• Journal of Information Processing Systems
• /
• 제19권6호
• /
• pp.778-790
• /
• 2023

Although density peak clustering can often easily yield excellent results, there is still room for improvement when dealing with complex, high-dimensional datasets. One of the main limitations of this algorithm is its reliance on geometric distance as the sole similarity measurement. To address this limitation, we draw inspiration from the information bottleneck theory, and propose a novel density peak clustering algorithm that incorporates this theory as a similarity measure. Specifically, our algorithm utilizes the joint probability distribution between data objects and feature information, and employs the loss of mutual information as the measurement standard. This approach not only eliminates the potential for subjective error in selecting similarity method, but also enhances performance on datasets with multiple centers and high dimensionality. To evaluate the effectiveness of our algorithm, we conducted experiments using ten carefully selected datasets and compared the results with three other algorithms. The experimental results demonstrate that our information bottleneck-based density peaks clustering (IBDPC) algorithm consistently achieves high levels of accuracy, highlighting its potential as a valuable tool for data clustering tasks.

• 산업경영시스템학회지
• /
• 제32권1호
• /
• pp.102-110
• /
• 2009

Concurrent Engineering(CE) has presented new possibilities for successful product development by incorporating various product life-cycle functions from the earlier stage of design. In the product design, geometric representation is vital not only in its traditional role as a means of communicating design information but also in its role as a means of externalizing designer's thought process by visualizing the design product. During the last dozens of years, there has been extraordinary development of computer-aided tools intended to generate, present or communicate 3D models. However, there has not been comparable progress in the development of 3D-CAD systems intended to represent and manipulate a variety of product life-cycle information in a consistent manner. This paper proposes a novel concept, Minus Volume (MV), to incorporate various design information relevant to product lift-cycle functions. MV is a functional shape that is extracted from a design object within a bounding box. A prototype 3D-CAD system is implemented based on the MV concept and illustrated with the successful implementation of concurrent design and manufacturing.

• 산업경영시스템학회지
• /
• 제32권4호
• /
• pp.169-177
• /
• 2009

Concurrent Engineering (CE) has presented new possibilities for successful product development by incorporating various product life-cycle functions from the earlier stage of design. In the product design, geometric representation is vital not only in its traditional role as a means of communicating design information but also in its role as a means of externalizing designer's thought process by visualizing the design product. During the last dozens of years, there has been extraordinary development of computer-aided tools intended to generate, present or communicate 3D models. However, there has not been comparable progress in the development of 3D-CAD systems intended to represent and manipulate a variety of product life-cycle information in a consistent manner. In the previous research, the authors proposed a novel concept called Minus Volume (MV) to incorporate various design information relevant to product life-cycle functions. This paper proposes the use of the MV concept for the collaborative design environment, where many team members are geographically distributed over the networked environment, including Internet, Intranet, WWW, etc. A prototype 3D-CAD system is implemented based on the MV concept and illustrated with the successful implementation of collaborative design example.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4300-4314
• /
• 2019

With the development of video-related applications, media content has increased dramatically through applications. There is a substantial amount of near-duplicate videos (NDVs) among Internet videos, thus NDVR is important for eliminating near-duplicates from web video searches. This paper proposes a novel NDVR system that supports large-scale retrieval and contributes to the efficient and accurate retrieval performance. For this, we extracted keyframes from each video at regular intervals and then extracted both commonly used features (LBP and HSV) and new image features from each keyframe. A recent study introduced a new image feature that can provide more robust information than existing features even if there are geometric changes to and complex editing of images. We convert a vector set that consists of the extracted features to binary code through a set of hash functions so that the similarity comparison can be more efficient as similar videos are more likely to map into the same buckets. Lastly, we calculate similarity to search for NDVs; we examine the effectiveness of the NDVR system and compare this against previous NDVR systems using the public video collections CC_WEB_VIDEO. The proposed NDVR system's performance is very promising compared to previous NDVR systems.

• 전자공학회논문지B
• /
• 제32B권10호
• /
• pp.1247-1258
• /
• 1995

Input-output decoupling is well-known to be effective in the control of the nonlinear systems. This paper points out some problems of this technique in applications, and obtains a new digital input-output decoupling feedback law by using the inherent structure of the system. The effectiveness (accuracy) of our new control technique are confirmed by simple computer simulations. Finally, a digital compensator is also designed. The problems we study are of importance in the field of nonlinear control of robots, aerospace navigation, and vehicular control. The methodology to be employed involves both algebraic and geometric aspects of the systems.

