• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.455-457
• /
• 2021

App is used on mobile devices such as smartphones and also has malicious code, which can be divided into normal and malicious depending on the presence or absence of hacking codes. Because there are many kind of malware, it is difficult to detect directly, we propose a method to detect malicious app using AI. Most of the existing methods are to detect malicious app by extracting features from malicious app. However, the number of types have increased exponentially, making it impossible to detect malicious code. Therefore, we would like to propose two more methods besides detecting malicious app by extracting features from most existing malicious app. The first method is to learn normal app to extract normal's features, as opposed to the existing method of learning malicious app and find abnormalities (malicious app). The second one is an 'ensemble technique' that combines the existing method with the first proposal. These two methods need to be studied so that they can be used in future mobile environment.

• Journal of Ginseng Research
• /
• v.41 no.3
• /
• pp.339-346
• /
• 2017

Background: In this study, we investigated how to convert the Panax ginseng DNA sequence code and chemical fingerprints into a two-dimensional code. In order to improve the compression efficiency, GATC2Bytes and digital merger compression algorithms are proposed. Methods: HPLC chemical fingerprint data of 10 groups of P. ginseng from Northeast China and the internal transcribed spacer 2 (ITS2) sequence code as the DNA sequence code were ready for conversion. In order to convert such data into a two-dimensional code, the following six steps were performed: First, the chemical fingerprint characteristic data sets were obtained through the inflection filtering algorithm. Second, precompression processing of such data sets is undertaken. Third, precompression processing was undertaken with the P. ginseng DNA (ITS2) sequence codes. Fourth, the precompressed chemical fingerprint data and the DNA (ITS2) sequence code were combined in accordance with the set data format. Such combined data can be compressed by Zlib, an open source data compression algorithm. Finally, the compressed data generated a two-dimensional code called a quick response code (QR code). Results: Through the abovementioned converting process, it can be found that the number of bytes needed for storing P. ginseng chemical fingerprints and its DNA (ITS2) sequence code can be greatly reduced. After GTCA2Bytes algorithm processing, the ITS2 compression rate reaches 75% and the chemical fingerprint compression rate exceeds 99.65% via filtration and digital merger compression algorithm processing. Therefore, the overall compression ratio even exceeds 99.36%. The capacity of the formed QR code is around 0.5k, which can easily and successfully be read and identified by any smartphone. Conclusion: P. ginseng chemical fingerprints and its DNA (ITS2) sequence code can form a QR code after data processing, and therefore the QR code can be a perfect carrier of the authenticity and quality of P. ginseng information. This study provides a theoretical basis for the development of a quality traceability system of traditional Chinese medicine based on a two-dimensional code.

• International Journal of Ocean Engineering and Technology Speciallssue:Selected Papers
• /
• v.4 no.1
• /
• pp.38-43
• /
• 2001

This paper provides review of research results undertaken on reinforced concrete wall panels in one way and two way. The review also highlights two well accepted code design methods from the American (ACI) and Australia Concrete structures standards. The emphasis is on walls under axial compression only with changes in various parameters. These include the variation of panel dimensions panels (ie. Slenderness, thinness and aspect ratios), steel reinforcement, eccentricities, concrete strength and support conditions. The main purpose of this review is to compile research previous by undertaken to highlight the inadequate in certain research literature. It is envisage that this review will expose areas in wall research required so that inadequate in current methods can be rectified.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.15 no.3
• /
• pp.1-6
• /
• 1978

This paper deals with speech digitization and bandwidth compression techniques, particularly two predictive coding methods-namely, adaptive diferentia1 pulse code modulation(ADPCM) and adaptive delta modulation (ADM). The principle of a typical adoptive quantizer that is used in ADPCM is explained, and two analysis methods for the adaptive predictor coefficents, block and sequential analyses, are discussed. Also, three companding methods (instantaneous, syllabic, and hybrid companding) that are used in ADM are explained in detail, and their performances are compared. In addition, the performances of ADPCM and ADM as speech coders are compared, and the merits of each coder are discussed.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.3E
• /
• pp.19-23
• /
• 1997

The goal of postprocessing in automatic speech recognition is to improve recognition performance by utterance verification at the output of recognition stage. It is focused on the effective rejection of out-of vocabulary words based on the confidence score of hypothesized candidate word. We present two methods for computing confidence scores. Both methods are based on the distance between each observation vector and the representative code vector, which is defined by the most likely code vector at each state. While the first method employs simple time normalization, the second one uses a normalization technique based on the concept of on-line garbage mode[1]. According to the speaker independent isolated words recognition experiment with discrete density HMM, the second method outperforms both the first one and conventional likelihood ratio scoring method[2].

