Buildings In Areas Research Articles

Estimation of the Hazardous Chemical Leakage Scale Inside Buildings Using CFD

Increased industrialization and aging infrastructure have resulted in leaks of hazardous chemicals, such as CO. Leak modeling is crucial to developing emergency response strategies. Therefore, we simulated the time to criticality (TTC), which is the time to reach the threshold limit for occupational exposure, of a CO leak. The basis of the study is a fire dynamics simulator, a computational fluid dynamics model that was used to investigate the movement of CO in various scenarios, including using different building layouts and areas, temperatures, and leak diameters. Multiple regression analysis was performed to obtain regression equations for the TTC as a function of the independent variables. Ultimately, we found that the type of dispersion varies with respect to the temperature-dependent density of CO, and, among the independent variables, the leak diameter had the strongest effect on the TTC. The regression equations with logarithmic conversion were validated and found to have higher accuracy than those without logarithmic conversion. The findings provide useful information for developing emergency response plans regarding leak size in the case of hazardous chemical leakage. However, empirical studies of different gas types and leakage scenarios are required.

Improving cross-axis wind turbine performance: A Lab-scale investigation of rotor size and blades number

Horizontal and vertical-axis wind turbines have long been used to generate electricity in open areas by utilizing horizontal wind flow. Under certain conditions, for example in multi-storey building areas, wind flows not only from horizontal but also vertical directions. Therefore, this research aims to develop a new turbine model known as a cross-axis to capture wind flow from horizontal and vertical directions around multi-storey buildings. Design, production, testing, and performance analysis are carried out in this project. The model is designed with a rotor diameter of 700 mm which has 5 vertical blades and 10 horizontal blades with a total height of 600 mm which is divided into two configurations, upper and lower. Performance analysis was carried out using a wind tunnel in a conditioned laboratory both in loaded and unloaded conditions. The output power of the wind turbine is measured using an electric dynamometer. The no-load test was applied to determine the time required to move from non-rotating to constant rotation at different speeds and horizontal blade angles. Meanwhile, the load test is used to determine the power coefficient at various speeds, horizontal blade pitch angles, and loads. The research results show that the time required to move from a non-rotating speed to a constant speed is influenced by the wind speed and the blade pitch angle. The power coefficient was also observed to be influenced by wind speed, blade pitch angle, and load. Furthermore, the shortest time to reach a constant rotation speed is around 20 seconds at a wind speed of 7.6 m/s and a blade pitch angle of 25°. The maximum power coefficient of the wind turbine was obtained at 5.2% at a wind speed of 7.6 m/s, blade pitch angle of 25°, and tip speed ratio of 0.5.

Indoor Air Quality and Personnel Satisfaction in Different Functional Areas of Semi-Underground Buildings

Indoor Air Quality and Personnel Satisfaction in Different Functional Areas of Semi-Underground Buildings

Refining urban morphology: An explainable machine learning method for estimating footprint-level building height

Fine-grained 3D buildings with diverse morphology are a cornerstone of urban physical structures and have profound implications for sustainable city development. However, accurately estimating building height at the footprint-level is a challenge. This study bridged this gap by using random forest models to integrate the elevation, geometry and shape attributes of individual buildings, further refining those with spatial aggregation. It considered over one million buildings across 10 large Chinese cities and trained two-types models that demonstrated commendable performance in city-specific (the mean absolute error (MAE) ranged from 3.43 m to 5.06 m) and combined (MAE = 4.68 m) models. Results revealed that the current dataset had a finer urban morphology compared with existing datasets and showed outstanding generalisability in method transfer and feature ablation tests. By incorporating Shapley values, we explored the features' global and local impacts. The explainable results demonstrated that building area was the most impactful feature, and the elevation-dimension features were particularly beneficial in estimating high-rise buildings. Using the fine-grained 3D buildings, we explored the connections between explicit morphology differences and implicit contexts in cities. Overall, our work is an endeavour to estimate footprint-level building height as fuel for refining urban morphology and enabling sustainable city studies.

