• Journal of the Korea Convergence Society
• /
• v.7 no.6
• /
• pp.7-11
• /
• 2016

Voice recognition systems which use a white noise and voice recognition environment are not correct voice recognition with variable voice mixture. Therefore in this paper, we propose a method using the convergence of Bayesian technique and selecting voice for effective voice recognition. we make use of bank frequency response coefficient for selective voice extraction, Using variables observed for the combination of all the possible two observations for this purpose, and has an voice signal noise information to the speech characteristic extraction selectively is obtained by the energy ratio on the output. It provide a noise elimination and recognition rates are improved with combine voice recognition of bayesian methode. The result which we confirmed that the recognition rate of 2.3% is higher than HMM and CHMM methods in vocabulary recognition, respectively.

• The KIPS Transactions:PartB
• /
• v.9B no.6
• /
• pp.765-774
• /
• 2002

The purpose of this paper is a design and implementation for korean character and pen-gesture recognition system in multimedia terminal, PDA and etc, which demand both a fast process and a high recognition rate. To recognize writing-types which are written by various users, the korean character recognition system uses a database which is based on the characteristic information of korean and the stroke information Which composes a phoneme, etc. In addition. it has a fast speed by the phoneme segmentation which uses the successive process or the backtracking process. The pen-gesture recognition system is performed by a matching process between the classification features extracted from an input pen-gesture and the classification features of 15 pen-gestures types defined in the gesture model. The classification feature is using the insensitive stroke information. i.e., the positional relation between two strokes. the crossing number, the direction transition, the direction vector, the number of direction code. and the distance ratio between starting and ending point in each stroke. In the experiment, we acquired a high recognition rate and a fart speed.

• KSCI Review
• /
• v.14 no.1
• /
• pp.241-248
• /
• 2006

The recognition of a relatively big and rarely movable object. such as refrigerator and air conditioner, etc. is necessary because these objects can be crucial global stable features of Simultaneous Localization and Map building(SLAM) in the indoor environment. In this paper. we propose a novel method to recognize these big objects using a sequence of 3D scenes. The particles representing an object to be recognized are scattered to the environment and then the probability of each particles is calculated by the matching test with 3D lines of the environment. Based on the probability and degree of convergence of particles, we can recognize the object in the environment and the pose of object is also estimated. The experimental results show the feasibility of incremental object recognition based on particle filtering and the application to SLAM

• Journal of the East Asian Society of Dietary Life
• /
• v.11 no.4
• /
• pp.247-258
• /
• 2001

This study focused on the recognition and information need for GMO(Genetically Modified Organism). The data were collected from 350 adults living in Daegu and Busan by means of a self-administered questionnaire. Frequencies and chi-square tests were conducted by SPSS Windows. The results of the survey were as follows: (1) the concerns about GMO were high but recognition was low. (2) many respondents were worried about the safety of GMO. (3) many people desired the labelling of GMO, and (4) the need for information about GMO was high and most respondents wanted to be informed about safety of GMO. This study suggests that the consumer education about GMO should be conducted through mass media and consumer protection organizations.

• Archives of design research
• /
• v.16 no.2
• /
• pp.233-242
• /
• 2003

Whit trade increasingly taking place on the global stale, packaging becomes even more important However, there is only a fine line between the balance of waste created by damaged goods and waste created by over-packaging. A vast quantity of material is used by the packaging industry for the reason of bringing products safely to the customers. In this research I gathered 87 samples of various kinds of confectionery to analyse the actual conditions of the appropriate packaging. As a result, the rate of the needless space excluding actual contents comes to over 60% which clearly says that the most products are over-packaged. Despite assertions from the packaging industry that all packaging is necessary in reducing product waste, the research shows us the fact that it's over-packaged. What needs to be questioned, here, is the level of materials we use in packaging our products, and how we can continue to decrease that amount and recycle what we do use. In the future where materials and resources become more scarce, and therefore more expensive, and the methods of disposal become more costly and accountable, designers and manufacturers constantly need rethink and improve methods of packaging.

• Journal of Navigation and Port Research
• /
• v.30 no.6 s.112
• /
• pp.427-432
• /
• 2006

The purpose of the present study was to investigate the effect of mariner's situation awareness(SA) training on navigation performance using a full mission ship-handling simulator. For this purpose, the mariners were trained in terms of various aspects of SA. Independent variables such as risk levels of ship-to-ship collision, navigational route types of 'target ship(TS)', and number of ships around the own ship(OS) were systematically varied, and dependent variables of closest point of approach(CPA) between TS and OS, number of collision, types of collision-avoidance strategy were measured The results can be summarized as followings. First, training on mariner's SA appeared to induce improved performances in various aspects of ship handling. Second, mariners in the routine navigation situation where TS had priority following maritime rules seemed to suffer to prepare collision avoidance when the TS altered its route. However, this tendency greatly reduced after the training These results suggest the benefit of mariner's SA training on maritime safety.

