• Smart Structures and Systems
• /
• v.29 no.3
• /
• pp.475-484
• /
• 2022

The loss of cable tension for civil infrastructure reduces structural bearing capacity and causes harmful deformation of structures. Currently, most of the structural health monitoring (SHM) approaches for cables rely on contact transducers. This paper proposes a cable tension identification technology using percussion sound, which provides a fast determination of steel cable tension without physical contact between cables and sensors. Notably, inspired by the concept of tensioning strings for piano tuning, this proposed technology predicts cable tension value by deep learning assisted classification of "percussion" sound from tapping a steel cable. To simulate the non-linear mapping of human ears to sound and to better quantify the minor changes in the high-frequency bands of the sound spectrum generated by percussions, Mel-frequency cepstral coefficients (MFCCs) were extracted as acoustic features to train the deep learning network. A convolutional neural network (CNN) with four convolutional layers and two global pooling layers was employed to identify the cable tension in a certain designed range. Moreover, theoretical and finite element methods (FEM) were conducted to prove the feasibility of the proposed technology. Finally, the identification performance of the proposed technology was experimentally investigated. Overall, results show that the proposed percussion-based technology has great potentials for estimating cable tension for in-situ structural safety assessment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1671-1686
• /
• 2022

Face manipulation tools represented by Deepfake have threatened the security of people's biological identity information. Particularly, manipulation tools with deep learning technology have brought great challenges to Deepfake detection. There are many solutions for Deepfake detection based on traditional machine learning and advanced deep learning. However, those solutions of detectors almost have problems of poor performance when evaluated on different quality datasets. In this paper, for the sake of making high-quality Deepfake datasets, we provide a preprocessing method based on the image pixel matrix feature to eliminate similar images and the residual channel attention network (RCAN) to resize the scale of images. Significantly, we also describe a Deepfake detector named Cascaded-Hop which is based on the PixelHop++ system and the successive subspace learning (SSL) model. By feeding the preprocessed datasets, Cascaded-Hop achieves a good classification result on different manipulation types and multiple quality datasets. According to the experiment on FaceForensics++ and Celeb-DF, the AUC (area under curve) results of our proposed methods are comparable to the state-of-the-art models.

• Korean Journal of Plant Taxonomy
• /
• v.31 no.4
• /
• pp.321-341
• /
• 2001

Phytoliths of leaf blades of Oryza were studied by light and scanning electron microscopy in order to assign the diagnostic character and taxonomic key for the genus. Some phytoliths such as stomatal apparatus, long-cell and short-cell, existing at the same position on the abaxial side of leaf blade, were intensively investigated because of their various forms documented in a previous study. These characters have value either for testing infrageneric classification or for identifying taxa within the genus. Stomatal phytolith is formed by integration of several kinds of sources, such as the guard and subsidiary cell and the papillae. The stomatal phytolith, characterized by not only the absence and presence of phytolith originated by the papillae developed on the guard and subsidiary cell but also their pattern of arrangement, shows various morphologies, and these features have congruent with the infrageneric classification such as section and/or series. Long-cell phytolith is characterized by the absence/presence, arrangement and morphology of phytoliths originated by the papillae on the cell surface. These features may hardly have any systematic relevance within the genus, but contain some informations for identifying of species. All of short-cell phytoliths found are silica body. They form various shapes like cross, bilobate, saddlelike and trilobate, and these features are consistent with infrageneric classification such as section and/or series. Also, some characters, the absence/presence of band of short cell phytolith within costal strip, the absence/presence of saddlelike phytolith within intercostal strip and the number of band of short cell phytolith within costal strip are various according to taxa, but these features do not fall into infrageneric classification. Some taxonomic keys on the phytoliths of stomatal, long-cell and short-cell were developed by their features, and the agreement between these characters and infrageneric classifications was also discussed.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.19 no.3
• /
• pp.119-131
• /
• 2009

The world's widely used key exchange protocols are open cryptographic communication protocols, such as TLS/SSL, whereas in the financial field in Korea, key exchange protocols developed by industrial classification group have been used that are based on PKI(Public Key Infrastructure) which is suitable for the financial environments of Korea. However, the key exchange protocols are not only vulnerable to client impersonation attacks and known-key attacks, but also do not provide forward secrecy. Especially, an attacker with the private keys of the financial security server can easily get an old session-key that can decrypt the encrypted messages between the clients and the server. The exposure of the server's private keys by internal management problems, etc, results in a huge problem, such as exposure of a lot of private information and financial information of clients. In this paper, we analyze the weaknesses of the cryptographic communication protocols in use in Korea. We then propose two key exchange protocols which reduce the replacement cost of protocols and are also secure against client impersonation attacks and session-key and private key reveal attacks. The forward secrecy of the second protocol is reduced to the HDH(Hash Diffie-Hellman) problem.