Psychological Effects of a Living Wall System on Office Occupants: A Comparative Study Based on Physiological Responses

A Living wall system (LWS) is a biophilic design element that has been introduced into indoor environments in recent years. Previous studies have demonstrated that the LWS improves indoor visual comfort and air quality. However, studies on its psychological effects on occupants are still scarce. In this paper, the psychological effects were investigated by recording and analyzing the parameters of occupants’ physiological responses including an electroencephalogram (EEG) and heart rate variability (HRV). A cross-over experiment was conducted among 43 participants under three different desk work environments based on various materials involving an LWS, a fake LWS, and a bare white wall. The results conclude that LWSs effectively reduce the accumulation speed of negative psychological states caused by desk work to about 1/3, compared with a regular office environment without an LWS. However, occupants tend to be less excited and focused after resting in the LWS environment. Therefore, it is recommended to place LWSs in the rest area rather than close to the desk area in an office building, considering the balance between mental health and work efficiency.

Monitoring and Cause Analysis of Land Subsidence along the Yangtze River Utilizing Time-Series InSAR

Time-series monitoring of the land subsidence in the Yangtze River coastal area is crucial for maintaining river stability and early warning of disasters. This study employed PS-InSAR and SBAS-InSAR techniques to monitor the land subsidence along the Yangtze River in Nanjing, using a total of 42 Sentinel-1A images obtained between April 2015 and November 2021. The accuracy of both methods was compared and validated, while a comprehensive analysis was conducted to ascertain the spatial distribution characteristics and underlying causes of land subsidence. The maximum deviation between the two methods and six leveling point data did not exceed ±5 mm. Within the 5 km buffer zone on either side of the Yangtze River in Nanjing, four subsidence funnels were identified. Analysis of the factors contributing to land subsidence in this area indicates that underground engineering construction and operation, increasing ground building area, and geological condition all have certain correlations to the land subsidence. The results obtained through PS-InSAR and SBAS-InSAR technologies revealed a high degree of consistency in monitoring outcomes, and the latter method exhibited superior monitoring accuracy than the former one in this area. This study holds significant implications for guiding the scientific management of urban geohazards along the Yangtze River.

EVALUATION OF INTERACTIVE SPACES FOR ENHANCED LEARNING IN ARCHITECTURE DEPARTMENT BUILDINGS IN NIGER STATE, NIGERIA

The design studio is still the focal point of curricular programmes in architectural faculties around the world, and it is regarded as the gold standard for architectural design education. However, the architecture studio's primary role in the existing academic framework of architectural education needs to be reconsidered. As a result, a shift to architecture studio design is required to create an environment that delivers an immersive and collaborative feeling of setting for studio users. The job of architecture is to build and develop places that fulfil the demands of architecture users and the usage of spaces by different individuals and groups of people, just as an architecture design studio is considered as a learning environment and usually a location where interactions occur. This study investigates the methodologies and goals of architectural design for open space facilities that relieve stress in learning environments such as those found on university campuses in a compact urban setting. The literature reviews, along with expert input, indicate strategies for integrating sustainability as the foundation for achieving a functional institutional environment structure for Nigerian schools of architecture; thus, this serves as the foundation for the development of a questionnaire to collect relevant data. Improving quality and service delivery through better interactive space organisation. The findings suggest that architects should incorporate sustainable building areas into their theoretical preparation. According to the study, it is critical to set standards for an alternative design approach that is user-centered while also strengthening the training of student architects by creating more interactive spaces.

