• Journal of the Korea Institute of Military Science and Technology
• /
• v.9 no.1 s.24
• /
• pp.24-32
• /
• 2006

This paper is to analyze the effectiveness of multistatic sonar network based on detection performance. The multistatic sonar network is a distributed detection system that places a source and multi-receivers apart. So it needs a detection technique that relates to decision rule and optimization of sonar system to improve the detection performance. For this we propose a data fusion procedure using Bayesian decision and optimal sensor arrangement by optimizing a bistatic sonar. Also, to analyze the detection performance effectively, we propose the environmental model that simulates a propagation loss and target strength suitable for multistatic sonar networks in real surroundings. The effectiveness analysis on the multistatic sonar network confirms itself as a promising tool for effective allocation of detection resources in multistatic sonar system.

• Journal of Korean Association for Spatial Structures
• /
• v.15 no.2
• /
• pp.87-94
• /
• 2015

This paper aimed at modeling a fine triangular grid for network dome by using Harmony Search (HS) algorithm. For this purpose, an optimization process to find a fine regular triangular mesh on the curved surface was proposed and the analysis program was developed. An objective function was consist of areas and edge's length of each triangular and its standard deviations, and design variables were subject to the upper and lower boundary which was calculated on the nodal connectivity. Triangular network dome model, which was initially consist of randomly irregular triangular mesh, was selected for the target example and the numerical result was analyzed in accordance with the HS parameters. From the analysis results of adopted model, the fitness function has been converged and the optimized triangular grid could be obtained from the initially distorted network dome example.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.9
• /
• pp.111-117
• /
• 2002

In most machining companies, operators decide the cutting condition, a pair of spindle speed (5) and table federate (F) by experience and subjective judgment. As cutting conditions are determined by operators' experience and ability, inconsistent cutting conditions are given in same operating conditions. The objective of this study is to develop the cutting condition decision system which utilizes shop data and predicts tool life by neural network and eventually leads to the optimal cutting condition. The production time per piece is considered for an optimization object. We will discuss the process of an optimal cutting condition decision by neural network. By this process, a series of shop data is stored. And neural network is constructed for prediction of tool life and the optimal cutting condition is recommended from a cutting condition decision system using the stored shop data. The results show that the developed system is rational in searching the optimal cutting conditions on job operations.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.174-177
• /
• 2016

Wireless network-on-chip (WNoC) can alleviate critical path problem of existing typical NoCs by integrating radio-frequency module on router. In this paper, core-connection-aware genetic algorithm-based core and WIR mapping methodology at small world WNoC is presented. The methodology could optimize the critical path between cores with heavy communication. The 33% of average latency improvement is achieved compared to random mapping methodology.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.10
• /
• pp.2382-2388
• /
• 2014

To provide network reliability in indoor wireless communication systems, we should resolve the problem of unexpected network failure rapidly. In this paper, we propose an adaptive resource management (ARM) scheme to support seamless connectivity to users. In consideration of system throughput and user fairness simultaneously, the ARM scheme adaptively determines the set of healing channels, and performs scheduling and power allocation iteratively based on a constrained non-convex optimization technique. Through intensive simulations, we demonstrate the superior performance results of the proposed ARM scheme in terms of the average cell capacity and user fairness.

• Phonetics and Speech Sciences
• /
• v.13 no.1
• /
• pp.45-51
• /
• 2021

End-to-end (E2E) automatic speech recognition (ASR) has achieved promising performance gains with the introduced self-attention network, Transformer. However, due to training time and the number of hyperparameters, finding the optimal hyperparameter set is computationally expensive. This paper investigates the impact of hyperparameters in the Transformer network to answer two questions: which hyperparameter plays a critical role in the task performance and training speed. The Transformer network for training has two encoder and decoder networks combined with Connectionist Temporal Classification (CTC). We have trained the model with Wall Street Journal (WSJ) SI-284 and tested on devl93 and eval92. Seventeen hyperparameters were selected from the ESPnet training configuration, and varying ranges of values were used for experiments. The result shows that "num blocks" and "linear units" hyperparameters in the encoder and decoder networks reduce Word Error Rate (WER) significantly. However, performance gain is more prominent when they are altered in the encoder network. Training duration also linearly increased as "num blocks" and "linear units" hyperparameters' values grow. Based on the experimental results, we collected the optimal values from each hyperparameter and reduced the WER up to 2.9/1.9 from dev93 and eval93 respectively.

