• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.1989-2011
• /
• 2019

Vehicle detection based on aerial images is an interesting and challenging research topic. Most of the traditional vehicle detection methods are based on the sliding window search algorithm, but these methods are not sufficient for the extraction of object features, and accompanied with heavy computational costs. Recent studies have shown that convolutional neural network algorithm has made a significant progress in computer vision, especially Faster R-CNN. However, this algorithm mainly detects objects in natural scenes, it is not suitable for detecting small object in aerial view. In this paper, an accurate and effective vehicle detection algorithm based on Faster R-CNN is proposed. Our method fuse a hyperactive feature map network with Eltwise model and Concat model, which is more conducive to the extraction of small object features. Moreover, setting suitable anchor boxes based on the size of the object is used in our model, which also effectively improves the performance of the detection. We evaluate the detection performance of our method on the Munich dataset and our collected dataset, with improvements in accuracy and effectivity compared with other methods. Our model achieves 82.2% in recall rate and 90.2% accuracy rate on Munich dataset, which has increased by 2.5 and 1.3 percentage points respectively over the state-of-the-art methods.

• Journal of Information Technology Applications and Management
• /
• 제17권1호
• /
• pp.127-139
• /
• 2010

Customer behavior pattern discovery is the fundament for conducting customer oriented services and the services management. But, the composition, need, interest and experience of customers may be continuously changing, thereof lead to the difficulty in refining a stable description of their consistent behavior pattern. This paper presented a new method for the behavior pattern discovery from a changing collection of customers. It was originally inspired from the swarm intelligence of ant colony. By the adaptive clustering, some typical behavior patterns which reflect the characteristics of related customer clusters can extracted dynamically and adaptively.

• Journal of Information Processing Systems
• /
• 제15권1호
• /
• pp.1-6
• /
• 2019

Recently, big data and artificial intelligence (AI) based on communication systems have become one of the hottest issues in the technology sector, and methods of analyzing big data using AI approaches are now considered essential. This paper presents diverse paradigms to subjects which deal with diverse research areas, such as image segmentation, fingerprint matching, human tracking techniques, malware distribution networks, methods of intrusion detection, digital image watermarking, wireless sensor networks, probabilistic neural networks, query processing of encrypted data, the semantic web, decision-making, software engineering, and so on.

• 한국조리학회지
• /
• 제22권1호
• /
• pp.126-134
• /
• 2016

This study examines effect in customer satisfaction of the emotional intelligence of members at service providing department in the hotel; A case of five star hotels in Dajeon Research hypotheses were developed based on previous literature, and data were collected from 350 employees working at the hotel restaurant service business located in Daejeon, ROK, were investigated herein The collected data were then analysed using frequence reliability For this research analysis, a self-recording method was used where and examiner explains the survey and respondents writhen down their answers to survey questions Statistical processing in this study was done through data cidubg and data cleaning then with the SPSS(Statistical Package for Social Science)v. 18.0. This result the emotional intelligence of service-providing employees at food service department of hotel was found to have a positive effect on customer satisfaction via understanding of others and emotional control. And the understanding of oneself, understanding of others and emotional control in emotional intelligence had a positive effect on job satisfaction. Emotional control, and emotioal use were found to affect organizational commitment positively.

• 디지털융복합연구
• /
• 제13권10호
• /
• pp.579-586
• /
• 2015

어린 초등학교 2~6학년 학생들을 대상으로 과학적이며, 체계적인 훈련을 지원하기 위하여 전국 권역별 대학교를 중심으로 체육영재센터를 운영하고 있다. 이를 위하여 초등학생 2~6학년을 대상으로 기초체력 및 잠재력 검사를 통해 선발운영토록 한다. 하지만 현재 시행 중인 이러한 선발방법은 체육영재 학생들에 대한 질적 평가는 포함되어 있지 않으며, 특히 측정시점에서의 체력, 체격요인에 의하여 상위 순위에 의하여 체육영재를 선발하는 방식으로써 대상 학생들에 대한 잠재적 능력의 평가 및 내재적 평가는 포함되어 있지 않다. 이에 본 연구에서는 윤영길(2011)의 경기지능을 바탕으로 체육영재의 잠재력을 평가할 수 있는 관찰방법에 기초한 영재성 판별 도구를 개발하고자 하였다. 이를 위하여 2회에 걸친 전문가 협의를 통해 체육영재 판별을 위한 하위요인을 추출하였으며, 추출된 하위요인을 바탕으로 현장 지도자들의 관찰방법에 기초한 훈련지능, 학습능력, 실천지능의 요인별 16개의 평가문항을 개발, 제시하였다. 제시된 평가문항은 체육영재 학생들의 질적 평가에 도움이 될 것이며, 아울러 체육영재 선발을 위한 내재적 평가 방법으로의 활용도 기대해 본다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권8호
• /
• pp.2688-2703
• /
• 2022

