• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1114-1121
• /
• 2021

In this paper, we implement a recipe recommendation system using ingredient harmonization analysis based on recipe data. The proposed system receives an image of a food ingredient purchase receipt to recommend ingredients and recipes to the user. Moreover, it performs preprocessing of the receipt images and text extraction using the OCR algorithm. The proposed system can recommend recipes based on the combined data of ingredients. It collects recipe data to calculate the combination for each food ingredient and extracts the food ingredients of the collected recipe as training data. And then, it acquires vector data by learning with a natural language processing algorithm. Moreover, it can recommend recipes based on ingredients with high similarity. Also, the proposed system can recommend recipes using replaceable ingredients to improve the accuracy of the result through preprocessing and postprocessing. For our evaluation, we created a random input dataset to evaluate the proposed recipe recommendation system's performance and calculated the accuracy for each algorithm. As a result of performance evaluation, the accuracy of the Word2Vec algorithm was the highest.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.3
• /
• pp.92-103
• /
• 2021

With the continuous acceleration of economic and social development, people gradually pay attention to their health, improve their living environment, diet, strengthen exercise, and even conduct regular health examination, to ensure that they always understand the health status. Even so, people still face many health problems, and the number of chronic diseases is increasing. Recently, COVID-19 has also reminded people that public health problems are also facing severe challenges. With the development of artificial intelligence equipment and technology, medical diagnosis expert systems based on big data have become a topic of concern to many researchers. At present, there are many algorithms that can help computers initially diagnose diseases for patients, but they want to improve the accuracy of diagnosis. And taking into account the pathology that varies from person to person, the health diagnosis expert system urgently needs a new algorithm to improve accuracy. Through the understanding of classic algorithms, this paper has optimized it, and finally proved through experiments that the combined classification algorithm improved by latent factors can meet the needs of medical intelligent diagnosis.

• Journal of Software Assessment and Valuation
• /
• v.16 no.2
• /
• pp.63-68
• /
• 2020

This paper proposes a face authentication system based on deep learning framework. The proposed system is consisted of face region detection and feature extraction using deep learning algorithm, and performed the face authentication using joint-bayesian matrix learning algorithm. The performance of proposed paper is evaluated by various face database , and the face image of one person consists of 2 images. The face authentication algorithm was performed by measuring similarity by applying 2048 dimension characteristic and combined Bayesian algorithm through Deep Neural network and calculating the same error rate that failed face certification. The result of proposed paper shows that the proposed system using deep learning and joint bayesian algorithms showed the equal error rate of 1.2%, and have a good performance compared to previous approach.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.3
• /
• pp.129-136
• /
• 2023

In this paper, we describe a rule-based risk classification algorithm to perform Risk-based Inspection (RBI) on imported goods at customs. The RBI system is a method to automatically select which cargos have to be inspected and manage potential risks in boarder. In this study, we designed a rule-based risk classification algorithm for RBI solutions and implemented them using the Svelte web application framework. The risk classification algorithm proposed in this paper uses different indicative risk factors such as HS code, country of origin, importer's reliability, trade relationships, and logistics routes to classify cargos into Green, Yellow, and Red channels. To achieve this, we assigned risk categories to each risk factor and randomly generated risk scores within a specific range for each risk category. This system is expected to contribute to the increased efficiency of customs operations and protect public safety by minimizing the risk of imported hazardous materials.

• Journal of the Korea Society for Simulation
• /
• v.19 no.4
• /
• pp.1-9
• /
• 2010

In this paper, advanced evacuation analysis simulation on a passenger ship is performed. Velocity based model has been implemented and used to calculate the movement of the individual passengers under the evacuation situation. The age and gender of each passenger are considered as the factors of walking speed. Flocking algorithm is applied for the passenger's group behavior. Penalty walking velocity is introduced to avoid collision between the passengers and obstacles, and to prevent the position overlap among passengers. Application of flocking algorithm and penalty walking velocity to evacuation simulation is verified through implementation of the 11 test problems in IMO (International Maritime Organization) MSC (Maritime Safety Committee) Circulation 1238.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.6
• /
• pp.120-127
• /
• 1995

