• International Journal of Automotive Technology
• /
• v.6 no.6
• /
• pp.643-655
• /
• 2005

The frontal crash optimization of S-shaped closed-hat section member using the homogenization method, design of experiment (DOE) and response surface method (RSM) was studied. The optimization to effectively absorb more crash energy was studied to introduce the reinforcement design. The main focus of design was to decide the optimum size and thickness of reinforcement. In this study, the location of reinforcement was decided by homogenization method. Also, the effective size and thickness of reinforcements was studied by design of experiments and response surface method. The effects of various impact velocity for reinforcement design were researched. The high impact velocity reinforcement design showed to absorb the more crash energy than low velocities design. The effect of size and thickness of reinforcement was studied and the sensitivity of size and thickness was different according to base thickness of model. The optimum size and thickness of the reinforcement has shown a direct proportion to the thickness of base model. Also, the thicker the base model was, the effect of optimization using reinforcement was the bigger. The trend curve for effective size and thickness of reinforcement using response surface method was obtained. The predicted size and thickness of reinforcement by RSM were compared with results of DOE. The results of a specific dynamic mean crushing loads for the predicted design by RSM were shown the small difference with the predicted results by RSM and DOE. These trend curves can be used as a basic guideline to find the optimum reinforcement design for S-shaped member.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.319-325
• /
• 2023

In this study, we proposed a method for hyperparameter optimization in the building and training of a deep learning model designed to process point cloud data collected by a millimeter-wave radar system. The primary aim of this study is to facilitate the deployment of a baseline model in resource-constrained IoT devices. We evaluated a RadHAR baseline deep learning model trained on a public dataset composed of point clouds representing five distinct human activities. Additionally, we introduced a coarse-to-fine hyperparameter optimization procedure, showing substantial potential to enhance model efficiency without compromising predictive performance. Experimental results show the feasibility of significantly reducing model size without adversely impacting performance. Specifically, the optimized model demonstrated a 3.3% improvement in classification accuracy despite a 16.8% reduction in number of parameters compared th the baseline model. In conclusion, this research offers valuable insights for the development of deep learning models for resource-constrained IoT devices, underscoring the potential of hyperparameter optimization and model size reduction strategies. This work contributes to enhancing the practicality and usability of deep learning models in real-world environments, where high levels of accuracy and efficiency in data processing and classification tasks are required.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.157-164
• /
• 2022

The proposed privacy preserving scheme has identified the drawbacks of existing schemes in Vehicular Networks. This prototype enhances the number of nodes by decreasing the cluster size. This algorithm is integrated with the whale optimization algorithm and Block Chain Technology. A set of results are done through the NS-2 simulator in the direction to check the effectiveness of proposed algorithm. The proposed method shows better results than with the existing techniques in terms of Delay, Drop, Delivery ratio, Overhead, throughout under the denial of attack.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2005.04a
• /
• pp.351-358
• /
• 2005

Many methods have been developed and are in use for structural size optimization problems, In which the cross-sectional areas or sizing variables are usually assumed to be continuous. In most practical structural engineering design problems, however, the design variables are discrete. This paper proposes an efficient optimization method for structures with discrete-sized variables based on the harmony search (HS) meta-heuristic algorithm. The recently developed HS algorithm was conceptualized using the musical process of searching for a perfect state of harmony. It uses a stochastic random search instead of a gradient search so that derivative information is unnecessary In this paper, a discrete search strategy using the HS algorithm is presented in detail and its effectiveness and robustness, as compared to current discrete optimization methods, are demonstrated through a standard truss example. The numerical results reveal that the proposed method is a powerful search and design optimization tool for structures with discrete-sized members, and may yield better solutions than those obtained using current method.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.10a
• /
• pp.664-667
• /
• 1997

In this study, it is attempted to obtain the optimized size of holes in 15 square plate models where a hole exists on every quadrant of a plate, and to get eigenvalues and mode shapes by performing free vibration analysis for each model. For free vibration analysis and optimization of' hole sizes, the uniaxial tension is applied for the loading condition. From the results of this study, it is known that more stable structures can be designed by changing the natural frequency depending on the location and the optuiiunl size of holes. and further studies are considered to be necessary for the basic design information.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4228-4247
• /
• 2018

