• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권1호
• /
• pp.131-146
• /
• 2021

Multimodal biometric-based recognition has been an active topic because of its higher convenience in recent years. Due to high user convenience of finger, finger-based personal identification has been widely used in practice. Hence, taking Finger-Print (FP), Finger-Vein (FV) and Finger-Knuckle-Print (FKP) as the ingredients of characteristic, their feature representation were helpful for improving the universality and reliability in identification. To usefully fuse the multimodal finger-features together, a new robust representation algorithm was proposed based on hierarchical model. Firstly, to obtain more robust features, the feature maps were obtained by Gabor magnitude feature coding and then described by Local Binary Pattern (LBP). Secondly, the LGBP-based feature maps were processed hierarchically in bottom-up mode by variable rectangle and circle granules, respectively. Finally, the intension of each granule was represented by Local-invariant Gray Features (LGFs) and called Hierarchical Local-Gabor-based Gray Invariant Features (HLGGIFs). Experiment results revealed that the proposed algorithm is capable of improving rotation variation of finger-pose, and achieving lower Equal Error Rate (EER) in our homemade database.

• 품질경영학회지
• /
• 제48권4호
• /
• pp.553-566
• /
• 2020

Purpose: The purpose of this study was to design a framework for generating one-class classification algorithm based on Hyper-Rectangle(H-RTGL) in a distributed environment connected by network. Methods: At first, we devised one-class classifier based on H-RTGL which can be performed by distributed computing nodes considering model and data parallelism. Then, we also designed facilitating components for execution of distributed processing. In the end, we validate both effectiveness and efficiency of the classifier obtained from the proposed framework by a numerical experiment using data set obtained from UCI machine learning repository. Results: We designed distributed processing framework capable of one-class classification based on H-RTGL in distributed environment consisting of physically separated computing nodes. It includes components for implementation of model and data parallelism, which enables distributed generation of classifier. From a numerical experiment, we could observe that there was no significant change of classification performance assessed by statistical test and elapsed time was reduced due to application of distributed processing in dataset with considerable size. Conclusion: Based on such result, we can conclude that application of distributed processing for generating classifier can preserve classification performance and it can improve the efficiency of classification algorithms. In addition, we suggested an idea for future research directions of this paper as well as limitation of our work.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권10호
• /
• pp.3373-3389
• /
• 2022

Exploration of mobile robot without prior data about environments is a fundamental problem during the SLAM processes. In this work, we propose improved version of previous Rmap algorithm by modifying its Exploration submodule. Despite the previous Rmap's performance which significantly reduces the overhead of the grid map, its exploration module costs a lot because of its rectangle following algorithm. To prevent that, we propose a new Rmap+ algorithm for autonomous path planning of mobile robot to explore an unknown environment. The algorithm bases on paired frontiers. To navigate and extend an exploration area of mobile robot, the Rmap+ utilizes the inner and outer frontiers. In each exploration round, the mobile robot using the sensor range determines the frontiers. Then robot periodically changes the range of sensor and generates inner pairs of frontiers. After calculating the length of each frontiers' and its corresponding pairs, the Rmap+ selects the goal point to navigate the robot. The experimental results represent efficiency and applicability on exploration time and distance, i.e., to complete the whole exploration, the path distance decreased from 15% to 69%, as well as the robot decreased the time consumption from 12% to 86% than previous algorithms.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2000년도 THE THIRD INTERNATIONAL CONFERENCE ON AGRICULTURAL MACHINERY ENGINEERING. V.III
• /
• pp.715-721
• /
• 2000

In this research, rule and neuro net based boundary extraction algorithm was developed. Extracting boundary of the interest, lean tissue, is essential for the quality evaluation of the beef based on color machine vision. Major quality features of the beef are size, marveling state of the lean tissue, color of the fat, and thickness of back fat. To evaluate the beef quality, extracting of loin parts from the sectional image of beef rib is crucial and the first step. Since its boundary is not clear and very difficult to trace, neural network model was developed to isolate loin parts from the entire image input. At the stage of training network, normalized color image data was used. Model reference of boundary was determined by binary feature extraction algorithm using R(red) channel. And 100 sub-images(selected from maximum extended boundary rectangle 11${\times}$11 masks) were used as training data set. Each mask has information on the curvature of boundary. The basic rule in boundary extraction is the adaptation of the known curvature of the boundary. The structured model reference and neural net based boundary extraction algorithm was developed and implemented to the beef image and results were analyzed.

• Advances in materials Research
• /
• 제12권1호
• /
• pp.15-29
• /
• 2023

In this paper, fracture analysis of a continuously inhomogeneous arch structure with two longitudinal cracks is developed in terms of the time-dependent strain energy release rate. The arch under consideration exhibits non-linear creep behavior. The cross-section of the arch is a rectangle. The material is continuously inhomogeneous along the thickness of the cross-section. The arch is loaded by two bending moments applied at its end sections. The mechanical behavior of the material is described by using a non-linear stress-strain-time relationship. The two longitudinal cracks are located symmetrically with respect to the mid-span of the arch. Due to the symmetry, only half of the arch is considered. Time-dependent solutions to strain energy release rate are obtained by analyzing the balance of the energy. For verification, time-dependent solutions to the strain energy release rate are derived also by considering the time-dependent complementary strain energy. The evolution of the strain energy release rate with the time is analyzed. The effects of material inhomogeneity, locations of the two cracks along the thickness of the arch and the magnitude of the external loading on the time-dependent strain energy release rate are evaluated.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.410-412
• /
• 2021

