• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.642-645
• /
• 2004

This paper focuses on recovering systematic biases during LIDAR calibration, particularly using natural surfaces as control features. Many previous approaches have utilized all the points overlapping with the control features and often experienced with an inaccurate value converged with a poor rate due to wrong correspondence in pairing a point and the corresponding control features. To overcome these shortcomings, we establish a preventive scheme to select the pairs of high confidence, where the confidence value is based on the error budget associated with the point measurement and the linearity and roughness of the control feature. This approach was then applied to calibraring the LIDAR data simulated with the given systematic biases. The parameters were successfully recovered using the proposed approach with the accuracy and convergence rate superior to those using the previous approaches.

• Journal of information and communication convergence engineering
• /
• v.7 no.2
• /
• pp.141-147
• /
• 2009

To initialize and maintain self-organizing networks such as mobile ad hoc networks, address allocation protocol is essentially required. However, centralized approaches that pervasively used in traditional networks are not recommended in this kind of networks since they cannot handle with mobility efficiently. In addition, previous distributed approaches suffer from inefficiency with control overhead caused by duplicated address detection and management of available address pool. In this paper, we propose a new dynamic address allocation scheme, which is based on adaptive partition. An available address is managed in distributed way by multiple agents and partitioned adaptively according to current network environments. Finally, simulation results reveal that a proposed scheme is superior to previous approach in term of address acquisition delay under diverse simulation scenarios.

• Journal of Ubiquitous Convergence Technology
• /
• v.2 no.1
• /
• pp.40-50
• /
• 2008

The problem of assigning customers to satellite channels is a difficult combinatorial optimization problem and is NP-complete. For this combinatorial optimization problem, standard optimization methods take a large computation time and so genetic algorithms (GA) and ant colony optimization (ACO) can be used to obtain the best and/or optimal assignment of customers to satellite channels. In this paper, we present a comparative study of GA and ACO to this problem. Various issues related to genetic algorithms approach to this problem, such as solution representation, selection methods, genetic operators and repair of invalid solutions are presented. We also discuss an ACO for this problem. In ACO methodology, three strategies, ACO with only ranking, ACO with only max-min ant system (MMAS), and ACO with both ranking and MMAS, are considered. A comparison of these two approaches (i,e., GA and ACO) with the standard optimization method is presented to show the advantages of these approaches in terms of computation time.

• Journal of information and communication convergence engineering
• /
• v.11 no.4
• /
• pp.241-246
• /
• 2013

A classic document clustering technique may incorrectly classify documents into different clusters when documents that should belong to the same cluster do not have any shared terms. Recently, to overcome this problem, internal and external knowledge-based approaches have been used for text document clustering. However, the clustering results of these approaches are influenced by the inherent structure and the topical composition of the documents. Further, the organization of knowledge into an ontology is expensive. In this paper, we propose a new enhanced text document clustering method using non-negative matrix factorization (NMF) and WordNet. The semantic terms extracted as cluster labels by NMF can represent the inherent structure of a document cluster well. The proposed method can also improve the quality of document clustering that uses cluster labels and term weights based on term mutual information of WordNet. The experimental results demonstrate that the proposed method achieves better performance than the other text clustering methods.

• Journal of information and communication convergence engineering
• /
• v.17 no.1
• /
• pp.21-40
• /
• 2019

This paper presents a comprehensive survey of various artificial intelligence (AI) techniques implemented in cognitive radio engine to improve cognition capability in cognitive radio networks (CRNs). AI enables systems to solve problems by emulating human biological processes such as learning, reasoning, decision making, self-adaptation, self-organization, and self-stability. The use of AI techniques is studied in applications related to the major tasks of cognitive radio including spectrum sensing, spectrum sharing, spectrum mobility, and decision making regarding dynamic spectrum access, resource allocation, parameter adaptation, and optimization problem. The aim is to provide a single source as a survey paper to help researchers better understand the various implementations of AI approaches to different cognitive radio designs, as well as to refer interested readers to the recent AI research works done in CRNs.

