• The Magazine of the IEIE
• /
• v.39 no.2
• /
• pp.45-54
• /
• 2012

Object detection is a fundamental task for many high-level computer vision applications such as image retrieval, scene understanding, activity recognition, visual surveillance and many others. Although object detection is one of the most popular problems in computer vision and various algorithms have been proposed thus far, it is also notoriously difficult, mainly due to lack of proper models for object representation, that handle large variations of object structure and appearance. In this article, we review a branch of object detection algorithms based on Support Vector Machines (SVMs), a well-known max-margin technique to minimize classification error. We introduce a few variations of SVMs-Structural SVMs and Latent SVMs-and discuss their applications to object detection and localization.

• Electronics and Telecommunications Trends
• /
• v.34 no.1
• /
• pp.98-110
• /
• 2019

Machine learning has been applied to medical imaging and has shown an excellent recognition rate. Recently, there has been much interest in preventive medicine. If data are accessible, machine learning packages can be used easily in digital healthcare fields. However, it is necessary to prepare the data in advance, and model evaluation and tuning are required to construct a reliable model. On average, these processes take more than 80% of the total effort required. In this study, we describe the basic concepts of machine learning, pre-processing and visualization of datasets, feature engineering for reliable models, model evaluation and tuning, and the latest trends in popular machine learning frameworks. Finally, we survey a explainable machine learning analysis tool and will discuss the future direction of machine learning.

• Electronics and Telecommunications Trends
• /
• v.33 no.6
• /
• pp.107-117
• /
• 2018

In recent years, with the development of autonomous driving technology, high-performance artificial intelligence computing hardware platforms have been developed that can process multi-sensor data, object recognition, and vehicle control for autonomous vehicles. Most of these hardware platforms have been developed overseas, such as NVIDIA's DRIVE PX, Audi's zFAS, Intel GO, Mobile Eye's EyeQ, and BAIDU's Apollo Pilot. In Korea, however, ETRI's artificial intelligence computing platform has been developed. In this paper, we discuss the specifications, structure, performance, and development status centering on hardware platforms that support autonomous driving rather than the overall contents of autonomous driving technology.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.76-88
• /
• 2019

With advances in olfactory sensor technologies, the number of reports on various intelligent applications using multiple sensors (sensor arrays) are continuously increasing for fields such as medicine, environment, security, etc. For intelligent and point-of-care applications, it is not only important for the sensor technology to perform chemical or physical measurements rapidly and accurately, but it is also important for artificial intelligence technology to recognize and quantify specific chemicals or diagnose diseases such as lung cancer and diabetes. In particular, great advances in pattern recognition technologies, including deep learning algorithms, as well as sensor array technologies, are expected to enhance the potential of various types of olfactory intelligence applications, including early cancer diagnosis, drug seeking, military operations, and air pollution monitoring.

• The Journal of the Korean dental association
• /
• v.53 no.10
• /
• pp.732-742
• /
• 2015

The objective of this study was to identify bisphosphonate-related osteonecrosis of the jaw (BRONJ) awareness and experience level of patients by medical doctors who prescribes bisphosphonate being used, analyze dental examination referral reality and to utilize its result as basic education data for early diagnosis of BRONJ and its prevention. The study was carried out through a self-administered questionnaire distributed among a sample 192 residents and specialists. They belonged to family medicine, internal medicine and orthopedics of 6 tertiary medical centers located in Seoul. The survey consisted of 22 questions; general characteristics, bisphosphonate therapy, awareness of BRONJ, implementation level of dental examination referral. Among 192 medical doctorss, 78.1% (n=150) showed awareness of BRONJ. Only 8.9% (n=17) had correct response in all 5 BRONJ knowledge questions. Dental examination referral by medical doctors was implemented in below 30% of the total patients. At the time of bisphosphonate administration, specialist of oncology most highly recognized necessity of dental examination referral and it was represented in the order of endocrinology, rheumatology, family medicine, orthopedics specialists. As recognition of medical doctors for BRONJ and implementation level of dental referral were represented to be low, it is considered that enhancement of BRONJ recognition for medical doctors and development of high accessible education program for increasing implementation rate of dental examination referral would be required.

• Journal of the Korean Professional Engineers Association
• /
• v.32 no.3
• /
• pp.92-105
• /
• 1999

With the advent of the information age and the knowledge-based society, human resource development has become a key factor in determining a nation's competitiveness. And technological qualification systems have a direct and significant influence on human resource development. In order to guarantee Korea's continued development as a competitive member of the international community, it is demanded that a Korean Technology Qualification System (KTQS) is to accept international qualification criteria. This study was conducted in order to analysis current movements about the international mutual recognition of Professional Engineer and present problems for introducing APEC Engineer System to KTQS, and also recommend reasonable plans which overcome those. Under the WTO/GATS, the liberalization of trade in professional services will steadily increase. APEC activities to facilitate the portability of qualifications is considered complementary to the WTO movement. If the government attempts to introduce the APEC criteria for university degree requirements, university curriculum standards, programs for continuing professional developments(CPD), and practical, on-site experience. In the standpoints with the recent developments of APEC Engineer agreement on profession qualification, it is important to guarantee that Korean qualifications have a common, international currency. Measures have to be taken to harmonize the qualifications standards for Professional Engineer with those set out by the WTO/GATS movement. Also this will require an increase in the quality of university curriculum and an establishment of CPD. This process will be further enhanced by the organization of APEC Engineer Monitoring committee, Consisting of government officials, professional engineers and university professors. At this committee we can discuss the best strategies to keep our nation's interests.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.89-97
• /
• 2019

