the S_hmin using indirect methods has been proved to be awkward because a lot of data are required in all of these models. Also, direct techniques such as hydraulic fracturing are costly and time-consuming. To figure these problems out, this work aims to apply the long-short-term memory (LSTM) algorithm to S_hmin time-series prediction. 13956 datasets obtained from an oil well logging operation were applied in the models. 80% of the data were used for training, and 20% of the data were used for testing. In order to achieve the maximum accuracy of the LSTM model, its hyper-parameters were optimized significantly. Through different statistical indices, the LSTM model's performance was compared with with other machine learning methods. Finally, the optimized LSTM model was recommended for S_hmin prediction in the well logging operation.

• Asia pacific journal of information systems
• /
• 제29권4호
• /
• pp.752-770
• /
• 2019

The purpose of this study is to incorporate telemarketing processes to improve telemarketing performance. For this application, we have attempted to mix the model of machine learning to extract potential customers with personalisation techniques to derive recommended products from actual contact. Most of traditional recommendation systems were mainly in ways such as collaborative filtering, which predicts items with a high likelihood of future purchase, based on existing purchase transactions or preferences for products. But, under these systems, new users or items added to the system do not have sufficient information, and generally cause problems such as a cold start that can not obtain satisfactory recommendation items. Also, indiscriminate telemarketing attempts can backfire as they increase the dissatisfaction and fatigue of customers who do not want to be contacted. To this purpose, this study presented a multi-purpose hybrid recommendation algorithm to achieve two goals: to select customers with high possibility of contact, and to recommend products to selected customers. In addition, we used subscription data from telemarketing agency that handles insurance products to derive realistic applicability of the proposed recommendation system. Our proposed recommendation system would certainly solve the cold start and scarcity problem of existing recommendation algorithm by using contents information such as customer master information and telemarketing history. Also. the model could show excellent performance not only in terms of overall performance but also in terms of the recommendation success rate of the unpopular product.

• 한국ITS학회 논문지
• /
• 제11권5호
• /
• pp.38-45
• /
• 2012

시간 종속적 가로망에 대한 최단경로 탐색은 ITS분야의 경로 일정계획과 실시간 내비게이션 시스템에서 중요한 부분을 차지한다. 본 연구에서는 매시간간격 변동적인 링크 통행속도를 고려하는 one-to-one 시간 종속적 최단시간 경로 알고리즘을 제시한다. 이를 위해, 먼저 기존의 일반적인 최단거리 경로 알고리즘 중에서 실제 도로망에서 비교적 빠르고 효율적인 알고리즘으로 알려져 있는 3가지의 알고리즘들, 즉, two queues 구조를 가진 Graph growth 알고리즘, approximate buckets 구조를 가진 Dijkstra 알고리즘, double buckets 구조를 가진 Dijkstra 알고리즘이 선택되었다. 이 알고리즘들은 모두 네트워크 내 하나의 노드에서 모든 노드(one-to-all)로의 최단거리 경로를 빠르게 탐색하기위해 개발되었다. 선택된 알고리즘들은 시간 종속적 도로망에 대해 하나의 출발노드에서 하나의 목적노드(one-to-one)로의 최단시간 경로 탐색이 가능하도록 확장된다. 또한, 제안된 3가지의 시간 종속적 최단시간 경로탐색 알고리즘들은 미국의 Anaheim, Baltimore, Chicago, Philadelphia 4개 도시의 실제 가로망에 적용하여 검증 평가된다. 결과적으로, 도시부 가로망을 대상으로 한 시간 종속적 최단시간 경로탐색 알고리즘으로 double buckets 구조를 가진 확장된 Dijkstra 알고리즘이 추천된다.

• 한국정보처리학회논문지
• /
• 제4권4호
• /
• pp.955-962
• /
• 1997

현재 및 미래의 다양한 통신망에서 멀티미디어 회의 관련 응용 서비스를 구현하기 위해서는 기본적인 회의 서비스에 관련된 규약이 필요하며 이와 관련하여 제정된 규약이 MCS(Multipoint Communication Service)이다. 본 논문은 멀티미디어 회의 시스템을 위하여 국제 표준으로 권고되어 있는 다지점 통신 서비스(MCS)를 구현하기 위하여 관련 자료를 분석하고, 이를 근간으로 하여 알고리즘의 제안하고 이를 UMX machine 및 windows/NT cachine에서 구현하였다.

