• Title/Summary/Keyword: feature engineering

Search Result 5,841, Processing Time 0.033 seconds

Performance Evaluations for Leaf Classification Using Combined Features of Shape and Texture (형태와 텍스쳐 특징을 조합한 나뭇잎 분류 시스템의 성능 평가)

  • Kim, Seon-Jong;Kim, Dong-Pil
    • Journal of Intelligence and Information Systems
    • /
    • v.18 no.3
    • /
    • pp.1-12
    • /
    • 2012
  • There are many trees in a roadside, parks or facilities for landscape. Although we are easily seeing a tree in around, it would be difficult to classify it and to get some information about it, such as its name, species and surroundings of the tree. To find them, you have to find the illustrated books for plants or search for them on internet. The important components of a tree are leaf, flower, bark, and so on. Generally we can classify the tree by its leaves. A leaf has the inherited features of the shape, vein, and so on. The shape is important role to decide what the tree is. And texture included in vein is also efficient feature to classify them. This paper evaluates the performance of a leaf classification system using both shape and texture features. We use Fourier descriptors for shape features, and both gray-level co-occurrence matrices and wavelets for texture features, and used combinations of such features for evaluation of images from the Flavia dataset. We compared the recognition rates and the precision-recall performances of these features. Various experiments showed that a combination of shape and texture gave better results for performance. The best came from the case of a combination of features of shape and texture with a flipped contour for a Fourier descriptor.

Study on Fraud and SIM Box Fraud Detection Method in VoIP Networks (VoIP 네트워크 내의 Fraud와 SIM Box Fraud 검출 방법에 대한 연구)

  • Lee, Jung-won;Eom, Jong-hoon;Park, Ta-hum;Kim, Sung-ho
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.40 no.10
    • /
    • pp.1994-2005
    • /
    • 2015
  • Voice over IP (VoIP) is a technology for the delivery of voice communications and multimedia sessions over Internet Protocol (IP) networks. Instead of being transmitted over a circuit-switched network, however, the digital information is packetized, and transmission occurs in the form of IP packets over a packet-switched network which consist of several layers of computers. VoIP Service that used the various techniques has many advantages such as a voice Service, multimedia and additional service with cheap cost and so on. But the various frauds arises using VoIP because VoIP has the existing vulnerabilities at the Internet and based on complex technologies, which in turn, involve different components, protocols, and interfaces. According to research results, during in 2012, 46 % of fraud calls being made in VoIP. The revenue loss is considerable by fraud call. Among we will analyze for Toll Bypass Fraud by the SIM Box that occurs mainly on the international call, and propose the measures that can detect. Typically, proposed solutions to detect Toll Bypass fraud used DPI(Deep Packet Inspection) based on a variety of detection methods that using the Signature or statistical information, but Fraudster has used a number of countermeasures to avoid it as well. Particularly a Fraudster used countermeasure that encrypt VoIP Call Setup/Termination of SIP Signal or voice and both. This paper proposes the solution that is identifying equipment of Toll Bypass fraud using those countermeasures. Through feature of Voice traffic analysis, to detect involved equipment, and those behavior analysis to identifying SIM Box or Service Sever of VoIP Service Providers.

Real-Time Vehicle License Plate Recognition System Using Adaptive Heuristic Segmentation Algorithm (적응 휴리스틱 분할 알고리즘을 이용한 실시간 차량 번호판 인식 시스템)

