Özge Öztürk Hacar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Özge Öztürk Hacar has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Müslüm Hacar
Yildiz Technical University
3 shared publications - Serdar Bilgi
Department of Geomatics Engineering, Istanbul Technical University, 34469 Istanbul, Türkiye
3 shared publications - Ayse Giz Gulnerman
Ankara Haci Bayram Veli Universitesi
2 shared publications - Fatih Gülgen
Department of Geomatic Engineering, Yildiz Technical University, 34220 İstanbul, Türkiye
2 shared publications - Luca Pappalardo
Institute of Information Science and Technologies (ISTI), National Research Council (CNR), Pisa, Italy
2 shared publications - Birgül Arslanoğlu
Istanbul Technical University
1 shared publication
Latest Publications
- Open Access
- 19 September 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (18) , 9621
Prioritizing Building-Integrated Greenhouse Potential in Accommodation Facilities Using a Spatially Oriented Multi-Criteria Decision Framework: The Case of Istanbul
This study develops a multi-criteria decision-support approach that integrates spatial, functional, and managerial dimensions to assess the suitability potential of accommodation facilities in Istanbul for building-integrated greenhouse applications within the context of sustainable food systems and sustainable tourism. The dataset, comprising 688 lodging facilities affiliated with the Ministry of Culture and Tourism of the Republic of Türkiye, was analyzed in accordance with a hierarchical evaluation framework that includes categories, criteria, and subcriteria. In this context, the distribution of facilities across each criterion was first examined to assess the current situation; subsequently, the criterion weights were determined using the Best–Worst Method (BWM) based on expert opinions, and the Greenhouse Integration Suitability Scores (GISSs) were calculated using the Weighted Linear Cumulative (WLC) method. Facilities were ranked according to their continuous GISSs; under the Jenks Natural Breaks classification, only 13.4% of the sites (92 out of 688) fell into the high and very high classes. The six-dimensional sensitivity analysis showed that facility rankings remained largely stable under different data, weighting, and method scenarios, whereas class boundaries were more sensitive to the classification method used. Spatial statistical analyses revealed that GISS values exhibited significant and positive spatial autocorrelation (Moran’s I = 0.2478, p < 0.001); Beşiktaş, Pendik, and Ümraniye emerged as the top-priority districts. The findings reveal that physical and spatial conditions are the key determinants of greenhouse integration potential, while functional and managerial variables play a significant role in the varying levels of suitability of the facilities. The framework developed extends the assessment of building-integrated greenhouse applications from the individual building scale to the urban scale, offering a transferable decision-support approach for public institutions, planners, and facility managers. In this regard, the study establishes a data-driven and adaptable prioritization tool that can guide decisions on urban food production, sustainable tourism, and investment.
- 19 September 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (18) , 9621
Open AccessPrioritizing Building-Integrated Greenhouse Potential in Accommodation Facilities Using a Spatially Oriented Multi-Criteria Decision Framework: The Case of Istanbul
This study develops a multi-criteria decision-support approach that integrates spatial, functional, and managerial dimensions to assess the suitability potential of accommodation facilities in Istanbul for building-integrated greenhouse applications within the context of sustainable food systems and sustainable tourism. The dataset, comprising 688 lodging facilities affiliated with the Ministry of Culture and Tourism of the Republic of Türkiye, was analyzed in accordance with a hierarchical evaluation framework that includes categories, criteria, and subcriteria. In this context, the distribution of facilities across each criterion was first examined to assess the current situation; subsequently, the criterion weights were determined using the Best–Worst Method (BWM) based on expert opinions, and the Greenhouse Integration Suitability Scores (GISSs) were calculated using the Weighted Linear Cumulative (WLC) method. Facilities were ranked according to their continuous GISSs; under the Jenks Natural Breaks classification, only 13.4% of the sites (92 out of 688) fell into the high and very high classes. The six-dimensional sensitivity analysis showed that facility rankings remained largely stable under different data, weighting, and method scenarios, whereas class boundaries were more sensitive to the classification method used. Spatial statistical analyses revealed that GISS values exhibited significant and positive spatial autocorrelation (Moran’s I = 0.2478, p < 0.001); Beşiktaş, Pendik, and Ümraniye emerged as the top-priority districts. The findings reveal that physical and spatial conditions are the key determinants of greenhouse integration potential, while functional and managerial variables play a significant role in the varying levels of suitability of the facilities. The framework developed extends the assessment of building-integrated greenhouse applications from the individual building scale to the urban scale, offering a transferable decision-support approach for public institutions, planners, and facility managers. In this regard, the study establishes a data-driven and adaptable prioritization tool that can guide decisions on urban food production, sustainable tourism, and investment.