• Journal of KSNVE
• /
• v.9 no.2
• /
• pp.310-316
• /
• 1999

4-Pole parameter method based on an acoustic theory is very popular for the analysis of the acoustic behavior of the car exhaust system. However, this method is applicable only for the simple shape of acoustic elements of the muffler. Numerical methods such as FEM(Finite Element Method) or BEM(Boundary Element Method) can also provide acceptable results for the acoustic analysis of the car exhaust system. Even though these numerical methods have benefits for the analysis of complicated shape of acoustic elements of the muffler, time consuming is another problem during modeling and numerical calculation. Combining benefits of both methods, the new code called the hybrid method for car exhaust system is introduced. And the developed code is utilized for calculation of the transmission loss of a main muffler of an automobile comparing with the experimental results.

• Journal of Information Processing Systems
• /
• v.18 no.5
• /
• pp.628-636
• /
• 2022

Automatic program repair (APR) techniques focus on automatically repairing bugs in programs and providing correct patches for developers, which have been investigated for decades. However, most studies have limitations in repairing complex bugs. To overcome these limitations, we developed an approach that augments datasets by utilizing token tagging and applying machine learning techniques for APR. First, to alleviate the data insufficiency problem, we augmented datasets by extracting all the methods (buggy and non-buggy methods) in the program source code and conducting token tagging on non-buggy methods. Second, we fed the preprocessed code into the model as an input for training. Finally, we evaluated the performance of the proposed approach by comparing it with the baselines. The results show that the proposed approach is efficient for augmenting datasets using token tagging and is promising for APR.

• Convergence Security Journal
• /
• v.14 no.2
• /
• pp.17-24
• /
• 2014

Form of backdoor penetration attacks "trapdoor" penetration points to bypass the security features and allow direct access to the data. Backdoor without modifying the source code is available, and even code generation can also be modified after compilation. This approach by rewriting the compiler when you compile the source code to insert a specific area in the back door can be due to the use of the method. Defense operations and the basic structure of the backdoor or off depending on the nature of the damage area can be a little different way. This study is based on the diagnosis of a back door operating mechanism acting backdoor analysis methods derived. Research purposes in advance of the attack patterns of malicious code can respond in a way that is intended to be developed. If we identify the structures of backdoor and the infections patterns through the analysis, in the future we can secure the useful information about malicious behaviors corresponding to hacking attacks.

• Journal of Digital Convergence
• /
• v.12 no.2
• /
• pp.285-293
• /
• 2014

Two-dimensional PDF417 bar code has a wide range of use and has a storage capacity to compress a large amount of data. With these characteristics, PDF417 has been used in various ways to prevent the forgery and alteration of important information in documents. On the other hand, previous decoding methods in PDF417 barcode are slow and inefficient because they simply employ the standard specifications of AIM (Association for Automatic Identification and Mobility). Therefore, this paper propose an efficient and fast algorithm of decoding PDF417 bar code. As a result, the proposed decoding algorithm will be more faster and efficient than previous methods.

• Journal of Korea Multimedia Society
• /
• v.11 no.1
• /
• pp.13-22
• /
• 2008

This paper proposes an efficient ROI code block discrimination algorithm for dynamic ROI coding. The proposed algorithm calculates the girth of the ROI only with some mask information in consideration of the characteristics of the shape of the ROI for reducing a ROI code block discrimination time, and this proposed algorithm discriminates whether there is a ROI code block by the girth and the critical value of the ROI. Also, this discrimination algorithm is capable of treating the coefficients of the background within a ROI code block preferentially and controlling a loss by controlling the threshold value of the ROI. In order to demonstrate the utility of the proposed method, this paper conducted a comparative experiment of the proposed method with the existing methods. As a result of this experiment, it was confirmed that the proposed method was superior to the conventional methods in terms of quality and speed.