• Journal of Digital Convergence
• /
• v.15 no.10
• /
• pp.151-160
• /
• 2017

Giving behavior can be defined to be a behavior intended to benefit the society's charity works and public works via sharing one's financial resources. The determinants of giving behavior largely consist of sociodemographic factors, such as the income, age, gender, religion, education level, residential areas, and tax deduction policy, etc. This paper considers the income level, self-esteem, and perceived responsibility toward social welfare, as the major research variables. Statistical results, based on 2014 Korean Welfare Panel data, show that the income level and self-esteem have positive influence on participation intention in charitable giving. However, welfare responsibility has negative impact on participation intention. Second, household income was the only salient, negative factor for giving efforts defined as the amount of donation over income, implying that the higher income brackets are giving less money relative to their income level, than those with lower income level. Contrary to our expectation, self-esteem and welfare responsibility were not statistically significant explanatory variables.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.909-914
• /
• 2024

This study suggests a quantitative evaluation of transfer learning, which is widely used in various AI fields, including image recognition for robot vision. Quantitative and qualitative analyses of results applying transfer learning are presented, but transfer learning itself is not discussed. Therefore, this study proposes a quantitative evaluation of transfer learning itself based on MNIST, a handwritten digit database. For the reference network, the change in recognition accuracy according to the depth of the transfer learning frozen layer and the ratio of transfer learning data and pre-training data is tracked. It is observed that when freezing up to the first layer and the ratio of transfer learning data is more than 3%, the recognition accuracy of more than 90% can be stably maintained. The transfer learning quantitative evaluation method of this study can be used to implement transfer learning optimized according to the network structure and type of data in the future, and will expand the scope of the use of robot vision and image analysis AI in various environments.

• Journal of dental hygiene science
• /
• v.7 no.4
• /
• pp.213-218
• /
• 2007

The purpose of this study was to analyze the effects of dentistry users' perception of concern about oral health on their perception of oral health and behaviors. For this purpose, the researcher sampled the outpatients who had used 2 dentistries in Kangnam, Seoul and another 2 dentistries in Kangbuk, Seoul and a hospital attached to a dental college in Bundang, Kyonggi-do and thereby, conducted a self-administered questionnaire survey from April 4 through 28, 2006. 291 responses from the survey were analyzed using the SPSS 12.0 statistical program. The results of this study can be summarized as follows; 1. 45.0% of the patients perceived that their oral conditions were not healthy, 32% thought normal for their oral conditions and 23% felt healthy for their oral conditions. 2. Less women (44.1%) felt healthy for their oral conditions than men (46.3%). 3. The more negative patients' perception of their oral health was, they were more likely (55.1%) to rely on relatives for choice of a dentistry. 45.0% of this group worried about their oral health always, 15.1% were more or less worried, and 11.9% of them felt that their oral health was good(P < 0.05). 4. 66.0% of the subjects worried about their oral health sometimes, and 27.8% of them worried always, and 6.2% worried little. There was no significant gender difference, but the older they were, they worried more always(P < 0.05). 5. 93.8% of the group who worried about their oral health always had ever had their teeth scaled, and 65.8% of them had regularly had their teeth scaled. Such ratios differed significantly from the group who worried about their oral health sometimes (49.7% and 46.2%, respectively). The three groups differed in terms of regular checks significantly: 56.6%, 45.3% and 33.3%, respectively. And the rate of visiting the dentistry without fail was significantly highest (71.6%) in the first group (P < 0.05).

• Journal of Digital Convergence
• /
• v.10 no.10
• /
• pp.363-372
• /
• 2012

The purpose of this study was to investigate drinking habits of employees and to provide basic descriptive data for effective drinking prevention programs, therapies and rehabilitation services for the health improvement of employees. Data were collected from 500 employees living in Gangwondo, from June 12 to August 25, 2010. The collected data were analyzed by the SPSS 10.1 program. The mean score of positive views on alcohol was 2.93 and the mean score of negative views on alcohol was 3.18. Among alcohol abuse people who answered 'yes' on more than 2 variables out of 4 CAGE variables were 25.1% of the subjects. Problem drinkers with more than 8 points from AUDIT accounted for 64.8% of the subjects. The most common disease due to alcohol drinking was gastrointestinal tract disease. The result of this study suggests that it is necessary to maintain the atmosphere to improve drinking culture and to develop for drinking preventive educations and implementations for employees in farming and fishing communities.