머신러닝기반 색채조화 배색 모델 구현

송수림,이현수 한국실내디자인학회 2022 한국실내디자인학회논문집 Vol.31 No.1

To satisfy the diverse needs of consumers, emotional designs that focus on consumers have emerged. Consumers who consume emotionally have a high score on the happiness index and satisfaction. Among them, consumers pursue a style that suits their lifestyle in the residential space where they live. And in detail, consumers are highly satisfied by changing the color and material of objects placed in the space. Consumers prefer the natural and the modern styles from among the styles of interior design. Furthermore, when consumers plan the color scheme of residential spaces, living rooms are the top priority among residential spaces. Therefore, the purpose of this paper is to develop a model based on machine learning that recommends colors of furniture or objects to be placed in the living room of consumers. The data learned in the developed model is RGB of three colors extracted from natural and modern living room images. The living room space images are collected based on keywords on the I.R.I image scale, which visually measures Koreans' color sensitivity, and in addition, the living room space images are collected through a sharing platform. The collected images are cleaned and integrated using the I.R.I color image scale and CNN model. The color data (RGB) of the cleaned images are learned in XGBoost and LightGBM, which perform machine learning tasks. The color recommendation models in this paper are evaluated using r² and MSE, which are evaluation methods for regression models supported by Scikit-Learn. And the model with the highest evaluation score is selected. Therefore, in this paper, a color scheme model for color harmony in the living room was selected as XGBoost No. 2 “train : value = 8 : 2”. This is effective as a color scheme model, and it will be a model that can satisfy consumers with individuality in the era of emotional design.

A New Remote USB Architecture for Live Migration of Virtual Machines in SoD (System on-Demand) Service

Dong-oh Kang,Jinho Yoo,Jeunwoo Lee 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10

In this paper, we propose a new remote USB architecture to support live migration of virtual machines in SoD (System on-Demand) service. The SoD (System on-Demand) service is the service that provides virtual personal computers which are optimized virtual machines using distributed u-computing devices around users when the users demand. The virtual USB technology for virtual machines is a kind of I/O virtualization to make users of virtual machines use remote USB devices as local USB devices. In a SoD system, a virtual machine can migrate among some SoD servers even when users use virtual machines due to resource reallocation mechanism of the system. In case of the live migration of the virtual machine, the connection of remote USB to the virtual machine will be broken, which means the break of I/O virtualization. For the seamless I/O virtualization of remote USB in spite of live migration of virtual machines, we propose a new remote USB architecture by adopt the virtual connection manager which sustains the virtual connection among the virtual machine and remote USB devices. With the proposed remote USB architecture, users of the virtual machine use remote USB devices seamlessly without noticing live migration of virtual machines.

포스트휴먼의 꿈, 최우람의 ‘기계 생명체’를 중심으로

이재은 이화여자대학교 이화인문과학원 2021 탈경계인문학 Vol.14 No.2

This study focuses on the allegory of Anima machine that U-Ram Choe known as a kinetic artist has been making since 2000. I take a closer look at the Posthuman symptoms of the Anima machine. The kinetic element of his works is intended to symbolize the emergence and the self-organizaation in the living system. His mechanical living beings have the value of beauty that anthropocentrism does not allow non-humans. These aspects provide an opportunity to contemplate the posthuman sensitivity against the aesthetic based the dichotomy between humans and non-humans in which Man defined. Thus this paper is intended to verify that Anima machines function as the allegory of symbioses between humans and non-humans that displaces anthropocentrism. Furthermore, this study will be meaningful in that it reveals the reason why Choe has been examining the symbiotic relationship between humans and non-humans in the course of techno-futurism of Korean society since the 1990s.

HOW DO BROADCASTERS BEHAVE ON LIVE STREAMING PLATFORMS? A MACHINE LEARNING APPROACH

Honglong Wang,Guoxin Li,Xiaodong Xie,Shaohui Wu 글로벌지식마케팅경영학회 2023 Global Marketing Conference Vol.2023 No.07

The popularity of live streaming is driving the emergence of a new business model, known as live-streaming commerce (LSC). While there are more and more broadcasters in LSC, their behaviors and performance of them are significantly different. To have a better understanding of broadcasters, we employ different machine learning models to identify different portraits in both static and dynamic dimensions. We collect a rich live-streaming dataset from one leading platform in China. Our dataset features information for both broadcasters and viewers, including viewers’ purchasing behaviors, viewers’ records of posting words, broadcasters’ gender, the number of followers for broadcasters, and the live streaming show information, including the start and end time, and the viewers in each live streaming show. The rich textual information in broadcasters’ profile induction provides us a good opportunity to uncover different static portraits and the records in live streaming shows give us a chance to identify different dynamic behavioral portraits for broadcasters.