Carbon emissions path of public buildings based on LEAP model in Changsha city (China)

China is currently the world's top carbon emitter due to the acceleration of urbanization, the rapid growth of energy consumption and the rise in carbon emissions, with the construction industry leading the three energy sectors in terms of emission reduction potential. Among the various sectors, the construction industry holds immense potential for emission reduction, with public buildings playing a crucial role. In China, the expansion of public building spaces is closely linked to the pace of urbanization and contributes to a rising share of total building area. Public buildings, characterized by high energy usage, offer a great opportunity for energy conservation and emission reduction. Changsha is experiencing rapid growth and change, and the city is becoming more industrialized and urbanized, which leads to a prominent contradiction between energy supply and demand. There is also great potential for energy conservation and emission reduction in public buildings. Additionally, Changsha is an important node city in the Yangtze River urban agglomeration and the middle reaches of the Yangtze River Economic Belt. It is a typical area that has hot summer and cold winter, thus Changsha is selected as the research case to examine the carbon emission path of public buildings. The primary influencing factors of carbon emissions of public buildings in Changsha City are determined by using the LMDI factor decomposition method addition model. The scenario analysis method is adopted to set the two energy consumption forecast scenarios, which are the baseline scenario and the green scenario. Based on LEAP model and GREAT framework structure, the LEAP prediction model is constructed to predict the carbon emissions of public buildings in Changsha City from 2021 to 2035. The Baseline scenario indicates that while carbon emissions from public buildings in Changsha continue to rise, they are expected to decline starting in 2030. The peak carbon emission of 34.279 million tons of CO2 is predicted for 2032. In contrast, the Green scenario reveals a significantly slower growth rate in carbon emissions from public buildings, with the peak carbon emission projected to reach 27.054 million tons in 2030. This aligns with China's national goal. The findings of this study support the accuracy of the long-term prediction of the model, and offer recommendations for energy conservation and emission reduction in Changsha. This study also provides an example and certain guidance for other provinces and cities that have similar development models and climate conditions. Pertinent development strategies serve as a point of reference for other typical hot summer and cold winter regions.

Provenance Studies of Natural Stones Used in Historical Buildings of the Peninsula de Barbanza, Galicia, Spain (North-Western Iberia)

Traditionally, the building stones used in the architectural heritage of Galicia (Spain) during the past were mainly extracted from quarries located in the surrounding areas of the historical buildings. Thus, a great variety of monuments were built with the same type of granite but with different degrees of weathering depending on local conditions, geological context (facies), and period of construction. The main purpose of this work is to evaluate the probable origin of the construction materials of six historical buildings on the Barbanza Peninsula, Galicia (Spain), based on the degree of weathering and petrographic-mineralogical characteristics. The evaluation was performed on six different samples of granite according to the geological context in outcrops of places where there are old quarries. We used X-ray fluorescence spectrometry (XRF), X-ray diffraction (XRD), and petrographic microscopy (PM) to attempt to address whether the origin is really local to the Barbanza Peninsula or whether the stone was brought from more distant places, based on our knowledge of the geological context of the study area. Based on the chemical, textural, and mineralogical analyses obtained, the material used for construction has a local origin and comes from small quarries spread over a wide area within the Peninsula itself. Barbanza-type granite is the most abundant within the geological context of the area and also the most used as a construction material. Other types of granites identified are the Confurco Granite and other granitoids of the Noya complex. The Chemical Alteration Index (CIA) shows low to moderate weathering in the granites, fitting petrographic observations. In monuments, samples show higher concentrations of Na and K due to salt crystallization. They show microcracks due to extraction, cutting, and finishing processes and common alteration processes of the main minerals, such as sericitization of plagioclase and chloritization of biotite. This work consists of a multidisciplinary study focused on the geological perspective for the identification and preservation of historic quarries. Knowledge of the original material also presents a unique opportunity for the restoration and/or reconstruction of monuments, which allows for the maintenance of their conceptual and constructive homogeneity.

