• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.5179-5196
• /
• 2019

To explore an effective non-invasion medical imaging diagnostics approach for hepatocellular carcinoma (HCC), we propose a method based on adopting the multiple technologies with the multi-parametric data fusion, transfer learning, and multi-scale deep feature extraction. Firstly, to make full use of complementary and enhancing the contribution of different modalities viz. multi-parametric MRI images in the lesion diagnosis, we propose a data-level fusion strategy. Secondly, based on the fusion data as the input, the multi-scale residual neural network with SPP (Spatial Pyramid Pooling) is utilized for the discriminative feature representation learning. Thirdly, to mitigate the impact of the lack of training samples, we do the pre-training of the proposed multi-scale residual neural network model on the natural image dataset and the fine-tuning with the chosen multi-parametric MRI images as complementary data. The comparative experiment results on the dataset from the clinical cases show that our proposed approach by employing the multiple strategies achieves the highest accuracy of 0.847±0.023 in the classification problem on the HCC differentiation. In the problem of discriminating the HCC lesion from the non-tumor area, we achieve a good performance with accuracy, sensitivity, specificity and AUC (area under the ROC curve) being 0.981±0.002, 0.981±0.002, 0.991±0.007 and 0.999±0.0008, respectively.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.2
• /
• pp.699-707
• /
• 2015

Although digit character recognition has got a significant improvement in recent years, it is still challenging to achieve satisfied result if the data contains an amount of distracting factors. This paper proposes a novel digit character recognition approach using a multi-layer hierarchical model, Hybrid Restricted Boltzmann Machines (HRBMs), which allows the learning architecture to be robust to background distracting factors. The insight behind the proposed model is that useful high-level features appear more frequently than distracting factors during learning, thus the high-level features can be decompose into hybrid hierarchical structures by using only small label information. In order to extract robust and compact features, a stochastic 0-1 layer is employed, which enables the model's hidden nodes to independently capture the useful character features during training. Experiments on the variations of Mixed National Institute of Standards and Technology (MNIST) dataset show that improvements of the multi-layer hierarchical model can be achieved by the proposed method. Finally, the paper shows the proposed technique which is used in a real-world application, where it is able to identify digit characters under various complex background images.

• ETRI Journal
• /
• v.29 no.5
• /
• pp.700-702
• /
• 2007

We present a relevance feedback approach based on multi-class support vector machine (SVM) learning and cluster-merging which can significantly improve the retrieval performance in region-based image retrieval. Semantically relevant images may exhibit various visual characteristics and may be scattered in several classes in the feature space due to the semantic gap between low-level features and high-level semantics in the user's mind. To find the semantic classes through relevance feedback, the proposed method reduces the burden of completely re-clustering the classes at iterations and classifies multiple classes. Experimental results show that the proposed method is more effective and efficient than the two-class SVM and multi-class relevance feedback methods.

• Journal of the Korea Safety Management & Science
• /
• v.16 no.4
• /
• pp.323-330
• /
• 2014

Various inventory control theories have tried to modelling and analyzing supply chains by using quantitative methods and characterization of optimal control policies. However, despite of various efforts in this research filed, the existing models cannot afford to be applied to the realistic problems. The most unrealistic assumption for these models is customer demand. Most of previous researches assume that the customer demand is stationary with a known distribution, whereas, in reality, the customer demand is not known a priori and changes over time. In this paper, we propose a reinforcement learning based adaptive echelon base-stock inventory control policy for a multi-stage, serial supply chain with non-stationary customer demand under the service level constraint. Using various simulation experiments, we prove that the proposed inventory control policy can meet the target service level quite well under various experimental environments.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2001.04a
• /
• pp.233-240
• /
• 2001

Artificial neural networks(ANN) have been exploited where the relationship among information is very complicated and nonlinear. It is appropriate to computerize the information and knowledge used in the preliminary design stage where it lacks of formality of representation of designers' experience and intuition. However, most designers start the preliminary design stage with very little information. Therefore, the ANN model for this stage must be designed to have input much less than output. This case usually causes big troubles such as in learning time, convergence and reliability of solutions. To address this problem, this paper proposes multi-level neural networks for progressive structural design considering that all the design information can not be obtained at a time but are growing gradually. The use of multi-level networks developed in this paper has been proved its validity by applying it to the preliminary design of cable-stayed bridges.

