• International Journal of Computer Science & Network Security
• /
• 제23권4호
• /
• pp.48-54
• /
• 2023

Nowadays, a blind man finds it very difficult to cross the roads. They should be very vigilant with every step they take. To resolve this problem, Convolutional Neural Networks(CNN) is a best method to analyse the data and automate the model without intervention of human being. In this work, a traffic signal recognition system is designed using CNN for the visually impaired. To provide a safe walking environment, a voice message is given according to light state and timer state at that instance. The developed model consists of two phases, in the first phase the CNN model is trained to classify different images captured from traffic signals. Common Objects in Context (COCO) labelled dataset is used, which includes images of different classes like traffic lights, bicycles, cars etc. The traffic light object will be detected using this labelled dataset with help of object detection model. The CNN model detects the color of the traffic light and timer displayed on the traffic image. In the second phase, from the detected color of the light and timer value a text message is generated and sent to the text-to-speech conversion model to make voice guidance for the blind person. The developed traffic light recognition model recognizes traffic light color and countdown timer displayed on the signal for safe signal crossing. The countdown timer displayed on the signal was not considered in existing models which is very useful. The proposed model has given accurate results in different scenarios when compared to other models.

• 대한임베디드공학회논문지
• /
• 제18권5호
• /
• pp.233-240
• /
• 2023

Nutrition information about food is written on the label paper, which is very inconvenient for visually impaired people to recognize. In order to solve the inconvenience of visually impaired people with nutritional information recognition, this paper proposes a product nutrition information guide system for visually impaired people. In the proposed system, user's image data input through UI, and object recognition is carried out through YOLO v5. The proposed system is a system that provides voice guidance on the names and nutrition information of recognized products. This paper constructs a new dataset that augments the 319 classes of canned/late-night snack product image data using rotate matrix techniques, pepper noise, and salt noise techniques. The proposed system compared and analyzed the performance of YOLO v5n, YOLO v5m, and YOLO v5l models through hyperparameter tuning and learned the dataset built with YOLO v5n models. This paper compares and analyzes the performance of the proposed system with that of previous studies.

• 한국유체기계학회 논문집
• /
• 제11권5호
• /
• pp.30-36
• /
• 2008

Axial fan without static blades requires the duct as a guidance for unskewed inflows. This work examined the geometric effects of a duct guided the in and out flows through an impeller. The present methodologies are computational predictions with parallel work by experimental validation. Several different positions of a rotor in a duct are proposed for plausible models of a rotor inside a duct. The optimum axial position of an impeller in a duct is found at the #4 model where the impeller lies on the inlet edge of a circular duct. The model shows a wider inlet area. The result of computational prediction is in good agreement with experiment measurement.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2008년도 추계학술대회 및 정기총회
• /
• pp.364-368
• /
• 2008

Recently, necessity of VV & A is also embossed as practical use and importance of M & S are increased in National Defense. The purpose of VV&A is to assure development of correct and valid simulations and to provide simulation users with sufficient information to determine if the simulation can meet their needs. VV&A processes are performed to establish the credibility of the models and simulations. Guidance and Regulation of VV&A are insufficient actual conditions in Korea and example that apply to actuality M&S is state that is hardly. In this paper, VV&A assure its credibility of application VV&A process in Army on the basis of US Organization's application example and provide initial point of VV&A application of National Defense M&S that is developed subsequentness.

• Computers and Concrete
• /
• 제14권5호
• /
• pp.547-561
• /
• 2014

Artificial neural networks (ANN) has been proven to be able to predict the compressive strength and elastic modulus of recycled aggregate concrete (RAC) made with recycled aggregates (RAs) from different sources. However, ANN is itself like a black box and the output from the model cannot generate an exact mathematical model that can be used for detailed analysis. So in this study, sensitivity analysis is conducted to further examine the influence of each selected factor on the output value of the models. This is not only conducive to the determination and selection of the more important factors affecting the results, but also can provide guidance for researchers in adjusting mix proportions appropriately when designing RAC based on the variation of these factors.

• International Journal of Internet, Broadcasting and Communication
• /
• 제8권1호
• /
• pp.27-32
• /
• 2016

The global positioning system (GPS)-enabled mobile phones provide location-based applications such as car and pedestrian navigation services. The pedestrian navigation services provide safe and comfortable route and path guidance for pedestrians and handicapped or elderly people. One of the essential components for a navigation system is a spatial database used to perform navigation and routing functions. In this paper, we develop modeling and categorization of pedestrian path components for smart tour guide services using the mobile pedestrian navigation application. We create pedestrian networks using 2D base map and sky view map in urban area. We also construct pedestrian networks and attributes of node, link, and POI using on-site GPS data and photos for smart pedestrian tour guide in the major walking tourist spots in Jeju.

• Journal of the Optical Society of Korea
• /
• 제13권2호
• /
• pp.201-205
• /
• 2009

We investigated the optimum adhesive thickness for athermalizing an elastomeric lens mount in our space optics application. Theoretical results were compared with finite element solutions using two different models; discrete circular pads and discrete circular pads with columns filling the insertion holes reflecting the reality. A noticeable difference between their optimal thicknesses was observed, and physical interpretation revealed the uncertainty of prevailing athermal equations. A pilot sample was made to check our results and thermo-optical stress was assessed using an interferometer after isothermal load. This study presented insight into preliminary design guidance in elastomeric lens mounting.

• 대한임상독성학회지
• /
• 제3권1호
• /
• pp.11-16
• /
• 2005

Chemical mixtures of components, each of which are present at less than guidance concentrations, may be hazardous due to additivity, interactions, or both. Toxicological interactions may increase the health hazard above what would be expected from an assessment of each component singly, or all components additively. So chemical mixture are a particular issue in public health. There are several approach to assess whether there are additivity or interaction in assessing toxicological effects, such as, components-based approach, physiologically-based pharmacokinetic /pharmacodynamic(PBPK/PD) models, hazard index method, and weight-of evidence method. If we consider interaction or additivity effects in assessing the health effects of chemcial mixtures, we can get more accurate information about toxicological effects and dose-response relationship in chemical mixtures.

• Nutritional Sciences
• /
• 제9권3호
• /
• pp.201-211
• /
• 2006

The purpose of this study was to provide dietitians with the guidance in forecasting meal counts for a university/college foodservice facility. The forecasting methods to be analyzed were the following: naive model 1, 2, and 3; moving average, double moving average, simple exponential smoothing, double exponential smoothing, Holt's, and Winters' methods, and simple linear regression. The accuracy of the forecasting methods was measured using mean squared error and Theil's U-statistic. This study showed how to project meal counts using 10 forecasting methods for dietitians. The results of this study showed that WES was the most accurate forecasting method, followed by $na\ddot{i}ve$ 2 and naive 3 models. However, naive model 2 and 3 were recommended for using by dietitians in university/college dining facilities because of the accuracy and ease of use. In addition, the 2000 spring semester data were better than the 2000 fall semester data to forecast 2001spring semester data.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.624-627
• /
• 2002

Experimental study showed that the existing mathematical model doesn't fully describe the lateral motion of a moving web fur different operating conditions. So, a physically interpretable model of lateral motion of a moving web in a typical web guidance system, operated at Konkuk Univ., was developed using the system identification technique. A well-known Least Square Method based on ARX model was used for the system identification. Lateral displacement of the web was measured at the exit of each span by infrared sensors. The model obtained from identifying a linear time-invariant system for a typical operating condition yields an improved prediction capability of the lateral dynamics of the moving web compared to other mathematical models proposed in literature.