Computational Fluid Dynamics Simulation of High-Resolution Spatial Distribution of Sensible Heat Fluxes in Building-Congested Area

Urban areas consist of various land cover types, with a high proportion of artificial surfaces among them. This leads to unfavorable thermal environments in urban areas. Continuous research on the thermal environment, specifically on the sensible heat flux (Qh), has been conducted. However, previous research has faced temporal, spatial, and resolution limitations when it comes to detailed analysis of sensible heat flux in urban areas. Therefore, in this study, a computational fluid dynamics (CFD) model combined with the LDAPS and the VUCM was developed to simulate Qh at one-hour intervals over a 1-month period in an urban area with various land cover types. Model validation was performed by comparing it with measurements, confirming the suitability of the model for simulating Qh. The land cover was categorized into five types: building, road, bare land, grassland, and tree areas. Qh exhibited distinct patterns depending on the land cover type. When averaging the Qh distribution over the target period, buildings, roads, and bare land areas showed a predominance of upward Qh values, while grassland and tree areas displayed dominant downward Qh values. Additionally, even within the same land cover types, slight Qh variations were identified based on their surroundings. The averaged Qh value for building areas was the highest at 36.79 W m−2, while that for tree areas was −3.04 W m−2. Moreover, during the target period, the time-averaged Qh showed that building, road, and bare land areas peaked at 14 LST, while grassland and tree areas exhibited very low Qh values. Notably, buildings reached a maximum Qh of 103.30 W m−2 but dropped to a minimum of 1.14 W m−2 at 5 LST.

Prognostication of zones with variable physical and mechanical characteristics of soil massifs

Purpose. The use of geographic information systems, in particular Google Earth Pro and Golden Software Surfer, to predict and visualize changes in the geological structure and create 3D models of built-up areas in the central part of Kyiv. Methodology. The research methodology included several stages and an integrated approach to the analysis of man-made soils in the city of Kyiv. Field studies were carried out with soil sampling in the building area for laboratory analyzes with the degree of concentration of man-made sediments. Modeling and data analysis with the creation of 3D models of man-made soils in the Surfer software package with interpolation of field and laboratory research data into GIS to analyze the distribution of man-made soils. The results of the study were obtained. The results of the study emphasize the importance of an integrated approach to the analysis and management of man-made soils in the urban environment, which contributes to improving the safety and efficiency of construction processes in Kyiv. Based on the collected data, 3D models of man-made soils were created, which made it possible to visualize their distribution and assess the risks associated with construction in dense urban areas. Originality. A methodology for studying the distribution of geotechnogenic soils depending on their concentration has been developed. The dependencies of the distribution of pollution in depth on the building area of the Podilskyi district of Kyiv have been obtained. The use of geographic information systems for forecasting the distribution and volumes of soils with variable physical and mechanical characteristics is proposed. Using Google Earth Pro cellular data and creating a 3D model allows you to analyze the concentration of pollution by man-made soils in an urbanized area. Practical value. The results of the study allow for a better understanding of the geological structure of man-made soils and their impact on the bearing capacity of building foundations. This helps to avoid possible problems with the stability of buildings and increases the safety of building structures. The use of geographic information systems and 3D modeling makes it possible to conveniently and accurately predict the distribution of man-made soils on construction sites, which contributes to the optimization of design solutions and efficient use of resources.

