• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.173-178
• /
• 2022

Recently, a recommendation system using deep learning in social network services has been actively studied. However, in the case of a recommendation system using deep learning, the cold start problem and the increased learning time due to the complex computation exist as the disadvantage. In this paper, the user-tailored exercise routine recommendation algorithm is proposed using the user's metadata. Metadata (the user's height, weight, sex, etc.) set as the input of the model is applied to the designed model in the proposed algorithms. The exercise recommendation system model proposed in this paper is designed based on the neural collaborative filtering (NCF) algorithm using multi-layer perceptron and matrix factorization algorithm. The learning proceeds with proposed model by receiving user metadata and exercise information. The model where learning is completed provides recommendation score to the user when a specific exercise is set as the input of the model. As a result of the experiment, the proposed exercise recommendation system model showed 10% improvement in recommended performance and 50% reduction in learning time compared to the existing NCF model.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.471-476
• /
• 2024

With the spread of various smart devices and computing devices, big data generation is occurring widely. Machine learning is an algorithm that performs reasoning by learning data patterns. Among the various machine learning algorithms, the algorithm that attracts attention is deep learning based on neural networks. Deep learning is achieving rapid performance improvement with the release of various applications. Recently, among deep learning algorithms, attempts to analyze data using graph structures are increasing. In this study, we present a graph generation method for transferring to a deep learning network. This paper proposes a method of generalizing node properties and edge weights in the graph generation process and converting them into a structure for deep learning input by presenting a matricization We present a method of applying a linear transformation matrix that can preserve attribute and weight information in the graph generation process. Finally, we present a deep learning input structure of a general graph and present an approach for performance analysis.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.1
• /
• pp.116-125
• /
• 2014

Road conditions can provide important information for driving safety in driving assistance systems. The input images usually include unnecessary information and they need to be analyzed only in a region of interest (ROI) to reduce the amount of computation. In this paper, a vision-based road ROI determination algorithm is proposed to detect the road region using the positional information of a vanishing point and line segments. The line segments are detected using Canny's edge detection and Hough transform. The vanishing point is traced by a Kalman filter to reduce the false detection due to noises. The road ROI can be determined automatically and adaptively in every frame after initialization. The proposed method is implemented using C++ and the OpenCV library, and the road ROIs are obtained from various video images of black boxes. The results show that the proposed algorithm is robust.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.5
• /
• pp.77-86
• /
• 2016

This paper describes a dual-mode reference-less CDR(Clock Data Recovery) operating at full / half-rate and its operation algorithm. Proposed reference-less CDR consists of a frequency detector, a phase detector, a charge pump, a loop filter, a voltage controlled oscillator, and a digital block. The frequency and phase detectors operate at both full / half-rate for dual-mode operation and especially the frequency detector is capable of detecting the difference between data rate and clock frequency in the dead zone of general frequency detectors. Dual-mode reference-less CDR with the proposed algorithm can recover the data and clock within 1.2-1.3 us and operates reliably at both full-rate (2.7 Gb/s) and half-rate (5.4 Gb/s) with 0.5-UI input jitter.

• The KIPS Transactions:PartB
• /
• v.19B no.2
• /
• pp.107-112
• /
• 2012

An active object tracking algorithm using Pan and Tilt camera based in the stepwise application of region and color information from realtime image sequences is proposed. To reduce environment noises in input sequences, Gaussian filtering is performed first. An image is divided into background and objects by using the adaptive Gaussian mixture model. Once the target object is detected, an initial search window close to an object region is set up and color information is extracted from the region. We track moving objects in realtime by using the CAMShift algorithm which enables to trace objects in active camera with the color information. The proper tracking is accomplished by controlling the amount of pan and tilt to be placed the center position of object into the middle of field of view. The experimental results show that the proposed method is more effective than the hand-operated window method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1611-1633
• /
• 2022

At EUROCRYPT 2019, a new block cipher algorithm called BISON was proposed by Canteaut et al. which uses a novel structure named as Whitened Swap-Or-Not (WSN). Unlike the traditional wide trail strategy, the differential and linear properties of this algorithm can be easily determined. However, the encryption speed of the BISON algorithm is quite low due to a large number of iterative rounds needed to ensure certain security margins. Commonly, denoting by n is the data block length, this design requires 3n encryption rounds. Moreover, the block size n of BISON is always odd, which is not convenient for operations performed on a byte level. In order to overcome these issues, we propose a new block cipher, named DBISON, which more efficiently employs the ideas of double layers typical to the BISON-like construction. More precisely, DBISON divides the input into two parts of size n/2 bits and performs the round computations in parallel, which leads to an increased encryption speed. In particular, the data block length n of DBISON can be even, which gives certain additional implementation benefits over BISON. Furthermore, the resistance of DBISON against differential and linear attacks is also investigated. It is shown the maximal differential probability (MDP) is 1/2^n-1 for n encryption rounds and that the maximal linear probability (MLP) is strictly less than 1/2^n-1 when (n/2+3) iterative encryption rounds are used. These estimates are very close to the ideal values when n is close to 256.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.12
• /
• pp.1089-1099
• /
• 2015

This paper proposes vision-based collision risk estimation method for an unmanned surface vehicle. A robust image-processing algorithm is suggested to detect target obstacles from the vision sensor. Vision-based Target Motion Analysis (TMA) was performed to transform visual information to target motion information. In vision-based TMA, a camera model and optical flow are adopted. Collision risk was calculated by using a fuzzy estimator that uses target motion information and vision information as input variables. To validate the suggested collision risk estimation method, an unmanned surface vehicle experiment was performed.

• Communications for Statistical Applications and Methods
• /
• v.10 no.2
• /
• pp.595-601
• /
• 2003

In this paper we propose an on line training method for classification based on least squares support vector machine. Proposed method enables the computation cost to be reduced and the training to be peformed incrementally, With the incremental formulation of an inverse matrix in optimization problem, current information and new input data can be used for building the new inverse matrix for the estimation of the optimal bias and Lagrange multipliers, so the large scale matrix inversion operation can be avoided. Numerical examples are included which indicate the performance of proposed algorithm.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.5 no.2
• /
• pp.157-165
• /
• 2009

Existing methods for image segmentation using diffusion can't preserve contour information, or noises with high gradients become more salient as the umber of times of the diffusion increases, resulting in over-segmentation when applied to watershed. This thesis proposes a method for image segmentation by applying morphology operation together with robust anisotropic diffusion. For an input image, transformed into LUV color space, closing by reconstruction and anisotropic diffusion are applied to obtain a simplified image which preserves contour information with noises removed. With gradients computed from this simplifed images, watershed algorithm is applied. Experiments show that color images are segmented very effectively without over-segmentation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.299-302
• /
• 2001

The statistical analysis of the feature extraction and the neural networks are proposed to recognize a human face. In the preprocessing step, the normalized skin color map with Gaussian functions is employed to extract the region of face candidate. The feature information in the region of the face candidate is used to detect the face region. In the recognition step, as a tested, the 120 images of 10 persons are trained by the backpropagation algorithm. The images of each person are obtained from the various direction, pose, and facial expression. Input variables of the neural networks are the geometrical feature information and the feature information that comes from the eigenface spaces. The simulation results of$.$10 persons show that the proposed method yields high recognition rates.