• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.659-666
• /
• 2021

With the continuous development of deep learning, human behavior recognition algorithms have achieved good results. However, in a multi-person recognition environment, the complex behavior environment poses a great challenge to the efficiency of recognition. To this end, this paper proposes a multi-person pose estimation model. First of all, the human detectors in the top-down framework mostly use the two-stage target detection model, which runs slow down. The single-stage YOLOv3 target detection model is used to effectively improve the running speed and the generalization of the model. Depth separable convolution, which further improves the speed of target detection and improves the model's ability to extract target proposed regions; Secondly, based on the feature pyramid network combined with context semantic information in the pose estimation model, the OHEM algorithm is used to solve difficult key point detection problems, and the accuracy of multi-person pose estimation is improved; Finally, the Euclidean distance is used to calculate the spatial distance between key points, to determine the similarity of postures in the frame, and to eliminate redundant postures.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1341-1368
• /
• 2024

The concept of privacy-preserving collaborative filtering (PPCF) has been gaining significant attention. Due to the fact that model-based recommendation methods with privacy are more efficient online, privacy-preserving memory-based scheme should be avoided in favor of model-based recommendation methods with privacy. Several studies in the current literature have examined ant colony clustering algorithms that are based on non-privacy collaborative filtering schemes. Nevertheless, the literature does not contain any studies that consider privacy in the context of ant colony clustering-based CF schema. This study employed the ant colony clustering model-based PPCF scheme. Attacks like shilling or profile injection could potentially be successful against privacy-preserving model-based collaborative filtering techniques. Afterwards, the scheme's robustness was assessed by conducting a shilling attack using six different attack models. We utilize masked data-based profile injection attacks against a privacy-preserving ant colony clustering-based prediction algorithm. Subsequently, we conduct extensive experiments utilizing authentic data to assess its robustness against profile injection attacks. In addition, we evaluate the resilience of the ant colony clustering model-based PPCF against shilling attacks by comparing it to established PPCF memory and model-based prediction techniques. The empirical findings indicate that push attack models exerted a substantial influence on the predictions, whereas nuke attack models demonstrated limited efficacy.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.10a
• /
• pp.251-259
• /
• 1999

In the literature, the general framework of competitive forces has been used extensively to analyze industries in the traditional economy. More specifically, the model has been used to develop strategies for companies in various sectors. The general model can also be used to analyze the use of information technology to enhance competitive advantage. This paper extends the conceptual model to the Internet environment. For concreteness, the concepts are examined in the context of the health care industry. In addition, a comparative analysis is performed to examine the similarities and differences in providing merchandise or services in cyberspace.

• Journal of Engineering Education Research
• /
• v.16 no.3
• /
• pp.79-86
• /
• 2013

The purpose of this study was to analyze the factors related to the satisfaction of the introductory engineering education program for the employees, who majored liberal arts or commerce, among the educational programs for industrial workers which are performed as an effort to spread the performance of the Innovation Center for Engineering Education, and reinforce the competitiveness through effective program operation. This study was performed on the basis of CIPP evaluation model (context, input, process, product). A factorial analysis and a regression analysis were conducted based on a survey made on 87 persons who completed the introductory engineering education program among the employees of D group who majored liberal arts or commerce. It is expected that this study will contribute toward suggesting the implications for designing and operating the educational programs for industrial workers in order to find out the important factors of satisfaction and to conduct the education operation with professionalism.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.5
• /
• pp.1213-1235
• /
• 2013

In this paper, we investigated the factors affecting the intention to use smartphone banking with a research model based on the Technology Acceptance Model (TAM) extended to include security risk, trust, and self-efficacy. With analysis after controlling factors such as age, gender, and previous experience of smartphone banking that may have effects, we conclude that perceived usefulness, perceived ease of use, security risk, and trust have direct effect on the intention to use smartphone banking, and self-efficacy has indirect effect on the intention to use through mediation of perceived ease of use. We performed a study to check the validity of TAM in the context of smartphone banking, and confirmed that perceived ease of use has both direct and indirect effect on the intention to use.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.11
• /
• pp.65-74
• /
• 2002

This paper examines the usefulness of a Brake Steer System (BSS), which uses differential brake forces for steering intervention in the context of Intelligent Transportation Systems (ITS). In order to help the car to turn, a yaw moment can be achieved by altering the left/right and front/rear brake distribution. This resulting yaw moment on the vehicle affects lateral position thereby providing a limited steering function. The steering function achieved through BSS can then be used to control lateral position in an unintended road departure system. A 8-DOF nonlinear vehicle model including STI tire model will be validated using the equations of motion of the vehicle. Then a controller will be developed. This controller, which will be a PID controller tuned by Ziegler-Nichols, will be designed to explore BSS feasibility by modifying the brake distribution through the control of the yaw rate of the vehicle.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2005.05a
• /
• pp.9-13
• /
• 2005

A comprehension-based computational model of pilot action planning called ADAPT is presented to model pilot performance in a flight simulation context. Individual pilots were asked to execute a series of flight maneuvers using a flight simulator, and their eye-scanning, control movements, and flight performance were recorded in a time-synched database. Computational models of each of the 25 individual pilots were constructed, and the individual models simulated execution of the same flight maneuvers performed by human pilots. The time-synched eye-scanning, control movements, and flight performance of individual pilots and their respective models were compared to test ADAPT's predictive validity.

• Korean Management Science Review
• /
• v.29 no.1
• /
• pp.57-71
• /
• 2012

In this paper, we deal with a sector investment strategy by implementing the black-litterman model that incorporates expert evaluation and sector rotation momentum. Expert evaluation analyzes the relative performance of the industry sector compared with the market, while sector rotation momentum reflects the price impact of significant sector anomaly. In addition, we consider the portfolio impact of sector cardinality and weight constraints within the context of mean-variance portfolio optimization. Finally, we demonstrate the empirical viability of the proposed sector investment strategy with KOSPI 200 data.

• 한국연소학회:학술대회논문집
• /
• 2004.06a
• /
• pp.75-82
• /
• 2004

The conditional moment closure(CMC) model has been implemented in context with the unstructured-grid finite-volume method which efficiently handle the physically and geometrically complex turbulent reacting flows. The validation cases include a turbulent nonpremixed $CO/H_2/N_2$ Jet flame and a turbulent nonpremixed $H_2/CO$ flame stabilized on an axisymmetric bluff-body burner. In terms of mean flame field, minor species and NO formation, numerical results has the overall agreement with expermental data. The detailed discussion has been made for the turbulence-chemistry interaction and NOx formation characteristics as well as the comparative performance for CMC and flamelet model.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.18 no.3
• /
• pp.129-149
• /
• 1993

The high level of activity in the development and maintenance of computer software makes the scheduling of software projects an importnat factor in reducing operating costs and increasing competitiveness. Software activity is labor intensive. Scheduling management of hours of software work is complicated by ther interdependencies between the segments of work, and the uncertainties of the work itself. This paper discusses issues of scheduling in software engineering management, and presents a modular decomposition model for software project scheduling, taking advantage of the facility for decomposition of a software project into relatively independent work segment modules. Modular decomposition makes it possible to treat scheduling as clustering and sequencing in the context of integer programming. A heuristic algorithm for the model is presented with some computational experiments.