• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1997.11a
• /
• pp.224-227
• /
• 1997

The International Affective Picture System (IAPS) developed by Lang and colleagues[1] is a world-widely adopted tool in studices relating a variety of physiological indices to subjective emotions induced by the presentation of standardized pictures of which subjective ratings are well established in the three dimensions of pleasure, arousal and dominance. In the present stuey we investigated whether distinctive EEG characteristics for six discrete emotions can be discernible using 12 IAPS pictures that scored highest subjective ratings for one of the 6 categorical emotions, i. e., happiness, sadness, fear, anger, disgust, and surprise (Two slides for each emotion). These pictures as visual stimuli were randomly given to 38 right-handed college students (20-26 years old) with 30 sec of exposure time and 30sec of inter-stimulus interval for each picture while EEG signals were recorded from F3, F4, O1, and O2 referenced to linked ears. The FFT technoque were used to analyze the acquired EEG data. There were significant differences in RP value changes of EEG bands, most prominent in theta, between positive positive and negative emotions, and partial also among negative emotions. This result is in agreement with previous studies[2, 3]. However, it requires further studied to decided whether IAPS could be a useful tool for catigorical approaches to emotion in addition to its traditional uwe, namely dimensional to emotion.

• Proceedings of the ESK Conference
• /
• 1998.04a
• /
• pp.36-39
• /
• 1998

In this study, the postural stresses in automobile assembly tasks were evaluated through an experiment. We had 19 subjects who simulated 42 different working postures occuring in the automobile assembly tasks for1 min and rated their whole body discomforts subjectively. We sued a free modulus magnitude estimation technique, commonly used as a psycophysical rating technique, and fully trained the subjects for the technique. The postures were selected through the analysis of the characteristics of te automobile assembly tasks and the expected difficulties. The subjective discomfort rating data were normalized by min-max standardization method. The consistency of the rating data was guaranteed by the analysis of spear man rank-order. The postures were ranked on their ratings and the relationships between the whole body discomfort ratings, and joint discomfort ratings were analysed. It is expected taht a system for evaluating postural stresses, which was specific to automobile assembly tasks, can be developed based on the relationship and can also be expended to a general purpose system with a minor modification.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.707-720
• /
• 2021

To improve the accuracy of the recommendation system, multi-criteria recommendation systems have been widely researched. However, it is highly complicated to extract the preferred features of users and items from the data. To this end, subjective indicators, which indicate a user's priorities for personalized recommendations, should be derived. In this study, we propose a method for generating recommendation candidates by predicting multi-criteria ratings from reviews and using them to derive user priorities. Using a deep learning model based on convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM), multi-criteria prediction ratings were derived from reviews. These ratings were then aggregated to form a linear regression model to predict the overall rating. This model not only predicts the overall rating but also uses the training weights from the layers of the model as the user's priority. Based on this, a new score matrix for recommendation is derived by calculating the similarity between the user and the item according to the criteria, and an item suitable for the user is proposed. The experiment was conducted by collecting the actual "TripAdvisor" dataset. For performance evaluation, the proposed method was compared with a general recommendation system based on singular value decomposition. The results of the experiments demonstrate the high performance of the proposed method.

• Journal of the Korean Society of Safety
• /
• v.23 no.5
• /
• pp.105-110
• /
• 2008

This study focused on the decreased effect of the work load on using the lower extremity supporter in kneeling posture. Fatigue measures included subjective discomfort ratings through the use of the Borg's CR-10 scale based parameters. The resting period and work method were considered as independent variables. The break time conditions are grouped into 10 seconds after work for 1 min and not exist break time. The method of work conditions are divided into four types. There are kneeling with the lower extremity supporter, kneeling with the knee protector, just kneeling and squatting. The result of the ANOVA of the shift value of subjective discomfort showed the followings: 1) There were differences as regards to the method of the work, the break time and the part of body($p{\leq}0.05$). 2) The lower extremity supporter showed the least subjective discomfort in other part of body except the upper leg.

• Journal of the Ergonomics Society of Korea
• /
• v.30 no.6
• /
• pp.695-703
• /
• 2011

Objective: This study was to investigate the effects of coordinated upper-limb body postures on the subjective discomfort rating, heart rate, and muscle activities. Background: Although generally many checklists such as OWAS, RULA, and REBA were applied to evaluate various body postures, the body postures were might be overestimated or underestimated because each body part(i.e., back, shoulder, and elbow etc.) was evaluated separately, and then added all rates of individual body parts to assess an overall risk level for the body posture in these methodologies. Methods: A total of 20 participants maintained 14 postures which were combinations of back, shoulder, and elbow flexion angles and then muscle activities, subjective discomfort, and heart rates were collected every three minute during a sustained 15 minute and 0.5kg weight holding task. Four muscle groups were investigated: erector spine, anterior deltoid, upper trapezius, triceps brachii. Results: Results showed that subjective discomfort was the lowest when the angle of back and shoulder were both $0^{\circ}s$, while the body posture with $45^{\circ}$ of back angle and $45^{\circ}$ shoulder angle was rated as the most subjective discomfort posture. In general, the subjective discomfort ratings increased as back and shoulder flexion angles increased. It was noted that, however, the subjective discomfort of body posture with a $45^{\circ}$ back angle and $45^{\circ}$ shoulder flexion angle was lower than that of body posture with a $0^{\circ}$ back and $45^{\circ}$ shoulder flexion angle. The research findings of heart rates and muscle activities showed similar results for the analyses of subjective discomfort ratings. Conclusions: The possible limitations of the current ergonomics evaluation techniques which assessing a body posture with summing all body part score after individually analyzed in this study. Based on the analyses of subjective discomfort, heart rate, and muscle activities, it was recommended that a use of effects of coordinated upper-limb body postures would be considered when one evaluates work-load for various working postures. Application: These findings can be used for developing a more accurate assessment checklist for working posture as well as preventing musculoskeletal disorders of workers in workplaces.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2001.10a
• /
• pp.156-161
• /
• 2001

