• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.288-296
• /
• 2021

Automated face recognition in a runtime environment is gaining more and more important in the fields of surveillance and urban security. This is a difficult task keeping in mind the constantly volatile image landscape with varying features and attributes. For a system to be beneficial in industrial settings, it is pertinent that its efficiency isn't compromised when running on roads, intersections, and busy streets. However, recognition in such uncontrolled circumstances is a major problem in real-life applications. In this paper, the main problem of face recognition in which full face is not visible (Occlusion). This is a common occurrence as any person can change his features by wearing a scarf, sunglass or by merely growing a mustache or beard. Such types of discrepancies in facial appearance are frequently stumbled upon in an uncontrolled circumstance and possibly will be a reason to the security systems which are based upon face recognition. These types of variations are very common in a real-life environment. It has been analyzed that it has been studied less in literature but now researchers have a major focus on this type of variation. Existing state-of-the-art techniques suffer from several limitations. Most significant amongst them are low level of usability and poor response time in case of any calamity. In this paper, an improved face recognition system is developed to solve the problem of occlusion known as FRS-OCC. To build the FRS-OCC system, the color and texture features are used and then an incremental learning algorithm (Learn++) to select more informative features. Afterward, the trained stack-based autoencoder (SAE) deep learning algorithm is used to recognize a human face. Overall, the FRS-OCC system is used to introduce such algorithms which enhance the response time to guarantee a benchmark quality of service in any situation. To test and evaluate the performance of the proposed FRS-OCC system, the AR face dataset is utilized. On average, the FRS-OCC system is outperformed and achieved SE of 98.82%, SP of 98.49%, AC of 98.76% and AUC of 0.9995 compared to other state-of-the-art methods. The obtained results indicate that the FRS-OCC system can be used in any surveillance application.

• Journal of Korean Society of Rural Planning
• /
• v.24 no.4
• /
• pp.69-80
• /
• 2018

In this study, we typified the project for revitalizing the rural area through text analysis using news data, and analyzed the main direction and characteristics of the project. In order to examine the factors emphasized among the issues related to the revitalization of rural areas, we used news data related to 'tourism' and 'livelihood', which are the main keyword of the project to promote rural areas. In the analysis, text mining techniques were used. Topic modeling was conducted on LDA techniques for major projects in 'tourism' and 'livelihood' keyword. Based on this, this study typified the projects that are carried out for the activation of rural areas by topic. As a result of the analysis, it was fount that the topics included in the project were distributed in 11 sub-types(Tourism Promotion, Regional Specialization, Local Festival, Development of Regional Scale, Urban and Rural Exchange, Agricultural Support, Community Forest Management, Improve the Settlement Environment, General Welfare Service, Low Class Support, Others). The characteristics of the rural revitalization projects were examined, and it was confirmed that domestic projects were carried out by tourism-oriented projects. To summarize, the government is making projects to revitalize rural areas through related ministries. Within the structure where the project is spreading to the region, a lot of projects are being carried out. It is understood that the tourism and welfare oriented projects are being carried out in the revitalization project of the domestic rural area. Therefore, in order to achieve the goal of rural revitalization, it is believed that it will be effective to carry out a balanced project to improve the settlement environment of the residents.

• Journal of Forest and Environmental Science
• /
• v.37 no.3
• /
• pp.169-192
• /
• 2021

Sacred groves are large areas of virgin or human-modified landscape with a diverse range of species that have been protected by local people for centuries due to cultural, religious beliefs, and taboo that the deities live in them and protect the villagers from various calamities. The present study was carried out for quantitative analysis of diversity, population structure, regeneration and conservation status of tree species in the four 36.86 ha sacred groves of Jhargram district in West Bengal. Tree species composition, population structure and regeneration status were analyzed by randomly establishing of 1 ha subplots within the sacred groves. Density, frequency, basal area, abundance, evenness, and other diversity indices were calculated for adult trees with girth at breast height (GBH) >31 cm. A total of 146 tree species belonging to 116 genera distributed in 44 families from 21 orders were recorded. Pterospermum suberifolium, family Malvaceae showed the highest Species Importance Value Index (SIVI, 21.33) and Fabaceae showed the highest Family Importance Value Index (FIVI, 35.59) values respectively. Individuals are categorised into three groups, seedling, sapling and adult based on girth classes. The majority of tree species exhibited good (52.74%) regeneration followed by fairly (24.66%), poor (15.75%) and no regeneration (6.85%) respectively. With the healthy existence of the sacred grove, the overall population structure of tree species showed a strong regeneration potential. The current data will be useful in determining the current status of tree species and will be used by the forest department, politicians, and conservationists to establish management plans for the conservation of priority species in the region. Since the study areas were sacred groves, tribal members were keen to preserve them due to their religious significance.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.24 no.2
• /
• pp.85-102
• /
• 2021