• 국제학술발표논문집
• /
• The 5th International Conference on Construction Engineering and Project Management
• /
• pp.300-303
• /
• 2013

On BIPV systems, especially roof-top PV systems, the power generation is easier to be reduced due to the shades of facilities nearby, or roof itself. To secure profitability of roof-top PV systems, the optimal design of solar arrays through the precise shading analysis is an important item of design considerations. In this paper, an optimization system for array design of roof-top PVs is to be developed using three-dimensional Geospatial Information System(GIS). The profitability of income and expense is considered through the shading analysis of entire roofs. By applying the system to project for validation, the adequacy and the improvement of NPV of the system were verified compared to expert's design. The system has significance by reason that PV modules are placed through rules established with expert knowledge and geometric rules were applied to reflect the constructability and maintainability.

• 센서학회지
• /
• 제26권4호
• /
• pp.266-273
• /
• 2017

In this research a medical palpation guidance system for minimally invasive surgery (MIS) is proposed. Palpation is a useful tool for identifying a size and location of a lump during a surgery. However, conventional manual palpation is only available in open surgery, so there has been several researches about palpation assistant or guidance system for MIS. The previously developed systems are based on a pressure based or stiffness based approach. These previous approaches have some limitations in increasing complexity of the systems and lack of geometric information about the lump which is more important information for the lump removal than the stiffness information. We propose a palpation guidance system using a novel approach using contact pressure distribution. Since our approach gives the geometry information of the lump as well as the existence information, the operator can easily notice the currently identified lump region and the optimal position for the next palpation. The experiment results show that our approach can offer the geometry information of the lump correctly.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2754-2768
• /
• 2013

Video fingerprints generated from global features are usually vulnerable against general geometric transformations. In this paper, a novel video fingerprinting algorithm is proposed, in which a new spatio-temporal gradient is designed to represent the spatial and temporal information for each frame, and a new partition scheme, based on concentric circle and rings, is developed to resist the attacks efficiently. The centroids of spatio-temporal gradient orientations (CSTGO) within the circle and rings are then calculated to generate a robust fingerprint. Our experiments with different attacks have demonstrated that the proposed approach outperforms the state-of-the-art methods in terms of robustness and discrimination.

• 대한공간정보학회지
• /
• 제10권3호
• /
• pp.115-122
• /
• 2002

위성으로 취득되는 영상이 원천적으로 가지게 되는 기하적, 물리적인 왜곡을 제거하기 위해서는 보정 과정이 필요하다. 기하 보정 방법에는 시스템 기하보정과 지상기준점을 이용한 기하보정 방법이 있는데, 본 논문에서는 지상기준점을 이용한 보정 방법에 대해 기술하고 TIN 단위로 기하보정하는 방법을 제안한다. 영상과 지상기준점과의 수학적인 상관 관계를 이용하여 왜곡을 보정하는 방법으로서 평면 전체를 변환시키는 평면기하보정이 주로 사용되어 왔으나, 이것은 지형 변화가 큰 지역의 왜곡을 제대로 보정하지 못하는 단점이 있다. 본 논문에서는 이를 보완하기 위해 TIN단위의 기하보정 방법을 제안하고 평면기하보정 방법과 결과를 비교하며, 지상기준점과의 상관성을 분석한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권4호
• /
• pp.1721-1737
• /
• 2020

Human apparent age estimation has become a popular research topic and attracted great attention in recent years due to its wide applications, such as personal security and law enforcement. To achieve the goal of age estimation, a large number of methods have been pro-posed, where the models derived through the cumulative attribute coding achieve promised performance by preserving the neighbor-similarity of ages. However, these methods afore-mentioned ignore the geometric structure of extracted facial features. Indeed, the geometric structure of data greatly affects the accuracy of prediction. To this end, we propose an age estimation algorithm through joint feature selection and manifold learning paradigms, so-called Feature-selected and Geometry-preserved Least Square Regression (FGLSR). Based on this, our proposed method, compared with the others, not only preserves the geometry structures within facial representations, but also selects the discriminative features. Moreover, a deep learning extension based FGLSR is proposed later, namely Feature selected and Geometry preserved Neural Network (FGNN). Finally, related experiments are conducted on Morph2 and FG-Net datasets for FGLSR and on Morph2 datasets for FGNN. Experimental results testify our method achieve the best performances.