• Communications for Statistical Applications and Methods
• /
• v.15 no.2
• /
• pp.283-292
• /
• 2008

Smoothing parameter or bandwidth plays a key role in nonparametric classification based on kernel density estimation. We consider choosing smoothing parameter in nonparametric classification, which optimize the Bayes risk. Hall and Kang (2005) clarified the theoretical properties of smoothing parameter in terms of minimizing Bayes risk and derived the optimal order of it. Bootstrap method was used in their exploring numerical properties. We compare cross-validation and bootstrap method numerically in terms of optimal order of bandwidth. Effects on misclassification rate are also examined. We confirm that bootstrap method is superior to cross-validation in both cases.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.263-266
• /
• 2009

Comments are short and not use spacing words or comma more than general document. We convert the 7-gram into 3-gram and select key features using topic signature. Topic signature is widely used for selecting features in document classification and summarization. We use the SVM(Support Vector Machines) as a classifier. From the result of experiments, we can see that the proposed method is outstanding over the previous methods. The proposed system can also apply to other languages.

• ETRI Journal
• /
• v.34 no.4
• /
• pp.602-612
• /
• 2012

It is becoming increasingly difficult to identify promising technologies due to the influx of new technologies and the high level of complexity involved in many of these technologies. Identifying promising information and communications technology (ICT)-based converging technologies holds the key to finding new sources of economic growth and forward momentum. The goal of this study is to identify cutting-edge ICT-based converging technologies by examining the latest trends in the US patent market. Analyzing the US patent market, the most competitive of such markets in the world, can yield certain clues about which of the ICT-based converging technologies may be the next revolutionary technologies. For a classification of these technologies, this study follows the International Patent Classification system. As for ICT, there are 58 related fields at the subclass level and 831 fields at the main-group level. For emerging and converging technologies, there are 75 at the main-group level. From these technologies, a final selection for cutting-edge ICT-based converging technologies is made using a composite index reflecting the converging coefficient, emerging coefficient, and technology impact index.

• Journal of Computing Science and Engineering
• /
• v.10 no.2
• /
• pp.58-67
• /
• 2016

With the large amount of complex network data that is increasingly available on the Web, link prediction has become a popular data-mining research field. The focus of this paper is on a link-prediction task that can be formulated as a binary classification problem in complex networks. To solve this link-prediction problem, a sparse-classification algorithm called "Truncated Kernel Projection Machine" that is based on empirical-feature selection is proposed. The proposed algorithm is a novel way to achieve a realization of sparse empirical-feature-based learning that is different from those of the regularized kernel-projection machines. The algorithm is more appealing than those of the previous outstanding learning machines since it can be computed efficiently, and it is also implemented easily and stably during the link-prediction task. The algorithm is applied here for link-prediction tasks in different complex networks, and an investigation of several classification algorithms was performed for comparison. The experimental results show that the proposed algorithm outperformed the compared algorithms in several key indices with a smaller number of test errors and greater stability.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.851-865
• /
• 2017

Ransomware such as WannaCry is a global issue and methods to defend against malware attacks are important. We have to be able to classify the malware types efficiently in order to minimize the damage from malwares. This study makes models to classify malware properly with various statistical techniques. Several classification techniques such as logistic regression, random forest, gradient boosting, and support vector machine are used to construct models. This study also helps us understand key variables to classify the type of malicious software.

• Journal of Biomedical Engineering Research
• /
• v.18 no.4
• /
• pp.357-364
• /
• 1997

The early detection of breast cancer is clearly a key ingredient for reducing breast cancer mortality. Microcalcification is the only visible feature of the DCIS's(ductal carcinoma in situ) which consist 15 ~ 20% of screening-detected breast cancer. Therefore, the analysis of the shapes and distributions of microcalcifications is very significant for the early detection. The automatic detection procedures have b(:on the concern of digital image processing for many years. We proposed here one efficient method which is essentially statistical pattern classification accelerated by one representative feature, correlation coefficient. We compared the results by this additional feature with results by a simple gray level thresholding. The average detection rate was increased from 48% by gray level feature only to 83% by the proposed method The performances were evaluated with TP rates and FP counts, and also with Bayes errors.