• Journal of Power Electronics
• /
• v.18 no.3
• /
• pp.910-922
• /
• 2018

Conventional battery state-of-charge (SoC) estimation methods either involve sophisticated models or consume considerable computational resource. This study constructs an enhanced coulomb counting method (Ah method) for the SoC estimation of lithium-ion batteries (LiBs) by expanding the Peukert equation for the discharging process and incorporating the Coulombic efficiency for the charging process. Both the rate- and temperature-dependence of battery capacity are encompassed. An SoC mapping approach is also devised for initial SoC determination and Ah method correction. The charge counting performance at different sampling frequencies is analyzed experimentally and theoretically. To achieve a favorable compromise between sampling frequency and accumulation accuracy, a frequency-adjustable current sampling solution is developed. Experiments under the augmented urban dynamometer driving schedule cycles at different temperatures are conducted on two LiBs of different chemistries. Results verify the effectiveness and generalization ability of the proposed SoC estimation method.

• Proceedings of the KSR Conference
• /
• 1998.05a
• /
• pp.427-435
• /
• 1998

In this paper will be presented an algorithm for designing of a railway interlocking table which is a document describing the functional specification of the interlocking device. The ability to produce an interlocking table has been handed down in the signalling engineers society. And the signalling engineer makes the most of his expertise to produce an interlocking table. But, the expertise has not yet been organized into technical system, the core of the expertise is a hard nut to crack. Therefore, we analyze into signal engineering expertise, and propose a generalization of interlocking notion. Also, an algorithm is drawn up based on a train route setting principle to solve practical and general problems by computer And the performance of the algorithm is evaluated for test program based on AutoCAD technology. The evaluation result shows that it can be utilized as the effective algorithm for computer control of the signalling system as interlocking device, that it improved in safety

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.11 no.3
• /
• pp.46-54
• /
• 2012

The accuracy of cost estimation at an early stage in school building project is one of the critical factors for successful completion. So various of techniques are developed to predict the construction cost accurately and expeditely. Among the techniques, Support Vector Machine(SVM) has an excellent ability for generalization performance. Therefore, the purpose of this study is to construct the prediction model for construction cost of educational building project using support vector machine technique. And to verify the accuracy of prediction model for construction cost. The performance data used in this study are 217 school building project cost which have been completed from 2004 to 2007 in Gyeonggi-Do, Korea. The result shows that average error rate was 7.48% for SVM prediction model. So using SVM model on predicting construction cost of educational building project will be a considerably effective way at the early project stage.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.472-474
• /
• 2019

Because of the difference in network structure and loss function, Verification and identification models have their respective advantages and limitations for person reidentification (re-ID). In this work, we propose a multi-task network simultaneously computes the identification loss and verification loss for person reidentification. Given a pair of images as network input, the multi-task network simultaneously outputs the identities of the two images and whether the images belong to the same identity. In experiments, we analyze the major factors affect the accuracy of person reidentification. To address the occlusion problem and improve the generalization ability of reID models, we use the Random Erasing Augmentation (REA) method to preprocess the images. The method can be easily applied to different pre-trained networks, such as ResNet and VGG. The experimental results on the Market1501 datasets show significant and consistent improvements over the state-of-the-art methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.397-400
• /
• 2021

To solve the problem that existing computing methods cannot adequately represent the semantic features of sentences, Siamese TRAT, a semantic feature extraction model based on Transformer encoder is proposed. The transformer model is used to fully extract the semantic information within sentences and carry out deep semantic coding for sentences. In addition, the interactive attention mechanism is introduced to extract the similar features of the association between two sentences, which makes the model better at capturing the important semantic information inside the sentence. As a result, it improves the semantic understanding and generalization ability of the model. The experimental results show that the proposed model can improve the accuracy significantly for the semantic similarity calculation task of English and Chinese, and is more effective than the existing methods.

• Steel and Composite Structures
• /
• v.46 no.3
• /
• pp.435-449
• /
• 2023

Time domain method and frequency domain method are commonly used in the current fatigue life calculation theory. The time domain method has complicated procedures and needs a large amount of calculation, while the frequency domain method has poor applicability to different materials and different spectrum, and improper selection of spectrum model will lead to large errors. Considering that artificial neural network has strong ability of nonlinear mapping and generalization, this paper applied this technique to random fatigue life prediction, and the effect of average stress was taken into account, thereby achieving more accurate prediction result of random fatigue life.