Many methods have been developed for the vehicles to create clusters in vehicular ad hoc networks (VANETs). Usually, nodes are vehicles in the VANETs, and they are dynamic in nature. Clusters of vehicles are made for making the communication between the network nodes. Cluster Heads (CHs) are selected in each cluster for managing the whole cluster. This CH maintains the communication in the same cluster and with outside the other cluster. The lifetime of the cluster should be longer for increasing the performance of the network. Meanwhile, lesser the CH's in the network also lead to efficient communication in the VANETs. In this paper, a novel algorithm for clustering which is based on the social behavior of Gray Wolf Optimization (GWO) for VANET named as Intelligent Clustering using Gray Wolf Optimization (ICGWO) is proposed. This clustering based algorithm provides the optimized solution for smooth and robust communication in the VANETs. The key parameters of proposed algorithm are grid size, load balance factor (LBF), the speed of the nodes, directions and transmission range. The ICGWO is compared with the well-known meta-heuristics, Multi-Objective Particle Swarm Optimization (MOPSO) and Comprehensive Learning Particle Swarm Optimization (CLPSO) for clustering in VANETs. Experiments are performed by varying the key parameters of the ICGWO, for measuring the effectiveness of the proposed algorithm. These parameters include grid sizes, transmission ranges, and a number of nodes. The effectiveness of the proposed algorithm is evaluated in terms of optimization of number of cluster with respect to transmission range, grid size and number of nodes. ICGWO selects the 10% of the nodes as CHs where as CLPSO and MOPSO selects the 13% and 14% respectively.

• Structural Engineering and Mechanics
• /
• v.5 no.5
• /
• pp.609-624
• /
• 1997

The optimization of cutouts in composite plates was investigated by implementing a procedure known as Evolutionary Structural Optimization. Perforations were introduced into a finite element mesh of the plate from which one or more cutouts of a predetermined size were evolved. In the examples presented, plates were rejected from around each evolving cutout based on a predefined rejection criterion. The limiting ply within each plate element around the cutout was determined based on the Tsai-Hill failure criterion. Finite element plates with values below the product of the average Tsai-Hill number and a rejection criterion were subsequently removed. This process was iterated until a steady state was reached and the rejection criterion was then incremented by an evolutionary rate and the above steps repeated until the desired cutout area was achieved. Various plates with differing lay-up and loading parameters were investigated to demonstrate the generality and robustness of this optimization procedure.

• Advances in Computational Design
• /
• v.2 no.3
• /
• pp.195-210
• /
• 2017

Simultaneous optimization of trusses which concurrently takes into account design variables related to the size, shape and topology of the structure is recognized as highly complex optimization problems. In this class of optimization problems, it is possible to encounter several unstable mechanisms throughout the solution process. However, to obtain a feasible solution, these unstable mechanisms somehow should be rejected from the set of candidate solutions. This study proposes triangular unit based method (TUBM) instead of ground structure method, which is conventionally used in the topology optimization, to decrease the complexity of search space of simultaneous optimization of the planar truss structures. TUBM considers stability of the triangular units for 2 dimensional truss systems. In addition, integrated particle swarm optimizer (iPSO) strengthened with robust technique so called improved fly-back mechanism is employed as the optimizer tool to obtain the solution for these class of problems. The results obtained in this study show the applicability and efficiency of the TUBM combined with iPSO for the simultaneous optimization of planar truss structures.

• Journal of Mechanical Science and Technology
• /
• v.16 no.5
• /
• pp.609-618
• /
• 2002

In practical designs, most of the multidisciplinary problems have a large-size and complicate design system. Since multidisciplinary problems have hundreds of analyses and thousands of variables, the grouping of analyses and the order of the analyses in the group affect the speed of the total design cycle. Therefore, it is very important to reorder and regroup the original design processes in order to minimize the total computational cost by decomposing large multidisciplinary problems into several multidisciplinary analysis subsystems (MDASS) and by processing them in parallel. In this study, a new decomposition method is proposed for parallel processing of multidisciplinary design optimization, such as collaborative optimization (CO) and individual discipline feasible (IDF) method. Numerical results for two example problems are presented to show the feasibility of the proposed method.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.54 no.4
• /
• pp.163-173
• /
• 2005

The conventional optimization study for electromagnetic systems has been mostly on the shape or size optimization. The goal for these optimization methods is to improve performance of electromagnetic systems by optimizing the interface shape of two different materials while their given layout or initial topology are held. The feasible topology can be diverse and an appropriate topology will give much better design results. In this paper we propose a theory and an algorithm for topology optimization of electromagnetic systems, which are based on the finite element method. The topology optimization technique employes a direct searching method of sensitivity analysis in which the information of material sensitivity is used. Two numerical examples of a switched reluctance motor and an electrostatic actuator of MEMS are tested and their design results show that the optimization method is valid and useful for the topology and basic layout design of electromagnetic systems.