Phytosociological characteristics on Quercus acutissima forests distribution in Daechong-dam basin survey has been carried out using Z.-M. School's methodology and numerical-classification analyses. A total of 43 phytosociological relevés were sampled. Syntaxa were described as Oplismenus undulatifolius-Quercus acutissima community(typicum subcommunity, Phryma leptostachya var. asiatica subcommunity, Ulmus davidiana var. japonica subcommunity), Quercus acutissima community and Quercus variabilis-Quercus acutissima community (typicum subcommunity, Castanea crenata subcommunity). The above three plant communities were classified with species composition reflecting local environmental characteristics of mountain topographies, inclination degrees, and rock exposure rates. Conclusively, those communities were recognized as secondary vegetation affected by high intensity and frequency of human impacts as they inhabited in southward hill lands and low lying grounds in mountains adjacent to human settlements and arable lands. Quercus acutissima community was classified as rural type syntax based on their inlandward distribution and species composition differences from urban forests. Afforest process and natural succession were discussed in relation with habitat environmental elements of Quercus acutissima forest in the survey area.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.327-335
• /
• 2021

We aimed to find new space types and characteristics for creating gardens in the city through the type of idle space in the city, present guidelines that can be used in creating gardens in the future, and establish basic data for expanding green infrastructure. As a result, we found that the idle space in the city was classified into four types, and it was determined that differentiation should be given to the creation of each type. The achievements of this study can be a potential source of urban ecosystem services that can provide community benefits and opportunities for urban regeneration through the redevelopment of the community and support the health and well-being of local residents. In addition, urban idle space can be a valuable resource as a green infrastructure that can be used to support the health of urban ecosystems and improve the quality of life of urban residents.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.34 no.2
• /
• pp.75-82
• /
• 2018

Green roof in Korea has been recognized as part of landscape area and local governments enacted municipal ordinance for supporting green roof thereby assisting part of expenses spent for green roof within a range of budget for buildings which are eligible for the green roof support of existing buildings. However, it is necessary to enforce a regulation of mandatory green roof for new buildings in order to expand green roof application and provide a variety of assistances such as subsidy payment, tax relief, and mitigation of floor area ratio-related regulation as done in other advanced nations. In particular, LEED(Leadership in Environmental and Energy Design) in the USA applies additional point directly for green roof in terms of the reduction in heat island effects. For example, the following items are beneficial to have additional points: habitat preservation or restoration, external space, rainwater management, reduction in outdoor water usage, minimum energy performance, and optimum energy performance. In addition, the BREEAM(Building Research Establishment Environmental Assessment Method) in the UK specifies green roof as one of assessment items to be complied in terms of diversity of species. As such, LEED and BREEAM reflect direct and indirect effects of green roof on assessment criteria, which suggest a direction to green building certification criteria in Korea where only additional points are given for green roof according to soil depth.

• Journal of Korea Planning Association
• /
• v.54 no.2
• /
• pp.33-45
• /
• 2019

