간행물

한국감성과학회> 한국감성과학회 국제학술대회(ICES)

한국감성과학회 국제학술대회(ICES) update

  • : 한국감성과학회
  • : 공학분야  >  기타(공학)
  • :
  • :
  • : 학술발표집
  • : 부정기
  • :
  • :
  • :

수록정보
수록범위 : 2017권0호(2017)~2021권0호(2021) |수록논문 수 : 179
한국감성과학회 국제학술대회(ICES)
2021권0호(2021년 11월) 수록논문
최근 권호 논문
| | | |

저자 : Chung-heon Lee , Jun-dong Cho

발행기관 : 한국감성과학회 간행물 : 한국감성과학회 국제학술대회(ICES) 2021권 0호 발행 연도 : 2021 페이지 : pp. 64-66 (3 pages)

다운로드

(기관인증 필요)

초록보기

The objective of this research is to provide a barrierfree artwork appreciation experience for people with visual impairment (PVI) who have limitations because of the lack of cognitive and sensory access to exhibitions, museums, etc. We applied artificial intelligence (AI) to our previous works with visual appreciation solutions recommending poets according to the colors and objects. To extract the color and object elements in the poet, we used a natural language toolkit (NLTK) and in the visual art, we used convolutional neural networks (CNNs) to train the dataset of moon and church images. Unlike the researches of classification on natural images, despite the small size of the dataset and numerous variables in the visual arts such as techniques (oil, watercolor, etc.) and styles (impressionism, modernism, etc.), we attained successful results.

저자 : G. Keerthi , M. S. Abirami

발행기관 : 한국감성과학회 간행물 : 한국감성과학회 국제학술대회(ICES) 2021권 0호 발행 연도 : 2021 페이지 : pp. 67-70 (4 pages)

다운로드

(기관인증 필요)

초록보기

Diabetes is a leading reason of death, disability, and economic loss around the world. Type 2 diabetes is the maximum shared kind of diabetes in women (80-90 percent worldwide).It can be avoided or postponed by receiving the appropriate maintenance and interventions, including an initial diagnosis. There has remained a lot of progress in the area of medical diagnosis using many machine learning algorithms. However, due to incomplete medical data sets, accuracy suffers, resulting in a higher frequency of misclassifications, which might lead to dangerous complications. Many researchers find that accurately predicting and diagnosing a disease is a difficult scientific topic. As a result, the goal was to improve the diagnostic. The first technique is to collect the dataset, which comprises of 769 pregnant women's records. On the foundation of accuracy, machine learning approaches are utilized to forecast diabetes and non-diabetes women. We used seven machine learning algorithms to calculate diabetes using the dataset. We discovered that a diabetes prediction model that combines Linear Regression and Support Vector Machine performs well, with an accuracy of 77 percent -78 percent.

저자 : Vigneswari Gowri , Prabhu Sethuramalingam

발행기관 : 한국감성과학회 간행물 : 한국감성과학회 국제학술대회(ICES) 2021권 0호 발행 연도 : 2021 페이지 : pp. 71-74 (4 pages)

다운로드

(기관인증 필요)

초록보기

Health monitoring and care is been considered as the major field in medical technological advancements. Sensors and wireless communication technologies has been applied with learning techniques to design low-cost, and low power integrated circuits with intelligent systems. This system detects, measures and analyses the health parameters such as Sp02, Heart rate, ECG and Body temperature. This system is capable of analyzing, processing and communicating the sensor data in real-time using Wi-Fi to achieve a seamless data transfer. These systems become an inseparable part of the medical environment both to the patient and the doctor. It enables the information transfer at a faster and accurate manner. Integration of these systems with robots has a major advantage of food and medicine delivery, UV sanitization and haptic video calling. Applied Machine learning algorithms with experimentation such as Min-max algorithm, Feature selection and SVM gives refines the data with most accurate values and predicts the medicine or further treatment to be provided. Along with this, robot integrated with this system serves as an emotional support with the sensor values. This can predict the patient condition on emotional basis and plays songs or movies of their preference and calls their paired friends or relatives which boosts their energy and normalizes the body parameters. The result of the combined algorithms gives 96.2% accuracy which can be improved on further classification of obtained data.