• International Journal of Computer Science & Network Security
• /
• v.22 no.3
• /
• pp.236-244
• /
• 2022

Network Mobility Basic Support (NEMO BS) protocol has been accredited and approved by Internet Engineering Task Force (IETF) working group for mobility of sub-networks. Trains, aircrafts and buses are three examples of typical applications for this protocol. The NEMO BS protocol was designed to offer Internet access for a group of passengers in a roaming vehicle in an adequate fashion. Furthermore, in NEMO BS protocol, specific gateways referred to Mobile Routers (MRs) are responsible for carrying out the mobility management operations. Unfortunately, the main limitations of this basic solution are pinball suboptimal routing, excessive signaling cost, scalability, packet delivery overhead and handoff latency. In order to tackle shortcomings of triangular routing and Quality of Service (QoS) deterioration, the proposed scheme (Diff-FH NEMO) has previously evolved for end-users in moving network. In this sense, the article focuses on an exhaustive analytic evaluation at Home Agent (HA) entity of the proposed solutions. An investigation has been conducted on the signaling costs to assess the performance of the proposed scheme (Diff-FH NEMO) in comparison with the standard NEMO BS protocol and MIPv6 based Route Optimization (MIRON) scheme. The obtained results demonstrate that, the proposed scheme (Diff-FH NEMO) significantly improves the signaling cost at the HA entity in terms of the subnet residence time, number of mobile nodes, the number of DMRs, the number of LFNs and the number of CNs.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.33-38
• /
• 2021

This paper presents a comparative study between the parameter-optimized Pacejka model and artificial neural network model for the tire force estimation. The two different approaches are investigated and compared in this study. First, offline optimization is conducted based on Pacejka Magic Formula model to determine the proper parameter set for the minimization of tire force error between the model and test data set. Second, deep neural network model is used to fit the model to the tire test data set. The actual tire forces are measured using MTS Flat-Track test platform and the measurements are used as the reference tire data set. The focus of this study is on the applicability of machine learning technique to tire force estimation. It is shown via the regression results that the deep neural network model is more effective in describing the tire force than the parameter-optimized Pacejka model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.334-349
• /
• 2022

The effectiveness of Wi-Fi networks is greatly influenced by the optimization of contention window (CW) parameters. Unfortunately, the conventional approach employed by IEEE 802.11 wireless networks is not scalable enough to sustain consistent performance for the increasing number of stations. Yet, it is still the default when accessing channels for single-users of 802.11 transmissions. Recently, there has been a spike in attempts to enhance network performance using a machine learning (ML) technique known as reinforcement learning (RL). Its advantage is interacting with the surrounding environment and making decisions based on its own experience. Deep RL (DRL) uses deep neural networks (DNN) to deal with more complex environments (such as continuous state spaces or actions spaces) and to get optimum rewards. As a result, we present a new approach of CW control mechanism, which is termed as contention window threshold (CW_Threshold). It uses the DRL principle to define the threshold value and learn optimal settings under various network scenarios. We demonstrate our proposed method, known as a smart exponential-threshold-linear backoff algorithm with a deep Q-learning network (SETL-DQN). The simulation results show that our proposed SETL-DQN algorithm can effectively improve the throughput and reduce the collision rates.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.171-176
• /
• 2022

A dramatic rise in the number of people dying from heart disease has prompted efforts to find a way to identify it sooner using efficient approaches. A variety of variables contribute to the condition and even hereditary factors. The current estimate approaches use an automated diagnostic system that fails to attain a high level of accuracy because it includes irrelevant dataset information. This paper presents an effective neural network with convolutional layers for classifying clinical data that is highly class-imbalanced. Traditional approaches rely on massive amounts of data rather than precise predictions. Data must be picked carefully in order to achieve an earlier prediction process. It's a setback for analysis if the data obtained is just partially complete. However, feature extraction is a major challenge in classification and prediction since increased data increases the training time of traditional machine learning classifiers. The work integrates the CNN-MDRP classifier (convolutional neural network (CNN)-based efficient multimodal disease risk prediction with TANFIS (tuned adaptive neuro-fuzzy inference system) for earlier accurate prediction. Perform data cleaning by transforming partial data to informative data from the dataset in this project. The recommended TANFIS tuning parameters are then improved using a Laplace Gaussian mutation-based grasshopper and moth flame optimization approach (LGM²G). The proposed approach yields a prediction accuracy of 98.40 percent when compared to current algorithms.