• Industrial Engineering and Management Systems
• /
• v.8 no.3
• /
• pp.171-180
• /
• 2009

Population learning algorithm (PLA) is a population-based method that was inspired by the similarities to the phenomenon of social education process in which a diminishing number of individuals enter an increasing number of learning stages. The study aims to develop a framework that repeatedly applying the PLA to solve the discrete resource constrained project scheduling problem with two objectives: minimizing project makespan and renewable resource availability, which are two most common concerns of management when a project is being executed. The PLA looping framework will provide a number of near Pareto optimal schedules for the management to make a choice. Different improvement schemes and learning procedures are applied at different stages of the process. The process gradually becomes more and more sophisticated and time consuming as there are less and less individuals to be taught. An experiment with ProGen generated instances was conducted, and the results demonstrated that the looping framework using PLA outperforms those using genetic local search, particle swarm optimization with local search, scatter search, as well as biased sampling multi-pass algorithm, in terms of several performance measures of proximity. However, the diversity using spread metric does not reveal any significant difference between these five looping algorithms.

• Journal of the Korean Institute of Educational Facilities
• /
• v.21 no.6
• /
• pp.33-42
• /
• 2014

The objective of this study is to investigate learning factors (stability, attention and activation) in school by electroencephalogram (theta, alpha and beta waves) analysis during relaxed or concentrated. In order to measure electroencephalograms, MP 150 by Biopac and ECI Electro-Cap are employed. Three types of color temperatures (3000K, 5000K, 7000K) are used and 13 undergraduate and 12 graduate students are selected as experimental subjects. When subjects are relaxed during contemplation or concentrated during mental arithmetic, we compare with stability, attention and activation indices. The test results show that subjects were stable when color temperature is 5000K. Subjects gave best attention when color temperature is 7000K. Subjects activated well when color temperature is 3000K during relaxed attention. However, subjects activated rigorous when color temperature is 7000K during constrained attention.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.6
• /
• pp.522-530
• /
• 2002

This paper introduces a neural network (NN) -based nonlinear predictor for the LP (Linear Prediction) residual. To evaluate the effectiveness of the NN-based nonlinear predictor for LP-residual, we first compared the average prediction gain of the linear long-term predictor with that of the NN-based nonlinear long-term predictor. Then, the effects on the quantization noise of the nonlinear prediction residuals were investigated for the NN-based nonlinear predictor A new NN predictor takes into consideration not only prediction error but also quantization effects. To increase robustness against the quantization noise of the nonlinear prediction residual, a constrained back propagation learning algorithm, which satisfies a Kuhn-Tucker inequality condition is proposed. Experimental results indicate that the prediction gain of the proposed NN predictor was not seriously decreased even when the constrained optimization algorithm was employed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.1
• /
• pp.32-40
• /
• 2013

In this paper, we propose a multi-channel speech enhancement algorithm using beamforming and direction-of-arrival (DOA)-based masking. The proposed algorithm enhances noisy speech basically by the linearly constrained minimum variance (LCMV) algorithm and then a mel-scale Wiener filter designed using DOA-based masking is applied to remove still remaining noises. To improve the performance, we optimize the learning rate of the adaptive filters in LCMV and the DOA threshold to detect target speech spectrum. As performance indices, the perceptual evaluation of speech quality (PESQ) score and output SNRs are measured. Experimantal results show that the proposed algorithm outperforms the conventional LCMV beamformer by 0.09 in PESQ score and 5.75 dB in output SNR, respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.316-321
• /
• 2003

This paper presents a design method of the wavelet neural network based controller using direct adaptive control method to deal with a stable intelligent control of chaotic systems. The various uncertainties, such as mechanical parametric variation, external disturbance, and unstructured uncertainty influence the control performance. However, the conventional control methods such as optimal control, adaptive control and robust control may not be feasible when an explicit, faithful mathematical model cannot be constructed. Therefore, an intelligent control system that is an on-line trained WNN controller based on direct adaptive control method with adaptive learning rates is proposed to control chaotic nonlinear systems whose mathematical models are not available. The adaptive learning rates are derived in the sense of discrete-type Lyapunov stability theorem, so that the convergence of the tracking error can be guaranteed in the closed-loop system. In the whole design process, the strict constrained conditions and prior knowledge of the controlled plant are not necessary due to the powerful learning ability of the proposed intelligent control system. The gradient-descent method is used for training a wavelet neural network controller of chaotic systems. Finally, the effectiveness and feasibility of the proposed control method is demonstrated with application to the chaotic systems.

