• Proceedings of The KACE
• /
• 2017.08a
• /
• pp.47-49
• /
• 2017

인공 신경망 기반 자연어 처리 시스템들에서 단어를 벡터로 변환할 때, 크게 색인 및 순람표를 이용하는 방법과 합성곱 신경망이나 회귀 신경망을 이용하는 방법이 있다. 이 때, 전자의 방법을 사용하려면 시스템이 수용 가능한 어휘집이 정의되어 있어야 하며 새로운 단어를 어휘집에 추가하기 어렵다. 반면 후자의 방법을 사용하면 단어를 구성하는 문자들을 바탕으로 벡터 표현을 생성하기 때문에 어휘집이 필요하지 않지만, 추가적인 인공 신경망 구조가 필요하기 때문에 모델의 복잡도와 파라미터의 수가 증가한다는 단점이 있다. 본 연구에서는 위 두 방법의 한계를 극복하고자 Bag of Characters를 응용하여 단어를 구성하는 문자들의 집합을 바탕으로 벡터 표현을 생성하는 방법을 제안한다. 제안된 방법은 문자를 기반으로 동작하기 때문에 어휘집을 정의할 필요가 없으며, 인공 신경망 구조가 사용되지 않기 때문에 시스템의 복잡도도 증가시키지 않는다. 또한, 단어의 벡터 표현에 단어를 구성하는 문자들의 정보가 반영되기 때문에 Out-Of-Vocabulary 단어에 대한 성능도 어휘집을 사용하는 방법보다 우수할 것으로 기대된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.6
• /
• pp.2648-2668
• /
• 2016

Modern mobile devices are equipped with various accelerated processing units to handle computationally intensive applications; therefore, Open Computing Language (OpenCL) has been proposed to fully take advantage of the computational power in heterogeneous systems. This article introduces a parallel software decoder of Low Density Parity Check (LDPC) codes on an embedded heterogeneous platform using an OpenCL framework. The LDPC code is one of the most popular and strongest error correcting codes for mobile communication systems. Each step of LDPC decoding has different parallelization characteristics. In the proposed LDPC decoder, steps suitable for task-level parallelization are executed on the multi-core central processing unit (CPU), and steps suitable for data-level parallelization are processed by the graphics processing unit (GPU). To improve the performance of OpenCL kernels for LDPC decoding operations, explicit thread scheduling, vectorization, and effective data transfer techniques are applied. The proposed LDPC decoder achieves high performance and high power efficiency by using heterogeneous multi-core processors on a unified computing framework.

• Journal of Broadcast Engineering
• /
• v.16 no.6
• /
• pp.1009-1017
• /
• 2011

Fast generation of digital hologram is of importance for real-time holography broadcasting. In this paper, we propose such a method that parallelizes the Computer-Generated Holography (CGH) algorithm for digital hologram generation and make it faster using Multi Graphic Processing Unit (Multi-GPU) with help of the Compute Unified Device Architecture (CUDA) and the Open Multi-Processing (OpenMP). In addition, we propose optimization methods such as fixation variable, vectorization, and loop unrolling for making the CGH algorithm much faster. Experimental results show that our method is about 9,700 times faster than a CPU-based one.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.34-39
• /
• 2002

Road information is very important for topographic mapping, transportation application, urban planning and other related application fields. Therefore, automatic detection of road networks from spatial imagery, such as aerial photos and satellite imagery can play a central role in road information acquisition. In this paper, we use least squares correlation matching alone for road center tracking and show that it works. We assumed that (bright) road centerlines would be visible in the image. We further assumed that within a same road segment, there would be only small differences in brightness values. This algorithm works by defining a template around a user-given input point, which shall lie on a road centerline, and then by matching the template against the image along the orientation of the road under consideration. Once matching succeeds, new match proceeds by shifting a matched target window further along road orientation at the target window. By repeating the process above, we obtain a series of points, which lie on a road centerline successively. A 1m resolution IKONOS images over Seoul and Daejeon were used for tests. The results showed that this algorithm could extract road centerlines in any orientation and help in fast and exact he ad-up digitization/vectorization of cartographic images.

• Journal of Korea Multimedia Society
• /
• v.7 no.4
• /
• pp.579-591
• /
• 2004

This paper presents a new arc segmentation method which extracts curves from simple drawing consisted of straight lines and curves and segments them into circular arcs. First, it finds center points and finds line segments and curve segments by tracing connected center points. Next, it expands the segment by searching neighbor segment at the two endpoints. Next, it removes straight lines and segments the extracted curves into circular arcs by using the recursive subdivision method. The proposed method has been compared with previous vectorization software and vector based arc segmentation method. Experimental results show that the proposed method produces more correct results for the curves which contain intersection with other lines or curves.

