• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.1 s.307
• /
• pp.53-66
• /
• 2006

This paper proposes the combined image retrieval system that gives the same relevance as exhaustive search method while its performance can be considerably improved. This system is combined with two different retrieval methods and each gives the same results that full exhaustive search method does. Both of them are two-stage method. One uses condensation of feature vectors, and the other uses binary-tree clustering. These two methods extract the candidate images that always include correct answers at the first stage, and then filter out the incorrect images at the second stage. Inasmuch as these methods use equal algorithm, they can get the same result as full exhaustive search. The first method condenses the dimension of feature vectors, and it uses these condensed feature vectors to compute similarity of query and images in database. It can be found that there is an optimal condensation ratio which minimizes the overall retrieval time. The optimal ratio is applied to first stage of this method. Binary-tree clustering method, searching with recursive 2-means clustering, classifies each cluster dynamically with the same radius. For preserving relevance, its range of query has to be compensated at first stage. After candidate clusters were selected, final results are retrieved by computing similarities again at second stage. The proposed method is combined with above two methods. Because they are not dependent on each other, combined retrieval system can make a remarkable progress in performance.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.3 s.345
• /
• pp.49-58
• /
• 2006

In this paper, a curve-fitting channel estimation method is proposed for orthogonal frequency division multiplexing (OFDM) system in a time-varying frequency-selective fading channel. The method can greatly improve channel state information (CSI) estimation accuracy by performing smoothing and interpolation through consecutive curve-fitting processes in both time domain and frequency domain. It first evaluates least-squares (LS) estimates using pilot symbols and then the estimates are approximated to a polynomial with proper degree in the LS error sense, starting from one preferred domain in which pilots we densely distributed. Smoothing, interpolation, and prediction are performed subsequently to obtain CSI estimates for data transmission. The channel estimation processes are completed by smoothing and interpolating CSI estimates in the other domain once again using the channel estimates obtained in one domain. The performance of proposed method is influenced heavily on the time variation and frequency selectivity of channel and pilot arrangement. Hence, a proper degree of polynomial and an optimum approximation interval according to various system and channel conditions are required for curve-fitting. From extensive simulation results in various channel environments, we see that the proposed method performs better than the conventional methods including the optimal Wiener filtering method, in terms of the mean square error (MSE) and bit error rate (BER).

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.67-78
• /
• 1996

The purpose of this paper is object recognition even in the presence of occlusion by using generalized Hough transform(GHT). The GHT can be considered as a kind of model based object recognition algorithm and is executed in the following two stages. The first stage is to store the information of the model in the form of R-table (Reference table). The next stage is to identify the existence of the objects in the image by using the R-table. The improved GHT method is proposed for the practical vision system. First, in constructing the R-table, we extracted the partial arc from the portion of the whole object boundary, and this partial arc can be used for constructing the R-table. Also, clustering algorithm is employed for compensating an error arised by digitizing an object image. Second, an efficient method is introduced to avoid Ballard's use of 4-D array which is necessary for estimating position, orientation and scale change of an object. Only 2-D array is enough for recognizing an object. Especially, scale token method is introduced for calculating the scale change which is easily affected by camera zoom. The results of our test show that the improved hierarchical GHT method operates stably in the realistic vision situation, even in the case of object occlusion.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.9
• /
• pp.92-99
• /
• 2013

As a recent cyber attack has a characteristic that is intellectual, advanced, and complicated attack against precise purpose and specified object, it becomes extremely hard to recognize or respond when accidents happen. Since a scale of damage is very large, a corresponding system about this situation is urgent in national aspect. Existing data center or integration security framework of computer lab is evaluated to be a behind system when it corresponds to cyber attack. Therefore, this study suggests a better sophisticated next generation convergence security framework in order to prevent from attacks based on advanced persistent threat. Suggested next generation convergence security framework is designed to have preemptive responses possibly against APT attack consisting of five hierarchical steps in domain security layer, domain connection layer, action visibility layer, action control layer and convergence correspondence layer. In domain connection layer suggests security instruction and direction in domain of administration, physical and technical security. Domain security layer have consistency of status information among security domain. A visibility layer of Intellectual attack action consists of data gathering, comparison, decision, lifespan cycle. Action visibility layer is a layer to control visibility action. Lastly, convergence correspond layer suggests a corresponding system of before and after APT attack. An introduction of suggested next generation convergence security framework will execute a better improved security control about continuous, intellectual security threat.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.6
• /
• pp.23-36
• /
• 2005

