• Advances in Computational Design
• /
• 제8권1호
• /
• pp.37-59
• /
• 2023

Squat reinforced concrete (SRC) shear walls are a critical part of the structure for both office/residential buildings and nuclear structures due to their significant role in withstanding seismic loads. Despite this, empirical formulae in current design standards and published studies demonstrate a considerable disparity in predicting SRC wall shear strength. The goal of this research is to develop and evaluate hybrid and ensemble artificial neural network (ANN) models. State-of-the-art population-based algorithms are used in this research for hybrid intelligence algorithms. Six models are developed, including Honey Badger Algorithm (HBA) with ANN (HBA-ANN), Hunger Games Search with ANN (HGS-ANN), fitness-distance balance coyote optimization algorithm (FDB-COA) with ANN (FDB-COA-ANN), Averaging Ensemble (AE) neural network, Snapshot Ensemble (SE) neural network, and Stacked Generalization (SG) ensemble neural network. A total of 434 test results of SRC walls is utilized to train and assess the models. The results reveal that the SG model not only minimizes prediction variance but also produces predictions (with R²= 0.99) that are superior to other models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.816-839
• /
• 2023

In a random vector functional link (RVFL) network, shortcomings such as local optimal stagnation and decreased convergence performance cause a reduction in the accuracy of illumination correction by only inputting the weights and biases of hidden neurons. In this study, we proposed an improved regularized random vector functional link (RRVFL) network algorithm with an optimized grey wolf optimizer (GWO). Herein, we first proposed the moth-flame optimization (MFO) algorithm to provide a set of excellent initial populations to improve the convergence rate of GWO. Thereafter, the MFO-GWO algorithm simultaneously optimized the input feature, input weight, hidden node and bias of RRVFL, thereby avoiding local optimal stagnation. Finally, the MFO-GWO-RRVFL algorithm was applied to ameliorate the performance of illumination correction of various test images. The experimental results revealed that the MFO-GWO-RRVFL algorithm was stable, compatible, and exhibited a fast convergence rate.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.878-879
• /
• 2021

Most state-of-the-art CNNs for action recognition are based on a two-stream architecture: RGB frames stream represents the appearance and the optical flow stream interprets the motion of action. However, the cost of optical flow computation is very high and then it increases action recognition latency. We introduce a design strategy for action recognition inspired by a two-stream network and teacher-student architecture. There are two sub-networks in our neural networks, the optical flow sub-network as a teacher and the RGB frames sub-network as a student. In the training stage, we distill the feature from the teacher as a baseline to train student sub-network. In the test stage, we only use the student so that the latency reduces without computing optical flow. Our experiments show that its advantages over two-stream architecture in both speed and performance.

• Journal of Positioning, Navigation, and Timing
• /
• 제13권2호
• /
• pp.137-147
• /
• 2024

This paper presents a novel Long Short-Term Memory (LSTM) network architecture for the integration of an Inertial Measurement Unit (IMU) and Global Navigation Satellite Systems (GNSS). The proposed algorithm consists of two independent LSTM networks and the LSTM networks are trained to predict attitudes and velocities from the sequence of IMU measurements and mechanization solutions. In this paper, three GNSS receivers are used to provide Real Time Kinematic (RTK) GNSS attitude and position information of a vehicle, and the information is used as a target output while training the network. The performance of the proposed method was evaluated with both experimental and simulation data using a lowcost IMU and three RTK-GNSS receivers. The test results showed that the proposed LSTM network could improve positioning accuracy by more than 90% compared to the position solutions obtained using a conventional Kalman filter based IMU/GNSS integration for more than 30 seconds of GNSS outages.

• Management Science and Financial Engineering
• /
• 제14권2호
• /
• pp.45-66
• /
• 2008

Refuse collection, one of important elements in reverse logistics, is an activity rendering recyclables or wastes and moving them to some points where further treatment is required. Among various decisions in the collection activity, we focus on network design, which is the problem of locating collection points as well as allocating refuses at demand points to collection points while satisfying the capacity restriction at each collection point. Here, the collection point is the place where recyclables or wastes near the point are gathered, and locating the collection points is done by selecting them from a given set of potential sites. The objective is to minimize the sum of fixed costs to open collection points and transportation costs to move refuses from demand points to collection points. An integer programming model is developed to represent the problem mathematically and due to the complexity of the problem, two types of heuristics, one with simultaneous and the others with separate location and allocation, are suggested. Computational experiments were done on test problems up to 500 potential sites, and the results are reported. In particular, some heuristics gave near optimal solutions for small-size test problems, i.e., 2% gaps in average from the optimal solution values.