• Asia pacific journal of information systems
• /
• 제6권2호
• /
• pp.5-17
• /
• 1996

There are various cases that we vote for making a decision or combining ideas (i.e. human being's opinions) in group meetings. Group Decision Support System(GDSS) provides us with a number of voting methods for decision making or aggregation of the ideas. It is generally difficult to select a voting method appropriate for given a meeting situation, without any aid of experts or computers having a knowledge on voting. In this paper we propose a supporting system for selecting an appropriate voting method. Since the selected method is recommended to the facilitator of GDSS, a part of time and effort related with the voting would be reduced. The knowledge in the system is represented as rules that are inductively generated from examples of voting. We used UNiK-INDUCE with ID3 algorithm so as to learn, which is a tool of developing expert systems.

• 응용통계연구
• /
• 제10권2호
• /
• pp.339-352
• /
• 1997

소표본으로부터 형성되는 2원 분할표에는 빈도가 작은 칸들이 적지 않기 때문에 대표본이론에 근거한 카이제곱 검증 등 기존 통계적 방법의 적용이 적절하지 않응 수가 있다. 이런 경우에 한 대안으로서 정확검증법(exact tests)이 개발되어 있으나 이것이 너무 많은 계산을 요구하므로 사용하기가 쉽지 않다. 본 연구는 소표본 2원 분할표에서, 단순한 몬테칼로 알로리즘에 의한 행 균일성 가설의 카이제곱 임의화 검증법(randomization test)을 제안하고 튜키(Tukey) 형의 행간 다중비교법을 제안한다. 아울러 열 범주가 순서형인 2원 분할표에 대하여도 유사한 방법론을 적용할 수 있음을 밝힌다.

• 대한기계학회논문집B
• /
• 제21권2호
• /
• pp.202-212
• /
• 1997

In this study, performance of the multi-stage explicit methods for numerical computation of the unsteady Navier-Stokes equations is investigated. Three methods under consideration are 1 st-, 2 nd-, and 4 th-order Runge-Kutta (R-K) methods. Compared in this estimation is stability, accuracy, and CPU time of each method. The computational codes developed are applied to the two-dimensional flow in a square cavity driven by an oscillating lid. It turned out that at Reynolds number 400, the 1 st-order R-K method is the best, while at 3200 the 2 nd-order R-K is recommended. At higher Reynolds numbers, it is conjectured that the 4 th-order R-K method will be the best algorithm among three due to its highest stability.

• 한국자동차공학회논문집
• /
• 제10권1호
• /
• pp.133-142
• /
• 2002

To improve the hydraulic control performance of ABS, it is necessary to establish an efficient control algorithm. And also it is necessary to ova]Hate a hydraulic modulator with solenoid valve quantitatively. In this paper, FEM and permeance method are used to analyze dynamic characteristics of outlet valve. In return, mathmatical modeling of a hydraulic modulator and operating pressure is presented, and the model parameters of an outlet valve are moving plunger, spring constant and orifice diameter. This study shows the way to improve the dynamic characteristic of an ABS outlet valve heavily depending on operating pressure. It is recommended that operating pressure should be justified at the first step toward the design to get the optimal design of an outlet valve.

• Structural Engineering and Mechanics
• /
• 제43권6호
• /
• pp.795-821
• /
• 2012

The size and topology of geometrically nonlinear dome structures are optimized thereby minimizing both its entire weight & joint (node) displacements and maximizing load-carrying capacity. Design constraints are implemented from provisions of American Petroleum Institute specification (API RP2A-LRFD). In accordance with the proposed design constraints, the member responses computed by use of arc-length technique as a nonlinear structural analysis method are checked at each load increment. Thus, a penalization process utilized for inclusion of unfeasible designations to genetic search is correspondingly neglected. In order to solve this complex design optimization problem with multiple objective functions, Non-dominated Sorting Genetic Algorithm II (NSGA II) approach is employed as a multi-objective optimization tool. Furthermore, the flexibility of proposed optimization is enhanced thereby integrating an automatic dome generating tool. Thus, it is possible to generate three distinct sphere-shaped dome configurations with varying topologies. It is demonstrated that the inclusion of brace (diagonal) members into the geometrical configuration of dome structure provides a weight-saving dome designation with higher load-carrying capacity. The proposed optimization approach is recommended for the design optimization of geometrically nonlinear dome structures.