• Korean Journal of Forensic Psychology
• /
• v.11 no.1
• /
• pp.1-20
• /
• 2020

Witnesses will be exposed to a variety of misinformation after the witnessing of the event and state at the scene of the investigation after the delay period. This study was conducted to promote correct recall reporting without being affected by factors that against correct recall. Self-Administered Interview(SAI) is known to obtain eyewitness accounts quickly and accurately. Therefore, we performed a SAI to see if it reported more information than the control group that did not perform the SAI. Also, it also performed that correct information was maintained without being affected by misinformation and delay. Eighty-eight participants were asked to perform SAI or game after showing a video of mock crime. Misinformation was presented in the first or second session to see if it affected recall. An analysis of responses from the final test conducted in the second session by participants showed that groups that conducted SAI after a four-week delay reported more correct information than control groups, while there was no difference between incorrect- and confabulation information. In particular, the timing of presenting misinformation did not affect the amount of recall. This suggests that conducting the SAI immediately after witnessing the event protects correct information even after four weeks. Finally, the significance and limitations of this study, and subsequent studies were discussed.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1141-1147
• /
• 2020

The hornet species are so similar in shape that they are difficult for non-experts to classify, and because the size of the objects is small and move fast, it is more difficult to detect and classify the species in real time. In this paper, we developed a system that classifies hornets species in real time based on a deep learning algorithm using a boundary box. In order to minimize the background area included in the bounding box when labeling the training image, we propose a method of selecting only the head and body of the hornet. It also experimentally compares existing boundary box-based object recognition algorithms to find the best algorithms that can detect wasps in real time and classify their species. As a result of the experiment, when the mish function was applied as the activation function of the convolution layer and the hornet images were tested using the YOLOv4 model with the Spatial Attention Module (SAM) applied before the object detection block, the average precision was 97.89% and the average recall was 98.69%.

• Phonetics and Speech Sciences
• /
• v.11 no.4
• /
• pp.89-96
• /
• 2019

In this paper, we propose a deep learning architecture that can effectively detect speech segmentation in broadcast contents. We also propose a multi-scale time-dilated layer for learning the temporal changes of feature vectors. We implement several comparison models to verify the performance of proposed model and calculated the frame-by-frame F-score, precision, and recall. Both the proposed model and the comparison model are trained with the same training data, and we train the model using 32 hours of Korean broadcast data which is composed of various genres (drama, news, documentary, and so on). Our proposed model shows the best performance with F-score 91.7% in Korean broadcast data. The British and Spanish broadcast data also show the highest performance with F-score 87.9% and 92.6%. As a result, our proposed model can contribute to the improvement of performance of speech detection by learning the temporal changes of the feature vectors.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.13-20
• /
• 2023

In this paper, the actual data of VOC reduction facilities was analyzed through a model that detects and predicts data anomalies. Using the USAD model, which shows stable performance in the field of anomaly detection, anomalies in real-time data are detected and sensors that cause anomalies are searched. In addition, we propose a method of predicting and warning, when abnormalities that time will occur by predicting future outliers with an auto-regressive model. The experiment was conducted with the actual data of the VOC reduction facility, and the anomaly detection test results showed high detection rates with precision, recall, and F1-score of 98.54%, 89.08%, and 93.57%, respectively. As a result, averaging of the precision, recall, and F1-score for 8 sensors of detection rates were 99.64%, 99.37%, and 99.63%. In addition, the Hamming loss obtained to confirm the validity of the detection experiment for each sensor was 0.0058, showing stable performance. And the abnormal prediction test result showed stable performance with an average absolute error of 0.0902.

• Journal of Korea Multimedia Society
• /
• v.3 no.5
• /
• pp.454-460
• /
• 2000

To retrieve complex data such as images, the content-based retrieval method rather than keyword based method is required. In this paper, we implemented a content-based image retrieval system which retrieves object of user query effectively using invariant moments which have invariant properties about linear transformation like position transition, rotation and scaling. To extract the shape feature of objects in an image, we propose a labeling algorithm that extracts objects from an image and apply invariant moments to each object. Hashing method is also applied to reduce a retrieval time and index images effectively. The experimental results demonstrate the high retrieval efficiency i.e precision 85%, recall 23%. Consequently, our retrieval system shows better performance than the conventional system that cannot express the shale of objects exactly.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1114-1135
• /
• 2018

A multiple classification system based on a new boosting technique has been approached utilizing different biometric traits, that is, color face, iris and eye along with fingerprints of right and left hands, handwriting, palm-print, gait (silhouettes) and wrist-vein for person authentication. The images of different biometric traits were taken from different standard databases such as FEI, UTIRIS, CASIA, IAM and CIE. This system is comprised of three different super-classifiers to individually perform person identification. The individual classifiers corresponding to each super-classifier in their turn identify different biometric features and their conclusions are integrated together in their respective super-classifiers. The decisions from individual super-classifiers are integrated together through a mega-super-classifier to perform the final conclusion using programming based boosting. The mega-super-classifier system using different super-classifiers in a compact form is more reliable than single classifier or even single super-classifier system. The system has been evaluated with accuracy, precision, recall and F-score metrics through holdout method and confusion matrix for each of the single classifiers, super-classifiers and finally the mega-super-classifier. The different performance evaluations are appreciable. Also the learning and the recognition time is fairly reasonable. Thereby making the system is efficient and effective.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.870-876
• /
• 1993

