• Journal of Information Science Theory and Practice
• /
• v.12 no.2
• /
• pp.64-78
• /
• 2024

Sentiment analysis is one of the promising approaches for developing a point of interest (POI) recommendation system. It uses natural language processing techniques that deploy expert insights from user-generated content such as reviews and feedback. By applying sentiment polarities (positive, negative, or neutral) associated with each POI, the recommendation system can suggest the most suitable POIs for specific users. The proposed study combines two models for POI recommendation. The first model uses bidirectional long short-term memory (BiLSTM) to predict sentiments and is trained on an election dataset. It is observed that the proposed model outperforms existing models in terms of accuracy (99.52%), precision (99.53%), recall (99.51%), and F1-score (99.52%). Then, this model is used on the Foursquare dataset to predict the class labels. Following this, user and POI embeddings are generated. The next model recommends the top POIs and corresponding coordinates to the user using the LSTM model. Filtered user interest and locations are used to recommend POIs from the Foursquare dataset. The results of our proposed model for the POI recommendation system using sentiment analysis are compared to several state-of-the-art approaches and are found quite affirmative regarding recall (48.5%) and precision (85%). The proposed system can be used for trip advice, group recommendations, and interesting place recommendations to specific users.

• Journal of The Korean Digital Architecture Interior Association
• /
• v.5 no.1
• /
• pp.9-16
• /
• 2005

In Interior design, light is the most important factor in deciding color, texture and illumination level which are the basic factors of spatial design. To apply rendering technologies on prediction of illuminating effect, it is important to understand and analyse the basic properties of the illumination models that are local illumination model and global illumination model. The illumination models in computer graphics express the factors which determine the surface color, texture and light distribution through the reflection. The purpose of this study is to propose the best way of shading algorithm in interior space provided by the computer, based on the experimental analysis that 5 shading methods are applied to the interior space. The results of this study were as followed. 1) Local illumination models that are Lambert shading, Ground shading and Phong shading are not suitable to the prediction of interior illumination effect. 2) Ray tracing that is global illumination model could be adopted to interior illumination effects. Ray tracing is a very versatile algorithm because of the large range of lighting effects it can model. 3) Neither radiality nor ray tracing offers a complete solution for simulating all interior illumination effects. 4) Radiosity excels at rendering diffuse-to-diffuse inter-reflections and ray tracing excels at rendering specular reflections. By merging both shading techniques, that offers the best of both. Using computer technologies to simulate lighting in preliminary design stage which will provide information for designers and occupants to determine the effect of using artificial light sources at each stage of their design process. Further study in illumination analysis, prediction of illumination effect, and lighting calculation is required as computer media expands.

• Journal of Biosystems Engineering
• /
• v.20 no.3
• /
• pp.275-287
• /
• 1995

The rice processing complex(RPC) consisted of the rice handling, drying, storage, and milling processes. It has been established at 83 locations domestically by April 1994, and 200 of RPC will be built more throughout the country. Therefore, this study has been performed to achieve two objectives as the followings : 1) Development of mathematical models which can assess the requirement of electricity, fuel, and labor for four model systems of rice processing complex. 2) Development of a computer simulation model which produce the improved designs of RPC by the evaluation results of energy requirements of four RPC models. The results from this study are summarized as follows : 1) Mathematical models were developed on the basis of result of mass balance analysis and required power of machines for each process. 2) A computer simulation model was developed, which can produce the improved designs of RPC by the evaluation results of energy requirements. The computer simulation model language was BORLAND $C^{++}$. 3) The results of simulation showed that total energy requirements were ranged from 75.94㎾h/t to 124.30㎾h/t. 4) From the results of computer analysis of energy requirement classified by drying type, it was found that energy requirement of the drying type A{paddy rice (PR) for storage-natural air drying(15%), PR for milling-heated air drying(16%)} were less than that of the drying type B{1 step-natural air drying(PR for storage : 18%, PR for milling : 20%), 2 step-heated air drying(PR for storage : 15%, PR for milling : 16%)}. 5) The energy efficient drying method is that all the incoming rough rice to RPC should be dried by national air drying systems. If it is more than the capacity of national air drying system, the amount of surplus rough rice is recommended to be dried by the heated air drying method.

