• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.80-87
• /
• 2024

This paper focuses on improving accuracy in constrained computing settings by employing the ReLU (Rectified Linear Unit) activation function. The research conducted involves modifying parameters of the ReLU function and comparing performance in terms of accuracy and computational time. This paper specifically focuses on optimizing ReLU in the context of a Multilayer Perceptron (MLP) by determining the ideal values for features such as the dimensions of the linear layers and the learning rate (Ir). In order to optimize performance, the paper experiments with adjusting parameters like the size dimensions of linear layers and Ir values to induce the best performance outcomes. The experimental results show that using ReLU alone yielded the highest accuracy of 96.7% when the dimension sizes were 30 - 10 and the Ir value was 1. When combining ReLU with the Adam optimizer, the optimal model configuration had dimension sizes of 60 - 40 - 10, and an Ir value of 0.001, which resulted in the highest accuracy of 97.07%.

• Journal of the Korea Society of Computer and Information
• /
• v.5 no.2
• /
• pp.90-97
• /
• 2000

This paper describes an speaker-adaptive speech recognition system which make a reliable recognition of speech signal for new speakers. In the Proposed method, an speech spectrum of new speaker is adapted to the reference speech spectrum by using Parameters of a 1st linear transformation network at the front of phoneme classification neural network. And the recognition system is based on semicontinuous HMM(hidden markov model) which use the multilayer perceptron as a fuzzy vector quantizer. The experiments on the isolated word recognition are performed to show the recognition rate of the recognition system. In the case of speaker adaptation recognition, the recognition rate show significant improvement for the unadapted recognition system.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.11
• /
• pp.176-183
• /
• 1998

A new recognition technique using neural network coupled with Genetic Algorithms (GAs) was proposed. This technique concentrate on efficient Electromyography signal recognition through out improving neural network's several demerits. GAs paly a role of selecting Multilayer Perceptron's optimized initial connection weights by its typical global search. Electro Myography signal was pre-processed with Hidden Markov Model (HMM) in order to refect its time-varying property into input pattern except other features such as Zero Crossing Number(ZCN) and Integral Absolute Value (IAV). Results for 6 primitive motions show that the suggested technique has better performance in learning time and recognition rates than already established ordinary methods. Moreover, it performed stable recognition without convergence into a local minimum.

• Journal of Ecology and Environment
• /
• v.31 no.3
• /
• pp.233-241
• /
• 2008

Functional feeding groups (FFGs) of benthic macroinvertebrates are guilds of invertebrate taxa that obtain food in similar ways, regardless of their taxonomic affinities. They can represent a heterogeneous assemblage of benthic fauna and may indicate disturbances of their habitats. The proportion of different groups can change in response to disturbances that affect the food base of the system, thereby offering a means of assessing disruption of ecosystem functioning. In this study, we used benthic macroinvertebrate communities collected at 650 sites of 23 different water types in the province of Overijssel, The Netherlands. Physical and chemical environmental factors were measured at each sampling site. Each taxon was assigned to its corresponding FFG based on its food resources. A multilayer perceptron (MLP) using a backpropagation algorithm, a supervised artificial neural network, was applied to evaluate the influence of environmental variables to the FFGs of benthic macroinvertebrates through a sensitivity analysis. In the evaluation of input variables, the sensitivity analysis with partial derivatives demonstrates the relative importance of influential environmental variables on the FFG, showing that different variables influence the FFG in various ways. Collector-filterers and shredders were mainly influenced by $Ca^{2+}$ and width of the streams, and scrapers were influenced mostly with $Ca^{2+}$ and depth, and predators were by depth and pH. $Ca^{2+}$ and depth displayed relatively high influence on all four FFGs, while some variables such as pH, %gravel, %silt, and %bank affected specific groups. This approach can help to characterize community structure and to ecologically assess target ecosystems.

• Journal of the Korea Convergence Society
• /
• v.8 no.10
• /
• pp.45-52
• /
• 2017

Drifter is an equipment for observing the characteristics of seawater in the ocean, and it can be used to predict effluent oil diffusion and to observe ocean currents. In this paper, we design models or the prediction of drifter trajectory using machine learning. We propose methods for estimating the trajectory of drifter using support vector regression, radial basis function network, Gaussian process, multilayer perceptron, and recurrent neural network. When the propose mothods were compared with the existing MOHID numerical model, performance was improve on three of the four cases. In particular, LSTM, the best performed method, showed the imporvement by 47.59% Future work will improve the accuracy by weighting using bagging and boosting.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2519-2521
• /
• 2003