The Legal Floor Area Ratio (L-FAR) has been used as a major urban planning tool for efficient management of land use, landscape, and density. The Developed Floor Area Ratio (D-FAR) in each parcel is realized by such physical and institutional factors as urban tissue, local characteristics, and zoning with the L-FAR. The Achieved Floor Area Ratio (A-FAR), the ratio of the D-FAR to the L-FAR, is the relationship between realized density and the intended/desired outcomes of the regulations. The A-FAR informs the efficiency of L-FAR and its effect on parcels, and is an indicator of the demands of real estate developments under the zoning regulation. This study used detailed data of each parcel's characteristics, including parcel size, road width, and the number of roads bordered by a parcel, to identify the influencing factors on A-FAR. This analysis confirmed that the parcel size has a non-linear negative effect in the residential zone but a linear positive effect on A-FAR in the commercial zone. The width of the parcel's frontage in the commercial zone has a positive effect on the value, while in the residential zone the narrower width has higher A-FAR. In Seoul, the residential zone has higher A-FAR than the commercial zone, which means that the former has a relatively higher development pressure but a lower designated L-FAR. This result reflects that Seoul's residential zone absorbs the demand of commercial uses because of the significant permitting of mixed land use and has high-density residential buildings.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.25 no.3
• /
• pp.17-28
• /
• 2022

We evaluated the effect of CO₂ offsetting by estimating changes in carbon uptake under various forest management scenarios and proposed forest management strategies to achieve carbon neutrality. Paju and Goseong, which have relatively large forest areas but different industrial characteristics, were selected for the study sites. The current state of forest distribution was analyzed using forest type maps and aerial photographs, and the amount of carbon uptake was calculated using the equation presented by the IPCC Guidelines for National Greenhouse Gas Inventories and the national emission/absorption coefficients from the Korea National Greenhouse Gas Inventory Report. As of 2015, the forest carbon absorption in Paju and Goseong was 49,931 t/yr and 94,225 t/yr, respectively, and the annual carbon absorption per unit area was 2.28 t/ha/yr and 2.16 t/ha/yr. Under the forest management scenarios, the annual maximum carbon absorption per unit area is estimated to increase to 5.68 t/ha/yr in Paju and 4.22 t/ha/yr in Goseong, and this absorption would increase further if urban forests were additionally created. Even if the current forests of Paju and Goseong are maintained as they are, emissions from electricity use can be sufficiently offset. However, by applying appropriate forest management strategies, emissions from sectors other than electricity use could be offset. This study can be applied to the establishment of carbon absorption strategies in the forest sector to achieve carbon neutrality.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.25 no.2
• /
• pp.69-84
• /
• 2022

The purpose of this research is to examine the user experience design that effectively exhibits botanical information through a virtual habitat built with 3D modeling and scanning data for the conservatory at Seoul Botanic Park. Seoul Botanic Park's conservatory contains environmental and ecological information on the wide spectrum of diverse plants under twelve cities all over the world. However, the exhibition method, which focuses on maps and information boards, has limitations in delivering diverse plant and habitat information to visitors. Virtual and augmented reality can be used as an effective tool for educating and experiencing the contents of various plant species as it can convey the ecological and environmental conditions of the habitat and local culture at diverse levels. This study experimented with constructing virtual habitats using the Unreal Engine and effectively communicating various botanical information through the interaction. With the introduction of a virtual habitat, we intend to enhance the user experience of park visitors and ultimately explore the possibility of using virtual and augmented reality to convey multi-layered environmental and ecological information of landscape.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.2
• /
• pp.1-13
• /
• 2022

Agrivoltaic facility is the composite system that the solar panel is installed above the farmland, and it enables crop and electricity production simultaneously. Solar panels of the agrivoltaic facilities can block and reduce the amount of solar irradiance arriving at the farmland, but it can help the crop growth by preventing excessive solar irradiance. Therefore, to clarify how the agrivoltaic facilities affect the crop growth, precise solar irradiance distribution under the solar panel should be modeled. In this study, PAR (photosynthetically active radiation), radiation from 400 to 700 nm, which crops usually use to grow, was extracted from the total irradiance and its distribution model under various conditions was developed. Monthly irradiance distributions varied because the elevation of the sun was changed over time, which made the position changed that the local maximum and minimum irradiance appear. The higher panel height did not cause any significant difference in the amount of irradiance reaching below the solar panel, but its distribution became more uniform. Furthermore, the panel angles with the most irradiance arriving below the solar panel were different by month, but its difference was up to 2%p between the irradiance with 30° angle which is usually recommended in Korea. Finally, the interval between panels was adjusted; when the ratio of the length of the panel to the empty space was 1:2, the irradiance of 0.719 times was reached compared to when there was no panel, 0.579 times for 1:1 and 0.442 times for 2:1.