• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.232-240
• /
• 2022

To fulfill user expectations, the rapid evolution of software techniques and approaches has necessitated reliable and flawless software operations. Aging prediction in the software under operation is becoming a basic and unavoidable requirement for ensuring the systems' availability, reliability, and operations. In this paper, an improved evolutionary computing-driven extreme learning scheme (ECD-ELM) has been suggested for object-oriented software aging prediction. To perform aging prediction, we employed a variety of metrics, including program size, McCube complexity metrics, Halstead metrics, runtime failure event metrics, and some unique aging-related metrics (ARM). In our suggested paradigm, extracting OOP software metrics is done after pre-processing, which includes outlier detection and normalization. This technique improved our proposed system's ability to deal with instances with unbalanced biases and metrics. Further, different dimensional reduction and feature selection algorithms such as principal component analysis (PCA), linear discriminant analysis (LDA), and T-Test analysis have been applied. We have suggested a single hidden layer multi-feed forward neural network (SL-MFNN) based ELM, where an adaptive genetic algorithm (AGA) has been applied to estimate the weight and bias parameters for ELM learning. Unlike the traditional neural networks model, the implementation of GA-based ELM with LDA feature selection has outperformed other aging prediction approaches in terms of prediction accuracy, precision, recall, and F-measure. The results affirm that the implementation of outlier detection, normalization of imbalanced metrics, LDA-based feature selection, and GA-based ELM can be the reliable solution for object-oriented software aging prediction.

• Nuclear Engineering and Technology
• /
• v.53 no.2
• /
• pp.522-531
• /
• 2021

We describe a new deep learning model - Convolutional eXtreme Gradient Boosting (ConvXGB) for classification problems based on convolutional neural nets and Chen et al.'s XGBoost. As well as image data, ConvXGB also supports the general classification problems, with a data preprocessing module. ConvXGB consists of several stacked convolutional layers to learn the features of the input and is able to learn features automatically, followed by XGBoost in the last layer for predicting the class labels. The ConvXGB model is simplified by reducing the number of parameters under appropriate conditions, since it is not necessary re-adjust the weight values in a back propagation cycle. Experiments on several data sets from UCL Repository, including images and general data sets, showed that our model handled the classification problems, for all the tested data sets, slightly better than CNN and XGBoost alone and was sometimes significantly better.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.21 no.2
• /
• pp.137-143
• /
• 2022

Composite materials, being light-weight and of high mechanical strength, are increasingly used in various industries such as the aerospace, automobile, sporting-goods manufacturing, and ship-building industries. Recently, manufacturing of composite materials using 3D printers has increased. 3D-printed composite materials are made in free-form and adapted for end-use by adjusting the fiber content and orientation. However, research on the machining of 3D printed composite materials is limited. The aim of this study is to develop a machine learning method to select machining conditions for machining of 3D-printed composite materials. The composite material was composed of Onyx and carbon fibers and stacked sequentially. The experiments were performed using the following machining conditions: spindle speed, feed rate, depth of cut, and machining direction. Cutting forces of the different machining conditions were measured by milling the composite materials. PCA, a method of machine learning, was developed to select the machining conditions and will be used in subsequent experiments under various machining conditions.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.27 no.1
• /
• pp.56-74
• /
• 2023

In order to obtain practical and high-quality satellite images containing high-frequency components, a large aperture optical system is required, which has a limitation in that it greatly increases the payload weight. As an attempt to overcome the problem, many multi-aperture optical systems have been proposed, but in many cases, these optical systems do not include high-frequency components in all directions, and making such an high-quality image is an ill-posed problem. In this paper, we use deep learning to overcome the limitation. A deep learning model receives low-quality images as input, estimates the Point Spread Function, PSF, and combines them to output a single high-quality image. We model images obtained from three rectangular apertures arranged in a regular polygon shape. We also propose the Modulation Transfer Function Loss, MTF Loss, which can capture the high-frequency components of the images. We present qualitative and quantitative results obtained through experiments.