• Journal of IKEEE
• /
• v.11 no.2
• /
• pp.89-94
• /
• 2007

This paper is a study on continuous speech recognition in the Korean language using HMM-based models with continuous density functions. Here, we propose the most efficient method of continuous speech recognition for the Korean language under the condition of a continuous HMM model with 2 to 44 density functions. Two voice models were used CI-Model that uses 36 uni-phones and CD-Model that uses 3,000 tri-phones. Language model was based on N-gram. Using these models, 500 sentences and 6,486 words under speaker-independent condition were processed. In the case of the CI-Model, the maximum word recognition rate was 94.4% and sentence recognition rate was 64.6%. For the CD-Model, word recognition rate was 98.2% and sentence recognition rate was 73.6%. The recognition rate of CD-Model we obtained was stable.

• Journal of the Korean School Mathematics Society
• /
• v.2 no.1
• /
• pp.67-77
• /
• 1999

The purpose of this study was to design models of CAI programs for the graphing of quadratic functions. In order to achieve this aim, I researched the relationship between mathematics educations computer programing, and theoretical approaches of CAI. The CAI program, which was developed based on my research was then positively applied to the mathematics education class in a middle school. First of all, I selected two classes -An experimental class and a comparative class. The experimental class was taught using the CAI program and the comparative class was taught by conventional methods of instruction. The results of this study are as follows: 1. The class taught by using the CAI program scored higher academic achievement than the class taught by conventional methods of instruction. 2. The analysis of the two classes' academic scores shows that the instruction using CAI program is more effective than that by conventional methods in improving students' academic achievement. The followings are suggestion for developing CAI programs and students' understanding through this study. 1. Non computer specialists will require a few months to develope an effect CAI program. Thus, development of easier, more clearly defined and flexible models must be constructed. 2. Teachers should be eager to use pre-existing models to motivate their students irregardless of their own development of programs. 3. School should provide computer rooms with a perfect net work in proportion to class size. 4. CAI programs can make students understand faster and more directly than blackboard examples. However, inconsideration of mathematical characteristics, arithmetic by hand is more effective for the students' memory retention. Computers is an effective tool of instruction. But it is most effective when used in conjunction with other methods that complement its use.

• Ocean Systems Engineering
• /
• v.8 no.4
• /
• pp.381-407
• /
• 2018

This paper presents a hybrid numerical approach, which combines a two-phase Navier-Stokes model (NS) and the fully nonlinear potential theory (FNPT), for modelling wave-structure interaction. The former governs the computational domain near the structure, where the viscous and turbulent effects are significant, and is solved by OpenFOAM/InterDyMFoam which utilising the finite volume method (FVM) with a Volume of Fluid (VOF) for the phase identification. The latter covers the rest of the domain, where the fluid may be considered as incompressible, inviscid and irrotational, and solved by using the Quasi Arbitrary Lagrangian-Eulerian finite element method (QALE-FEM). These two models are weakly coupled using a zonal (spatially hierarchical) approach. Considering the inconsistence of the solutions at the boundaries between two different sub-domains governed by two fundamentally different models, a relaxation (transitional) zone is introduced, where the velocity, pressure and surface elevations are taken as the weighted summation of the solutions by two models. In order to tackle the challenges associated and maximise the computational efficiency, further developments of the QALE-FEM have been made. These include the derivation of an arbitrary Lagrangian-Eulerian FNPT and application of a robust gradient calculation scheme for estimating the velocity. The present hybrid model is applied to the numerical simulation of a fixed horizontal cylinder subjected to a unidirectional wave with or without following current. The convergence property, the optimisation of the relaxation zone, the accuracy and the computational efficiency are discussed. Although the idea of the weakly coupling using the zonal approach is not new, the present hybrid model is the first one to couple the QALE-FEM with OpenFOAM solver and/or to be applied to numerical simulate the wave-structure interaction with presence of current.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.21-28
• /
• 2022

