• Journal of Biomedical Engineering Research
• /
• v.34 no.4
• /
• pp.182-188
• /
• 2013

This study aims to develop a practical algorithm which can detect freezing of gait(FOG) in patients with Parkinson's disease(PD). Eighteen PD patients($68.8{\pm}11.1yrs.$) participated in this study, and three($68.7{\pm}4.0yrs.$) of them showed FOG. We suggested two time-domain algorithms(with 1-axis or 3-axes acceleration signals) and compared them with the frequency-domain algorithm in the literature. We measured the acceleration of left foot with a 3-axis accelerometer inserted at the insole of a shoe. In the time-domain method, the root-mean-square(RMS) acceleration was calculated in a moving window of 4s and FOG was defined as the periods during which RMS accelerations located within FOG range. The parameters in each algorithm were optimized for each subject using the simulated annealing method. The sensitivity and specificity were same, i.e., $89{\pm}8%$ for the time-domain method with 1-axis acceleration and were $91{\pm}7%$ and $90{\pm}8%$ for the time-domain method with 3-axes acceleration, respectively. Both performances were better in the time-domain methods than in the frequency-domain method although the results were statistically insignificant. The amount of calculation in the time-domain method was much smaller than in the frequency-domain method. Therefore it is expected that the suggested time domain algorithm would be advantageous in the systematic implementation of FOG detection.

• Journal of Computational Design and Engineering
• /
• v.1 no.3
• /
• pp.187-193
• /
• 2014

One of the hottest challenges in automotive industry is related to weight reduction in sheet metal forming processes, in order to produce a high quality metal part with minimal material cost. Stamping is the most widely used sheet metal forming process; but its implementation comes with several fabrication flaws such as springback and failure. A global and simple approach to circumvent these unwanted process drawbacks consists in optimizing the initial blank shape with innovative methods. The aim of this paper is to introduce an efficient methodology to deal with complex, computationally expensive multicriteria optimization problems. Our approach is based on the combination of methods to capture the Pareto Front, approximate criteria (to save computational costs) and global optimizers. To illustrate the efficiency, we consider the stamping of an industrial workpiece as test-case. Our approach is applied to the springback and failure criteria. To optimize these two criteria, a global optimization algorithm was chosen. It is the Simulated Annealing algorithm hybridized with the Simultaneous Perturbation Stochastic Approximation in order to gain in time and in precision. The multicriteria problems amounts to the capture of the Pareto Front associated to the two criteria. Normal Boundary Intersection and Normalized Normal Constraint Method are considered for generating a set of Pareto-optimal solutions with the characteristic of uniform distribution of front points. The computational results are compared to those obtained with the well-known Non-dominated Sorting Genetic Algorithm II. The results show that our proposed approach is efficient to deal with the multicriteria shape optimization of highly non-linear mechanical systems.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.146-149
• /
• 2002

The aim of stereotactic radiosurgery(SRS) is to deliver a high dose to a target region and a low dose to critical organ through only one or a few irradiation. To satisfy this aim, optimized irradiating conditions must be searched in the planning. Thus, many mathematical methods such as gradient method, simulated annealing and genetic algorithm had been proposed to find out the conditions automatically. There were some limitations using these methods: the long calculation time, and the difficulty of unique solution due to the different shape of tumor. In this study, optimization protocol using ideal models and data base was proposed. Proposed optimization protocol constitutes two steps. First step was a preliminary work. Some possible ideal geometry shapes, such as sphere, cylinder, cone shape or the combination, were assumed to approximate the real tumor shapes. Optimum variables such as isocenter position or collimator size, were determined so that the high dose region could be shaped to fit ideal models with the arrangement of multiple isocenter. Data base were formed with those results. Second, any shaped real targets were approximated to these models using geometry comparison. Then, optimum variables for ideal geometry were chosen from the data base predetermined, and final parameters were obtained by adjusting these data. Although the results of applying the data base to patients were not superior to the result of optimization in each case, it can be acceptable as a starting point of plan.

• Journal of Radiation Protection and Research
• /
• v.28 no.2
• /
• pp.87-95
• /
• 2003

The fabrication process and the structure of PIN semiconductor detectors have been designed optimally by simulation for doping concentration and width of p+ layer, impurities re-contribution due to annealing and the current distribution due to guard ring at the sliced edges. The characteristics to radiation response has been also simulated in terms of Monte Carlo Method. The device has been fabricated on n type, $400\;{\Omega}cm$, orientation <100>, Floating-Zone silicon wafer using the simulation results. The leakage current density of $0.7nA/cm^2/100{\mu}m$ is achieved by this process. The good linearity of radiation response to Cs-137 was kept within the exposure ranges between 5 mR/h and 25 R/h. This proposed process could be applied for fabricating a PIN semiconductor detector for measuring individual dose.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.27-35
• /
• 2021

