• 한국멀티미디어학회논문지
• /
• 제22권4호
• /
• pp.432-442
• /
• 2019

Most current human action recognition methods based on deep learning methods. It is required, however, a very high computational cost. In this paper, we propose an action change detection method to reduce repetitive human action recognition tasks. In reality, simple actions are often repeated and it is time consuming process to apply high cost action recognition methods on repeated actions. The proposed method decides whether action has changed. The action recognition is executed only when it has detected action change. The action change detection process is as follows. First, extract the number of non-zero pixel from motion history image and generate one-dimensional time-series data. Second, detecting action change by comparison of difference between current time trend and local extremum of time-series data and threshold. Experiments on the proposed method achieved 89% balanced accuracy on action change data and 61% reduced action recognition repetition.

• 유통과학연구
• /
• 제16권2호
• /
• pp.83-88
• /
• 2018

Purpose - For distribution corporate, the method of recognizing sales revenue may be different depending on the type of distribution transaction. Until the change in accounting standards for revenue recognition was made in 2002, the distribution corporate recognized the full amount of sales of goods regardless of the type of transaction. However, in accordance with accounting standards for revenue recognition, which began to be applied in 2003, distribution corporate differ in sales revenue recognition by transaction type. The Purpose of this study is to analyze the impact of sales revenue on the corporate value after the change of the revenue recognition accounting standards. Research design, data, and methodology - We selected a comprehensive wholesale and retail corporate listed on Korea Exchange. The research model extends the Ohlson(1995) model and regresses whether sales revenue affecting the corporate value is discriminatory value relevance between the corporate affected by changes in accounting standards for revenue recognition and those not. Results - The results of the analysis are as follows. First, The average value of stock price, net asset per share, and earnings per share are all higher than those before the change of accounting standards for revenue recognition. However, the average value of sales per share is lower than that before the change of accounting standards for revenue recognition. Second, the relationship between corporate value and net asset per share, earnings per share and sales per share, the coefficient of net asset per share, earnings per share and sales per share are all statistically significant positive value. Therefore, in explaining corporate value, besides net asset per share and earnings per share, sales per share provides additional information. And the coefficient of interaction variable between accounting standard change and sales per share is a statistically significant positive value. This result indicating that after the change of the revenue recognition accounting standards the usefulness of sales revenue has increased. Conclusions - The change in accounting standards for revenue recognition led to a decrease in distribution corporate sales revenue but the higher the relevance of the corporate value of the sales revenue information. These results shows that the change of accounting standards that reflects the transaction type of retailers was a revision to increase the value relevance of sales revenue in valuation of corporate value.

• 지역연구
• /
• 제33권4호
• /
• pp.19-28
• /
• 2017

본 연구의 목적은 기후변화 적응에 대한 공무원 도민들 간의 인식을 비교분석하는 것이다. 기후변화에 대한 두 집단 간의 인식차이를 확인하기 위해 집단별로 설문조사를 실시하였다. 설문조사를 통해 두 집단의 적응 정책의 우선순위 및 분야별 기후변화 피해에 대한 체감도를 조사하였다. 결과적으로, 두 집단 간에는 기후변화 적응 정책에 대한 인식차이가 있음을 확인하였다. 기후변화 적응정책은 정책 수립자와 수용자의 경계가 모호해질 때 정책적 효용성이 크므로, 본 연구는 인식차이를 통해 확인할 수 있는 집단의 특징을 분석하여 두 집단 간 인식격차를 줄일 수 있는 방향을 제시하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2014년도 춘계학술발표대회
• /
• pp.781-784
• /
• 2014

Face recognition under controlled settings, such as limited viewpoint and illumination change, can achieve good performance nowadays. However, real world application for face recognition is still challenging. In this paper, we use Affine SIFT to detect affine invariant local descriptors for face recognition under large viewpoint change. Affine SIFT is an extension of SIFT algorithm. SIFT algorithm is scale and rotation invariant, which is powerful for small viewpoint changes in face recognition, but it fails when large viewpoint change exists. In our scheme, Affine SIFT is used for both gallery face and probe face, which generates a series of different viewpoints using affine transformation. Therefore, Affine SIFT allows viewpoint difference between gallery face and probe face. Experiment results show our framework achieves better recognition accuracy than SIFT algorithm on FERET database.

• Journal of Information Processing Systems
• /
• 제11권4호
• /
• pp.643-654
• /
• 2015

Face recognition under controlled settings, such as limited viewpoint and illumination change, can achieve good performance nowadays. However, real world application for face recognition is still challenging. In this paper, we propose using the combination of Affine Scale Invariant Feature Transform (SIFT) and Probabilistic Similarity for face recognition under a large viewpoint change. Affine SIFT is an extension of SIFT algorithm to detect affine invariant local descriptors. Affine SIFT generates a series of different viewpoints using affine transformation. In this way, it allows for a viewpoint difference between the gallery face and probe face. However, the human face is not planar as it contains significant 3D depth. Affine SIFT does not work well for significant change in pose. To complement this, we combined it with probabilistic similarity, which gets the log likelihood between the probe and gallery face based on sum of squared difference (SSD) distribution in an offline learning process. Our experiment results show that our framework achieves impressive better recognition accuracy than other algorithms compared on the FERET database.