  • Jin, Moon Yong;Park, Jong Bin;Lee, Dong Suk;Park, Dong Sun
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.3 no.9
    • /
    • pp.361-368
    • /
    • 2014
  • The LPR(License plate recognition) system has been developed to efficient control for complex traffic environment and currently be used in many places. However, because of light, noise, background changes, environmental changes, damaged plate, it only works limited environment, so it is difficult to use in real-time. This paper presents a heuristic segmentation algorithm for robust to noise and illumination changes and introduce a real-time license plate recognition system using it. In first step, We detect the plate utilized Haar-like feature and Adaboost. This method is possible to rapid detection used integral image and cascade structure. Second step, we determine the type of license plate with adaptive histogram equalization, bilateral filtering for denoise and segment accurate character based on adaptive threshold, pixel projection and associated with the prior knowledge. The last step is character recognition that used histogram of oriented gradients (HOG) and multi-layer perceptron(MLP) for number recognition and support vector machine(SVM) for number and Korean character classifier respectively. The experimental results show license plate detection rate of 94.29%, license plate false alarm rate of 2.94%. In character segmentation method, character hit rate is 97.23% and character false alarm rate is 1.37%. And in character recognition, the average character recognition rate is 98.38%. Total average running time in our proposed method is 140ms. It is possible to be real-time system with efficiency and robustness.

Copyright Protection for Fire Video Images using an Effective Watermarking Method (효과적인 워터마킹 기법을 사용한 화재 비디오 영상의 저작권 보호)

  • Nguyen, Truc;Kim, Jong-Myon
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.2 no.8
    • /
    • pp.579-588
    • /
    • 2013
  • This paper proposes an effective watermarking approach for copyright protection of fire video images. The proposed watermarking approach efficiently utilizes the inherent characteristics of fire data with respect to color and texture by using a gray level co-occurrence matrix (GLCM) and fuzzy c-means (FCM) clustering. GLCM is used to generate a texture feature dataset by computing energy and homogeneity properties for each candidate fire image block. FCM is used to segment color of the fire image and to select fire texture blocks for embedding watermarks. Each selected block is then decomposed into a one-level wavelet structure with four subbands [LL, LH, HL, HH] using a discrete wavelet transform (DWT), and LH subband coefficients with a gain factor are selected for embedding watermark, where the visibility of the image does not affect. Experimental results show that the proposed watermarking approach achieves about 48 dB of high peak-signal-to-noise ratio (PSNR) and 1.6 to 2.0 of low M-singular value decomposition (M-SVD) values. In addition, the proposed approach outperforms conventional image watermarking approach in terms of normalized correlation (NC) values against several image processing attacks including noise addition, filtering, cropping, and JPEG compression.

Comparative Experiments to Assess the Effects of Accumulator Nitrogen Injection on Passive Core Cooling During Small Break LOCA

  • Li, Yuquan;Hao, Botao;Zhong, Jia;Wang, Nan
    • Nuclear Engineering and Technology
    • /
    • v.49 no.1
    • /
    • pp.54-70
    • /
    • 2017
  • The accumulator is a passive safety injection device for emergency core cooling systems. As an important safety feature for providing a high-speed injection flow to the core by compressed nitrogen gas pressure during a loss-of-coolant accident (LOCA), the accumulator injects its precharged nitrogen into the system after its coolant has been emptied. Attention has been drawn to the possible negative effects caused by such a nitrogen injection in passive safety nuclear power plants. Although some experimental work on the nitrogen injection has been done, there have been no comparative tests in which the effects on the system responses and the core safety have been clearly assessed. In this study, a new thermal hydraulic integral test facility-the advanced core-cooling mechanism experiment (ACME)-was designed and constructed to support the CAP1400 safety review. The ACME test facility was used to study the nitrogen injection effects on the system responses to the small break loss-of-coolant accident LOCA (SBLOCA) transient. Two comparison test groups-a 2-inch cold leg break and a double-ended direct-vessel-injection (DEDVI) line break-were conducted. Each group consists of a nitrogen injection test and a nitrogen isolation comparison test with the same break conditions. To assess the nitrogen injection effects, the experimental data that are representative of the system responses and the core safety were compared and analyzed. The results of the comparison show that the effects of nitrogen injection on system responses and core safety are significantly different between the 2-inch and DEDVI breaks. The mechanisms of the different effects on the transient were also investigated. The amount of nitrogen injected, along with its heat absorption, was likewise evaluated in order to assess its effect on the system depressurization process. The results of the comparison and analyses in this study are important for recognizing and understanding the potential negative effects on the passive core cooling performance caused by nitrogen injection during the SBLOCA transient.

