• Smart Media Journal
• /
• v.13 no.1
• /
• pp.24-35
• /
• 2024

The combination of Artificial Intelligence and the Internet of Things (AIoT) has gained significant popularity. Deep neural networks (DNNs) have demonstrated remarkable success in various applications. However, deploying complex AI models on embedded boards can pose challenges due to computational limitations and model complexity. This paper presents an AIoT-based system for smart parking lots using edge devices. Our approach involves developing a detection model and a decision tree for occupancy status classification. Specifically, we utilize YOLOv5 for car license plate (LP) detection by verifying the position of the license plate within the parking space.

• Journal of Digital Convergence
• /
• v.11 no.8
• /
• pp.41-52
• /
• 2013

Recently in Korea, it takes place as a social phenomenon the emergency of small family(1-2 persons). The City-Type Housing is constructed new standards and facilities for them from 2009. P.O.E(Post Occupancy Evaluation) carried out the building for a period of time, making the assessment says. The aims of this study were P.O.E. of the City-Type Housing and its political implications. Four City-Type Housing located Gang-Nam, Gang-Buk in Seoul, surveyed 62 questions and interviewed for City-Type Housing office. As the results revealed transportation issues, confined space, parking space, economic issues. In Gang-Nam resident were more satisfactoried the location, the building status, the construction status, the housing size, maintenance and economical sences 95% confidence level. Thus, it should be improved. the upward limited living space, parking space qualified, defined design technical issues.

• Journal of Broadcast Engineering
• /
• v.22 no.6
• /
• pp.774-784
• /
• 2017

Occupancy sensors installed in buildings and households turn off the light if the space is vacant. Currently PIR (pyroelectric infra-red) motion sensors have been utilized. Recently, the researches using camera sensors have been carried out in order to overcome the demerit of PIR that can not detect static people. If the tradeoff of cost and performance is satisfied, the camera sensors are expected to replace the current PIRs. In this paper, we propose vision sensor-based occupancy detection being composed of tracking, recognition and detection. Our softeware is designed to meet the real-time processing. In experiments, 14.5fps is achieved at 15fps USB input. Also, the detection accuracy reached 82.0%.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.22 no.2
• /
• pp.167-173
• /
• 2016

This study aims to present methodology for determining the appropriate anchorage area through the simulation reproduces the maritime transport environment, and analysis of the adequacy of anchorage applied at Ulsan E anchorage, suggests the formula of anchorage occupancy rater per hour and necessary anchorage area for this purpose. And configured simulation algorithm and modeling using MATLAB program, and applied Ulsan E anchorage, compared anchorage area with anchorage occupancy rate per hour. As a result, E1 necessary anchorage is 1.41 times, E2 necessary anchorage is 0.90 times and E3 necessary anchorage is 0.96 times compared to total anchorage area. If the result of adequacy analysis of anchor area reflect anchorage design criteria, it is determined to be helpful for the safety of the vessel using the anchorage.

• Journal of Korean Society of Transportation
• /
• v.18 no.3
• /
• pp.7-16
• /
• 2000

Traffic congestion has become severe in large metropolitan areas by the travel behavior of employees as the low rate of vehicle occupancy and the high rate of Private auto using. In order to relieve traffic congestion, central and local government plan to implement diverse transportation demand management strategies. The governments want to know what employment types and locations in different metropolitan areas lead to the highest rate of vehicle occupancy and Private auto use. This study suggest that in large metropolitan areas, the employment locations of urban and suburban as well as the employment type of service show low vehicle occupancy. In medium metropolitan sizes. low vehicle occupancies are observed in service employment as well as in the employment locations of CBD. CBD fringe. In small metropolitan areas, a low rate of vehicle occupancy exists in service employment as well as in the employment locations of urban and suburban areas. A high rate of auto use shows not only in basic employment but also in the employment locations of CBD and CBD fringe.

• Journal of Families and Better Life
• /
• v.27 no.5
• /
• pp.77-90
• /
• 2009

The purpose of this study was to investigate the residents' use and occupancy-behavior in the activity areas of the senior nursing facilities, and to provide basic information to establish the appropriate physical elements for planning the activity areas. For the study, the observations in five facilities were conducted for one day, from 10 a.m. to 4 p.m by four researchers. The results of the study are summarized as follows: First, most of the using behaviors in the activity areas were the doing nothing or sleeping. The meals and program services were provided in only one activity area of the floor and it showed that the unit care system was perfunctorily conducted at those facilities. In the representative activity area, its openness was the main physical element influencing the spatial using frequency, while the accessibility and the openness in the sub-activity area were most important. The seating arrangements having comers were helpful for residents' interactions. Second, while facility programs and meals were provided in the specific activity area, there was no residents' occupancy in other activity areas at the same time. There were interactions including residents' conversations and watching/observations in non-designated activity areas such as the nursing stations and near corridors. But the residents' interactions and self-regulations were blocked by absence of territoriality, monotonous spatial compositions and furniture arrangements, insecurity of residents' privacy, wide or narrow areas, and isolated spatial type. Based on the results at the above, basic guidelines for planning the activity areas of senior nursing facilities can be proposed as follows: First, the isolated type and the sight interception should be avoided in representative activity areas. It should be partitioned with couple of areas through the appropriate furniture arrangements, and be prepared semi-private spaces in non-designated areas such as nursing station for the interactions among the residents and the staff. Second, in activity areas for small group, the isolated type is not also good for the residents' accessibility. The residents' privacy should be confirmed through the various spatial compositions, and enough areas need to be sure for the diverse furniture arrangements.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.2
• /
• pp.65-72
• /
• 2011