• Korean Journal of Clinical Pharmacy
• /
• v.26 no.4
• /
• pp.283-290
• /
• 2016

Experiential education is a core curriculum of 6-year pharmacy education. Practicing pharmacists lie at the heart of experiential education serving as preceptors for undergraduate pharmacy students during experiential education. Preceptors are, however, confronted with a challenge of caring for patients and teaching students at the same time in a time-constrained environment. To improve the effectiveness and outcomes of experiential education, practicing pharmacists are required to demonstrate educational competence. Even small teaching moments can provide students with valuable learning opportunities that they could not have from on their own. Thus, it is vital to provide education and training for preceptors to advance their teaching skills. This article will describe practical and effective teaching skills that preceptors could adopt in the experiential education for pharmacy students. It is important that preceptors should use different teaching skills for different learners, according to their level of experience and knowledge, learning styles and needs, as well as the type of the practice. Therefore, possessing diverse teaching skills provides flexibility to adapt teaching to each student's learning levels and needs, and to the charateristics of the practice environment. Preceptors' level of confidence and comfort in using teaching skills can be enhanced through continuous practice and training, which consequently leads to the improved effectiveness of experiential education and student's satisfaction with the education.

• Journal of Broadcast Engineering
• /
• v.26 no.7
• /
• pp.855-861
• /
• 2021

Neural Architecture Search (NAS) is cutting-edge technology in the machine learning community. NAS Without Training (NASWOT) recently has been proposed to tackle the high demand of computational resources in NAS by leveraging some indicators to predict the performance of architectures before training. The advantage of these indicators is that they do not require any training. Thus, NASWOT reduces the searching time and computational cost significantly. However, NASWOT only considers high-performing networks which does not guarantee a fast inference speed on hardware devices. In this paper, we propose a multi objectives reward function, which considers the network's latency and the predicted performance, and incorporate it into the Reinforcement Learning approach to search for the best networks with low latency. Unlike other methods, which use FLOPs to measure the latency that does not reflect the actual latency, we obtain the network's latency from the hardware NAS bench. We conduct extensive experiments on NAS-Bench-201 using CIFAR-10, CIFAR-100, and ImageNet-16-120 datasets, and show that the proposed method is capable of generating the best network under latency constrained without training subnetworks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2801-2815
• /
• 2022

With the advent and realization of Software Defined Network (SDN) architecture, many organizations are now shifting towards this paradigm. SDN brings more control, higher scalability, and serene elasticity. The SDN spontaneously changes the network configuration according to the dynamic network requirements inside the constrained environments. Therefore, a monitoring system that can monitor the physical and virtual entities is needed to operate this type of network technology with high efficiency and proficiency. In this manuscript, we propose a real-time monitoring system for data collection and visualization that includes the Prometheus, node exporter, and Grafana. A node exporter is configured on the physical devices to collect the physical and virtual entities resources utilization logs. A real-time Prometheus database is configured to collect and store the data from all the exporters. Furthermore, the Grafana is affixed with Prometheus to visualize the current network status and device provisioning. A monitoring system is deployed on the physical infrastructure of the KOREN topology. Data collected by the monitoring system is further pre-processed and restructured into a dataset. A monitoring system is further enhanced by including machine learning techniques applied on the formatted datasets to identify the elephant flows. Additionally, a Random Forest is trained on our generated labeled datasets, and the classification models' performance are verified using accuracy metrics.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1223-1237
• /
• 2024

Autonomous vehicles use onboard sensors to sense the surrounding environment. In complex autonomous driving scenarios, the detection and recognition capabilities are constrained, which may result in serious accidents. An efficient way to enhance the detection and recognition capabilities is establishing collaborations with the neighbor vehicles. However, the collaborations introduce additional challenges in terms of the data heterogeneity, communication cost, and data privacy. In this paper, a novel personalized federated learning framework is proposed for addressing the challenges and enabling efficient collaborations in autonomous driving environment. For obtaining a global model, vehicles perform local training and transmit logits to a central unit instead of the entire model, and thus the communication cost is minimized, and the data privacy is protected. Then, the inference similarity is derived for capturing the characteristics of data heterogeneity. The vehicles are divided into clusters based on the inference similarity and a weighted aggregation is performed within a cluster. Finally, the vehicles download the corresponding aggregated global model and train a personalized model which is personalized for the cluster that has similar data distribution, so that accuracy is not affected by heterogeneous data. Experimental results demonstrate significant advantages of our proposed method in improving the efficiency of collaborative perception and reducing communication cost.

• Journal of Korea Game Society
• /
• v.10 no.2
• /
• pp.113-121
• /
• 2010

This study proposes an educational game system that fit for portable internet environment as a solution to disadvantages of conventional education systems such as lack of understanding learners' learning level and one-way learning. The study analyses conventional e-Learning contents and platforms and proposes a new system adequate for high contents reusability and user-demand service. The learning contents that mainly consist of animations and games can be adjusted to learners' level, and therefore, learners can study according to various scenarios, not constrained in a fixed pattern. Our system is expected to bring much more fun to learners and the education can be conducted more effectively. To show the effectiveness of our system, an example of english pronunciation game was illustrated. As a result, the week points of the conventional e-Learning was overcame and new features of the interactivity was adopted to build a more effective educational game system.