The olfactory bio technology is largely based on its corresponding recognition technology and smell stimulus that acquires, analyzes, and processes volatile organic compounds present in chemical molecules, which are present in the breath or air evoked by an electronic nose artificially imitating the human biological nose. The olfactory bio technology is also based on a scent display technology that automatically diverges various digital flavors based on aesthetics, concentration, duration, and intensity information required to enhance the sensibility using a computer. Recently, attempts have been made to apply noninvasive screening of dementia by sensing, analyzing, encoding, and transmitting bio information obtained through an olfactory interface, both domestically and externally; further, the olfactory medical content technology has been applied to delay or reduce the onset of dementia. In this study, we will focus on early screening of dementia using olfactory biology information and dementia cognitive enhancer content that delays or reduces the onset of dementia.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.55-64
• /
• 2019

In this study, we introduce trends in neural-network-based deep learning research applied to dialogue systems. Recently, end-to-end trainable goal-oriented dialogue systems using long short-term memory, sequence-to-sequence models, among others, have been studied to overcome the difficulties of domain adaptation and error recognition and recovery in traditional pipeline goal-oriented dialogue systems. In addition, some research has been conducted on applying reinforcement learning to end-to-end trainable goal-oriented dialogue systems to learn dialogue strategies that do not appear in training corpora. Recent neural network models for end-to-end trainable chit-chat systems have been improved using dialogue context as well as personal and topic information to produce a more natural human conversation. Unlike previous studies that have applied different approaches to goal-oriented dialogue systems and chit-chat systems respectively, recent studies have attempted to apply end-to-end trainable approaches based on deep neural networks in common to them. Acquiring dialogue corpora for training is now necessary. Therefore, future research will focus on easily and cheaply acquiring dialogue corpora and training with small annotated dialogue corpora and/or large raw dialogues.

• Cross-Cultural Studies
• /
• v.27
• /
• pp.291-317
• /
• 2012

Until now, the 'Ie' system, the distinct Japanese Family system, was dominantly recognized as the vestige of former feudal system. But as the research for gender-especially the family history-gets active, various aspects showing that 'Ie' is the modern product developed through thoroughly intended plans of Meiji government after latter-day. According to Ueno Chizuko, 'Ie' system is not at all a traditional feudal system, but it rather is the family revised by modernization, in other word, it is the Japanese version of modern family. This words began with it being the study of goodwill, and recognizing that 'Ie' is the creation of modernization, and as well as the need to listen to the new woman's inner voice under the Japanese patriarchal system. The most appealing characteristic of modern Japanese patriarchal system is that the it needs only the family members who are dedicated to the 'Nation'. With this, women were expected to submit to the authority and their roles, which are, as a wife and mother who obeys by supporting, preserving, and maintaining the patriarchal system. But as the new women themselves expressed their independence, these roles are hard to be expected. It was no other than new women's magazine Seito which arose against the Japanese patriarchal system. In this statement, careful observation was done on the novel based on tiny internal conflicts or the aspects of anguish, that could not have been illustrated enough after judging the significant issues of early modern liberalism of women based on new women's editorials, discussions, that were illustrated most directly and compressively. Through this, it was pointed out that Seito magazine is not consisted logically, and that reason for that is the female authors' different desires were tangled and it reflects the complicated situation of that period whether they were intended or not. Overall, unlike the literatures (men-centered) of same era, the genre of literature or the novel did not put them on prerogative place, and confirmation could be made once again that the women's writing aspects are related closely with gender recognition more than anything.

• Electronics and Telecommunications Trends
• /
• v.35 no.5
• /
• pp.112-122
• /
• 2020

In 3D computer graphics, a depth map is an image that provides information related to the distance from the viewpoint to the subject's surface. Stereo sensors, depth cameras, and imaging systems using an active illumination system and a time-resolved detector can perform accurate depth measurements with their own light sources. The 3D image information obtained through the depth map is useful in 3D modeling, autonomous vehicle navigation, object recognition and remote gesture detection, resolution-enhanced medical images, aviation and defense technology, and robotics. In addition, the depth map information is important data used for extracting and restoring multi-view images, and extracting phase information required for digital hologram synthesis. This study is oriented toward a recent research trend in deep learning-based 3D data analysis methods and depth map information extraction technology using a convolutional neural network. Further, the study focuses on 3D image processing technology related to digital hologram and multi-view image extraction/reconstruction, which are becoming more popular as the computing power of hardware rapidly increases.