• Journal of Information Processing Systems
• /
• v.19 no.4
• /
• pp.439-449
• /
• 2023

This paper deals with a resource efficient artificial intelligence (AI) service architecture for multi-channel video streams. As an AI service, we consider the object detection model, which is the most representative for video applications. Since most object detection models are basically designed for a single channel video stream, the utilization of the additional resource for multi-channel video stream processing is inevitable. Therefore, we propose a resource efficient AI service framework, which can be associated with various AI service models. Our framework is designed based on the modular architecture, which consists of adaptive frame control (AFC) Manager, multiplexer (MUX), adaptive channel selector (ACS), and YOLO interface units. In order to run only a single YOLO process without regard to the number of channels, we propose a novel approach efficiently dealing with multi-channel input streams. Through the experiment, it is shown that the framework is capable of performing object detection service with minimum resource utilization even in the circumstance of multi-channel streams. In addition, each service can be guaranteed within a deadline.

• Journal of Digital Convergence
• /
• v.16 no.8
• /
• pp.151-159
• /
• 2018

This study focused on appreciative inquiry(AI) of salespeople who have to respond to various types of emotions according to the desires of individual customers at service contact points and the effect of emotional labor on adaptive selling behavior and customer satisfaction. Dyadic questionnaires were administerd to 115 automobile salespeople and 2 customers who received service from each salesperson, and the collected data was analyzed by using structural equation modeling. The results showed that AI had positive influences on deep acting and surface acting. Only deep acting was found to have positive relationship with adaptive selling behavior, but not to surface acting. Adaptive selling behavior had a positive effect on customer satisfaction. This study will contribute to identifying the need for AI access for salespersons and for activating adaptive selling behavior through emotional labor related to AI practice.

• Journal of Internet Computing and Services
• /
• v.11 no.1
• /
• pp.1-13
• /
• 2010

It is not easy to set RED(Random Early Detection) parameter according to environment in managing Network Device. Especially, it is more difficult to set parameter in the case of maintaining the constant service rate according to the change of environment. In this paper, we hypothesize the router that has Multi-core CPU in output queue and propose AI RED(Artificial Intelligence RED), which directly induces Genetic Algorithm of Artificial Intelligence in the output queue that is appropriate to the optimization of parameter according to RED environment, which is automatically adaptive to workload. As a result, AI RED Is simpler and finer than FuRED(Fuzzy-Logic-based RED), and RED parameter that AI RED searches through simulations is more adaptive to environment than standard RED parameter, providing the effective service. Consequently, the automation of management of RED parameter can provide a manager with the enhancement of efficiency in Network management.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.234-240
• /
• 2022

This paper proposes a customized AI exercise recommendation service for balancing the relative amount of exercise according to the working environment by each occupation. WISDM database is collected by using acceleration and gyro sensors, and is a dataset that classifies physical activities into 18 categories. Our system recommends a adaptive exercise using the analyzed activity type after classifying 18 physical activities into 3 physical activities types such as whole body, upper body and lower body. 1 Dimensional convolutional neural network is used for classifying a physical activity in this paper. Proposed model is composed of a convolution blocks in which 1D convolution layers with a various sized kernel are connected in parallel. Convolution blocks can extract a detailed local features of input pattern effectively that can be extracted from deep neural network models, as applying multi 1D convolution layers to input pattern. To evaluate performance of the proposed neural network model, as a result of comparing the previous recurrent neural network, our method showed a remarkable 98.4% accuracy.

• Journal of Information Technology Services
• /
• v.11 no.sup
• /
• pp.165-176
• /
• 2012

Context-Awareness system provides an appropriate service to user by recognizing situation from surrounding environment. There are many successful studies on this framework, but still has some limitations. In this paper, we are describing a context-awareness middleware that can enhance the limitation of the previous approaches. We first defined a new concept of context-awareness environment as a social intelligence. This concept implies that intelligent objects can make relationships, can aware of situation from surrounding environment, and can collaborate to accomplish a given task. The significance of the study is as follows. First, the system is capable of multi context-awareness since it is designed with a structure that supports multiple lines of reasoning. Second, the system is capable of context planning by adapting AI planning mechanism. Third, the system is capable of making the intelligent objects as a group for collaboration, and provides adaptive service to user. We have developed a prototype of the system and tested with a virtual scenario.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.35-36
• /
• 2022

본 논문은 딥러닝 사람 자세 추정 모델이 사람의 관절 키포인트를 예측하는데 관절의 2차원 면적에 의해 키포인트별 𝜎, 즉, 표준 편차를 가지는 가우시안 커널(Gaussian Kernel)을 예측하는 방법을 제안한다. 각 관절 키포인트에 대해 다른 𝜎를 가지는 정답 히트맵(Ground Truth Heatmap)과 제안한 Gaussian Mixture Block를 모델에 추가해서 관절의 크기를 맞는 히트맵을 예측한다.