This paper presents a binary clustering network (BCN) and a heuristic algorithm to detect pitch for recognition of keywords in continuous speech. In order to classify nonlinear patterns, BCN separates patterns into binary clusters hierarchically and links same patterns at root level by using the supervised learning and the unsupervised learning. BCN has many desirable properties such as flexibility of dynamic structure, high classification accuracy, short learning time, and short recall time. Pitch Detection algorithm is a heuristic model that can solve the difficulties such as scaling invariance, time warping, time-shift invariance, and redundance. This recognition algorithm has shown recognition rates as high as 95% for speaker-dependent as well as multispeaker-dependent tests.

• Nutrition Research and Practice
• /
• v.9 no.2
• /
• pp.207-212
• /
• 2015

BACKGROUND/OBJECTIVES: The Recaller app was developed to help individuals record their food intakes. This pilot study evaluated the usability of this new food picture application (app), which operates on a smartphone with an embedded camera and Internet capability. SUBJECTS/METHODS: Adults aged 19 to 28 years (23 males and 22 females) were assigned to use the Recaller app on six designated, nonconsecutive days in order to capture an image of each meal and snack before and after eating. The images were automatically time-stamped and uploaded by the app to the Recaller website. A trained nutritionist administered a 24-hour dietary recall interview 1 day after food images were taken. Participants' opinions of the Recaller app and its usability were determined by a follow-up survey. As an evaluation indicator of usability, the number of images taken was analyzed and multivariate Poisson regression used to model the factors determining the number of images sent. RESULTS: A total of 3,315 food images were uploaded throughout the study period. The median number of images taken per day was nine for males and 13 for females. The survey showed that the Recaller app was easy to use, and 50% of the participants would consider using the app daily. Predictors of a higher number of images were as follows: greater interval (hours) between the first and last food images sent, weekend, and female. CONCLUSIONS: The results of this pilot study provide valuable information for understanding the usability of the Recaller smartphone food picture app as well as other similarly designed apps. This study provides a model for assisting nutrition educators in their collection of food intake information by using tools available on smartphones. This innovative approach has the potential to improve recall of foods eaten and monitoring of dietary intake in nutritional studies.

• 한국노년학
• /
• v.38 no.1
• /
• pp.83-102
• /
• 2018

According to socioemotional selectivity theory, if people perceive their time left in life as expanded, they have a future-oriented goal of life, but if perceive as limited the goal of life is changed into the pursuit of present emotional satisfaction. Thus, if we perceive our time left as getting limited as we get older, we pay more attention to the positive stimuli than the negative ones and remember more the positive stimuli in order to maintain the current emotional state as positive. This is known as the positivity effect. This study examined whether the positivity effect is caused by a limited future time perspective. The participants were presented with scenarios for hypothetical situations in which the future time was expanded or limited, and were encouraged to immerse in the virtual situation by talking about what they would like to do and whom they wanted to spend time with. Then the participants were presented with 48 positive, negative, and neutral emotional pictures and were asked to recall after 10 minutes delay. 75 university students and 65 elderly participated in the study. In the control condition where the future time perspective was not manipulated, the elderly showed the positivity effect but the youth showed the bias toward negative pictures. The elderly in the expanded time condition recalled positive pictures less and negative pictures more than the elderly in the control condition. On the other hand, the youth in the limited time condition recalled less the negative pictures than the youth in the control condition. These results demonstrated that the elderly did not show the positive bias when the future time perspective was expanded, and that the youth showed the positive bias when the future time perspective was limited. These results show that the positivity effect is related with the limited future time perspective.

• Journal of Families and Better Life
• /
• v.8 no.2
• /
• pp.163-180
• /
• 1990

The objective of this study was to investigate the time used for daily activities by rural housewives. This study was carried out two aspects-the amount and the distribution of time. However, the characteristics of agriculture and the farming season influenced on rural housewives activities. There fore, in this study, survey areas divided into two groups-the traditional and the commercial agricultural area. And I conducted surveys in two times-the busy farming season and the leisure season for farmers. Data for 286 housewives(76 in traditional area on the leisure season, and 68 in commercial 142 in traditional area on the busy farming season)were collected by interviews, in which wives were asked to recall the used of time on the previous day, and a time record chart broken into fifteen minute intervals. The statistics for data analysis were frequency, percentile, T-test, and F-test by SPSS PC programs. The findings are as follows; 1)The average total time of rural housewives on labour was 8 hours 53 minutes, on socio-cultural activities 4 hours 18 minutes, and on physiological activities 11 hours 2 minutes. 2) The amount of time on agricultural labour was 6 hours 47 minutes in busy farming season, and 2 hour 45 minutes in leisure season. 3) The average time on household labour was 3 hours 51 minutes. 4) The amount of time on socioculture activities was 2 hours 19 minutes in busy farming, and 6 hours 16 minutes in leisure season. 5) The average time on physiological activities was 11 hours 2 minutes.