Product Design of Vegetable Floss Made from Kluwih (Artocarpus camansi) Fruit

Abstract Increasing awareness of health risks encourages the development of plant-based products to replace the animal products. One of the popular snack foods is floss made from beef or chicken meat. Vegetable floss is a potential product to develop for vegetarian or kids. This study aims to provide a product design of vegetable floss made from kluwih fruit starts from formulation, characterization, scale up in small scale industry, include factory layout, calculation of cost of goods sold as well as business development model that was suitable for vegetable floss market. Notably, this study aims to make vegetable floss without using garlic or shallots in the seasoning, distinguishing it from the previous research of vegetable floss. Human-Centered Design used to match the product with the consumer’s expectations. The vegetable floss formulation and production process were successfully defined after several iteration. The best results had the characteristics of brown color, fibrous, light, and acceptable tastes. The floss had water, ash, protein, fat and carbohydrate contents of 6.05%; 2.29%; 2.07%; 27.80% and 61.79%, respectively, and organoleptic quality of its color and flavor were in the like category. Small scale production was planned with the capacity of 300 kg kluwih fruits per month using a series of machine for peeling, shredding, seasoning preparation, boiling, mixing, frying, oil draining, and packaging. Factory required a building area of 92.31 m2. The cost of goods sold was set at IDR 32,178.8 for 150 g aluminum foil pouch and IDR 12,534.6 for 50 g plastic jar packaging. Business Model Canvas showed the overall business activity of vegetable floss products. Based on the SWOT analysis and matrix, there were 12 alternative strategies that have an effect on improving the element of key partners, key activities, value propositions, customer relationship, customer segments, channels, and revenue streams.

Wayfinding Analysis for Evacuation Optimization with Urban Network Analysis in Disaster Preparedness School KB TK Masjid Syuhada

The existence of evacuation routes is one of the most important elements in disaster management because it will determine the smoothness of the rescue process during a disaster. An evacuation route is a route to an assembly point or exit that is assumed to be a safe space. Wayfinding is the process of moving from one point to another within the closest or fastest distance. In relation to the evacuation process, wayfinding will show the movement from a point, which in relation to buildings can be a specific space, to an exit or assembly point. As one of the disaster preparedness schools in Yogyakarta's Special Region, Masjid Syuhada Kindergarten was chosen as the site of the research. It is a complex of schools ranging from playgroup, kindergarten, elementary school, to junior high school, all of which are connected by the Syuhada Mosque. The analysis of evacuation routes in the kindergarten was conducted using Urban Network Analysis (UNA). UNA is used as a method to determine the effectiveness of providing evacuation routes in a building area because it can analyze trips between points, called origin and destination. Of the various analyses that UNA can perform, this research uses the closest facility analysis. In this study, the origins were all the class in the kindergarten which placed at the door as the open access and in the middle of the class if the class have two doors; while the destinations were the stairs which heading to assembly point. The conclusion is reached after analyzing the network that connects the origin of the class to the destination of the stairs, which is connected to the assembly point.

PROPOSALS FOR THE LOCATION OF SOCIAL PROTECTION INSTITUTIONS FOR THE ELDERLY IN THE URBAN ENVIRONMENT

The article discusses the design of social protection institutions in China, their main urban planning directions, which must be based on the current state regulations of the PRC, as well as the DBN (State Building Norms) of Ukraine mentioned in the article. The urban placement of social protection institutions is subordinate to the strategy for the development of the spatial system of settlements. This system of state-guaranteed economic, social, and legal measures provides elderly people with opportunities to overcome the limitations of life activities by creating specialized institutions where inclusive spaces are formed. Defined approaches to the urban placement of these institutions within the city structure include locations in green zones of central city parts, suburbs, and recreational areas of towns and rural settlements. The placement, capacity, and sizes of land plots for social protection institutions must be determined based on the design task, taking into account the requirements of such Ukrainian regulatory acts as: DBN B 2.2-12:2018; DBN B. 2.2-5:2011; DBN V.1.1-7:2016; DBN B 2.3-18:2007; DBN V. 2.2-9: 2018; DBN V. 2.2-16: 2007; DBN V. 2.2-40:2018; DBN V. 2.2 - 10: 2022; DBN V.2.2 -13: 2003; DBN V. 2.2 -16-2018; DBN V. 2.2 - 25: 2009; DBN V.2.2- 11:2002. The location of social protection institutions depends on the chosen development plot because these facilities require adjacent areas to have natural greening, which will facilitate the conduct of rehabilitation and rehabilitation processes within these institutions. The area of green plantings, which will include lawns, flower beds, fruit gardens, and vegetable gardens, must constitute no less than 50% of the plot area of the social protection institution building.