• International Journal of Quality Innovation
• /
• v.8 no.3
• /
• pp.156-172
• /
• 2007

The high-tech industry is the economic lifeline for Taiwan. Its characteristics are short product life cycle, rapid changes in the market, and a high obsolescence rate for new products. Under globalization, the high-tech industry has adopted Information Technology (IT) to shorten the manufacturing process, reduce costs and conduct product research and development (R&D) to increase the core competence of enterprises and achieve the goal of sustainable operations. Enterprises should actively strengthen their integration with internal and external resources and lead in R&D management to increase industrial operating performance. Effectively managing operations and R&D management evaluation in Taiwan's High-tech Industry has become a critical subject. This study adopted 4 major Balanced Scorecard (BSC) perspectives to establish the Total Performance Evaluation Indicators for the R&D management department in Taiwan's High-tech Industry. The Analytic Network Process (ANP) was applied to evaluate the overall performance of the R&D management department. The research framework is divided into 2 phases. The first phase is combined with the 4 major perspectives, Financial, Customer, Internal Business Process and Learning and Growth, as the related indicators for each measurement perspective. The Key Performance Indicators (KPI) were selected using Factor Analysis to identify the key factor from the complicated indicators. The relationship between the characteristics of each BSC's evaluation perspective is dependence and feedback. This study applied ANP to conduct the calculation and adjustment of correlation between each KPI, and determine on their relative weights for the objective KPI. The "Financial Perspective" for R&D management department in Taiwan's High-tech Industry focused on the budget achievement rate of R&D management. The weight indicator value is (0.05863). The "Customer Perspective" focused on problem-solving satisfaction. The weight value of this indicator is (0.17549). The "Internal Business Process Perspective" focused on the quantity and quality of R&D. The weight value of this indicator is (0.13506). The "Learning and Growth Perspective" focused on improving competence in the research personnel's professional techniques. The weight value of this indicator is (0.02789). From the total weighting indicators, the order of the Performance Indicators for the R&D management department in Taiwan's High-tech Industry is: (1) Customer Perspective; (2) Internal Business Process Perspective; (3) Financial Perspective; and (4) Learning and Growth Perspective.

• Korean Journal of Food Science and Technology
• /
• v.45 no.5
• /
• pp.661-665
• /
• 2013

The aim of this study was to investigate the anti-amnesic effect of daebo (Castanea crenata) extract on trimethyltin chloride (TMT)-induced learning and memory impairment, in vivo. The inner skin of daebo was extracted using distilled water under reflux conditions. At the end of the adaptation period, ICR mice were divided into a control group, a TMT injection group (negative control), and a sample group (C5: 5 mg/kg body weight; C10: 10 mg/kg body weight; and C20: 20 mg/kg body weight), and were tested with learning and memory tests. The ethylacetate fraction of the daebo inner skin extract was found to increase TMT-induced memory deficit in the Y-maze and passive avoidance test. Brain tissue analysis showed that the ethylacetate fraction of daebo extract lowered the acetylcholine esterase (AChE) activity and malondialdehyde (MDA) content of neuronal cells, both of which are indicative of lipid peroxidation.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.2E
• /
• pp.14-23
• /
• 1996

This paper is a on the neural network to recognize the phonemes, the weight initialization to reduce learning speed, and LR parser for continuous speech recognition. The neural network spots the phonemes in continuous speech and LR parser parses the output of neural network. The whole phonemes recognized in neural network are divided into several groups which are grouped by the similarity of phonemes, and then each group consists of neural network. Each group of neural network to recognize the phonemes consisits of that recognize the phonemes of their own group and VGNN(Verify Group Neural Network) which judges whether the inputs are their own group or not. The weights of neural network are not initialized with random values but initialized from learning data to reduce learning speed. The LR parsing method applied to this paper is not a method which traces a unique path, but one which traces several possible paths because the output of neural network is not accurate. The parser processes the continuous speech frame by frame as accumulating the output of neural network through several possible paths. If this accumulated path-value drops below the threshold value, this path is deleted in possible parsing paths. This paper applies the continuous speech recognition system to the threshold value, this path is deleted in possible parsing paths. This paper applies the continuous speech recognition system to the continuous Korea digits recognition. The recognition rate of isolated digits is 97% in speaker dependent, and 75% in speaker dependent. The recognition rate of continuous digits is 74% in spaker dependent.