In this paper, we propose Self-Organizing Fuzzy Polynomial Neural Networks(SOFPNN) architecture for optimal model identification and discuss a comprehensive design methodology supporting its development. It is shown that this network exhibits a dynamic structure as the number of its layers as well as the number of nodes in each layer of the SOFPNN are not predetermined (as this is the case in a popular topology of a multilayer perceptron). As the form of the conclusion part of the rules, especially the regression polynomial uses several types of high-order polynomials such as linear, quadratic, and modified quadratic. As the premise part of the rules, both triangular and Gaussian-like membership function are studied and the number of the premise input variables used in the rules depends on that of the inputs of its node in each layer. We introduce two kinds of SOFPNN architectures, that is, the basic and modified one with both the generic and the advanced type. The superiority and effectiveness of the proposed SOFPNN architecture is demonstrated through nonlinear function numerical example.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_2
• /
• pp.1307-1315
• /
• 2021

The Changjiang Diluted Water (CDW) spreads over the East China Sea every summer and significantly affects the sea surface salinity changes in the seas around Jeju Island and the southern coast of Korea peninsula. Sometimes its effect extends to the eastern coast of Korea peninsula through the Korea Strait. Specifically, the CDW has a significant impact on marine physics and ecology and causes damage to fisheries and aquaculture. However, due to the limited field surveys, continuous observation of the CDW in the East China Sea is practically difficult. Many studies have been conducted using satellite measurements to monitor CDW distribution in near-real time. In this study, an algorithm for estimating Sea Surface Salinity (SSS) in the East China Sea was developed using the Geostationary Ocean Color Imager (GOCI). The Multilayer Perceptron Neural Network (MPNN) method was employed for developing an algorithm, and Soil Moisture Active Passive (SMAP) SSS data was selected for the output. In the previous study, an algorithm for estimating SSS using GOCI was trained by 2016 observation data. By comparison, the train data period was extended from 2015 to 2020 to improve the algorithm performance. The validation results with the National Institute of Fisheries Science (NIFS) serial oceanographic observation data from 2011 to 2019 show 0.61 of coefficient of determination (R²) and 1.08 psu of Root Mean Square Errors (RMSE). This study was carried out to develop an algorithm for monitoring the surface salinity of the East China Sea using GOCI and is expected to contribute to the development of the algorithm for estimating SSS by using GOCI-II.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.6
• /
• pp.757-772
• /
• 2019

The purpose of this paper is to measure the clustering change and analyze empirical results, and choose the clustering ports for Busan, Incheon, and Gwangyang ports by using Artificial Neural Network, Social Network, and Tabu Search models on 38 Asian container ports over the period 2007-2016. The models consider number of cranes, depth, birth length, and total area as inputs and container throughput as output. Followings are the main empirical results. First, the variables ranking order which affects the clustering according to artificial neural network are TEU, birth length, depth, total area, and number of cranes. Second, social network analysis shows the same clustering in the benevolent and aggressive models. Third, the efficiency of domestic ports are worsened after clustering using social network analysis and tabu search models. Forth, social network and tabu search models can increase the efficiency by 37% compared to that of the general CCR model. Fifth, according to the social network analysis and tabu search models, 3 Korean ports could be clustered with Asian ports like Busan Port(Kobe, Osaka, Port Klang, Tanjung Pelepas, and Manila), Incheon Port(Shahid Rajaee, and Gwangyang), and Gwangyang Port(Aqaba, Port Sulatan Qaboos, Dammam, Khor Fakkan, and Incheon). Korean seaport authority should introduce port improvement plans by using the methods used in this paper.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.4
• /
• pp.47-55
• /
• 2010

In this paper, we proposed a recognition system of smile facial expression for smile treatment training. The proposed system detects face candidate regions by using Haar-like features from camera images. After that, it verifies if the detected face candidate region is a face or non-face by using SVM(Support Vector Machine) classification. For the detected face image, it applies illumination normalization based on histogram matching in order to minimize the effect of illumination change. In the facial expression recognition step, it computes facial feature vector by using PCA(Principal Component Analysis) and recognizes smile expression by using a multilayer perceptron artificial network. The proposed system let the user train smile expression by recognizing the user's smile expression in real-time and displaying the amount of smile expression. Experimental result show that the proposed system improve the correct recognition rate by using face region verification based on SVM and using illumination normalization based on histogram matching.

• The KIPS Transactions:PartB
• /
• v.10B no.7
• /
• pp.777-784
• /
• 2003

In this Paper. we propose a recognition method of machine printed characters based on the combination of recognition units using multiple neural networks. In our recognition method, the input character is classified into one of 7 character types among which the first 6 types are for Hangul character and the last type is for non-Hangul characters. Hangul characters are recognized by several MLP (multilayer perceptron) neural networks through two stages. In the first stage, we divide Hangul character image into two or three recognition units (HRU : Hangul recognition unit) according to the combination fashion of graphemes. Each recognition unit composed of one or two graphemes is recognized by an MLP neural network with an input feature vector of pixel direction angles. In the second stage, the recognition aspect features of the HRU MLP recognizers in the first stage are extracted and forwarded to a subsequent MLP by which final recognition result is obtained. For the recognition of non-Hangul characters, a single MLP is employed. The recognition experiments had been performed on the character image database collected from 50,000 real letter envelope images. The experimental results have demonstrated the superiority of the proposed method.