Local search has been used to solve various combinatorial optimization problems. One of the most important factors in local search is the method of generating a neighbor solution. In this paper, we propose neighbor generation strategies of local search for permutation-based combinatorial optimization, and compare the performance of each strategies targeting the traveling salesman problem. In this paper, we propose a total of 10 neighbor generation strategies. Basically, we propose 4 new strategies such as Rotation in addition to the 4 strategies such as Swap which have been widely used in the past. In addition, there are Combined1 and Combined2, which are made by combining basic neighbor generation strategies. The experiment was performed by applying the basic local search, but changing only the neighbor generation strategy. As a result of the experiment, it was confirmed that the performance difference is large according to the neighbor generation strategy, and also confirmed that the performance of Combined2 is the best. In addition, it was confirmed that Combined2 shows better performance than the existing local search methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.8
• /
• pp.1011-1017
• /
• 2019

This paper proposes reinforcement learning to solve the node-disjoint path problem which establishes multipath for reliable data transmission in wireless ad-hoc networks. The node-disjoint path problem is a problem of determining a plurality of paths so that the intermediate nodes do not overlap between the source and the destination. In this paper, we propose an optimization method considering transmission distance in a large-scale wireless ad-hoc network using Q-learning in reinforcement learning, one of machine learning. Especially, in order to solve the node-disjoint path problem in a large-scale wireless ad-hoc network, a large amount of computation is required, but the proposed reinforcement learning efficiently obtains appropriate results by learning the path. The performance of the proposed reinforcement learning is evaluated from the viewpoint of transmission distance to establish two node-disjoint paths. From the evaluation results, it showed better performance in the transmission distance compared with the conventional simulated annealing.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1193-1201
• /
• 2020

Cell planning, which determines the cell structure for location management of mobile terminals in mobile communications, has been dealt with as an important research task to determine network performance. Among the factors influencing the cell structure planning in mobile communication, the signal cost for location management plays the most important role. In this paper, we propose an optimization algorithm that minimizes the location management cost of all the cells used to plan the cell structure in the network with reporting cell structure in mobile communication. The proposed algorithm uses a Tabu search algorithm, which is a meta-heuristic algorithm, and the proposed algorithm proposes a new neighborhood generation method to obtain a result close to the optimal solution. In order to evaluate the performance of the proposed algorithm, the simulation was performed in terms of location management cost and algorithm execution time. The evaluation results show that the proposed algorithm outperforms the existing genetic algorithm and simulated annealing.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.107-112
• /
• 2022

In an embedded system such as a drone, it is difficult to store, transfer and analyze the entire hyper-spectral image to a server in real time because it takes a lot of power and time. Therefore, the hyper-spectral image data is transmitted to the server through dimension reduction or compression pre-processing. Feature selection method are used to send only the bands for analysis purpose, and these algorithms usually take a lot of processing time depending on the size of the image, even though the efficiency is high. In this paper, by improving the temporal disadvantage of the band selection algorithm, the time taken 24 hours was reduced to around 60-180 seconds based on the 40000*682 image resolution of 8GB data, and the use of 7.6GB RAM was significantly reduced to 2.3GB using 45 out of 150 bands. However, in terms of pixel classification performance, more than 98% of analysis results were derived similarly to the previous one.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.10
• /
• pp.192-199
• /
• 2000

The design of multi-stage gear drives is a time-consuming process because it includes more complicated problems, which are not considered in the design of single-stage gear drives. The designer has no determine the number of reduction stages and the gear ratios of each reduction stage. In addition, the design problems include not only dimensional design but also configuration design of gear drive elements. There is no definite rule or principle for these types of design problems. Thus the design practices largely depend on the sense and the experiences of the designer, and consequently result in undesirable design solution. A new and generalized design algorithm has been proposed to support the designer at the preliminary phase of the design of multi-stage gear drives. The proposed design algorithm automates the design process by integrating the dimensional design and the configuration design process. The algorithm consists of four steps. In the first step, the user determines the number of reduction stages. In the second step, gear ratios of every stage are chosen using the random search method. The values of the basic design parameters of a gear are chose in the third step by using the generate and test method. Then the values of the dimensions, such as pitch diameter, outer diameter and face width, are calculated for the configuration design in the next step. The strength and durability of each gear is guaranteed by the bending strength and the pitting resistance rating practices by using AGMA rating formulas. In the final step, the configuration design is carried out using simulated annealing algorithm. The positions of gears and shafts are determined to minimize the geometrical volume (size) of a gearbox while avoiding interferences between them. These steps are carried out iteratively until a desirable solution is acquired. The proposed design algorithm is applied to the preliminary design of four-stage gear drives in order to validate the availability. The design solution has considerably good results in both aspects of the dimensional and the configuration design.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.6
• /
• pp.13-27
• /
• 2012

Integer programming-based local search(IPbLS) is a kind of local search based on simple hill-climbing search and adopts integer programming for neighbor generation unlike general local search. According to an existing research [1], IPbLS is known as an effective method for the multidimensional knapsack problem(MKP) which has received wide attention in operations research and artificial intelligence area. However, the existing research has a shortcoming that it verified the superiority of IPbLS targeting only largest-scale problems among MKP test problems in the OR-Library. In this paper, I verify the superiority of IPbLS more objectively by applying it to other problems. In addition, unlike the existing IPbLS that combines simple hill-climbing search and integer programming, I propose methods combining other local search algorithms like hill-climbing search, tabu search, simulated annealing with integer programming. Through the experimental results, I confirmed that IPbLS shows comparable or better performance than the best known heuristic search also for mid or small-scale MKP test problems.