• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.603-616
• /
• 2023

In this study, machine learning-based clustering and classification of residential noise in apartment buildings was conducted using frequency and temporal characteristics. First, a residential noise source dataset was constructed . The residential noise source dataset was consisted of floor impact, airborne, plumbing and equipment noise, environmental, and construction noise. The clustering of residential noise was performed by K-Means clustering method. For frequency characteristics, L_eq and L_max values were derived for 1/1 and 1/3 octave band for each sound source. For temporal characteristics, Leq values were derived at every 6 ms through sound pressure level analysis for 5 s. The number of k in K-Means clustering method was determined through the silhouette coefficient and elbow method. The clustering of residential noise source by frequency characteristic resulted in three clusters for both L_eq and L_max analysis. Temporal characteristic clustered residential noise source into 9 clusters for L_eq and 11 clusters for L_max. Clustering by frequency characteristic clustered according to the proportion of low frequency band. Then, to utilize the clustering results, the residential noise source was classified using three kinds of machine learning. The results of the residential noise classification showed the highest accuracy and f1-score for data labeled with L_eq values in 1/3 octave bands, and the highest accuracy and f1-score for classifying residential noise sources with an Artificial Neural Network (ANN) model using both frequency and temporal features, with 93 % accuracy and 92 % f1-score.

• Journal of Digital Contents Society
• /
• v.18 no.4
• /
• pp.733-738
• /
• 2017

This study is to find out empirically how the fear of crime is affected by the level of recognition of people. CPTED elements including natural surveillance, access control, utilization enhancement, territoriality securement, etc. Safety of residents could be considered and then increased when we plan, design, and operate a city. In Korea, CPTED is currently being applied to every town. However, it is not systemized and neither efficient, for there are no constraint provisions, and the foreign cases are not specifically customized to the current situation of the country. This study, therefore, aims to find the limits from analyzing related laws and regimes, administrative regulations, and applied cases, and to deduct improvement plans based on examined foreign cases.

• Design Convergence Study
• /
• v.15 no.2
• /
• pp.333-345
• /
• 2016

Recently, an intelligent product in which information and robotic technologies are applied to an existing common product, called a mother product has been developed. In order to develop intelligent products which could be accepted by users, various intelligent product design methods have been introduced considering various interaction aspects or intelligent parts to be made. However, as an intelligent product is originated in a mother product, intelligent product design methods based on product attributes need to be explored. In this study, the impact of intelligent product types by product attributes on users' acceptance was investigated by comparing hedonic intelligent products and utilitarian intelligent products. An experiment was executed with child slippers as a case. As a result, participants evaluated utilitarian intelligent products more positively than hedonic intelligent products. They showed higher purchase intention and willingness to pay toward utilitarian intelligent products than hedonic intelligent products. In the case of child slippers, even though the hedonic attributes could be expected as they are child products, utilitarian attributes were perceived as much more important than hedonic attributes as the child slippers are related to the floor noise which is a severe social problem.

• Management & Information Systems Review
• /
• v.37 no.3
• /
• pp.27-47
• /
• 2018

In this study, we examine how land use zoning affects the land price controlling other variables such as road-facing condition of the land, land form, land age after its development and land size. We employ geographically weighted regression analysis which reflects spatial dependency as methodology with a data sample of land transaction price data of Jangyu, a new town, in Korea. The results of our empirical analysis show that the respective coefficients of traditional regression and geographically weighted regression are not significantly different. However, after calculating Moran's Index with residuals of both OLS and GWR models, we find that Moran's Index of GWR decreases around 26% compared to that of OLS model, thus improving the problem of spatial autoregression of residuals considerably. Unlike our expectation, though, in both traditional regression and geographically weighted regression where residential exclusive area is used as a reference variable, the dummy variable of the residential land for both housing and shops shows a negative sign. This may be because the residential land for both housing and shops is usually located in the level area while the residential exclusive area is located at the foot of a mountain or on a gentle hill where the residents can have good quality air and scenery. Although the utility of the residential land for both housing and shops is higher than its counterpart's since it has higher floor area ratio, amenity which can be explained as high quality of air and scenery in this study seems to have higher impact in purchase of land for housing. On the other hand, land for neighbourhood living facility seems to be valued higher than any other land zonings used in this research since it has much higher floor area ratio than the two land zonings above and can have a building with up to 5 stories constructed on it. With regard to road-facing condition, land buyers seem to prefer land which faces a medium-width road as expected. Land facing a wide-width road may have some disadvantage in that it can be exposed to noise and exhaust gas from cars and that entrance may not be easy due to the high speed traffic of the road. In contrast, land facing a narrow road can be free of noise or fume from cars and have privacy protected while it has some inconvenience in that entrance may be blocked by cars parked in both sides of the narrow road. Finally, land age variable shows a negative sign, which means that the price of land declines over time. This may be because decline of the land price of Jangyu was bigger than that of other regions in Gimhae where Jangyu, a new town, also belong, during the global financial crisis of 2008.