All health problems that occur in the circulatory system are refer to cardiovascular illness, such as heart and vascular diseases. Deaths from cardiovascular disorders are recorded one third of in total deaths in 2019 worldwide, and the number of deaths continues to rise. Therefore, if it is possible to predict diseases that has high mortality rate with patient's data and AI system, they would enable them to be detected and be treated in advance. In this study, models are produced to predict heart disease, which is one of the cardiovascular diseases, and compare the performance of models with Accuracy, Precision, and Recall, with description of the way of improving the performance of the Decision Tree(Decision Tree, KNN (K-Nearest Neighbor), SVM (Support Vector Machine), and DNN (Deep Neural Network) are used in this study.). Experiments were conducted using scikit-learn, Keras, and TensorFlow libraries using Python as Jupyter Notebook in macOS Big Sur. As a result of comparing the performance of the models, the Decision Tree demonstrates the highest performance, thus, it is recommended to use the Decision Tree in this study.

• Journal of Biomedical Engineering Research
• /
• v.22 no.4
• /
• pp.331-338
• /
• 2001

In this paper, we have proposed a new computer retina model reflecting the mechanism of transient amacrine cell on the basis of a conventional computer retina model to understand mechanism of visual information processing. The conventional computer retina model contained most of mechanism for other retina models and it was verified with the physiological data. However, we found that a conventional computer retina model doesn't have the mechanism of amacrine cell that was likely to respond to moving stimulus. In proposed model, therefore, a conventional computer model that considered from photoreceptors to bipolar cells and a new computer model that considered for transient amacrine cell and ganglion cell was combined. As we compared the physiological data with the results of computer simulation of transient amacrine cell about fixed stimulus and moving stimulus, we confirmed that the proposed new computer retina model was normally operated.

• Advances in aircraft and spacecraft science
• /
• v.2 no.4
• /
• pp.427-443
• /
• 2015

The present paper is the follow-on of a former work in which the influence of the gas-surface interaction models was evaluated on the aerodynamic coefficients of an aero-space-plane and on a section of its wing. The models by Maxwell and by Cercignani-Lampis-Lord were compared by means of Direct Simulation Monte Carlo (DSMC) codes. In that paper the diffusive, fully accommodated, semi-specular and specular accommodation coefficients were considered. The results pointed out that the influence of the interaction models, considering the above mentioned accommodation coefficients, is pretty strong while the Cercignani-Lampis-Lord and the Maxwell models are practically equivalent. In the present paper, the comparison of the same models is carried out considering the dependence of the accommodation coefficients on the angle of incidence (or partial accommodation coefficients). More specifically, the normal and the tangential momentum partial accommodation coefficients, obtained experimentally by Knetchel and Pitts, have been implemented. Computer tests on a NACA-0012 airfoil have been carried out by the DSMC code DS2V-64 bits. The airfoil, of 2 m chord, has been tested both in clean and flapped configurations. The simulated conditions were those at an altitude of 100 km where the airfoil is in transitional regime. The results confirmed that the two interaction models are practically equivalent and verified that the use of the Knetchel and Pitts coefficients involves results very close to those computed considering a diffusive, fully accommodated interaction both in clean and flapped configurations.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.4
• /
• pp.107-113
• /
• 2020

A number of studies have been conducted on predicting software faults, but most of them have been supervised models using labeled data as training data. Very few studies have been conducted on unsupervised models using only unlabeled data or semi-supervised models using enough unlabeled data and few labeled data. In this paper, we produced new semi-supervised models using tree algorithms in the self-training technique. As a result of the model performance evaluation experiment, the newly created tree models performed better than the existing models, and CollectiveWoods, in particular, outperformed other models. In addition, it showed very stable performance even in the case with very few labeled data.