• Journal of Computing Science and Engineering
• /
• v.5 no.3
• /
• pp.183-196
• /
• 2011

There has recently been a surge of interest in relational database mining that aims to discover useful patterns across multiple interlinked database relations. It is crucial for a learning algorithm to explore the multiple inter-connected relations so that important attributes are not excluded when mining such relational repositories. However, from a data privacy perspective, it becomes difficult to identify all possible relationships between attributes from the different relations, considering a complex database schema. That is, seemingly harmless attributes may be linked to confidential information, leading to data leaks when building a model. Thus, we are at risk of disclosing unwanted knowledge when publishing the results of a data mining exercise. For instance, consider a financial database classification task to determine whether a loan is considered high risk. Suppose that we are aware that the database contains another confidential attribute, such as income level, that should not be divulged. One may thus choose to eliminate, or distort, the income level from the database to prevent potential privacy leakage. However, even after distortion, a learning model against the modified database may accurately determine the income level values. It follows that the database is still unsafe and may be compromised. This paper demonstrates this potential for privacy leakage in multi-relational classification and illustrates how such potential leaks may be detected. We propose a method to generate a ranked list of subschemas that maintains the predictive performance on the class attribute, while limiting the disclosure risk, and predictive accuracy, of confidential attributes. We illustrate and demonstrate the effectiveness of our method against a financial database and an insurance database.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.1 no.1
• /
• pp.44-58
• /
• 2001

This study aims to establish new architectural agenda for the existing middle school facilities responding to individualized interactive learning approach(IILA). First, it investigates the mechanism of new teaching methods and contents proposed in the national level curriculum and the province guidances. Secondly, it suggests the Quality and Quantity of new (multi-purpose) classrooms that should be built for operating new curriculum in the existing middle schools. Finally, it finally emphasizes the educational specification that should be prepared prior to planning school buildings.

• KIPS Transactions on Computer and Communication Systems
• /
• v.4 no.11
• /
• pp.369-382
• /
• 2015

Energy aware server clusters aim to reduce power consumption at maximum while keeping QoS(quality of service) compared to energy non-aware server clusters. They adjust the power mode of each server in a fixed or variable time interval to activate only the minimum number of servers needed to handle current user requests. Previous studies on energy aware server cluster put efforts to reduce power consumption or heat dissipation, but they do not consider energy efficiency well. In this paper, we propose an energy efficient cluster management method to improve not only performance per watt but also QoS of the existing server power mode control method based on autonomous learning. Our proposed method is to adjust server power mode based on a hybrid approach of autonomous learning method with multi level thresholds and power consumption prediction method. Autonomous learning method with multi level thresholds is applied under normal load situation whereas power consumption prediction method is applied under abnormal load situation. The decision on whether current load is normal or abnormal depends on the ratio of the number of current user requests over the average number of user requests during recent past few minutes. Also, a dynamic shutdown method is additionally applied to shorten the time delay to make servers off. We performed experiments with a cluster of 16 servers using three different kinds of load patterns. The multi-threshold based learning method with prediction and dynamic shutdown shows the best result in terms of normalized QoS and performance per watt (valid responses). For banking load pattern, real load pattern, and virtual load pattern, the numbers of good response per watt in the proposed method increase by 1.66%, 2.9% and 3.84%, respectively, whereas QoS in the proposed method increase by 0.45%, 1.33% and 8.82%, respectively, compared to those in the existing autonomous learning method with single level threshold.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.11
• /
• pp.934-940
• /
• 1991

The multi-layer neural network that has broadly been utilized in designing the controller of robot manipulator possesses the desirable characteristics of learning capacity, by which the uncertain variation of the dynamic parameters of robot can be handled adaptively, and parallel distributed processing that makes it possible to control on real-time. However the error back propagation algorithm that has been utilized popularly in the learning of the multi-layer neural network has the problem of its slow convergencs speed. In this paper, an approach to improve the convergence speed is proposed using fuzzy logic that can effectively handle the uncertain and fuzzy informations by linguistic level. The effectiveness of the proposed algorithm is demonstrated by computer simulation of PUMA 560 robot manipulator.

• International conference on construction engineering and project management
• /
• 2013.01a
• /
• pp.359-366
• /
• 2013

Although many research efforts have been conducted to address the effect of crew members' work skills (e.g., technical and planning skills) on work performance (e.g., work duration and quality) in construction projects, the relationship between skill and performance has generated a great deal of controversy in the field of management (Inkpen and Crossan 1995). This controversy can lead to under- or over-estimations of the overall project schedule, and can make it difficult for project managers to implement appropriate managerial policies for enhancing project performance. To address this issue, the following aspects need to be considered: (a) work performances are determined not only by individual-level work skill but also by the group-level work skill affected by work team members, each member's role, and any working behavior pattern; (b) work planning has significant effects on to what extent work skill enhances performance; and (c) different types of activities in construction require different types of work, skill, and team composition. This research, therefore, develops a system dynamics (SD) model to analyze the effects of both individual-and group-level (i.e., multi-level) skill on performances by utilizing the advantages of SD in capturing a feedback process and state changes, especially in human factors (e.g., attitude, ability, and behavior). The model incorporates: (a) a multi-level skill evolution and relevant behavior development mechanism within a work group; (b) the interaction among work planning, a crew's skill-learning, skill manifestation, and performances; and (c) the different work characteristics of each activity. This model can be utilized to implement appropriate work planning (e.g., work scope and work schedule) and crew management policies (e.g., work team composition and decision of each worker's role) with an awareness of crew's skill and work performance. Understanding the different characteristics of each activity can also support project managers in applying strategic work planning and crew management for a corresponding activity, which may enhance each activity's performance, as well as the overall project performance.