Assessment of the Potential for Increasing the Energy Efficiency in the Cooling Sector

Cooling supply to ensure the indoor microclimate is becoming more important as global average air temperatures rise. With growing societal demands for higher thermal comfort and increasing individual cooling solutions in the building sector, global energy consumption for cooling is increasing accordingly. Scientific literature and studies estimate that the demand for cooling energy will have a significant impact on global energy demand in the future. In compliance with the European Union goal of achieving climate neutrality by 2050, it is essential to find solutions for reducing energy consumption in the building sector, which is already among the largest energy consumers and greenhouse gas emission producers. Replacing individual cooling solutions with district cooling in urban areas where higher energy density can be reached is one of the solutions for decarbonizing the building sector. To spatially assess the feasibility of district cooling in certain areas, energy demand mapping can be performed. Within this research mapping is carried out using a geographical information system (GIS) tool. The purpose of the mapping is to identify the places in the city of Riga with the highest district cooling potential. Spatial assessment using a GIS tool can be done in different ways – mostly it depends on the available data. The spatial data (buildings) of the cadastral information system and additional detailed information about buildings were obtained from the Latvian open data portal. Information on the type of use of the building, indoor area and the age of building was attached to each building on the map. Then building energy certificate data containing information on specific energy consumption for cooling (kWh/m2 per year) was obtained from the same portal. By processing the data of energy certificates of buildings, excluding outliers, a specific index was obtained for different types of buildings. For the residential sector, the age of the building is also used. Using cadastral data on the indoor area of buildings and the type of building use, the theoretical cooling demand in Riga is calculated and results are quantified and displayed visually. By visualizing the results with the GIS tool, hot spots with the highest cooling energy demand were detected. Results can be further used to calculate the technical and economic justification for the district cooling solutions in specific areas as well as assess the energy efficiency that would be provided by implementation of district cooling solutions.

Impact and implementation of UNESCO’s Recommendation on Open Educational Resources in academic libraries: SPARC Europe Case Study

This paper analyses the role of libraries in the development of Open Educational Resources (OER) and, more specifically, the impact and level of implementation of UNESCO’s (2019) OER Recommendation in Higher Education libraries. This study, the result of a joint undertaking between a national R&D project and SPARC Europe, is based on an online survey, disseminated amongst the European Network of Open Education Librarians (ENOEL) and uses a descriptive research methodology. The results highlight the implementation actions being taken by university libraries (n = 136) in each of the five areas of action of UNESCO’s Recommendation. We find that the main contributions are being made in the areas of capacity building and Open Education policies, but that considerable work has yet to be done in terms of promoting inclusiveness and the sustainability of OER. Thus, the full implementation of UNESCO’s recommendation requires a greater commitment on the part of librarians to joint actions undertaken via international networks and projects, as well as greater institutional commitment and the building of interdepartmental alliances.

Building Damage Degree Recognition Based on Temporal Attention Features

Natural disasters pose significant harm to society. As an important place for social activities and economic development, the degree of damage to building areas is directly related to disaster loss assessment and emergency rescue. Remote sensing image data, characterized by its wide coverage and multi-temporal features, provides important data support for post-disaster loss assessment. However, imaging differences caused by factors such as shooting time, imaging angle, and different sensors can interfere with the extraction of damage features and loss assessment. This paper proposes a Dual-Exchange-Attention U-Net (DERU-Net) model, which transforms the identification of building damage levels into intra-class semantic change detection. The DFMA feature attention fusion module is introduced to enhance the ability of dual-temporal feature extraction and achieve end-to-end assessment of building damage. The proposed method is comprehensively evaluated and tested on the xBD dataset. Experimental results show that compared with other methods, the DERU-Net proposed in this paper exhibits better stability and evaluation accuracy in assessing the degree of building damage.

