http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Detection of Lung Nodule on Temporal Subtraction Images Based on Artificial Neural Network
Takumi Tokisa,Noriaki Miyake,Shinya Maeda,Hyoungseop Kim,Joo Kooi Tan,Seiji Ishikawa,Seiichi Murakami,Takatoshi Aoki 한국지능시스템학회 2012 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.12 No.2
The temporal subtraction technique as one of computer aided diagnosis has been introduced in medical fields to enhance the interval changes such as formation of new lesions and changes in existing abnormalities on deference image. With the temporal subtraction technique radiologists can easily detect lung nodules on visual screening. Until now, two-dimensional temporal subtraction imaging technique has been introduced for the clinical test. We have developed new temporal subtraction method to remove the subtraction artifacts which is caused by mis-registration on temporal subtraction images of lungs on MDCT images. In this paper, we propose a new computer aided diagnosis scheme for automatic enhancing the lung nodules from the temporal subtraction of thoracic MDCT images. At first, the candidates regions included nodules are detected by the multiple threshold technique in terms of the pixel value on the temporal subtraction images. Then, a rule-base method and artificial neural networks is utilized to remove the false positives of nodule candidates which is obtained temporal subtraction images. We have applied our detection of lung nodules to 30 thoracic MDCT image sets including lung nodules. With the detection method, satisfactory experimental results are obtained. Some experimental results are shown with discussion.
Development of an Unmanned Autonomous Flying Wing for Aerial Observations
Takumi Fukuda,Takashi Takimoto 제어로봇시스템학회 2014 제어로봇시스템학회 국제학술대회 논문집 Vol.2014 No.10
The unmanned aerial vehicles (UAVs) are the aircraft without a human operator on board. Since operators can control the aircraft without some danger, they are useful as an emergency aerial observation method. In this paper, as one of these UAVs, we focus on the flying wing which is a fixed-wing aircraft. In general, the fixed-wing-type UAV can fly longer time than the helicopter-type one because the lift force is produced by rotation of propeller only. However, since the flying speed is very fast in order to produce lift force, it is difficult to take the stationary picture for the observation. Therefore, we have developed the flying wing which can fly slowly at a small field. Moreover, in order to realize the autonomous flight, we have proposed a target point follow-up control method. Then, the effectiveness of the proposed flying wing is explained by experimental results.
Development of a Game console with High Level Hardware description Language NSL
Takumi Furukawa,Naohiko Shimizu 대한전자공학회 2015 ITC-CSCC :International Technical Conference on Ci Vol.2015 No.6
We developed a NES-compatible game console with high level hardware description language NSL. Our method reduced 30% of development lines and 60% of logics with high level hardware description language NSL compare to the other work. In this paper, we will present the development flow and the HW/SW Co-simulation for the verification.
Takumi Okamoto,Tetsushi Koide,Anh-Tuan Hoang,Tatsuya Shimizu,Koki Sugi,Toru Tamaki,Bisser Raytchev,Kazufumi Kaneda,Shigeto Yoshida,Hiroshi Mieno,Kazufumi Kaneda 대한전자공학회 2015 ITC-CSCC :International Technical Conference on Ci Vol.2015 No.6
Recently, with the increase in the number of colorectal cancer patients, the computer-aided diagnosis (CAD) systems which support a doctor"s diagnosis are essential for early stage treatment. In this paper, we introduce a SVM hardware architecture for CAD system for colorectal endoscopic images with NBI magnification findings. Additionally, we also propose a pyramid style structure with multi-SVMs for effective diagnosis image segmentation.
Object Recognition Using Hierarchical Structure
Takumi Toyama,Koichi Kise 한국멀티미디어학회 2009 한국멀티미디어학회 국제학술대회 Vol.2009 No.-
Object recognition is one of the most challenging problems in the field of computer vision. Although recent approaches have shown promising results, such approaches are specialized in each recognition task. Therefore they cannot be extended many other recognition tasks. To integrate many types of recognition, we propose a novel recognition method which uses hierarchical structure. Our experimental results show the proposed method has advantages on processing time and accuracy compared to a conventional method for generic object recognition.
A study on the relations between criminal behaviors in purse-snatching and urban spaces
Takumi Kasuya,Hidenori Tamagawa 서울시립대학교 도시과학연구원 2012 도시과학국제저널 Vol.16 No.3
Many purse-snatching cases occur near or around stations or entertainment areas where many people gather. We examined 16 purse-snatching cases closely and verified how purse-snatching offenders utilized urban spaces and how they behaved. Our results showed that purse-snatching offenders headed for hunting grounds looking for their targets based on the distance between their bases and their hunting grounds. It also depended on the transportation means they used. Urban elements also affected the behaviors of the purse-snatching offenders and the offenders often utilized urban structures such as parks as their escape routes or hiding places.
Dosimetric properties of Mg-doped Al2O3 transparent ceramics
Takumi Kato,Noriaki Kawaguchi,Takayuki Yanagida 한양대학교 세라믹연구소 2019 Journal of Ceramic Processing Research Vol.20 No.5
Transparent ceramics of Al2O3 doped with different concentrations of Mg2+ ions (0.001, 0.01, 0.1 and 1.0%) were synthesized by the Spark Plasma Sintering (SPS) method, and scintillation and dosimetric properties were investigated. Under X-ray irradiation, all the samples showed emission peaks around 310, 380 and 693 nm. Based on the measured scintillation decay times and previous studies, the origins of the emission peaks at 310, 380 and 693 nm were attributed to F+ centers, F centers and Cr3+ impurity ions, respectively. The 0.1% Mg-doped sample showed a glow curve consisting of peaks around 50, 105, 135, 230, 350 and 400 oC. All the samples had a linear TSL response in a dose range from 0.1 to 1,000 mGy.