• The KIPS Transactions:PartD
• /
• v.8D no.2
• /
• pp.175-180
• /
• 2001

This paper presents the optimal fraction of validation set to obtain a prediction accuracy of software failure count or failure time in the future by a neuro-fuzzy system. Given a fixed amount of training data, the most popular effective approach to avoiding underfitting and overfitting is early stopping, and hence getting optimal generalization. But there is unresolved practical issues : How many data do you assign to the training and validation set\ulcorner Rules of thumb abound, the solution is acquired by trial-and-error and we spend long time in this method. For the sake of optimal fraction of validation set, the variant specific fraction for the validation set be provided. It shows that minimal fraction of the validation data set is sufficient to achieve good next-step prediction. This result can be considered as a practical guideline in a prediction of software reliability by neuro-fuzzy system.

• The Journal of the Korea Contents Association
• /
• v.9 no.2
• /
• pp.381-390
• /
• 2009

The study is intended to investigates any effective hotel employee's leadership on cohesiveness and trust. The results were as follows; First, hotel employee's leadership has correlation in trust and cohesiveness according to statistics. It should be interested in the leadership to display their potential ability and an initiative spirit in the organization. Second, trust has positive influence on the cohesiveness. The cohesiveness will has positive influence every organization so hotel employees should be interested in the result. Therefore, hotel employee should grasps a training system and recognition to apply their organization. According to the effective analysis, this study provides basic data about human resource management of the hotel but there is the limit in the study and it needs to study later. Because the subject is the hotel, it couldn't compare with other company so there is the limit to make generalization. Methodology in hypothesis only relies on the survey, using of a overseas scale and cross-section data should be studied to make generalization by a vertical study. Hereafter hotel employee's leadership is effected what factor is and the study should be achieved about specifical process and method to get the reliability to employees.

• Education of Primary School Mathematics
• /
• v.14 no.2
• /
• pp.117-134
• /
• 2011

The purpose of this research was to analyze mathematical task types to enhance creativity. Creativity is increasingly important in every field of disciplines and industries. To be excel in the 21st century, students need to have habits to think creatively in mathematics learning. The method of the research was to collect the previous research and papers concerning creativity and mathematics. To search the materials, the researcher used the search engines such as the GIL and the KISTI. The mathematical task types to enhance creativity were categorized 16 different types according to their forms and characteristics. The types of tasks include (1) requiring various strategies, (2) requiring preferences on strategies, (3) making word problems, (4) making parallel problems, (5) requiring transforming problems, (6) finding patterns and making generalization, (7) using open-ended problems, (8) asking intuition for final answers, (9) asking patterns and generalization (10) requiring role plays, (11) using literature, (12) using mathematical puzzles and games, (13) using various materials, (14) breaking patterned thinking, (15) integrating among disciplines, and (16) encouraging to change our lives. To enhance students' creativity in mathematics teaching and learning, the researcher recommended the followings: reshaping perspectives toward teaching and learning, developing and providing creativity-rich tasks, applying every day life, using open-ended tasks, using various types of tasks, having assessment ability, changing assessment system, and showing and doing creative thinking and behaviors of teachers and parents.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.2946-2952
• /
• 2014

Among the Example based Super Resolution(SR) techniques, Neighbor embedding(NE) has been inspired by manifold learning method, particularly locally linear embedding. However, the poor generalization of NE decreases the performance of such algorithm. The sizes of local training sets are always too small to improve the performance of NE. We propose the Learning Sparse-Neighbor Image Representation baesd on SVR having an excellent generalization ability to solve this problem. Given a low resolution image, we first use bicubic interpolation to synthesize its high resolution version. We extract the patches from this synthesized image and determine whether each patch corresponds to regions with high or low spatial frequencies. After the weight of each patch is obtained by our method, we used to learn separate SVR models. Finally, we update the pixel values using the previously learned SVRs. Through experimental results, we quantitatively and qualitatively confirm the improved results of the proposed algorithm when comparing with conventional interpolation methods and NE.