• Journal of KIISE:Software and Applications
• /
• v.34 no.1
• /
• pp.11-17
• /
• 2007

One of the popular methods used for pattern classification is the MBR (Memory-Based Reasoning) algorithm. Since it simply computes distances between a test pattern and training patterns or hyperplanes stored in memory, and then assigns the class of the nearest training pattern, it cannot explain how the classification result is obtained. In order to overcome this problem, we propose an incremental teaming algorithm based on RPA (Recursive Partition Averaging) to extract IF-THEN rules that describe regularities inherent in training patterns. But rules generated by RPA eventually show an overfitting phenomenon, because they depend too strongly on the details of given training patterns. Also RPA produces more number of rules than necessary, due to over-partitioning of the pattern space. Consequently, we present the IREA (Incremental Rule Extraction Algorithm) that overcomes overfitting problem by removing useless conditions from rules and reduces the number of rules at the same time. We verify the performance of proposed algorithm using benchmark data sets from UCI Machine Learning Repository.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2129-2147
• /
• 2019

This paper introduces an adaptive face recognition method based on a Novel Incremental Kernel Nonparametric Discriminant Analysis (IKNDA) that is able to learn through time. More precisely, the IKNDA has the advantage of incrementally reducing data dimension, in a discriminative manner, as new samples are added asynchronously. Thus, it handles dynamic and large data in a better way. In order to perform face recognition effectively, we combine the Gabor features and the ordinal measures to extract the facial features that are coded across local parts, as visual primitives. The variegated ordinal measures are extraught from Gabor filtering responses. Then, the histogram of these primitives, across a variety of facial zones, is intermingled to procure a feature vector. This latter's dimension is slimmed down using PCA. Finally, the latter is treated as a facial vector input for the advanced IKNDA. A comparative evaluation of the IKNDA is performed for face recognition, besides, for other classification endeavors, in a decontextualized evaluation schemes. In such a scheme, we compare the IKNDA model to some relevant state-of-the-art incremental and batch discriminant models. Experimental results show that the IKNDA outperforms these discriminant models and is better tool to improve face recognition performance.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.165-171
• /
• 2017

It is difficult to recognize Human's facial expression in the real-world. For these reason, when database and test data have similar condition, we can accomplish high accuracy. Solving these problem, we need to many facial expression data. In this paper, we propose the algorithm for gathering many facial expression data within various environment and gaining high accuracy quickly. This algorithm is training initial model with the ASSL (Active Semi-Supervised Learning) using deep learning network, thereafter gathering unlabeled facial expression data and repeating this process. Through using the ASSL, we gain proper data and high accuracy with less labor force.

• Proceedings of the Korea Database Society Conference
• /
• 2001.06a
• /
• pp.331-341
• /
• 2001

본 논문에서는 Naive Bayes 문서 분류기를 위한 새로운 학습모델을 제안한다. 이 모델에서는 라벨이 없는 문서들의 집합으로부터 선택한 적은 수의 학습 문서들을 이용하여 문서 분류기를 재학습한다. 본 논문에서는 이러한 학습 방법을 따를 경우 작은 비용으로도 문서 분류기의 정확도가 크게 향상될 수 있다는 사실을 보인다. 이와 같이, 알고리즘을 통해 라벨이 없는 문서들의 집합으로부터 정보량이 큰 문서를 선택한 후, 전문가가 이 문서에 라벨을 부여하는 방식으로 학습문서를 결정하는 것을 selective sampling이라 한다. 본 논문에서는 이러한 selective sampling 문제를 Naive Bayes 문서 분류기에 적용한다. 제안한 학습 방법에서는 라벨이 없는 문서들의 집합으로부터 재학습 문서를 선택하는 기준 측정치로서 평균절대편차(Mean Absolute Deviation), 엔트로피 측정치를 사용한다. 실험을 통해서 제안한 학습 방법이 기존의 방법인 신뢰도(Confidence measure)를 이용한 학습 방법보다 Naive Bayes 문서 분류기의 성능을 더 많이 향상시킨다는 사실을 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4776-4794
• /
• 2020

We propose a rapid adaptive learning framework for streaming object detection, called EER-ASSL. The method combines the expected error reduction (EER) dependent rollback learning and the active semi-supervised learning (ASSL) for a rapid adaptive CNN detector. Most CNN object detectors are built on the assumption of static data distribution. However, images are often noisy and biased, and the data distribution is imbalanced in a real world environment. The proposed method consists of collaborative sampling and EER-ASSL. The EER-ASSL utilizes the active learning (AL) and rollback based semi-supervised learning (SSL). The AL allows us to select more informative and representative samples measuring uncertainty and diversity. The SSL divides the selected streaming image samples into the bins and each bin repeatedly transfers the discriminative knowledge of the EER and CNN models to the next bin until convergence and incorporation with the EER rollback learning algorithm is achieved. The EER models provide a rapid short-term myopic adaptation and the CNN models an incremental long-term performance improvement. EER-ASSL can overcome noisy and biased labels in varying data distribution. Extensive experiments shows that EER-ASSL obtained 70.9 mAP compared to state-of-the-art technology such as Faster RCNN, SSD300, and YOLOv2.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2011.04a
• /
• pp.224-229
• /
• 2011

In this paper, in order to improve safety of hybrid electric vehicle a fault detection algorithm is introduced. The proposed algorithm uses SVDD techniques. Two methods for learning a lot of data are used in this technique. One method is to learn the data incrementally. Another method is to remove the data that does not affect the next learning. Using lines connecting support vectors selection of removing data is made. Using this method, lot of computation time and storage can be saved while learning many data. A battery data of commercial hybrid electrical vehicle is used in this study. In the study fault boundary via SVDD is described and relevant algorithm for virtual fault data is verified. It takes some time to generate fault boundary, nevertheless once the boundary is given, fault diagnosis can be conducted in real time basis.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.3989-4006
• /
• 2020