• 전기전자학회논문지
• /
• 제18권3호
• /
• pp.435-441
• /
• 2014

V2X 협력통신 시스템은 차량 운전을 쉽고 안전하게 할 수 있도록 도와주는 융합기술로 실제 교통상황에서 이러한 기술을 평가하고 효과를 예상하기 위해서는 실차 기반의 도로 구축과 통신 장비 구축, 검증 전문 인력 투입을 필요로 하며 많은 비용과 시간을 투입해야한다. 위와 같은 이유로 연구소 및 대학에서는 개발한 시스템을 테스트 하는데 어려움을 겪고 있으며, V2X 장비 개발이 가속화됨에 따라 차량 안전 어플리케이션과 V2X 통신기술을 테스트 할 수 있는 신뢰성 있는 테스트베드 구축에 대한 필요성이 증가하고 있다. 본 논문에서는 위와 같은 문제점들을 해결하기 위해 시뮬레이션을 기반으로 하는 테스팅 환경을 구성하기 위하여 External 인터페이스 구현을 통하여 트래픽 시뮬레이터와 네트워크 시뮬레이터를 연동하는 시스템을 구현하였다.

• 한국IT서비스학회지
• /
• 제14권1호
• /
• pp.159-173
• /
• 2015

This paper presents a study on the Internet of Things based low-power wireless sensor networks for remote monitoring of wildlife ecosystem due to climate change. Especially, it is targeting the wild vegetation communities ecological monitoring. First, we performed a pre-test and analysis for selecting the appropriate frequency for the sensor network to collect and deliver information reliably in harsh propagation environment of the forest area, and selected for sensors for monitoring wild vegetation communities on the basis of considerations for selecting the best sensor. In addition, we have presented the platform concept and hierarchical function structures for effectively monitoring, analyzing and predicting of ecosystem changes, to apply the Internet of Things in the ecological monitoring area. Based on this, this paper presents the system architecture and design of the Internet of Things based low-power wireless sensor networks for monitoring the ecosystem of the wild vegetation communities. Finally, we constructed and operated the test-bed applied to real wild trees, using the developed prototype based on the design.

• ETRI Journal
• /
• 제36권2호
• /
• pp.188-196
• /
• 2014

This paper describes a simple delay diversity technique for terrestrial digital multimedia broadcasting (T-DMB) and digital audio broadcasting in a single-frequency network (SFN). For the diversity technique, a delay diversity scheme is adopted. In the delay diversity scheme, a non-delayed signal is transmitted in the first antenna, and delayed versions of the signal are transmitted in each additional antenna. For an SFN environment with multiple transmitters, delay diversity can be executed by controlling the emission times of the transmitters. This SFN delay diversity scheme does not require any hardware changes in either the transmitter or receiver, and perfect backward compatibility can be acquired. To evaluate the performance improvement, laboratory tests are executed with various types of commercial T-DMB receivers as well as a measurement receiver. The improvement in the bit error rate performance is evaluated using a measurement receiver, and an improvement of the threshold of visibility value is evaluated for commercial receivers. Test results show that the T-DMB system can obtain diversity gain using the described technique.

• 한국의류학회지
• /
• 제44권3호
• /
• pp.556-571
• /
• 2020

This study predicts consumer preference for social clothing at work, excluding uniforms using the self-product congruence theory that also establishes a model to predict the preference for recommended products that match the consumer's own image. A total of 490 Korean male office workers participated in this study. Participants' self-image and the product images of 20 apparel items were measured using nine adjective semantic scales (namely elegant, stable, sincere, refined, intense, luxury, bold, conspicuous, and polite). A model was then constructed to predict the consumer preferences using a neural network with Python and TensorFlow. The resulting Predict Preference Model using Product Image (PPMPI) was trained using product image and the preference of each product. Current research confirms that product preference can be predicted by the self-image instead of by entering the product image. The prediction accuracy rate of the PPMPI was over 80%. We used 490 items of test data consisting of self-images to predict the consumer preferences for using the PPMPI. The test of the PPMPI showed that the prediction rate differed depending on product attributes. The prediction rate of work apparel with normative images was over 70% and higher than for other forms of apparel.

• Earthquakes and Structures
• /
• 제10권4호
• /
• pp.757-768
• /
• 2016

In the past decades, effect of near field earthquake on the historical monuments has attracted the attention of researchers. So, many analyses in this regard have been presented. Tunnels as vital arteries play an important role in management after the earthquake crisis. However, digging tunnels and seismic effects of earthquake on the historical monuments have always been a challenge between engineers and historical supporters. So, in a case study, effect of near field earthquake on the historical monument was investigated. For this research, Finite Element Analysis (FEM) in soil environment and soil-structure interaction was used. In Plaxis 2D software, different accelerograms of near field earthquake were applied to the geometric definition. Analysis validations were performed based on the previous numerical studies. Creating a nonlinear relationship with space parameter, time, angular and numerical model outputs was of practical and critical importance. Hence, artificial Neural Network (ANN) was used and two linear layers and Tansig function were considered. Accuracy of the results was approved by the appropriate statistical test. Results of the study showed that buildings near and far from the tunnel had a special seismic behavior. Scattering of seismic waves on the underground tunnels on the adjacent buildings was influenced by their distance from the tunnel. Finally, a static test expressed optimal convergence of neural network and Plaxis.