A Case Study of the Improvement of the Structural Work of a Logistics Facility by Using PC Member (PC부재에 의한 물류시설의 골조공사 개선사례 연구)

  • Kim, Seon-Hyung;Choi, Eun-Gyu;Kim, Sun-Kuk;Lee, Sung-Ho
    • Journal of the Korea Institute of Building Construction
    • /
    • v.10 no.6
    • /
    • pp.127-135
    • /
    • 2010
  • As logistics facilities have a high ceiling height, simple structure, and the need for a quick return on investment, it is usually essential to advance the construction schedule of such facilities. Accordingly, PC structures, which require less labor, cost and schedule, can be more competitive than RC structures. However, most construction companies in Korea are familiar with RC structure design, have negative perceptions regarding PC structures, and do not sufficiently adopt new construction techniques. The structure that this research features has 110 columns that are 14 m high and are built to the same specification, and applying an RC design to the structure will lead to issues related to constructibility, economic viability, project duration and safety. Therefore, this study intends to feature PC design as an alternative to the RC warehouse design, and perform a comparative analysis of the reduction in labor, cost and construction schedule to highlight benefits. The research outcomes herein will provide inputs to subsequent studies on new construction strategies to advance the construction schedule, improve quality and constructibility, enhance safety and save costs.

Improved SIM Algorithm for Contents-based Image Retrieval (내용 기반 이미지 검색을 위한 개선된 SIM 방법)

  • Kim, Kwang-Baek
    • Journal of Intelligence and Information Systems
    • /
    • v.15 no.2
    • /
    • pp.49-59
    • /
    • 2009
  • Contents-based image retrieval methods are in general more objective and effective than text-based image retrieval algorithms since they use color and texture in search and avoid annotating all images for search. SIM(Self-organizing Image browsing Map) is one of contents-based image retrieval algorithms that uses only browsable mapping results obtained by SOM(Self Organizing Map). However, SOM may have an error in selecting the right BMU in learning phase if there are similar nodes with distorted color information due to the intensity of light or objects' movements in the image. Such images may be mapped into other grouping nodes thus the search rate could be decreased by this effect. In this paper, we propose an improved SIM that uses HSV color model in extracting image features with color quantization. In order to avoid unexpected learning error mentioned above, our SOM consists of two layers. In learning phase, SOM layer 1 has the color feature vectors as input. After learning SOM Layer 1, the connection weights of this layer become the input of SOM Layer 2 and re-learning occurs. With this multi-layered SOM learning, we can avoid mapping errors among similar nodes of different color information. In search, we put the query image vector into SOM layer 2 and select nodes of SOM layer 1 that connects with chosen BMU of SOM layer 2. In experiment, we verified that the proposed SIM was better than the original SIM and avoid mapping error effectively.

  • PDF

The Meaning of Plant Species in Korean Gugok Poems(九曲詩歌) (우리나라 구곡시가에서 나타난 조경 식물종의 상징적 의미)