Atmospheric deposition of microplastics at a western China metropolis: Relationship with underlying surface types and human exposure

The issue of atmospheric microplastic (AMP) contamination is gaining increasing attention, yet the influencing factors and human exposure are not well-understood. In this study, atmospheric depositions were collected in the megacity of Chengdu, China, to investigate the pollution status and spatial disparities in AMP distribution. The relationship between AMP abundance and underlying surface types was then analyzed with the aid of back trajectory simulation. Additionally, a probabilistic estimation of human exposure to AMP deposition during outdoor picnics was provided, followed by the calculation of AMP loading into rivers. Results revealed that the mean deposition flux ranged within 207.1–364.0 N/m2/d (14.17–33.75 μg/m2/d), with significantly larger AMP abundance and sizes in urban compared to rural areas. Areas of compact buildings played an important role in contributing to both fibrous and non-fibrous AMP contamination from urban to rural areas, providing new insight into potential sources of pollution. This suggests that appropriate plastic waste disposal in compact building areas should be prioritized for controlling AMP pollution. Besides, the median ingestion of deposited AMPs during a single picnic was 34.9 N/capita/hour (3.03 × 10−3 μg/capita/hour) for urban areas and 17.8 N/capita/hour (7.74 × 10−4 μg/capita/hour) for suburbs. Furthermore, the worst-case scenario of AMPs loading into rivers was investigated, which could reach 170.7 kg in summertime Chengdu. This work could contribute to a better understanding of the status of AMP pollution and its sources, as well as the potential human exposure risk.

Impact of Real-Time Blind Slat Angle Control on Reducing Total Energy Consumption of a Library Building Using an Optimized Artificial Neural Network Model: A Case Study of the Six Moroccan Thermal Zones

Abstract The prevalence of extensive glazed areas in contemporary buildings contributes significantly to solar radiation infiltration, elevating energy demands and causing discomfort for occupants. Window shading devices play a pivotal role in addressing this challenge. This paper presents the development and optimization of an artificial neural network (ANN) predictive model, designed to enable real-time control of slat angles by predicting total energy loads, specifically during summer (for cooling and lighting purposes). The refined model demonstrates high precision, achieving a normalized root mean square error (nRMSE) of approximately 1.72% and a correlation coefficient (R) of around 0.999, despite utilizing limited meteorological data. Key inputs for the model include solar radiation, solar altitude, and external temperature, with a particular focus on slat reflectivity. The study assesses the efficiency of three slat types based on their reflectivity: high (80%), medium (50%), and low (20%). Additionally, the research explores the impact of window-to-wall ratio (WWR) values on the control system's efficacy, revealing a positive correlation between higher WWR values and improved energy savings through ANN slat angle control. Furthermore, the study extends the applicability of the ANN model to the six thermal zones in Morocco, affirming its generalization across diverse environmental conditions.

Extracting building outlines based on convolutional neural networks using the property of linear connectivity

Abstract. For years, researchers have been developing an automated method that can replace humans by drawing the outlines of individual buildings in a vector format, which plays an important role in GIS creation, environmental monitoring, urban planning, population density estimation, and energy supply. There is no doubt that this is an extremely difficult task, not only because of the labor required to develop such a highly intelligent algorithm, but also because of the challenges posed by imperfect imaging conditions, different building structures, and the complexity of the background. One of the current challenges in extracting building outlines is to accurately recreate the polygonal boundaries of the building while extracting vectorized building masks as output for direct use in various applications. This work provides a comprehensive workflow for building extraction and improves the predicted area of buildings through boundary regularization. First, a convolutional neural network is used to train instance segmentation model, then regularization and vectorization processes are performed. The main difference from existing methods is a new regularization method based on the concepts of linear connectivity and convexity of a set of points. This approach can effectively identify and remove points that do not belong to the detected building but were incorrectly segmented by the algorithm. Based on the results of experiments, the algorithm showed a high level of efficiency, comparable to leading methods for extracting building boundaries as PolyWorld.