http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Fire Image Classification Based on Convolutional Neural Network for Smart Fire Detection
Joohyung Roh(Joohyung Roh),Yukyung Kim(Yukyung Kim),Minsuk Kong(Minsuk Kong) 한국화재소방학회 2022 International Journal of Fire Science and Engineer Vol.36 No.3
This study investigated the effect of the class number on the prediction performance of the convolutional neural network (CNN) classification model that is applied in fire detectors to reduce nuisance fire alarms by appropriately recognizing fire images including those of flames and smoke. A CNN model trained by transfer learning using five image datasets of flame, smoke, normal, haze, and light was realized and trained by altering the class number to generate the classification model. A total of three classification models were generated as follows: classification model 1 was trained using normal and fire images including flames and smoke; classification model 2 was trained using flame, smoke, and normal images; and classification model 3 was trained using flames, smoke, normal, and haze, and light images. A test image dataset independent of training was used to assess the prediction performance of the three classification models. The results indicate that the prediction accuracy for classification models 1, 2, and 3 were approximately 93.0%, 94.2%, and 97.3%, respectively. The performance of the predicted classification improved as the class number increased, because the model could learn with greater precision the features of the normal images that are similar to those of the fire images.
Kim, Soo Hyun,Shin, Mi Soon,Lee, Han Sul,Lee, Eun Sook,Ro, Jung Sil,Kang, Han Sung,Kim, Seok Won,Lee, Won Hee,Kim, Hee Soon,Kim, Chun Ja,Kim, Joohyung,Yun, Young Ho Oncology Nursing Society 2011 Oncology nursing forum Vol.38 No.2
<P>Purpose/Objectives: To investigate the feasibility and preliminary effects of a simultaneous stage-matched exercise and diet (SSED) intervention in breast cancer survivors.Design: Randomized, controlled trial.Setting: Oncology outpatient treatment clinics at the National Cancer Center in South Korea.Sample: 45 women with breast cancer who completed their cancer therapy.Methods: Participants were assigned to the SSED intervention group (n = 23) or a control group (n = 22). Participants in the SSED group received a 12-week individualized intervention promoting prescribed exercise and a balanced diet through stage-matched telephone counseling and a workbook.Main Research Variables: Program feasibility, behavioral outcomes (stage of motivational readiness for exercise and diet, physical activity, and diet quality), and quality-of-life (QOL) outcomes (functioning and global QOL, fatigue, anxiety, and depression).Findings: Participant evaluations of the SSED intervention indicated that it was feasible and acceptable. All women felt that the overall intervention contents were appropriate, and 95% believed that the intervention helped to promote healthy behaviors. Objective data also supported the SSED intervention's feasibility (i.e., 91% completed the trial and 100% of intervention calls were received). When compared to control, the SSED intervention group showed significantly greater improvement in motivational readiness for exercise and diet, emotional functioning, fatigue, and depression.Conclusions: Preliminary results suggest that the SSED intervention delivered via telephone counseling and workbook is feasible and beneficial for positive behavioral and QOL outcomes.Implications for Nursing: Nurse-led lifestyle interventions may improve QOL for cancer survivors.</P>
김주형(Joohyung Kim),성덕환(Dukhwan Sung),송한림(Hanlim Song),임채홍(Chaehong Lim),김정준(Jungjune Kim),석창성(Changsung Seok),김현수(Hyunsoo Kim) 한국자동차공학회 2002 한국자동차공학회 춘 추계 학술대회 논문집 Vol.2002 No.5_2
Shift force simulator for a manual transmission is developed to estimate the shift force that is transmitted to the drivers hand. In order to develop the simulator, dynamic models of the external linkage, internal linkage, synchronizer and drivetrain are obtained. The synchronizing motion is modelled as eleven steps depending on the relative displacement of the sleeve to the ring spring, outer ring chamfer, and gear chamfer. The contact mechanism between the chamfer to chamfer is modelled as a linear spring. Based on the dynamic model of each element, a shift force simulator is developed. The simulator calculates the sleeve displacement, cone torque, poppet ball torque, sleeve force, shift force and the speed of the input and output shaft. It is found that the shift force by the simulator shows a good correlation with the test results and it is expected that the shift force simulator developed in this study can be used as a useful design tool to evaluate the shift feeling in the initial design stage.
김주형(Joohyung Kim),송한림(Hanlim Song),성덕환(Dukhwan Sung),임채홍(Chaehong Lim),김정준(Jungjune Kim),김현수(Hyunsoo Kim) 한국자동차공학회 2002 한국자동차공학회 Symposium Vol.2002 No.11
In this paper, a shift feeling simulator for manual transmission is developed with driver model. The shift feeling simulator consists of dynamic models of the linkage system, single, double and triple cone synchronizer, drivetrain and driver model. In order to describe the synchronizing motion, contact and impact models are introduced for the sleeve, outer ring, cone and gear. Synchronizing motion is modeled as II steps depending on the relative displacement of the sleeve to the other components. In addition, a driver model is developed, which is able to realize the driver's shift motion to react the shift force acting on the shift lever. Shift simulations are carried out using the shift feeling simulator developed with MATLAB SIMULINK. From the shift feeling simulation, shift force, sleeve force, cone torque, index torque, input and output shaft speed can be calculated. It is found that simulation results are good agreement with the test results and it is expected that the shift feeling simulator developed in this study can be used to design manual transmission in concept design stage.