PLLs have been widely used for many applications including communication systems. This paper presents a VCO with an improved negative skewed delay scheme and a PLL using this VCO. The proposed VCO and PLL are intended for replacing traditional LC oscillators and PLLs used in communication systems and other applications. The circuit designs of the VCO and PLL are based on 0.18um CMOS technology with 1.8V supply voltage. The proposed VCO employs subfeedback loops using pass-transistors and needs two opposite control voltages for the pass transistors. The subfeedback loops speed up oscillation depending on the control voltages and thus provide a high oscillation frequency. The two voltage controls have opposite frequency gain characteristics and result in low phase-noise. The 7-stage VCO in 0.18um CMOS technology operates from $3.2GHz\~6.3GHz$ with phase noise of about -128.8 dBc/Hz at 1MHz frequency onset. For 1.8V supply voltage, the current consumption is about 3.8mA. The proposed PLL has dual loop-filters for the proposed VCO. The PLL is operated at 5GHz with 1.8V supply voltage. These results indicate that the proposed VCO can be used for radio frequency operations replacing LC oscillators. The circuits have been designed and simulated using 0.18um TSMC library.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.74-86
• /
• 2006

This paper proposes a robust and computationally efficient algorithm for automatic video object segmentation. For implementing the spatio-temporal segmentation, which aims for efficient combination of the motion segmentation and the color segmentation, an SOM-based hierarchical clustering method in which the segmentation process is regarded as clustering of feature vectors is employed. As results, problems of high computational complexity which required for obtaining exact segmentation results in conventional video object segmentation methods, and the performance degradation due to noise are significantly reduced. A measure of motion vector reliability which employs MRF-based MAP estimation scheme has been introduced to minimize the influence from the motion estimation error. In addition, a noise elimination scheme based on the motion reliability histogram and a clustering validity index for automatically identifying the number of objects in the scene have been applied. A cross projection method for effective object tracking and a dynamic memory to maintain temporal coherency have been introduced as well. A set of experiments has been conducted over several video sequences to evaluate the proposed algorithm, and the efficiency in terms of computational complexity, robustness from noise, and higher segmentation accuracy of the proposed algorithm have been proved.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.48 no.12
• /
• pp.91-96
• /
• 2011

In this paper, a low-power direct-conversion transmitter based on current-mode operation, which satisfies the IEEE 802.15.4 standard, is proposed and implemented in a $0.13{\mu}m$ CMOS technology. The proposed transmitter consists of DACs, LPFs, variable gain I/Q up-conversion mixer, a divide-by-two circuit with LO buffer, and a drive amplifier. By combining DAC, LPF, and variable gain I/Q up-conversion mixer with a simple current mirror configuration, the transmitter's power consumption is reduced and its linearity is improved. The drive amplifier is a cascode amplifier with gain controls and the 2.4GHz I/Q differential LO signals are generated by a divide-by-two current-mode-logic (CML) circuit with an external 4.8GHz input signal. The implemented transmitter has 30dB of gain control range, 0dBm of maximum transmit output power, 33dBc of local oscillator leakage, and 40dBc of the transmit third harmonic component. The transmitter dissipates 10.2mW from a 1.2V supply and the die area of the transmitter is $1.76mm{\times}1.26mm$.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.33-42
• /
• 2005

In this paper, we propose an efficient segmentation algerian using morphological grayscale reconstruction for region-based coding. Each segmentation stage consists of simplification, marker extraction and decision. The simplification removes unnecessary components to make an easier segmentation. The marker extraction finds the flat zones which are the seed points from the simplified image. The decision is to locate the contours of regions detected by the marker extraction. For the simplification, we use a new connected operator based on the size and contrast. In the marker extraction stage, the regions reconstructed to original values we excluded from the candidate marker. For the other regions, the regions which are larger than structuring elements or have higher contrast than a threshold value are selected as markers. For the initial segmentation, the conventional hierarchical watershed algorithm and the extracted markers are used. Finally in the region merging stage, we propose an efficient region merging algorithm which preserves a high quality in terms of the number of regions. At the same time, the pairs which have higher contrast than a threshold are excluded from the region merging stage. Experimental results show that the proposed marker extraction method produces a small number of markers, while maintaining high quality and that the proposed region merging algorithm achieves a good performance in terms of the image quality and the number of regions.