Fingerprint Liveness Detection Using Gray Level Co-Occurrence Matrix Based Texture Feature

Chengsheng Yuan,Zhihua Xia,Xingming Sun,Decai Sun,Rui Lv 보안공학연구지원센터 2016 International Journal of Grid and Distributed Comp Vol.9 No.10

Fingerprint-based recognition systems have been widely deployed in numerous civilian and government applications. However, the fingerprint recognition systems can be deceived by using an accurate imitation of a real fingerprint such as an artificially made fingerprint. In this paper, we propose a novel software-based fingerprint liveness detection algorithm based on gray level co-occurrence matrix (GLCM), from which we can calculate the texture features of fingerprint images and obtain satisfactory results. For the first time, we extract texture features by constructing four-direction GLCMs in an image, and then quantization operation and normalization operation are adopted. After these, we detected whether a fingerprint image belongs to a real fingerprint or an artificial replica of it. A trained RBF SVM (support vector machine) classifiers scheme is used to make the final live/spoof decision via training and testing feature vectors. The experimental results reveal that our proposed method can discriminate between live fingerprints and fake ones with high classification accuracy.

2축 가속도 신호와 Extreme Learning Machine을 사용한 행동패턴 분석 알고리즘

申伉植(Hang-Sik Shin),李榮範(Young-Bum Lee),李明鎬(Myoungho Lee) 대한전기학회 2007 전기학회논문지 Vol.56 No.7

In this paper, we propose pattern recogrution algorithm for activities of daily living by adopting extreme learning machine based on single layer feedforward networks(SLFNs) to the signal from bidirectional accelerometer. For activity classification, 20 persons are participated and we acquire 6 types of signals at standing, walking, running, sitting, lying, and falling. Then, we design input vector using reduced model for ELM input. In ELM classification results, we can find accuracy change by increasing the number of hidden neurons. As a result, we find the accuracy is increased by increasing the number of hidden neuron. ELM is able to classify more than 80 % accuracy for experimental data set when the number of hidden is more than 20.

1930年沈兹九在右翼期刊《长风》的文学创作研究――兼谈韩人题材小说《活的机器》

장린 한국중국언어문화연구회 2022 한중언어문화연구 Vol.- No.64

In 1930, Shen Zijiu published seven works of literature in the Right-wing nationalist literary periodical 《Changfeng》. The themes include anti-imperialism, anti-communism, criticism of social phenomenon, and praise of historical figures, which often appeared in nationalist literature. This creation seems to be an attempt to find a way to solve social problems while reflecting social reality. In addition, we could see that her political trend at that time still belongs to the Right. Among them, the novel 《Living Machine》, which was created based on real events, depicts the miserable reality that Chinese and Korean workers in Japan were exploited by Japanese capitalists in the 1920s and even massacred by Japanese after the Great Kanto Earthquake. As an intellectual, Shen Zijiu recorded historical events in the form of literature, showing interest in workers. Therefore, it has both literary and historical values. The novel describes a character named Kim Gye-saeng, a Korean worker. Compared to other Korean images already discovered, Kim Gye-saeng is a character with peculiarity, which served as an opportunity to expand the case of Korean figures in modern Chinese literature. 1930年沈兹九在右翼民族主义文艺期刊《长风》发表了7篇作品,主题都是民族主义文艺常见的反帝、反共、批判社会现象、颂扬历史人物等。这些创作注重反映社会现实,并试图寻找解决社会现实问题的出路,同时也表明当时她的政治倾向尚未向左转。其中以真实事件为基础创作的小说《活的机器》描述1920年代浙东劳工和朝鲜劳工在日本受到资本家的严酷剥削以及在关东大地震后遭到虐杀的悲惨境遇,表现了沈兹九作为一个知识分子对底层劳工的人文关怀,也为惨痛的历史事件留下了文学记录,具有文学与史料的双重价值。同时,这篇小说塑造的韩人形象金桂生是以往韩人题材作品研究中从未被提及的。新发现的在日朝鲜劳工金桂生的形象丰富了中国现代文学中韩人形象的图谱。

