• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.185-192
• /
• 2004

This paper presents face recognition using vector quantization in the eigenspace of the faces. The existing eigenface method is not enough for representing the variations of faces. For making up for its defects, the proposed method use a clustering of feature vectors by vector quantization in eigenspace of the faces. In the trainning stage, the face images are transformed the points in the eigenspace by eigeface(eigenvetor) and we represent a set of points for each people as the centroids of vector quantizer. In the recognition stage, the vector quantizer finds the centroid having the minimum quantization error between feature vector of input image and centriods of database. The experiments are performed by 600 faces in Faces94 database. The existing eigenface method has minimum 64 miss-recognition and the proposed method has minimum 20 miss-recognition when we use 4 codevectors. In conclusion, the proposed method is a effective method that improves recognition rate through overcoming the variation of faces.

• Korean Journal of Environmental Agriculture
• /
• v.28 no.1
• /
• pp.53-58
• /
• 2009

The propose of this study was to find out optimum conditions for no-tillage rice-winter cover crops cropping system. A field research was conducted to evaluate productivity and quality of rice cultivars (Dongjinbyeo and Junambybyeo) in rice-winter cover cropping systems at Doo-ryangmyeon., Sacheon, Gyeongsangnam-do, Korea from January 2005 to October 2006. The experimental soil was Juggog series (fine silty, mesic family of Fluvaquentic Eutrndepts). The rice cultivars were experimented under some different high residue farming systems, i.e. no-tillage no treatment (NTNT), no-tillage amended with rice straw (NTRS), no-tillage amended with rye (NTR), no-tillage amended with Chinese milkvetch (NTCMV), tillage no treatment (TNT), and conventional cropping system (Control). The miss-planted rate was 8.8% in 2005 and range of 10.8% to 13.3% in 2006 at NTR, and the other treatments were carried out at miss-planted rate ranging from 1.2% to 5.0%. Tiller numbers of Junambyeo, and Dongjinbyeo in both of years were the highest in Control, and decreased nearly in NTCMV, NTR, NTRS, NTNT, and TNT in that order. The lowest grain yield was observed in TNT both cultivars due to the lower tiller numbers per area, and spikelet numbers per panicle. Also, no-tillage treatments were lower grain yield than control. On the other hand, 1,000-grain weight was lowest in control due to higher tiller numbers per area, and spikelet numbers per panicle. Ripened grain ratio was a similar aspect in all treatments. The palatability score of milled rice was lowest in control while protein content of milled rice was highest in control. The NTCMV was considered an effective sustainable farming practice for rice yield and quality.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.12
• /
• pp.277-286
• /
• 2019

The Unmanned Aerial Vehicle (UAV) is one of the most precious inventions of Internet of things (IOT). UAV faces the necessity to charge battery or replace battery from the charging stations during or between services. We propose scheduling algorithms for drone power charging (SADPC). The basic idea of algorithm is considering both a deadline (for increasing deadline miss ratio) and a charging time (for decreasing waiting time) to decide priority on charging station among drones. Our simulation results show that our power charging algorithm for drones are efficient in terms of the deadline miss ratio as well as the waiting time in general in compare to other conventional algorithms (EDF or SJF). Also, we can choose proper algorithms for battery charge scheduling and charge ready battery allocation according to system parameters and user requirements based on our simulation.

• Korean Journal of Construction Engineering and Management
• /
• v.20 no.4
• /
• pp.69-76
• /
• 2019

This paper presents a method that identifies the unsafe behaviors at the level of near-misses using image analysis. The method establishes potential collision hazardous area in earthmoving operation. It is implemented using a game engine to reproduce the dangerous events that have been accepted as major difficulty in utilizing computer vision technology to support construction safety management. The method keeps realistically track of the ever-changing hazardous area by reflecting the volatile field conditions. The method opens a way to distinguish unsafe conditions and unsafe behaviors that have been overlooked in previous studies, and reflects the causal relationship which causes an accident. The case study demonstrate how to identify the unsafe behavior of a worker exposed to an unsafe area created by dump trucks at the level of near-misses and to determine the hazardous areas.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.5
• /
• pp.111-118
• /
• 2019

Recent graphic processing units (GPUs) provide high throughput by using powerful hardware resources. However, massive memory accesses cause GPU performance degradation due to cache inefficiency. Therefore, the performance of GPU can be improved by reducing thread parallelism when cache suffers memory contention. In this paper, we propose a dynamic warp scheduler which controls thread parallelism according to degree of cache contention. Usually, the greedy then oldest (GTO) policy for issuing warp shows lower parallelism than loose round robin (LRR) policy. Therefore, the proposed warp scheduler employs the LRR warp scheduling policy when Miss Status Holding Register(MSHR) utilization is low. On the other hand, the GTO policy is employed in order to reduce thread parallelism when MSHRs utilization is high. Our proposed technique shows better performance compared with LRR and GTO policy since it selects efficient scheduling policy dynamically. According to our experimental results, our proposed technique provides IPC improvement by 12.8% and 3.5% over LRR and GTO on average, respectively.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.10
• /
• pp.419-426
• /
• 2022

