• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.104-107
• /
• 2022

autoencoder deep learning model has excellent ability to restore abnormal data to normal data, so it is not appropriate for anomaly detection. In addition, the Inpainting method, which is a method of restoring hidden data after masking (masking) a part of the data, has a problem in that the restoring ability is poor for noisy images. In this paper, we use a method of modifying and improving the MLP-Mixer model to mask the image at a certain ratio and to reconstruct the image by delivering compressed information of the masked image to the model. After constructing a model learned with normal data from the MVTec AD dataset, a reconstruction error was obtained by inputting normal and abnormal images, respectively, and anomaly detection was performed through this. As a result of the performance evaluation, it was found that the proposed method has superior anomaly detection performance compared to the existing method.

• Smart Structures and Systems
• /
• v.32 no.1
• /
• pp.37-47
• /
• 2023

Indirect determination of pan evaporation (PE) has been highly regarded, due to the advantages of intelligent models employed for this objective. This work pursues improving the reliability of a popular intelligent model, namely multi-layer perceptron (MLP) through surmounting its computational knots. Available climatic data of Fresno weather station (California, USA) is used for this study. In the first step, testing several most common trainers of the MLP revealed the superiority of the Levenberg-Marquardt (LM) algorithm. It, therefore, is considered as the classical training approach. Next, the optimum configurations of two metaheuristic algorithms, namely cuttlefish optimization algorithm (CFOA) and teaching-learning-based optimization (TLBO) are incorporated to optimally train the MLP. In these two models, the LM is replaced with metaheuristic strategies. Overall, the results demonstrated the high competency of the MLP (correlations above 0.997) in the presence of all three strategies. It was also observed that the TLBO enhances the learning and prediction accuracy of the classical MLP (by nearly 7.7% and 9.2%, respectively), while the CFOA performed weaker than LM. Moreover, a comparison between the efficiency of the used metaheuristic optimizers showed that the TLBO is a more time-effective technique for predicting the PE. Hence, it can serve as a promising approach for indirect PE analysis.

• Steel and Composite Structures
• /
• v.44 no.6
• /
• pp.867-882
• /
• 2022

Predicting the compressive strength of concrete (CSoC) is of high significance in civil engineering. The CSoC is a highly dependent and non-linear parameter that requires powerful models for its simulation. In this work, two novel optimization techniques, namely evaporation rate-based water cycle algorithm (ER-WCA) and equilibrium optimizer (EO) are employed for optimally finding the parameters of a multi-layer perceptron (MLP) neural processor. The efficiency of these techniques is examined by comparing the results of the ensembles to a conventionally trained MLP. It was observed that the ER-WCA and EO optimizers can enhance the training accuracy of the MLP by 11.18 and 3.12% (in terms of reducing the root mean square error), respectively. Also, the correlation of the testing results climbed from 78.80% to 82.59 and 80.71%. From there, it can be deduced that both ER-WCA-MLP and EO-MLP can be promising alternatives to the traditional approaches. Moreover, although the ER-WCA enjoys a larger accuracy, the EO was more efficient in terms of complexity, and consequently, time-effectiveness.

• Tuberculosis and Respiratory Diseases
• /
• v.43 no.2
• /
• pp.210-220
• /
• 1996

Background : Neutrophils or monocytes separated in vitro by the adherence to plastic surface are known to be activated by surface adherence itself and subsequent experimental data might be altered by surface adherence. In the process of surface adherence, adhesion molecules have a clear role in intracellular signal pathway of cellular activation. Human alveolar macrophages(HAM) are frequently purified by the adherence procedure after bronchoalveolar lavage. But the experimental data of many reports about alveolar macrophages have ignored the possibility of adhesion-induced cellular activation. Method : Bronchoalveolar lavage was performed in the person whose lung of either side was confirmed to be normal by chest CT. With the measurement of hydrogen peroxide release from adherent HAM to plastic surface and non-adherent HAM with or without additional stimulation of phorbol myristate acetate(PMA) or N-formyl-methionyl-leucyl-phenylalanine (fMLP), we observed the effect of the adherence to plastic surface. We also evaluated the effect of various biological surfaces on adhesion-induced activation of HAM. Then, to define the intracellular pathway of signal transduction, pretreatment with cycloheximide, pertussis toxin and anti-CD11/CD18 monoclonal antibody was done and we measured hydrogen peroxide in the culture supernatant of HAM. Results : 1) The adherence itself to plastic surface directly stimulated hydrogen peroxide release from human alveolar macrophages and chemical stimuli such as phorbol myristate acetate(PMA) or N-formyl-methionyl-leucyl-phenylalanine(fMLP) colud not increase hydrogen peroxide release in these adherent macrophages which is already activated. 2) PMA activated human alveolar macrophages irrespective of the state of adhesion. However, fMLP stimulated the release of hydrogen peroxide from the adherent macrophages, but not from the non-adherent macrophages. 3) HAM adherent to A549 cell(type II alveolar epithelium-like human cell line) monolayer released more hydrogen peroxide in response to both PMA and fMLP. This adherence-dependent effect of fMLP was blocked by pretreatment of macrophages with cycloheximide, pertussis toxin and anti-CD18 monoclonal antibody, Conclusion : These results suggest that the stimulatory effect of PMA and fMLP can not be found in adherent macrophage because of the activation of human alveolar macrophage by the adherence to plastic surface and the cells adhered to biologic surface such as alveolar epithelial cells are appropriately responsive to these stimuli. It is also likely that the effect of fMLP on the adherent macrophage requires new protein synthesis via G protein pathway and is dependent on the adhesion between alveolar macrophages and alveolar epithelial cells by virtue of CD11/CD18 adhesion molecules.