• Journal of KIISE:Software and Applications
• /
• v.29 no.9
• /
• pp.669-675
• /
• 2002

In recent years most of personalized recommender systems in electronic commerce utilize collaborative filtering algorithm in order to recommend more appropriate items. User-based collaborative filtering is based on the ratings of other users who have similar preferences to a user in order to predict the rating of an item that the user hasn't seen yet. This nay decrease the accuracy of prediction because the similarity between two users is computed with respect to the two users and only when an item has been rated by the users. In item-based collaborative filtering, the preference of an item is predicted based on the similarity between the item and each of other items that have rated by users. This method, however, uses the ratings of users who are not the neighbors of a user for computing the similarity between a pair of items. Hence item-based collaborative filtering may degrade the accuracy of a recommender system. In this paper, we present a new approach that a user's neighborhood is used when we compute the similarity between the items in traditional item-based collaborative filtering in order to compensate the weak points of the current item-based collaborative filtering and to improve the prediction accuracy. We empirically evaluate the accuracy of our approach to compare with several different collaborative filtering approaches using the EachMovie collaborative filtering data set. The experimental results show that our approach provides better quality in prediction and recommendation list than other collaborative filtering approaches.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.27-65
• /
• 2020

Many companies on information and communication technology make public their own developed AI technology, for example, Google's TensorFlow, Facebook's PyTorch, Microsoft's CNTK. By releasing deep learning open source software to the public, the relationship with the developer community and the artificial intelligence (AI) ecosystem can be strengthened, and users can perform experiment, implementation and improvement of it. Accordingly, the field of machine learning is growing rapidly, and developers are using and reproducing various learning algorithms in each field. Although various analysis of open source software has been made, there is a lack of studies to help develop or use deep learning open source software in the industry. This study thus attempts to derive a strategy for adopting the framework through case studies of a deep learning open source framework. Based on the technology-organization-environment (TOE) framework and literature review related to the adoption of open source software, we employed the case study framework that includes technological factors as perceived relative advantage, perceived compatibility, perceived complexity, and perceived trialability, organizational factors as management support and knowledge & expertise, and environmental factors as availability of technology skills and services, and platform long term viability. We conducted a case study analysis of three companies' adoption cases (two cases of success and one case of failure) and revealed that seven out of eight TOE factors and several factors regarding company, team and resource are significant for the adoption of deep learning open source framework. By organizing the case study analysis results, we provided five important success factors for adopting deep learning framework: the knowledge and expertise of developers in the team, hardware (GPU) environment, data enterprise cooperation system, deep learning framework platform, deep learning framework work tool service. In order for an organization to successfully adopt a deep learning open source framework, at the stage of using the framework, first, the hardware (GPU) environment for AI R&D group must support the knowledge and expertise of the developers in the team. Second, it is necessary to support the use of deep learning frameworks by research developers through collecting and managing data inside and outside the company with a data enterprise cooperation system. Third, deep learning research expertise must be supplemented through cooperation with researchers from academic institutions such as universities and research institutes. Satisfying three procedures in the stage of using the deep learning framework, companies will increase the number of deep learning research developers, the ability to use the deep learning framework, and the support of GPU resource. In the proliferation stage of the deep learning framework, fourth, a company makes the deep learning framework platform that improves the research efficiency and effectiveness of the developers, for example, the optimization of the hardware (GPU) environment automatically. Fifth, the deep learning framework tool service team complements the developers' expertise through sharing the information of the external deep learning open source framework community to the in-house community and activating developer retraining and seminars. To implement the identified five success factors, a step-by-step enterprise procedure for adoption of the deep learning framework was proposed: defining the project problem, confirming whether the deep learning methodology is the right method, confirming whether the deep learning framework is the right tool, using the deep learning framework by the enterprise, spreading the framework of the enterprise. The first three steps (i.e. defining the project problem, confirming whether the deep learning methodology is the right method, and confirming whether the deep learning framework is the right tool) are pre-considerations to adopt a deep learning open source framework. After the three pre-considerations steps are clear, next two steps (i.e. using the deep learning framework by the enterprise and spreading the framework of the enterprise) can be processed. In the fourth step, the knowledge and expertise of developers in the team are important in addition to hardware (GPU) environment and data enterprise cooperation system. In final step, five important factors are realized for a successful adoption of the deep learning open source framework. This study provides strategic implications for companies adopting or using deep learning framework according to the needs of each industry and business.