저자 : D. Senthil Vadivelan , S. Prabhu , M. Uma

발행기관 : 한국감성과학회 간행물 : 한국감성과학회 국제학술대회(ICES) 2021권 0호 발행 연도 : 2021 페이지 : pp. 75-77 (3 pages)

다운로드

(기관인증 필요)

초록보기

A brain-computer interface (BCI) provides a new means of bridging the gap between humans and computers, now days by allowing computers to be intentionally controlled based on brain signals. The activity of neurons generates electrical impulses, which are recorded by electroencelography (EEG). The acquired EEG signals are used to control the external devices such as a robotic arm, wheelchair, moving cursors, etc., and hence, are very useful to develop personal assistants for the disabled person for interaction and communication to the outside world. This study gives a thorough examination of EEG signal processing in robotic arms control, with a focus on noninvasive brain computer interface systems. For EEG classification, several filtering procedures, feature extraction techniques, machine learning algorithms are explored and summarized.

저자 : Inik Kim , Junhyuk Jang , Jongwan Kim

발행기관 : 한국감성과학회 간행물 : 한국감성과학회 국제학술대회(ICES) 2021권 0호 발행 연도 : 2021 페이지 : pp. 79-82 (4 pages)

다운로드

(기관인증 필요)

초록보기

The intersubject correlation (ISC) has been used to understand the synchrony of brain activities across participants [1-3]. Li, Zhu, Vuoriainen, Ye and Astikainen [4] applied this novel analysis technique to the behavioral data and found a discrepancy of ratings between control and clinical groups. In this study, we implemented the ISC analysis to the ratings data of the ASMR stimulus set. We were able to measure the consistency of responses by computing correlations between all stimulus pairs across subjects. There were significant differences of ISCs between valence and modality conditions. The participants showed higher affect synchrony after watching the positive or audiovisual stimulus. Also, there was interaction between valence and modality. In the negative ASMR condition, there was no difference between auditory and audiovisual conditions. The results were discussed in the context of affect and modality research related to ISC.

저자 : Taebeum Ryu

발행기관 : 한국감성과학회 간행물 : 한국감성과학회 국제학술대회(ICES) 2021권 0호 발행 연도 : 2021 페이지 : pp. 83-85 (3 pages)

다운로드

(기관인증 필요)

초록보기

The weight of an object is an important research topic in terms of sensory and perception, and it is known that it has size-weight, color-weight, and material-weight illusion due to the influence of size, color, and material as well as the weight of the object. Although the physical size of an object is measured by volume, the size of an object that we subjectively feel depends on the shape of the object even if it has the same volume. Therefore, the shape of the object determines the size of the object, and the weight of the object may change accordingly. Existing related studies analyzed the effect of weight according to three shapes (tetrahedron, cube, and sphere), but only some shapes showed a difference in weight. Therefore, this study tried to experimentally prove the difference in weight according to the shape that has not yet been clearly identified. To this end, this study produced objects with the same physical size (volume) as in previous studies, but with tetrahedron, cube, and spherical shapes. In addition, the object volume in this study was set to 3 types of 64,000, 125,000, and 216,000 cm3, and the weight of the object was set to be 100, 150, and 200 g for small, medium, and large volumes, respectively, in proportion to the size. 38 college students (21 males, 17 females) participated in this weight test, and the perceived weight of a given object compared to a reference object was evaluated according to the modulus method used for sensory size measurement. As a result of the analysis of the experimental data, it was found that both weight (volume) and shape had a significant effect on the feeling of weight. Naturally, the weight (volume) of an object with a large weight (volume) was statistically significantly greater than that of an object with a small weight. At the same weight (volume), the weight of an object according to shape decreased statistically significantly in the order of a sphere, a cube, and a tetrahedron. In the same volume, subjective size according to shape is small in the order of tetrahedron, cube, and sphere (Kahrimanovic et al., 2010). Therefore, the results of weight perception according to shape in this study showed that subjective size of objects according to shape had an effect on weight. This is explained as a kind of size-weight illusion phenomenon.

저자 : Eiji Onchi , Max Hanssen , Kaihuan Wei , Pengcheng Wan , Cen Zhang , Muneo Kitajima , Seunghee Lee

발행기관 : 한국감성과학회 간행물 : 한국감성과학회 국제학술대회(ICES) 2021권 0호 발행 연도 : 2021 페이지 : pp. 86-90 (5 pages)

다운로드

(기관인증 필요)

초록보기

Our daily action selection processes are guided by conscious and unconscious behaviors. Being able to measure these signals may provide a clue into how we make decisions and allow us to create better systems that can help us during these action selection processes. A flexible and easy to manufacture tool was needed to bootstrap the research in this field. Therefore, this paper presents the design and development of 'My Daily Badge', a wearable device for habitual behavioral tracking, that is easy to manufacture. We also introduce the Off-the-Shelf Adaptive Design process that led to the creation of this device. Finally, several test measurements are described, as well as potential classification algorithms that can aid researchers in the research of daily conscious and unconscious behavioral patterns. This research contributes toward the development of accessible bioinstrumentation tools that can help researchers in different scientific fields.