  • Oh, Chang-Song;Park, Sang-Wook
    • Journal of the Korean Institute of Traditional Landscape Architecture
    • /
    • v.38 no.2
    • /
    • pp.77-94
    • /
    • 2020
  • Gugok poems were an important material for studying the Gugok landscape garden(九曲園林). the landscape feature(景物)that emerges from poetry is an important material that expresses the sense of placefulness and garden consciousness(園林意識). However, many studies are passive about plant materials that can explore the perception of nature or the aesthetic embodiment process. Therefore, this study seeks to discover various symbolic meanings and reveal the context of plants that have appeared in Gugok poems in order to expand the research material of the Gugok culture. To carry out the purpose of the study, I collected a total of 25 related poems from 18 Gugoks and found a total of 20 species of trees. I used 'R-program' to derive the meaning of trees and examined the meaning of trees by intertextuality. According to the study, the 20 species of trees contained symbolic meanings of world of Taoist hermit, pursuit of study, constancy, true pleasure, dignity, honest poverty, reign of peace, nostalgia. Many species focused on the symbolism of the 'world of Taoist hermit' and then on the 'dignity' was the most frequent. A number of species, except for the peach, zelkova and oak, had multiple meanings. Among them, pine trees and lotus had a wide range of symbolic meanings and different meanings depending on the characteristics of the surrounding landscape. While the Gugok culture generally targets natural scenery, Yongsan, Toegye, Deoksan, and Jusan showed the characteristics of strengthening or reproducing symbolic meanings through artificial plating and gardening. In order to overcome the limitations of the peach tree, which symbolizes 'Mureungdowon(武陵桃園)', Gugok poems used maple trees and reeds as alternative species. In accordance with the above context, the trees appearing in the Gugok poems expressed their symbolic meaning differently according to the landscape features, acts and purposes of the Gugoks, rather than sticking to the traditional meaning.

A Study on Utilization of Korea Science Citation Database(KSCD) Based on Data Mining Techniques (데이터마이닝 기술을 이용한 한국과학기술인용색인DB 활용 방안 연구)

  • Park, Jong-Hyun;Choi, Seon-Heui;Kim, Byung-Kyu
    • Journal of Information Management
    • /
    • v.43 no.4
    • /
    • pp.191-210
    • /
    • 2012
  • Scholarly science citation data is typically of large volume and consists of a variety of data. Moreover, the volume of data is increasing more and more. Therefore, there are some requirements to store and manage the data efficiently and Korea Institute of Science and Technology Information (KISTI) develops Korea Science Citation Database (KSCD) which manage and serve very large-volume of korea science technique information including citation data. However, current services based on KSCD are not enough for various users. Thus, it is important issue to offer a variety of services using KSCD. For example, if a user searches articles described by a specific author, then a user may want to find not only the articles cited by a certain author but also those articles that study similar topics. However, it is not always easy to provide these services with citation data. Therefore, this paper surveys studies about services using citation data in order to find approaches for better utilizing KSCD. Especially, this paper considers data mining techniques, because data mining is one of the main techniques to extracting semantic information from big data. Therefore, this paper discusses methods for utilizing large volume of KSCD based on data mining technique.

A Study on the Effects Plastics have on the Product Designs through the Development of Plastic Materials - On & Around the Streamline favored by the Generation 1920-30'th - (플라스틱의 개발이 제품 디자인에 미친 영향에 관한 연구 - 1920-30년대 유선형을 중심으로 -)

  • Lee, Ok-Bun
    • Archives of design research
    • /
    • v.19 no.2 s.64
    • /
    • pp.283-292
    • /
    • 2006
  • The Plastic material had been developed in the middle of the 19th century as an alternative material. Along with the development of the electrical engineering industry, it cropped up into center stage as an effective material and has increasingly expanded its use. As such, the plastic material has bound deep-seated ties with the design activities of industrial products, coming into the main material for a variety of industrial designs. Despite its dose affinity to design function in terms of its materialistic property, we have rarely seen examples of intensive study on the realtionship between plastics and designs. This study aims to find the importance that the substance affects industrial products in designs along with the development of plastic materials. With the objective in mind, we made a review of the streamline stylishness that had flourished in the twenties and thirties of the 19th century. Through this study, we understand that the plastic material has a close realtionshop with design activities in three different aspects. First, its amorphous state of nature makes it possible to change into any shape one desires in plastic surgery, which feature in turn influences the moulding of any design forms. Second, the plastic material is best suited to mass-manufacture, which induces to reduce the cost of production. Hence, the expansion of design industry. Third, the plastic material allows the multiple variety of colors, sensitivity, gloss and patterns and infinitely large possibility ranging from natural senses to human senses with the result that numberless diversity of designs cdould come into being.

  • PDF