Research on the advanced detection of harmful objects in airport cargo for passenger safety against terrorism has increased recently. However, because associated studies are primarily focused on the detection of relatively large objects, research on the detection of small objects is lacking, and the detection performance for small objects has remained considerably low. Here, we verified the limitations of existing research on object detection and developed a new model called the Small Hazardous Object detection enhanced and reconstructed Model based on the You Only Look Once version 5 (YOLOv5) algorithm to overcome these limitations. We also examined the performance of the proposed model through different experiments based on YOLOv5, a recently launched object detection model. The detection performance of our model was found to be enhanced by 0.3 in terms of the mean average precision (mAP) index and 1.1 in terms of mAP (.5:.95) with respect to the YOLOv5 model. The proposed model is especially useful for the detection of small objects of different types in overlapping environments where objects of different sizes are densely packed. The contributions of the study are reconstructed layers for the Small Hazardous Object detection enhanced and reconstructed Model based on YOLOv5 and the non-requirement of data preprocessing for immediate industrial application without any performance degradation.

• 공학교육연구
• /
• 제21권6호
• /
• pp.74-80
• /
• 2018

This paper proposes practical teaching methods for efficient progress of project-based learning in engineering design education. Engineering design courses consist of three categories; introductory, individual and capstone design courses. This study concentrates on the case of individual design courses. Individual design courses act as bridges between introductory and capstone design courses and deal with applicable projects based on theoretical frameworks. In this study, practical teaching methods are applied to Artificial Intelligence curriculum as an individual design course for Juniors in Computer Engineering Major. The results on application of practical teaching methods show relatively positive in all aspects.

• Journal of Digestive Cancer Research
• /
• 제12권1호
• /
• pp.31-37
• /
• 2024

Pancreatic cancer is a highly fatal malignancy with a 5-year survival rate of < 10%. Endoscopic ultrasound (EUS) is a useful noninvasive tool for differential diagnosis of pancreatic malignancy and treatment decision-making. However, the performance of EUS is suboptimal, and its accuracy for differentiating pancreatic malignancy has increased interest in the application of artificial intelligence (AI). Recent studies have reported that EUS-based AI models can facilitate early and more accurate diagnosis than other preexisting methods. This article provides a review of the literature on EUS-based AI studies of pancreatic malignancies.

• 농촌지도와개발
• /
• 제16권1호
• /
• pp.125-152
• /
• 2009

The objective of this study, which applies the multiple-disciplinary approach to the developmental characteristics of children, is to study and develop a class model that can be applied to actual kindergarten classes in rural area. For this purpose, this study proposes teaching and learning methodologies for children based on English children's tales to help make the English education of children more effective and efficient. Based on the findings, the following suggestions should be considered for improving the English-education class model for kindergartners for rural areas: First, various activities based on the multiple-intelligence approach are important methods of children-oriented education advanced by the Sixth Children's Curriculum, helping children grow their independence and creativity. Second, various activities developed by this study on the basis of the multiple-intelligence approach to promote children's reading, listening, speaking, and writing abilities helped children improve their linguistic capacities, improve creativity, and remain motivated, which was reinforced by the differences found between the test group and the control group.

• 한국IT서비스학회지
• /
• 제15권4호
• /
• pp.85-95
• /
• 2016

Recently, deep learning and machine learning have attracted considerable attention and many supporting frameworks appeared. In artificial intelligence field, a large body of research is underway to apply the relevant knowledge for complex problem-solving, necessitating the application of various learning algorithms and training methods to artificial intelligence systems. In addition, there is a dearth of performance evaluation of decision making agents. The decision making agent that can find optimal solutions by using reinforcement learning methods designed through this research can collect raw pixel data observed from dynamic environments and make decisions by itself based on the data. The decision making agent uses convolutional neural networks to classify situations it confronts, and the data observed from the environment undergoes preprocessing before being used. This research represents how the convolutional neural networks and the decision making agent are configured, analyzes learning performance through a value-based algorithm and a policy-based algorithm : a Deep Q-Networks and a Policy Gradient, sets forth their differences and demonstrates how the convolutional neural networks affect entire learning performance when using pixel data. This research is expected to contribute to the improvement of artificial intelligence systems which can efficiently find optimal solutions by using features extracted from raw pixel data.