• International journal of advanced smart convergence
• /
• v.10 no.3
• /
• pp.163-171
• /
• 2021

Recently, Machine Learning-based visualization approaches have been proposed to combat the problem of malware detection. Unfortunately, these techniques are exposed to Adversarial examples. Adversarial examples are noises which can deceive the deep learning based malware detection network such that the malware becomes unrecognizable. To address the shortcomings of these approaches, we present Block-matching and 3D filtering (BM3D) algorithm and deep image prior based denoising technique to defend against adversarial examples on visualization-based malware detection systems. The BM3D based denoising method eliminates most of the adversarial noise. After that the deep image prior based denoising removes the remaining subtle noise. Experimental results on the MS BIG malware dataset and benign samples show that the proposed denoising based defense recovers the performance of the adversarial attacked CNN model for malware detection to some extent.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.453-461
• /
• 2021

Many deep learning approaches have been studied for image classification in computer vision. However, there are not enough data to generate accurate models in medical fields, and many datasets are not annotated. This study presents a new method that can use both unlabeled and labeled data. The proposed method is applied to classify cervix images into normal versus cancerous, and we demonstrate the results. First, we use a patch self-supervised learning for training the global context of the image using an unlabeled image dataset. Second, we generate a classifier model by using the transferred knowledge from self-supervised learning. We also apply attention learning to capture the local features of the image. The combined method provides better performance than state-of-the-art approaches in accuracy and sensitivity.

• Korean Journal of Radiology
• /
• v.23 no.11
• /
• pp.1089-1101
• /
• 2022

Immunotherapy has revolutionized and opened a new paradigm for cancer treatment. In the era of immunotherapy and molecular targeted therapy, precision medicine has gained emphasis, and an early response assessment is a key element of this approach. Treatment response assessment for immunotherapy is challenging for radiologists because of the rapid development of immunotherapeutic agents, from immune checkpoint inhibitors to chimeric antigen receptor-T cells, with which many radiologists may not be familiar, and the atypical responses to therapy, such as pseudoprogression and hyperprogression. Therefore, new response assessment methods such as immune response assessment, functional/molecular imaging biomarkers, and artificial intelligence (including radiomics and machine learning approaches) have been developed and investigated. Radiologists should be aware of recent trends in immunotherapy development and new response assessment methods.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.08a
• /
• pp.385-385
• /
• 2012

Understanding the thermodynamics and structural transformation during the Metal-Insulator Transition (MIT) is critical to better understand the underlying physical origin of phase transition in the vanadiumdioxide ($VO_2$). Here, through the temperature-dependent in-situ high resolutiontransmission electron microscopy (HR-TEM), and systematic electrical transport study, we have shown that the tunable MIT transition of $VO_2$ nanowires is strongly affected by interplay between strain and domain nucleation by ion beam irradiation. Surprsingly, we have also observed that the $VO_2$ rutile (R) metallic phase could form directly in a strain-induced metastable monoclinic (M2) phase. These insights open the door toward more systematic approaches to synthesis for $VO_2$ nanostructures in desired phase and to use for applications including ultrafast optical switching, smart window, metamaterial, resistance RAM and synapse devices.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.5
• /
• pp.43-49
• /
• 2008

Motivated by the Communication Broadcasting Convergence service, various technical approaches are being used to develop more efficient antenna models. This paper proposes a compact mobile antenna which is attachable to a cell phone and is applicable for Communication Broadcasting Convergence. In the design of the antennas for mobile handsets, size reduction is a crucial factor. In this paper, the compactness of a loop antenna is realized by bending a folded-dipole. A short planar dipole is transformed to a twice folded dipole and a loop antenna to produce a larger input resistance. The current distribution of the antenna is the same as a loop antenna, and its radiation patterns are omni-directional. We also analyze the performance of the RFID antenna by exploring the current-induced near field radiation patterns using a electro-optic field mapping system.