• 한국정보시스템학회지:정보시스템연구
• /
• 제19권2호
• /
• pp.37-71
• /
• 2010

This article identifies factors affecting successful ERP systems by focusing on the stages after stabilizing ERP systems and overcoming temporary performance dip by introduction of ERP systems, and suggests change management tactics to control those identified factors. We can not expect that every users are familiar with the usage of an ERP system even after they are informed about the expected advantage of the newly implemented ERP system and trained intensively for changed business process and system usage while implementing a new ERP system. Moreover, even after more than six months usage of the system, the users may still have some trouble due to the reason why they have insufficient information about the expected advantage of the system (recognition gap) and insufficient knowledge about the changed usage of the system (knowledge gap). Hence, this article diagnoses by conducting a case study that those recognition and knowledge gap would have a severe bad influence upon the users' trust and satisfaction on ERP systems. This article suggests an appropriate change management tactics to overcome those recognition and knowledge gap by considering the relationship with the efforts for change management before, during, and after the introduction of ERP systems and performing an in-depth analysis on the users' dissatisfaction and request for update during the stages after the stabilization of the ERP systems. This article also shows a corroborative evidence that these efforts of change management consequently contributes to the solution of users' distrust and dissatisfaction. In sum, this article identifies the factors influencing badly on the magnitude and seriousness of knowledge and recognition gap, and suggests a conceptual research model which says that the satisfaction of ERP users could be uplifted by the solution of their knowledge and recognition gap if we keep making efforts on appropriate change management considering those identified factors during the stages after the stabilization of an ERP system.

• 대한전자공학회논문지
• /
• 제25권12호
• /
• pp.1503-1512
• /
• 1988

As the basic analysis to solve the within-and cross-speaker variability in phoneme based speech recognition, changes in pitch and formant frequencies of 8 Korean vowels with age and sex of speaker has been investigated by analyzing a large number fo samples. Conclusions obtained are as follows: 1) Changes in pitch frequency with age and sex of speaker for children are hard to distinguish and the difference of before and after the voice change is analyzed approximately 0.2 oct. for female an 0.9 oct. for male. 2) While most of the formants of vowel considerably change with the age of speaker, the change becomes smaller as the age becomes older. 3) While there is an indirect correlation between pitch and formant with change in age, it is hard to see a direct correlation. 4) When the objects of the recognition experiment by pitch and formants are various speakers in each age and sex, pitch also works as an efficient recognition parameter.

• International journal of advanced smart convergence
• /
• 제11권3호
• /
• pp.64-71
• /
• 2022

Various types of attendance management systems are being introduced in a remote working environment and research on using face recognition is in progress. To ensure accurate worker's attendance, a face recognition-based attendance management system must analyze every frame of video, but face recognition is a heavy task, the number of the task should be minimized without affecting accuracy. In this paper, we proposed a search model using time interval variation to minimize the number of face recognition task of recorded videos for attendance management system. The proposed model performs face recognition by changing the interval of the frame identification time when there is no change in the attendance status for a certain period. When a change in the face recognition status occurs, it moves in the reverse direction and performs frame checks to more accurate attendance time checking. The implementation of proposed model performed at least 4.5 times faster than all frame identification and showed at least 97% accuracy.

• Human Ecology Research
• /
• 제55권3호
• /
• pp.263-274
• /
• 2017

The purposes of this study were to verify the longitudinal mediating effects of work-family balance on the relationship of role recognition in the family, marital intimacy and job satisfaction of married women, and to introduce longitudinal mediating effects by using latent growth curve modeling and autoregressive cross-lagged modeling. The subjects were married women from the third year data of the Korean Longitudinal Survey of Women and Family. Structural equational models were conducted with Amos ver. 21.0. The major findings are as follows. First, the result of the longitudinal mediating effects of latent growth modeling is the rate of change of work-family balance mediated between the rate of change of role recognition in the family and the rate of change of job satisfaction, and the rate of change of work-family balance mediated between the rate of change of marital intimacy and the rate of change of job satisfaction. Second, when using the autoregressive cross-lagged modeling, the more role recognition and marital intimacy of third year were the more work-family balance of fourth year, job satisfaction of fifth year. In both models, work-family balance mediated between role recognition in the family, marital intimacy and job satisfaction. Therefore, through this study, mediating effects of work-family balance can be found that there was a longitudinal effects.

• 전자통신동향분석
• /
• 제33권3호
• /
• pp.89-99
• /
• 2018

Human activity recognition (HAR) is a technology that aims to offer an automatic recognition of what a person is doing with respect to their body motion and gestures. HAR is essential in many applications such as human-computer interaction, health care, rehabilitation engineering, video surveillance, and artificial intelligence. Smartphones are becoming the most popular platform for activity recognition owing to their convenience, portability, and ease of use. The noticeable change in smartphone-based activity recognition is the adoption of a deep learning algorithm leading to successful learning outcomes. In this article, we analyze the technology trend of activity recognition using smartphone sensors, challenging issues for future development, and a strategy change in terms of the generation of a activity recognition dataset.