• Journal of Bio-Environment Control
• /
• v.28 no.2
• /
• pp.95-103
• /
• 2019

Temperature and relative humidity are important factors in crop cultivation and should be properly controlled for improving crop yield and quality. In order to control the environment accurately, we need to predict how the environment will change in the future. The objective of this study was to predict air temperature and relative humidity at a future time by using a multilayer perceptron (MLP). The data required to train MLP was collected every 10 min from Oct. 1, 2016 to Feb. 28, 2018 in an eight-span greenhouse ($1,032m^2$) cultivating mango (Mangifera indica cv. Irwin). The inputs for the MLP were greenhouse inside and outside environment data, and set-up and operating values of environment control devices. By using these data, the MLP was trained to predict the air temperature and relative humidity at a future time of 10 to 120 min. Considering typical four seasons in Korea, three-day data of the each season were compared as test data. The MLP was optimized with four hidden layers and 128 nodes for air temperature ($R^2=0.988$) and with four hidden layers and 64 nodes for relative humidity ($R^2=0.990$). Due to the characteristics of MLP, the accuracy decreased as the prediction time became longer. However, air temperature and relative humidity were properly predicted regardless of the environmental changes varied from season to season. For specific data such as spray irrigation, however, the numbers of trained data were too small, resulting in poor predictive accuracy. In this study, air temperature and relative humidity were appropriately predicted through optimization of MLP, but were limited to the experimental greenhouse. Therefore, it is necessary to collect more data from greenhouses at various places and modify the structure of neural network for generalization.

• Proceedings of the Korea Contents Association Conference
• /
• 2003.11a
• /
• pp.213-217
• /
• 2003

In this paper, we analysize the noise robustness of MLPs(Multilayer perceptrons). Also, as a preprocessing stage of MLPs to improve noise robustness, we consider the ICA(independent component analysis) and PCA(principle component analysis). After analyzing the noise redunction effect using PCA or ICA, we verify the noise robustness of MLPs through handwritten-digit recognition simulations.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.434-436
• /
• 2000

본 논문에서는 기존의 확률적 화자군집 모델을 MLP(multi-layer perceptron)로 구현하는 방법과 원형 화자군집 모델이 갖는 문제를 해결할 수정 모델을 제시한다. 화자군집 모델은 화자등록 시간에 민감한 실용 환경에서 중요한 의미를 지닌다. 본 연구에서 사용한 인식단위는 여러 음소계열에서 지속적인 부분을 추출한 지속음이므로 화자등록과 증명 단계에서 특정한 어구에 한정되지 않는 어구독립 방식을 채택한다.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.766-771
• /
• 2006

현재 많은 신경망의 하드웨어 구현은 부동 소수점 연산에 비해서 적은 면적과 빠른 수행시간을 가지는 고정소수점 연산을 많이 사용하지만, 소프트웨어에서는 일반적으로 높은 정확도를 가지는 부동소수점 연산을 사용한다. 신경망의 하드웨어 구현에서 많이 사용하는 고정소수점 연산은 부동소수점 연산에 비해서 빠른 처리속도와 적은 면적으로써 쉽게 하드웨어 구현에 용이하지만, 부동소수점 연산에 비해서 낮은 정확도와 기존의 부동소수점 연산을 사용하는 소프트웨어 신경망을 쉽게 적용할 수 없는 단점을 가진다. 본 논문에서는 부동소수점 연산을 사용하여 문자 추출 MLP의 데이터 변환 없이 적용할 수 있는 전체 파이프라이닝 설계 구조를 제안한다. 제안된 설계방법은 신경망의 전체 구조를 입력층과 은닉층을 링크 병렬화 방법과 은닉층과 출력층을 뉴런 병렬화 방법을 개선하여 쉽게 파이프라이닝 구조로 설계함으로써 신경망 처리는 은닉층 뉴런수와 동일한 주기로 처리되며, 기존의 문자추출 소프트웨어 신경망을 제안된 하드웨어 설계방법으로 구현하였을 때 11배의 빠른 성능을 나타낸다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.6
• /
• pp.198-207
• /
• 1996

A PSRI (position, scale, and rotation invariant ) feature extraction and automatic target recognition system using a cooperative network and an MLP is proposed. We can extract position invarient features by obtaining the target center using the projection and the moment in preprocessing stage. The scale and rotation invariant features are extracted from the contour projection of the number of edge pixels on each of the concentric circles, which is input to the cooperative network. By extracting the representative PSRI features form the features and their differentiations using max-net and min-net, we can rdduce the number of input neurons of the MLP, and make the resulted automatic target recognition system less sensitive to input variances. Experiments are conduted on various complex images which are shifted, rotated, or scaled, and the results show that the proposed system is very efficient for PSRI feature extractions and automatic target recognitions.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.95-102
• /
• 2005

A Parallel Processing model by considering a spatiotemporal parallelism is presented for the training procedure of the MLP neural network. We tried to design the flexible Parallel Processing model by simultaneously applying both of the training-set decomposition for a temporal parallelism and the network decomposition for a spatial parallelism. The analytical Performance evaluation model shows that when the problem size is extremely large, the speedup of each implementation depends, in the extreme, on whether the problem size is pattern-size intensive or pattern-quantify intensive.