A nonlinear empirical state-space model of the Artificial Neural Network(ANN) has been developed. The nonlinear model structure incorporates characteristic, so as to enable identification of the transient response, as well as the steady-state response of a dynamic system. A hybrid feedfoward/feedback neural network, namely a Local Time Delayed Recurrent Multi-layer Perception(RMLP), is the model structure developed in this paper. RMLP is used to identify nonlinear dynamic system in an input/output sense. The feedfoward protion of the network architecture provides with the well-known curve fitting factor, while local recurrent and cross-talk connections provides the dynamics of the system. A dynamic learning algorithm is used to train the proposed network in a supervised manner. The derived dynamic learning algorithm exhibit a computationally desirable characteristic; both network sweep involved in the algorithm are performed forward, enhancing its parallel implementation. RMLP state-space and its associate learning algorithm is demonstrated through a simple examples. The simulation results are very encouraging.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.28-30
• /
• 2021

In this paper, an algorithm that detects the user's finger direction using the YOLO (You Only Look Once) library was proposed. The processing stage of the proposed finger direction detection algorithm consists of a learning data management stage, a data learning stage, and a finger direction detection stage. As a result of the experiment, it was found that the distance between the camera and the finger had a very large influence on the accuracy of detecting the direction of the finger. We plan to apply this function to Turtlebot3 after improving the accuracy and reliability of the proposed algorithm in the future.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.532-535
• /
• 2022

Path following algorithms have been intensively studied for various mobile platforms such as planetary exploration, unmanned delivery, and autonomous driving. However, ensuring high accuracy in practical applications is challenging due to enormous uncertainty inherent in real environment. In this paper, we aim to reveal the guideline for the design and implementation by investigating the path following performance of mobile robot controlled by the pure pursuit algorithm. To this end, we evaluate the accuracy of the pure pursuit algorithm when tuning the look ahead distance and deploying erroneous actuator.

• Structural Engineering and Mechanics
• /
• v.88 no.3
• /
• pp.239-249
• /
• 2023

The Radial Point Interpolation Method (RPIM) has been proposed to overcome the difficulties associated with the use of the Radial Basis Functions (RBFs). The RPIM has the following properties: Simple implementation in terms of boundary conditions as in the Finite Element Method (FEM). A less expensive CPU time compared to other collocation meshless methods such as the Moving Least Square (MLS) collocation method. In this work, we propose an adaptive high-order numerical algorithm based on RPIM to simulate the thermoviscoplastic behavior of a material mixing observed in the Friction Stir Welding (FSW) process. The proposed adaptive meshfree RPIM algorithm adapts well to the geometric and physical data by choosing a good shape parameter with a good precision. Our numerical approach combines the RPIM and the Asymptotic Numerical Method (ANM). A numerical procedure is also proposed in this work to automatically determine an improved shape parameter for the RBFs. The efficiency of the proposed algorithm is analyzed in comparison with an iterative algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2732-2749
• /
• 2023

Device-to-Device (D2D) communication has received increasing attention and been studied extensively thanks to its advantages in improving spectral efficiency and energy efficiency of cellular networks. This paper proposes a novel relay selection algorithm for multi-hop full-duplex D2D communications underlaying cellular networks. By selecting the relay of each hop in a reverse manner, the proposed algorithm reduces the heavy signaling overhead that traditional relay selection algorithms introduce. In addition, the social domain information of mobile terminals is taken into consideration and its influence on the performance of D2D communications studied, which is found significant enough not to be overlooked. Moreover, simulations show that the proposed algorithm, in absence of social relationship information, improves data throughput by around 70% and 7% and energy efficiency by 64% and 6%, compared with two benchmark algorithms, when D2D distance is 260 meters. In a more practical implementation considering social relationship information, although the proposed algorithm naturally achieves less throughput, it substantially increases the energy efficiency than the benchmarks.