저자 : Max Hanssen , Eiji Onchi , Muneo Kitajima , Seunghee Lee

발행기관 : 한국감성과학회 간행물 : 한국감성과학회 국제학술대회(ICES) 2021권 0호 발행 연도 : 2021 페이지 : pp. 91-99 (9 pages)

다운로드

(기관인증 필요)

초록보기

The reasons and benefits that people pursue through walking are often unconscious and unknown to many individuals. This research aims to find out whether understanding the underlying factors that make walking interesting could lead to a higher quality of walks. Participants walked an unfamiliar route after their usual familiar route, to identify previously unknown factors that contributed to the quality of their walking experience. The identified factors were categorized into four main themes. The relations that were found between the main themes and participants can act as a first step to guide those who do not see the value of walking to the potential motivations that they might have for walking.

저자 : S. Ramya , M. Uma

발행기관 : 한국감성과학회 간행물 : 한국감성과학회 국제학술대회(ICES) 2021권 0호 발행 연도 : 2021 페이지 : pp. 100-105 (6 pages)

다운로드

(기관인증 필요)

초록보기

One of the most chronic neurological illnesses is epilepsy that causes unprovoked, recurrent seizures [1]. Seizures are caused by sudden disturbances in the electrical activity of the brain. Over 70 million people are affected worldwide by this chronic disorder [1]. The occurrence of seizure can cause severe disorders in behavior, emotions, jerks in movements, unconsciousness of subjects and can lead to sudden death or injury. An efficient modality that acquires the brain signal is Electroencephalography (EEG). The signals are recorded from the cerebral cortex of the brain. There are two ways of procuring the bio potential signals from the brain i) invasive and ii) non-invasive techniques. Invasive technique is implanting electrodes inside the brain which is also called iEEG (intracranialElectroEncephalography). In this technique electrodes are placed very close to the skull so the unwanted noise can be eliminated and the signals acquired are more effective. In non-invasive technique the dry or wet electrodes are placed on the scalp normally said as scalp EEG. In this technique the signals collected are preprocessed and the artifacts should be removed to improve the accuracy of prediction of Epilepsy. However, the subject may not have any inconvenience of placing the electrodes invasively. The traditional way of predicting EEG signals is mostly error prone or takes more time for the medical practitioners to analyze the data. Hence automation is significant to enhance a quality of living in subjects with epilepsy. ML leverages many automations in the field of health care which ease the patient's diagnosis and prediction. This paper reviews the recent trends in developing a Machine Learning model for efficient prediction of epilepsy. The paper also highlights the various techniques involved in Classifying and detecting Epileptic Seizure (ES), challenges and future directions involved in analyzing EEG signals.

저자 : Dhruba Jyoti Sut , S. Prabhu

발행기관 : 한국감성과학회 간행물 : 한국감성과학회 국제학술대회(ICES) 2021권 0호 발행 연도 : 2021 페이지 : pp. 106-109 (4 pages)

다운로드

(기관인증 필요)

초록보기

Soft grippers have advanced rapidly thanks to development in soft robotics, science of materials, and flexible electronics. This paper reviewing comprehensive suggestion of soft grippers, including physical ideologies, and device topologies. Different sorts of grippers are required for handling different types of objects, both hard and soft. To acquire additional flexibility in holding objects, it is critical to use flexible and adaptive gripping approaches. Complimentary soft-robotic grasping systems, which are highly adaptable in terms of workpiece shape, size, and structure, are an excellent solution to boost production flexibility. The main reason behind the review is to know about the existing soft gripper and know about existing soft-robotic grippers repeatability with substantial payload capacities. A systematic inspection of soft gripper is offered. Flexible and soft end-effectors often able to grasp or move a broader range of objects than rigid grippers.

권호별 보기

내가 찾은 최근 검색어

최근 열람 자료

맞춤 논문

보관함

내 보관함
공유한 보관함

1:1문의

닫기