• Journal of Computational Design and Engineering
• /
• v.3 no.1
• /
• pp.14-23
• /
• 2016

The problem of fitting B-spline curves to planar point clouds is studied in this paper. A novel method is proposed to deal with the most challenging case where multiple intersecting curves or curves with self-intersection are necessary for shape representation. A method based on Delauney Triangulation of data points is developed to identify connected components which is also capable of removing outliers. A skeleton representation is utilized to represent the topological structure which is further used to create a weighted graph for deciding the merging of curve segments. Different to existing approaches which utilize local shape information near intersections, our method considers shape characteristics of curve segments in a larger scope and is thus capable of giving more satisfactory results. By fitting each group of data points with a B-spline curve, we solve the problems of curve structure reconstruction from point clouds, as well as the vectorization of simple line drawing images by drawing lines reconstruction.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.3
• /
• pp.842-850
• /
• 1998

In this paper, we propose a method that recognize hatched area based on segmentation and vectorization of a machine drawing. This recogntion of hatched area is composed of three parts. First, the proposed method segments an object, arrowheads and interpretation lines from the machine drawing and vectorizes the object and interpretation lines. Second, closed-loops are labeled with the vectorized objects, and then candidates of hatched areas arc determined. Finally, by recognizing hatched lines included in hatched areas, recognition of the hatched areas is completed. The proposed method is more useful in extracting and recognizing the hatched areas.

• ETRI Journal
• /
• v.43 no.4
• /
• pp.660-673
• /
• 2021

To efficiently use frequency resources, the next 6th generation mobile communication technology must solve the problem of out-of-band emission (OoBE) of cyclic prefix (CP) orthogonal frequency division multiplexing (OFDM), which is not solved in 5th generation technology. This study describes a new zero insertion technique to replace an existing filtering scheme to solve this internal problem in OFDM signals. In the development of the proposed scheme, a precoder with a two-dimensional structure is first designed by generating a two-dimensional mapper and using the specialty of each matrix. A spectral shaping technique based on zero insertion instead of a long filter is proposed, so it can be applied not only to long OFDM symbols, but also very short ones. The proposed method shows that the transmitted signal is completely blocked at the bandwidth boundaries of signals according to the current standards, and it is confirmed that the proposed scheme is ideal with respect to bit error rate (BER) performance because its BER is the same as that of CP-OFDM. In addition, the proposed scheme can transformed into a real time structure through vectorizing process with minimal complexity.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.842-857
• /
• 2023

Currently, most sentiment classification models on microblogging platforms analyze sentence parts of speech and emoticons without comprehending users' emotional inclinations and grasping moral nuances. This study proposes a hybrid sentiment analysis model. Given the distinct nature of microblog comments, the model employs a combined stop-word list and word2vec for word vectorization. To mitigate local information loss, the TextCNN model, devoid of pooling layers, is employed for local feature extraction, while BiLSTM is utilized for contextual feature extraction in deep learning. Subsequently, microblog comment sentiments are categorized using a classification layer. Given the binary classification task at the output layer and the numerous hidden layers within BiLSTM, the Tanh activation function is adopted in this model. Experimental findings demonstrate that the enhanced TextCNN-BiLSTM model attains a precision of 94.75%. This represents a 1.21%, 1.25%, and 1.25% enhancement in precision, recall, and F1 values, respectively, in comparison to the individual deep learning models TextCNN. Furthermore, it outperforms BiLSTM by 0.78%, 0.9%, and 0.9% in precision, recall, and F1 values.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1599-1618
• /
• 2024

Access control has always been one of the effective methods to protect data security. However, in new computing environments such as big data, data resources have the characteristics of distributed cross-domain sharing, massive and dynamic. Traditional access control mechanisms are difficult to meet the security needs. This paper proposes CACM-MMSR to solve distributed cross-domain access control problem for massive resources. The method uses blockchain and smart contracts as a link between different security domains. A permission decision model migration method based on access control logs is designed. It can realize the migration of historical policy to solve the problems of access control heterogeneity among different security domains and the updating of the old and new policies in the same security domain. Meanwhile, a semantic reasoning-based permission decision method for unstructured text data is designed. It can achieve a flexible permission decision by similarity thresholding. Experimental results show that the proposed method can reduce the decision time cost of distributed access control to less than 28.7% of a single node. The permission decision model migration method has a high decision accuracy of 97.4%. The semantic reasoning-based permission decision method is optimal to other reference methods in vectorization and index time cost.