머신러닝을 이용한 선제적 VNF Live Migration

정세연,유재형,홍원기 한국통신학회 2021 KNOM Review Vol.24 No.1

VM (Virtual Machine) live migration is a server virtualization technique for deploying a running VM to another server node while minimizing downtime of a service the VM provides. Currently, in cloud data centers, VM live migration is widely used to apply load balancing on CPU workload and network traffic, to reduce electricity consumption by consolidating active VMs into specific location groups of servers, and to provide uninterrupted service during the maintenance of hardware and software update on servers. It is critical to use VM live migration as a prevention or mitigation measure for possible failure when its indications are detected or predicted. In this paper, we propose two VNF live migration methods; one for predictive load balancing and the other for a proactive measure in failure. Both need machine learning models that learn periodic monitoring data of resource usage and logs from servers and VMs/VNFs. We apply the second method to a vEPC (Virtual Evolved Pakcet Core) failure scenario to provide a detailed case study. VM (Virtual Machine) live migration은 VM에서 동작하는 서비스의 downtime을 최소화하면서 해당 VM을 다른 서버 노드로 이전시키는 서버 가상화 기술이다. 클라우드 데이터센터에서는 로드밸런싱, 특정 위치 서버로의 consolidation 통한 전력 소비 감소, 서버 유지보수(maintenance) 작업 중에도 사용자에게 무중단 서비스를 제공하기 위한 목적 등으로 VM live migration 기술이 활발히 사용되고 있다. 또한 고장 및 장애 상황이 예측되거나 그 징후가 탐지되는 경우, 예방 및 완화 수단으로 활용될 수 있다. 본 논문에서 우리는 두 가지 선제적(proactive) VNF live migration 방법을 제안하며, 첫 번째 방법은 서버 로드밸런싱에 VNF live migration 기법을 사용하며 두 번째 방법은 고장 예측에 기반하여 고장 회피 목적으로 VNF live migration을 사용한다. 선제적 migration을 위한 예측에 머신러닝(기계학습)을 활용하며 실험을 통해 그 실효성을 검증한다. 특히 두 번째 방법에 대해 vEPC (Virtual Evolved Packet Core)의 고장 상황을 case study한 결과를 제시한다.

오이디푸스 콤플렉스를 넘어서: 로렌스와 들뢰즈의 정신분석학 비판

강미숙 ( Mi Sook Kang ) 한국로렌스학회 2011 D.H. 로렌스 연구 Vol.19 No.1

Though criticized for the apparently eccentric ideas quite different from those of Western scientific minds, D. H. Lawrence`s two psychological books, Psychology and the Unconscious and Fantasia of the Unconscious, remain central to understanding psychology in general as well as the novelist`s ethics and philosophy of life. For Lawrence, the unconscious of Freudian psychoanalysis has no positive meaning because the whole body of our repressions makes up our unconscious; it all along the line fails to determine the nature of the pristine unconscious in man. He points out that the incest motive is just a logical deduction of the human reason, which has recourse to this last extremity to save itself. Rather, the true unconscious is the spontaneous life-motive in every single living creature. It is underivable and inconceivable as a general thing or a mathematical unit because it exists only in living creatures. Furthermore, the baby`s first consciousness develops not from the brain, but from the solar plexus in the belly, which indicates the psychical to Lawrence is inseparable from the physical in its nature. In Anti-Oedipus published in 1972, Gille Deleuze and Felix Gattari find in Lawrence the poignant critic of Freudian psychoanalysis. They argue that Oedipus is not a real repressing representative, but a factitious product of the displaced psychic repression. So the desiring-machine, which is neither the living nor the machine, can escape the Oedipal codes which force the individuals to adjust to a unified whole. Also, "the body without organs" can provide the way out of the psychological framework of capitalism by preferring differences over uniformity, flows over unities, and the nomadic over the sedentary. However, having little regard for the life that is only in the living individuals, they ultimately fail to escape the idealistic nature of Western philosophy and determine the nature of true unconscious.

Virtual kiosk test for early screening of mild cognitive impairment through eye tracking data analysis

Se Young Kim,Jin-seok Park,Hojin Choi,Hokyoung Ryu,Kyoungwon Seo 한국HCI학회 2023 한국HCI학회 학술대회 Vol.2023 No.2

Early screening of mild cognitive impairment (MCI) is important to prevent progression to Alzheimer’s disease. Recent studies have shown that technology-activities of daily living (T-ADL) ability, such as how well older adults use kiosks, is useful in assessing their cognitive impairment. Using virtual reality (VR) and eye tracking technology, an older adult’s T-ADL ability can be quantified through non-invasive eye tracking data. In this context, this study developed a ‘virtual kiosk test’ to assess T-ADL ability through eye tracking data analysis in VR, as a novel method for early screening of MCI. Nine healthy controls and 11 MCI patients were recruited. Subjects performed a virtual kiosk test and neuropsychological tests in a random order. Results showed that MCI patients exhibited worse eye tracking data-lower fixation count (p=0.04) and duration (p=0.03) for the target menu items-when performing the virtual kiosk test compared to healthy controls. A Support vector machine (SVM) using these eye tracking data was able to screen MCI patients with 80.16% accuracy, 72.73% sensitivity, 72.73% precision, and 72.73% F1 score. Our findings demonstrated the effectiveness of the virtual kiosk test to early screen MCI patients.