• Phonetics and Speech Sciences
• /
• v.3 no.3
• /
• pp.91-98
• /
• 2011

In this paper, a multi-channel speech enhancement method using the linearly constrained minimum variance (LCMV) algorithm and a variable learning rate control is proposed. To control the learning rate for adaptive filters of the LCMV algorithm, the direction of arrival (DOA) is measured for each short-time input signal and the likelihood function of the target speech presence is estimated to control the filter learning rate. Using the likelihood measure, the learning rate is increased during the pure noise interval and decreased during the target speech interval. To optimize the parameter of the mapping function between the likelihood value and the corresponding learning rate, an exhaustive search is performed using the Bark's scale distortion (BSD) as the performance index. Experimental results show that the proposed algorithm outperforms the conventional LCMV with fixed learning rate in the BSD by around 1.5 dB.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.58 no.2
• /
• pp.164-171
• /
• 2009

This paper presents new learning algorithm of dynamic Bayesian networks (DBN) by means of constrained least square (LS) estimation algorithm and gradient descent method. First, we propose constrained LS based parameter estimation for a Markov chain (MC) model given observation data sets. Next, a gradient descent optimization is utilized for online estimation of a hidden Markov model (HMM), which is bi-linearly constructed by adding an observation variable to a MC model. We achieve numerical simulations to prove its reliability and superiority in which a series of non stationary random signal is applied for the DBN models respectively.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.419-422
• /
• 2024

본 논문에서는 다항식 보간법의 일종인 이동최소자승법(Moving least squares, MLS)을 네트워크로 학습하여, Divergence-constrained MLS 벡터장을 효율적으로 표현하는 방법을 제안한다. 벡터장을 구성하기 위해 MLS는 스칼라가 아닌 벡터 보간을 해야 하므로 행렬과 벡터의 크기가 더 커지며, 이는 계산량이 커짐을 나타낸다. 고차 보간(High-order interpolation)이 가능한 특징은 장점이 되지만, 계산량이 매우 크기 때문에 시뮬레이션에는 활용이 어렵다. Divergence-constrained MLS를 유체 시뮬레이션에 적용한 경우가 있지만, 실제로 슈퍼컴퓨터(Supercomputer)를 해야 장면 제작이 가능하므로 효용성이 떨어진다. 본 논문에서는 이러한 문제를 해결하기 위해 네트워크 학습을 통한 Divergence-constrained MLS 벡터장을 표현할 수 있는 결과를 보여준다.

• Journal of the Korea Convergence Society
• /
• v.11 no.11
• /
• pp.257-267
• /
• 2020

In this study, we predicted the employment ratio by the export industry using various machine learning methods and verified whether the prediction performance is improved by applying the constrained forecast combination method to these predicted values. In particular, the constrained forecast combination method is known to improve the prediction accuracy and stability by imposing the sum of predicted values' weights up to one. In addition, this study considered various variables affecting the employment ratio of each industry, and so we adopted recursive feature elimination method that allows efficient use of machine learning methods. As a result, the constrained forecast combination showed more accurate prediction performance than the predicted values of the machine learning methods, and in particular, the stability of the prediction performance of the constrained forecast combination was higher than that of other machine learning methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.50.4-50
• /
• 2001

In this paper, exploiting repetitive properties, a constrained digital regulation technique for first order hyperbolic PDE systems is proposed that guarantees the stability and performance of the closed loop system.

• Journal of Korea Multimedia Society
• /
• v.24 no.1
• /
• pp.67-74
• /
• 2021

As IoT(Internet Of Things) devices like a smart sensor have constrained power sources, a power strategy is critical in WSN(Wireless Sensor Networks). Therefore, it is necessary to figure out the residual power of each sensor node for managing power strategies in WSN, which, however, requires additional data transmission, leading to more power consumption. In this paper, a residual power estimation method was proposed, which uses ignorantly small amount of power consumption in the resource-constrained wireless networks including WSN. A residual power prediction is possible with the least data transmission by using Machine Learning method with some training data in this proposal. The performance of the proposed scheme was evaluated by machine learning method, simulation, and analysis.

• Smart Media Journal
• /
• v.12 no.3
• /
• pp.68-76
• /
• 2023

Emerging mobile edge computing (MEC) can be used in battery-constrained Internet of things (IoT). The execution latency of IoT applications can be improved by offloading computation-intensive tasks to an MEC server. Recently, the popularity of unmanned aerial vehicles (UAVs) has increased rapidly, and UAV-based MEC systems are receiving considerable attention. In this paper, we propose a dynamic computation offloading paradigm for UAV-based MEC systems, in which a UAV flies over an urban environment and provides edge services to IoT devices on the ground. Since most IoT devices are energy-constrained, we formulate our problem as a Markov decision process considering the energy level of the battery of each IoT device. We also use model-free Q-learning for time-critical tasks to maximize the system utility. According to our performance study, the proposed scheme can achieve desirable convergence properties and make intelligent offloading decisions.

• 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.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.1
• /
• pp.80-89
• /
• 2014

A stochastic optimal power flow (S-OPF) model considering uncertainties of load and wind power is developed based on chance constrained programming (CCP). The difficulties in solving the model are the nonlinearity and probabilistic constraints. In this paper, a limit relaxation approach and an iterative learning control (ILC) method are implemented to solve the S-OPF model indirectly. The limit relaxation approach narrows the solution space by introducing regulatory factors, according to the relationship between the constraint equations and the optimization variables. The regulatory factors are designed by ILC method to ensure the optimality of final solution under a predefined confidence level. The optimization algorithm for S-OPF is completed based on the combination of limit relaxation and ILC and tested on the IEEE 14-bus system.

• Nuclear Engineering and Technology
• /
• v.55 no.8
• /
• pp.2854-2863
• /
• 2023

Objective: To present a hybrid approach that incorporates a constrained beam-hardening estimator (CBHE) and deep learning (DL)-based post-refinement for metal artifact reduction in dental cone-beam computed tomography (CBCT). Methods: Constrained beam-hardening estimator (CBHE) is derived from a polychromatic X-ray attenuation model with respect to X-ray transmission length, which calculates associated parameters numerically. Deep-learning-based post-refinement with an artifact disentanglement network (ADN) is performed to mitigate the remaining dark shading regions around a metal. Artifact disentanglement network (ADN) supports an unsupervised learning approach, in which no paired CBCT images are required. The network consists of an encoder that separates artifacts and content and a decoder for the content. Additionally, ADN with data normalization replaces metal regions with values from bone or soft tissue regions. Finally, the metal regions obtained from the CBHE are blended into reconstructed images. The proposed approach is systematically assessed using a dental phantom with two types of metal objects for qualitative and quantitative comparisons. Results: The proposed hybrid scheme provides improved image quality in areas surrounding the metal while preserving native structures. Conclusion: This study may significantly improve the detection of areas of interest in many dentomaxillofacial applications.