• Journal of Information Science Theory and Practice
• /
• 제12권2호
• /
• 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.

• 한국디지털건축인테리어학회논문집
• /
• 제5권1호
• /
• 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
• /
• 제20권3호
• /
• 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.

• 전기전자학회논문지
• /
• 제11권2호
• /
• pp.89-94
• /
• 2007

본 논문은 연속 밀도 함수를 갖는 HMM별 한국어 연속 음성인식에 관한 연구이다. 여기서 우리는 밀도 함수가 2개에서 44개까지 갖는 연속 HMM모델에서 가장 효율적인 연속 음성인식을 위한 방법을 제시한다. 음성 모델은 36개로 구성한 기본음소를 사용한 CI-Model과 3,000개로 구성한 확장음소를 사용한 CD-Model을 사용하였고, 언어 모델은 N-gram을 이용하여 처리하였다. 이 방법을 사용하여 500개의 문장과 6,486개의 단어에 대하여 화자 독립으로 CI Model에서 최고 94.4%의 단어인식률과 64.6%의 문장인식률을 얻었고, CD Model에서는98.2%의 단어인식률과 73.6%의 문장인식률을 안정적으로 얻었다.

• 한국학교수학회논문집
• /
• 제2권1호
• /
• 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
• /
• 제8권4호
• /
• 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.

• 한국컴퓨터정보학회논문지
• /
• 제27권5호
• /
• pp.21-28
• /
• 2022

심혈관질환은 심장질환과 혈관질환 등 순환기계통에 생기는 모든 질병을 통칭한다. 심혈관질환은 2019년 사망의 1/3을 차지하는 전 세계 사망의 주요 원인이며, 사망자는 계속 증가하고 있다. 이와 같은 질병을 인공지능을 활용해 환자의 데이터로 미리 예측이 가능하다면 질병을 조기에 발견해 치료할 수 있을 것이다. 본 연구에서는 심혈관질환 중 하나인 심장질환을 예측하는 모델들을 생성하였으며 Accuracy, Precision, Recall의 측정값을 지표로 하여 모델들의 성능을 비교한다. 또한 Decision Tree의 성능을 향상시키는 방법에 대해 기술한다. 본 연구에서는 macOS Big Sur환경에서 Jupyter Notebook으로 Python을 사용해 scikit-learn, Keras, TensorFlow 라이브러리를 이용하여 실험을 진행하였다. 연구에 사용된 모델은 Decision Tree, KNN(K-Nearest Neighbor), SVM(Support Vector Machine), DNN(Deep Neural Network)으로 총 4가지 모델을 생성하였다. 모델들의 성능 비교 결과 Decision Tree 성능이 가장 높은 것으로 나타났다. 본 연구에서는 노드의 특성배치를 변경하고 트리의 최대 깊이를 3으로 지정한 Decision Tree를 사용하였을 때 가장 성능이 높은 것으로 나타났으므로 노드의 특성 배치 변경과 트리의 최대 깊이를 설정한 Decision Tree를 사용하는 것을 권장한다.

• 대한의용생체공학회:의공학회지
• /
• 제22권4호
• /
• 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
• /
• 제2권4호
• /
• 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.

• 한국인터넷방송통신학회논문지
• /
• 제20권4호
• /
• pp.107-113
• /
• 2020

매우 많은 소프트웨어 결함 예측에 관한 연구들이 수행되어왔지만 대부분은 라벨 데이터를 훈련 데이터로 사용하는 감독형 모델들이었다. 언라벨 데이터만을 사용하는 비감독형 모델이나 언라벨 데이터와 매우 적은 라벨 데이터 정보를 함께 사용하는 세미감독형 모델에 관한 연구는 극소수에 불과하다. 본 논문은 Self-training 기법에 트리 알고리즘들을 사용하여 새로운 세미감독형 모델들을 제작하였다. 세미감독형 기법인 Self-training 모델에 트리 기법들을 사용하는 새로운 세미감독형 모델들을 제작하였다. 모델 평가 실험 결과 새롭게 제작한 트리 모델들이 기존 모델들보다 더 나은 성능을 보였으며, 특히 CollectiveWoods는 타 모델들에 비해 압도적으로 우월한 성능을 보였다. 또한 매우 적은 라벨 데이터 보유 상황에서도 매우 안정적인 성능을 보였다.