• Toxicological Research
• /
• v.33 no.2
• /
• pp.165-171
• /
• 2017

Bisphenol A (BPA) is a monomer used in a polymerization reaction in the production of polycarbonate plastics. It has been used in many consumer products, including plastics, polyvinyl chloride, food packaging, dental sealants, and thermal receipts. However, there is little information available on the inhalation toxicity of BPA. Therefore, the aim of this study was to determine its inhalation toxicity and effects on the estrous cycle, spatial learning, and memory. Sprague-Dawley rats were exposed to 0, 10, 30, and $90mg/m^3$ BPA, 6 hr/day, 5 days/week for 8 weeks via whole-body inhalation. Mortality, clinical signs, body weight, hematology, serum chemistry, estrous cycle parameters, performance in the Morris water maze test, and organ weights, as well as gross and histopathological findings, were compared between the control and BPA exposure groups. Statistically significant changes were observed in serum chemistry and organ weights upon exposure to BPA. However, there was no BPA-related toxic effect on the body weight, food consumption, hematology, serum chemistry, organ weights, estrous cycle, performance in the Morris water maze test, or gross or histopathological lesions in any male or female rats in the BPA exposure groups. In conclusion, the results of this study suggested that the no observable adverse effect level (NOAEL) for BPA in rats is above $90mg/m^3$/6 hr/day, 5 days/week upon 8-week exposure. Furthermore, BPA did not affect the estrous cycle, spatial learning, or memory in rats.

• Journal of Life Science
• /
• v.6 no.3
• /
• pp.178-184
• /
• 1996

Aloe(Aloe vera LINNE) has been used as a home medicine for the past several thousand in the world, and has been studied on various chronic degenerative diseases such as atherosclerosis, myocardiac infarction and hypertension. SMAP8, learning and memory impairment animal mode, were fed basic or experimental diets with 1.0% of freeze dried(FD)-Aloe powder for 8 months. This study was designed to investigate the effects of Aloe on body weight gain, grading score of senescence(GSS), triglyceride, total and LDL-cholesterol levels, and atherogenic index in serum of SAMP8, and also designed to investigate the effects of Aloe on cholesterol accumultions in mitochondria and microsome fractions of SAMP8 brain. Body weight gain was consistently lower in aloe group than in control group, but no significantly differences between them. Grading score of senescence resulted ina marked decreases pf 20% in 1.0% Aloe group compared with control group. Administrations of 1.0% aloe resulted ina marked decreases in 15% and 20% of triglyceride and cholesterol levels, respectively, and also significantly decreased in 15% of LDL-cholesterol levels and atherogenic index in serum of SAMP8 compared with control group. Cholesterol accumulations were significantly inhibited in 20% and 10% of mitochondria and microsome fractions of SAMP8 brain, respectively, by administration of 1.0% Aloe. These results suggest that administration of Aloe mau not only effectively inhibit chronic degenerative diseases in serum of SAMP8, but may also improve learning and memory impairments of SAMP8 brain.

• Journal of KIISE:Software and Applications
• /
• v.33 no.8
• /
• pp.692-702
• /
• 2006

In this study, a weighted fuzzy min-max (WFMM) neural network model for pattern classification is proposed. The model has a modified structure of FMM neural network in which the weight concept is added to represent the frequency factor of feature values in a learning data set. First we present in this paper a new activation function of the network which is defined as a hyperbox membership function. Then we introduce a new learning algorithm for the model that consists of three kinds of processes: hyperbox creation/expansion, hyperbox overlap test, and hyperbox contraction. A weight adaptation rule considering the frequency factors is defined for the learning process. Finally we describe a feature analysis technique using the proposed model. Four kinds of relevance factors among feature values, feature types, hyperboxes and patterns classes are proposed to analyze relative importance of each feature in a given problem. Two types of practical applications, Fisher's Iris data and Cleveland medical data, have been used for the experiments. Through the experimental results, the effectiveness of the proposed method is discussed.