Currently, agricultural facilities are evaluated using either basic inspections or detailed analysis. However, conventional analyses as well as methods based on fuzzy logic and rule of thumb have not been very successful in providing a clear relationship between rating and real state of agricultural facilities, because they can't provide exactly acceptable reliability of degraded structures with manager or supervisor. Therefore, in this stage, we must define probabilistic variables for representing degradation of structures being given damages during a survival time. This paper describes the application of neural network system in developing the relation between subjective ratings and parameters of agricultural reservoir as well as that between subjective and analytical ratings. It is shown that neural networks can be trained and used successfully in estimating a rating based on several parameters. The specific application problem for agricultural reservoir in the rural area of Korea is presented and database is constructed to maintain training data set, the information of inspection and facilities. This study showed that a successful training of a neural network could be useful, especially if the input data set for target problem contains parameters with a diverse combination of inter-correlation coefficients. And the networks had a prediction rating of about $^{\ast}^{\ast}^{\ast}%$. The neural network system is expected to show high performance fairly in estimate than statistical method to use equation that is consisted of very lowly interrelated variables.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.23 no.4
• /
• pp.541-550
• /
• 1999

The purpose of this study is to find out the factors that explain the sense of touch and preference of man-made leather. Date base of descriptors for man-made leather was collected by interviewing 50 consumers, 33 different kinds of commercial man-made leathers(synthetic leather and artificial leather) were assessed subjectively by 605 consumers using the 9-point scale of 34 pairs of bipolar descriptors based on the data base. Subjective ratings were analyzed by principal axis factoring with varimax rota-tion. The sense of touch of man-made leather is explained by five factors ; surface property stretchiness thickness& weight thermal property(warmth & coolness) and moisture property (sticky & clingy). The difference in the sense of touch of man-made leathers is mainly attributable to surface property and stretchiness. And the preference of man-made leathers is mainly attributable to surface property and stretchiness. And the preference of man-made leather is explained by three factors ; surface property stretchiness and quality. Higher preference is found in man-mad leather of better quality touch and softness.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.28 no.3_4
• /
• pp.452-459
• /
• 2004

The purpose of this study was to evaluate the effect of reference fabric for the tactile sensation of worsted fabrics. As specimens, 32 worsted fabrics for spring/fall suits were selected. A series of subjective evaluation for roughness, harshness, coarseness, smoothness, warmth, bulkiness and softness were performed with 20 trained panels. The panels were selected by the test of consistency and trained for 3 weeks to enhance the reproducibility and consistency. Subjective evaluation was performed using 9 points Semantic Differential Scales with and without reference fabric. Results showed that the sensations were very similar between the results for the test of with or without reference. However the standard deviations of ratings for the with-reference were much less than that of without-reference which means the use of reference fabric can reduce the subjective error or can reduce the number of panels to test.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1997.04a
• /
• pp.370-375
• /
• 1997

The ratings of noise are consisted of physical factors and psychological factors. The physical factor means the scales and the spectrum characteristics of noise, on the other hand the psychological factor means the subjective emotion, sensation and individual judgement for it. Therefore the rating of noise must reflect the subjective psychology of people for it. But it is very difficult to establish an effective scale which can reflect well that because the subjective psychology has many variables according to the cultural differency, nationality and individual personalities. In this paper, Korean Vocabularys for the assessment of noise were surveyed in order to find out the effective noise scale for Korean.

• Journal of Internet Computing and Services
• /
• v.16 no.2
• /
• pp.41-48
• /
• 2015

On movie review sites, movie ratings are determined by netizens' subjective judgement. This means that inconsistency between ratings and opinions from netizens often occurs. To solve this problem, this paper proposes sentiment sentence sets which affect movie evaluation, and apply sets to comments to infer ratings. Creation of sentiment sentence sets is consisted of two stages, construction of sentiment word dictionary and creation of sentiment sentences for sentiment estimation. Sentiment word dictionary contains sentimental words and its polarities included in reviews. Elements of sentiment sentences are combined with movie related noun and predicate from words sentiment word dictionary. In this study, to make correspondence between polarity of sentiment sentence and sentiment word dictionary, sentiment sentences which have different polarity with sentiment word dictionary are removed. The scores of comments are calculated by applying averages of sentiment sentences elements. The result of experiment shows that sentence scores from sentiment sentence sets are closer to reflect real opinion of comments than ratings by netizens'.