In this paper, a real-time monocular vision based navigation system is developed for the disabled people, where online background learning and vector field histogram are used for identifying obstacles and recognizing avoidable paths. The proposed system is performed by three steps: obstacle classification, occupancy grid map generation and VFH-based path recommendation. Firstly, the obstacles are discriminated from images by subtracting with background model which is learned in real time. Thereafter, based on the classification results, an occupancy map sized at $32{\times}24$ is produced, each cell of which represents its own risk by 10 gray levels. Finally, the polar histogram is drawn from the occupancy map, then the sectors corresponding to the valley are chosen as safe paths. To assess the effectiveness of the proposed system, it was tested with a variety of obstacles at indoors and outdoors, then it showed the a'ccuracy of 88%. Moreover, it showed the superior performance when comparing with sensor based navigation systems, which proved the feasibility of the proposed system in using assistive devices of disabled people.

• Journal of Ecology and Environment
• /
• v.29 no.4
• /
• pp.331-335
• /
• 2006

We investigated the distribution of three anuran species, Three-striped pond frogs (Rana nigromaculata), Bullfrogs (Rana catesbeiana), and Narrow-mouthed toads (Kaloula borealis), in an administrative district, Haenam Gun, Junnam Province, Korea using volunteer call surveys. Twenty-eight volunteer call surveyors were assigned to each $2{\times}2km^2$ survey plot. Call surveys on whether the species are present or not were conducted for 5 minutes between 30 minutes after sunset and the midnight on rice fields and ponds from 10 April to 28 August in 2005. Depending on species, call surveys were carried out at seven to 28 plots with average 8.4 to 10.7 visits per the plot. We calculated the detection probabilities and occupancy rates of the three species using four models with three covariates: temperature, humidity, and the amount of water at the habitat. The model average detection probabilities of three anuran species of R. nigromaculata, R. catesbeiana, and K. borealis were 0.53, 0.74, and 0.41 respectively, and the site occupancy rates of them were 0.93, 0.94, and 0.86 respectively. Our results indicate that R. nigromaculata, R. catesbeiana, and K. borealis are common in Haenam Gun.

• Journal of Korean Port Research
• /
• v.14 no.2
• /
• pp.175-185
• /
• 2000

Today freeway is experiencing a severe congestion with incoming or outgoing traffic through freeway ramps during the peak periods. Thus, the purpose of this study is to identify the traffic characteristics, analyze the relationships between the traffic characteristics and finally construct the delay predictive models on the rap junctions of freeway with 70mph speed limit. From the traffic analyses, and model construction and verification for delay prediction on the ramp junctions of freeway, the following results were obtained : ⅰ) Traffic flow showed a big difference depending on the time periods. Especially, more traffic flows were concentrated on the freeway junctions in the morning peak period. ⅱ) The occupancy also showed a big difference depending on the time periods, and the downstream occupancy(Od) was especially shown to have a higher explanatory power for the delay predictive model construction on the ramp junctions of freeway. ⅲ) The delay-occupancy curve showed a remarkable shift based on the occupancies observed : O$\_$d/〈9% and O$\_$d/$\geq$9%. Especially, volume and occupancy were shown to be highly explanatory for delay prediction on the ramp junctions of freeway under O$\_$d/$\geq$9%, but lowly for delay prediction on the ramp junctions of freeway under O$\_$d/〈9%. Rather, the driver characteristics or transportation conditions around the freeway were thought to be a little higher explanatory for the delay prediction under O$\_$d/〈9%. ⅳ) Integrated delay predictive models showed a higher explanatory power in the morning peak period, but a lower explanatory power in the non-peak periods.

• Journal of Broadcast Engineering
• /
• v.23 no.2
• /
• pp.274-282
• /
• 2018

Most occupancy sensors installed in buildings, households and so forth are pyroelectric infra-red (PIR) sensors. One of disadvantages is that PIR sensor can not detect the stationary person due to its functionality of detecting the variation of thermal temperature. In order to overcome this problem, the utilization of camera vision sensors has gained interests, where object tracking is used for detecting the stationary persons. However, the object tracking has an inherent problem such as tracking drift. Therefore, the recognition of humans in static trackers is an important task. In this paper, we propose a CNN-based human recognition to determine whether a static tracker contains humans. Experimental results validated that human and non-humans are classified with accuracy of about 88% and that the proposed method can be incorporated into practical vision occupancy sensors.