In this paper, we propose a method to improve the accuracy of 3D human pose estimation model in various move motions. Existing human pose estimation models have some problems of jitter, inversion, swap, miss that cause miss coordinates when estimating human poses. These problems cause low accuracy of pose estimation models to detect exact coordinates of human poses. We propose a method that consists of detection and correction methods to handle with these problems. Deep learning-based outlier detection method detects outlier of human pose coordinates in move motion effectively and rule-based correction method corrects the outlier according to a simple rule. We have shown that the proposed method is effective in various motions with the experiments using 2D golf swing motion data and have shown the possibility of expansion from 2D to 3D coordinates.

• Safety and Health at Work
• /
• v.15 no.2
• /
• pp.213-219
• /
• 2024

Background: The design, implementation, and evaluation are three important stages of occupational safety and health (OSH) interventions. Historically, there has been a tendency to prioritize implementation, often neglecting detailed design and rigorous outcome evaluation. Currently, much has changed, and contemporary approaches recognize the interdependence of these stages, considering them integral to the success of any intervention. This work presents a comprehensive procedure for implementing interventions, not only to ensure short-term effectiveness but also their long-term sustainability through continuous monitoring. The focus is on a national OSH project introducing a near-miss management system (NMS) in Italy. Methods: Initial meetings were convened among project partners, complemented by interviews with diverse stakeholders, to plan implementation steps and test the NMS. Tailored questionnaires were designed for diverse stakeholder groups - initial promoters, company managers and employers, and employees - facilitating targeted implementation, and three case studies were started in Italian regions to assess the structured implementation, involving intervention promoters and collaborating companies. Results: The primary outcome is the development of practical tools, specifically three questionnaires, which are considered valuable for establishing an effective human-centered implementation strategy, meticulously designed to facilitate ongoing monitoring of processes and continual enhancement of instruments intended for NMS integration within companies. Conclusions: This work lays the foundation for successful NMS implementation in Italy and, although the outlined procedure had specific objectives, it also provides valuable insights applicable in enhancing the effectiveness and sustainability of interventions across diverse contexts. It underscores the importance of comprehensive planning, stakeholder engagement, and continuous evaluation in achieving lasting OSH interventions.

• Proceedings of KOSOMES biannual meeting
• /
• 2017.11a
• /
• pp.119-119
• /
• 2017

• International Journal of Aeronautical and Space Sciences
• /
• v.10 no.1
• /
• pp.37-45
• /
• 2009

A method of conflict detection and resolution is described by using simple geometric approach. Two VAVs are dealt with and considered as point masses with constant velocity. This paper discusses en route aircraft which are assumed to be linked by real time data bases like ADS-B. With this data base, all DAVs share the information each other. Calculating PCA (Point of Closest Approach), we can evaluate the worst conflict condition between two VAVs. This paper proposes one resolution maneuvering logic, which can be called 'Vector Sharing Resolution'. In case of conflict, using miss distance vector in PCA, we can decide the directions for two VAVs to share the conflict region. With these directions, VAVs are going to maneuver cooperatively. First of all, this paper describes some '2-D' conflict scenarios and then extends to '3-D' conflict scenarios.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.119-122
• /
• 2010

Cognitive Radioo(CR)기술은 주파수 자원을 효율적으로 이용하기 위해 Joseph Mitora가 개념을 적립한 것으로 유비쿼터스 시대의 부족한 주파수 자원을 극복 할 수 있는 기술로 각광받고 있다. 이와 같은 무선인지 기술(CR)을 도입하기 위한 핵심적인 요소는 부사용자(Secondary User)가 주사용자(Primary User)의 통신을 방해하지 않도록 주파수 점유 여부를 정확하게 판단하는 Spectrum Sensing기술이다. 이 스펙트럼 센싱 기술에 두 가지 종류의 에러가 발생하는데 하나는 미검출 오류(miss error)이고 또 하나는 오경보 오류(false alarm error)이다. 따라서 본 논문은 이 두 가지를 합친 검출 오류(detection error)를 최소화 하기위해 협력 스펙트럼 센싱(Cooperative spectrum sensing)에서 몇 명 이상의 부사용자가 주사용자가 사용중이라 검출하였을 때 최종 결정이 주사용자가 사용한다고 결론 짓는 것이 최적인지를 수학적으로 분석하고 그 최적의 K값을 사용하여 전체 시스템의 성능을 향상 시키는 방법을 제시 한다.