본 논문은 객체와 배경 히스토그램을 활용한 개선된 보행자 검출 방식을 제안하고 있다. HOG & SVM 알고리즘을 통해 검출한 객체는 사각형 형태로 검출된다. 사각형 영역 안에는 배경과 객체의 영역이 혼합되어있다. 배경을 제외한 객체의 영역만을 검출한다면 객체 관련 다양한 정보를 쉽게 얻을 수 있다. 검출된 사각형의 크기를 객체의 크기에 맞게 x-y축 투영 알고리즘을 사용하여 재조정한다. 그리고 나서 재조정 된 사각형 내의 객체에 대한 히스토그램을 바탕으로 배경과 객체를 구분하여 개선된 객체를 검출한다. 검출한 객체와 원본의 객체를 비교하는 신뢰성 평가인 정밀도와 재현율의 평균값이 각각 97.9%와 90%를 보이고 있다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.566-569
• /
• 2022

비젼 카메라를 이용하여 작업자의 장갑 칼라 및 위치를 인식하고 이를 기반으로 로봇팔의 모션을 제어하는 시스템을 개발하였다. 시스템은 물체의 영상정보를 인식하는 카메라, 로봇팔 제어 알고리즘, 자체 로봇팔 및 제어 시스템으로 구성된다. 카메라는 작업자가 착용한 장갑의 모양과 색을 인지하여 크기 및 위치정보를 출력하게 되며, 본 연구에서는 이러한 위치 및 물체를 둘러싼 크기 정보를 이용하여 로봇 팔의 모션 속도를 제어한다. 연구 방법의 검증은 6축 로봇으로 실행하였으며, 조종자의 손동작 조종에 의한 실험을 통해 제안한 영상정보 제어 및 로봇 선단 제어 방법이 성공적으로 동작함을 확인하였다.

• Animal Systematics, Evolution and Diversity
• /
• 제39권4호
• /
• pp.254-263
• /
• 2023

Two feather mites, Brephosceles anatina Dubinin, 1951 (Analgoidea: Alloptidae) and Freyana anatina (Koch, 1844) (Pterolichoidea: Freyanidae), have been reported for the first time from the Eastern Spot-billed Duck, Anas zonorhyncha Swinhoe, 1866 (Anseriformes: Anatidae), in Korea. The genera Brephosceles Hull, 1934 and Freyana Haller, 1877 are new records of Korean fauna. The morphology of B. anatina is distinguished from three species of the lambda species group in having legs IV extending the level of setae e2 with the distal end of the tarsus in males, and the incision on the posterior margin of the hysteronotal shield triangular-shaped and distinctly longer than its greatest width in females. Freyana anatina is distinguished from F. nyrocae and F. obliquasetae in having setae ps1 with a rectangle bend in homeomorphic males, and setae ps1 obliquely ovate and divergent, with the inner canal going obliquely across the membranous part of these setae in females. This study provides morphological redescriptions of both feather mite species supplemented with partial sequences of mitochondrial cytochrome c oxidase subunit I(COI), based on specimens collected in Korea.

• 국제학술발표논문집
• /
• The 4th International Conference on Construction Engineering and Project Management Organized by the University of New South Wales
• /
• pp.46-51
• /
• 2011

High-rise buildings are widely being constructed in the Middle-East, South-East, and East Asia. These buildings are usually willing to stand for the landmark of the region and, therefore, exhibit some extraordinary features such as super-tall height, elevation set-backs, overhangs, or free-form exterior surface, all of which makes the construction difficult, complex, and even unsafe at some construction stages. In addition to the elaborately planned construction sequence, prediction and monitoring of building's movement during construction and after completion are required for precise and safe construction. This is often called the Building Movement Control during construction. This study describes Building Movement Control of the KLCC Tower, a 58-story office building currently being built right next to the famous PETRONAS Twin Towers. The main items of the Building Movement Control for the KLCC Tower are axial shortening and verticality. Preliminary prediction of these items are already carried out by the structural design team but more accurate prediction based on construction stage analysis and combined with time-dependent material testing, field monitoring, and site survey is done by the main contractor. As of September 2010, the Tower is under construction at level 30, where the plan abruptly changes from rectangle to triangle. Findings and troubleshooting until the current construction stage are explained in detail and implementations are suggested for future applications.

• 한국산업융합학회 논문집
• /
• 제27권4_1호
• /
• pp.797-803
• /
• 2024

In this study, a device was used to conduct heat to the riser by combining a cylindrical heater with the riser to maintain the molten metal above a certain temperature while continuously compensating for the shrinkage phenomenon that occurs as the molten metal solidifies in the product area. A cylindrical heater is coupled to the riser portion of the upper part of the upper mold, and a heater portion mold is formed between the riser and the cylindrical heater. The cylindrical heater is connected to a controller to control the temperature and a power supply. The cylindrical heater conducts a heat source to the molten metal located on the riser and can continuously compensate for the shrinkage of the cast product by heating the molten metal located on the riser or maintaining it at a constant temperature. The block without a riser had a large shrinkage cavity at the top, and the top became concave due to shrinkage. There is no shrinkage in the block with the Ø100 mm riser. Blocks that did not apply heaters to the Ø50 mm riser experienced shrinkage around the riser and also at the bottom. There is no shrinkage in the block with the Ø50 mm riser to which the heater was applied.