The intelligent agriculture monitoring is based on the perception and analysis of environmental data, which enables the monitoring of the production environment and the control of environmental regulation equipment. As the scale of the application continues to expand, a large amount of data will be generated from the perception layer and uploaded to the cloud service, which will bring challenges of insufficient bandwidth and processing capacity. A fog-based offline and real-time hybrid data analysis architecture was proposed in this paper, which combines offline and real-time analysis to enable real-time data processing on resource-constrained IoT devices. Furthermore, we propose a data process-ing algorithm based on the incremental principal component analysis, which can achieve data dimensionality reduction and update of principal components. We also introduce the concept of Squared Prediction Error (SPE) value and realize the abnormal detection of data through the combination of SPE value and data fusion algorithm. To ensure the accuracy and effectiveness of the algorithm, we design a regular-SPE hybrid model update strategy, which enables the principal component to be updated on demand when data anomalies are found. In addition, this strategy can significantly reduce resource consumption growth due to the data analysis architectures. Practical datasets-based simulations have confirmed that the proposed algorithm can perform data fusion and exception processing in real-time on resource-constrained devices; Our model update strategy can reduce the overall system resource consumption while ensuring the accuracy of the algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2627-2647
• /
• 2022

The easy scalability and low cost of range-free localization algorithms have led to their wide attention and application in node localization of wireless sensor networks. However, the existing range-free localization algorithms still have problems, such as large cumulative errors and poor localization performance. To solve these problems, an incremental strategy-based residual regression network is proposed for node localization in wireless sensor networks. The algorithm predicts the coordinates of the nodes to be solved by building a deep learning model and fine-tunes the prediction results by regression based on the intersection of the communication range between the predicted and real coordinates and the loss function, which improves the localization performance of the algorithm. Moreover, a correction scheme is proposed to correct the augmented data in the incremental strategy, which reduces the cumulative error generated during the algorithm localization. The analysis through simulation experiments demonstrates that our proposed algorithm has strong robustness and has obvious advantages in localization performance compared with other algorithms.

• Asia Marketing Journal
• /
• v.15 no.3
• /
• pp.79-95
• /
• 2013

New product innovation is a process of embodying new knowledge in a product and technology licensing is getting popular as a means to innovations and introduction of new product to the market in today's competitive global market environment. Incumbents often rely on technology licensing to access new product opportunities created by other firms. Prior research has examined various aspects of technology licensing agreements such as specific contract terms of licensing agreements, e.g., distribution of control rights, exclusivity of licensing agreements, cross-licensing, and the scope of licensing agreements. This study aims to provide answers to an important, but under-researched question: why do some incumbents initiate more licensing agreement for exploratory learning while others do it for exploitative learning along the innovation process? We attempt to extend our knowledge of licensing agreements from an organizational learning perspective. Technology licensing as a specific form of interfirm linkages can be initiated with different learning objectives along the process of new product innovation. The exploratory stages of the innovation process such as discovery or research stages involve extensive searches to create new knowledge or capabilities, whereas the exploitative stages of the innovation process such as application or test stages near the commercialization are more focused on developing specific applications or improving their efficiency or reliability. Thus, different stages of the innovation process generate different types of learning and the resulting technological resources. We examine when incumbents as licensees initiate more licensing agreements for exploratory learning objectives and when more for exploitative learning objectives, focusing on two factors that may influence a firm's formation of exploratory and exploitative licensing agreements: 1) its past radical and incremental innovation experience and 2) its internal investments in R&D and marketing. We develop and test our hypotheses regarding the relationship between a firm's radical and incremental new product experience, R&D investment intensity and marketing investment intensity, and the likelihood of engaging in exploratory and exploitive licensing agreements. Using data collected from various secondary sources (Recap database, Compustat database, and FDA website), we analyzed technology licensing agreements initiated in the biotechnology and pharmaceutical industries from 1988 to 2011. The results of this study show that incumbents initiate exploratory rather than exploitative licensing agreements when they have more radical innovation experience and when they invest in R&D activities more intensively; in contrast, they initiate exploitative rather than exploratory licensing agreements when they have more incremental innovation experience and when they invest in marketing activities more intensively. The findings of this study contribute to the licensing and interfirm cooperation studies. First, this study lays a foundation to understand the organizational learning aspect of technology licensing agreements. Second, this study sheds lights on how a firm's internal investments in R&D and marketing are linked to its tendency to initiate licensing agreements along the innovation process. Finally, the findings of this study provide important insight to managers regarding which technologies to gain via licensing agreements. This study suggests that firms need to consider their internal investments in R&D and marketing as well as their past innovation experiences when they initiate licensing agreements along the process of new product innovation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.3
• /
• pp.319-327
• /
• 2012

In this paper, we present a sign language recognition model which does not use any wearable devices for object tracking. The system design issues and implementation issues such as data representation, feature extraction and pattern classification methods are discussed. The proposed data representation method for sign language patterns is robust for spatio-temporal variances of feature points. We present a feature extraction technique which can improve the computation speed by reducing the amount of feature data. A neural network model which is capable of incremental learning is described and the behaviors and learning algorithm of the model are introduced. We have defined a measure which reflects the relevance between the feature values and the pattern classes. The measure makes it possible to select more effective features without any degradation of performance. Through the experiments using six types of sign language patterns, the proposed model is evaluated empirically.