- 2 July 2026
- Published by Springer Nature
- p. 365-373
Control Point Detection for Network Alignment Using Large Language Model
- 2 July 2026
- Published by Springer Nature
- p. 365-373
Control Point Detection for Network Alignment Using Large Language Model
- 30 April 2026
- Published by Elsevier in Journal of Transport Geography
- Vol. 134
From sensor counts to OD flows: The N-Step model for urban pedestrian mobility
- 30 April 2026
- Published by Elsevier in Journal of Transport Geography
- Vol. 134
From sensor counts to OD flows: The N-Step model for urban pedestrian mobility
- Open Access
- 25 March 2026
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 15 (4) , 144
LLM-Based Map Conflation: Performance Assessment on Matching Embedded Road Lines
Map conflation is essential for integrating heterogeneous road datasets, but it often requires region- and data-specific algorithm design to automate the complex identification of feature-to-feature correspondences. This effort is increased when only cartographic products are available instead of GIS-ready vectors since both digitization or matching corresponding features manually are labor-intensive. In this study, we assess the performance of a multimodal LLM, GPT-5 “thinking” mode for map conflation directly on a PDF map where road networks from TomTom and OpenStreetMap are embedded as colored polylines. We instruct the LLM to interpret the PDF, extract road geometries and their identifiers, and generate both strict 1:1 and flexible M:N matches. In any hybrid-patterned network cases located around Bosphorus, Istanbul, while M:N matching process increased the number of matches, it also increased false positives and lowered overall F1 scores. In contrast, 1:1 matching produced more balanced correctness-completeness results. The model achieves its highest performance in the cellular-patterned networks. The results show that LLM-based matching can detect a substantial share of true correspondences in such a challenging hybrid setting, but performance clearly depends on the matching strategy: strict or flexible. It highlights both the potential promise and the current limitations of matching embedded road lines.
- 25 March 2026
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 15 (4) , 144
Open AccessLLM-Based Map Conflation: Performance Assessment on Matching Embedded Road Lines
Map conflation is essential for integrating heterogeneous road datasets, but it often requires region- and data-specific algorithm design to automate the complex identification of feature-to-feature correspondences. This effort is increased when only cartographic products are available instead of GIS-ready vectors since both digitization or matching corresponding features manually are labor-intensive. In this study, we assess the performance of a multimodal LLM, GPT-5 “thinking” mode for map conflation directly on a PDF map where road networks from TomTom and OpenStreetMap are embedded as colored polylines. We instruct the LLM to interpret the PDF, extract road geometries and their identifiers, and generate both strict 1:1 and flexible M:N matches. In any hybrid-patterned network cases located around Bosphorus, Istanbul, while M:N matching process increased the number of matches, it also increased false positives and lowered overall F1 scores. In contrast, 1:1 matching produced more balanced correctness-completeness results. The model achieves its highest performance in the cellular-patterned networks. The results show that LLM-based matching can detect a substantial share of true correspondences in such a challenging hybrid setting, but performance clearly depends on the matching strategy: strict or flexible. It highlights both the potential promise and the current limitations of matching embedded road lines.
- Open Access
- 18 January 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (2) , 931
Where We Rate: The Impact of Urban Characteristics on Digital Reviews and Ratings
In urban environments, eating and drinking out (EDO) is a widespread activity among residents and visitors, generating a wealth of digital footprints that reflect consumer experiences. These digital traces provide businesses with opportunities to enhance their services and guide entrepreneurs in selecting optimal locations for new establishments. This study investigates the relationship among urban spatial features, pedestrians and digital consumer interactions at EDO venues. It highlights the utility of integrating urban mobility and spatial data to model digital consumer behavior, offering potential urban planning and business strategies. By analyzing Melbourne’s city center, we evaluate how factors, such as pedestrian count by sensors on the streets, residential density, the centralities and geometric properties of streets, and place-specific characteristics, influence consumer reviews and ratings on Google Maps. The study employs a random forest machine learning model to predict review volumes and ratings, categorized into high and low classes. The results indicate that pedestrian counts and residential density are key predictors for both metrics, while centrality measures improve the prediction of visitor scores but negatively impact review volume predictions. The geometric features of streets play varying roles across different prediction tasks. The model achieved a 65% F1-score for review volume classifications and a 62% for visitor score. These findings not only provide actionable understanding for urban planners and business stakeholders but also contribute to a deeper understanding of how spatial dynamics affect digital consumer behavior, paving the way for more sustainable urban development and data-driven decision-making.
- 18 January 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (2) , 931
Open AccessWhere We Rate: The Impact of Urban Characteristics on Digital Reviews and Ratings
In urban environments, eating and drinking out (EDO) is a widespread activity among residents and visitors, generating a wealth of digital footprints that reflect consumer experiences. These digital traces provide businesses with opportunities to enhance their services and guide entrepreneurs in selecting optimal locations for new establishments. This study investigates the relationship among urban spatial features, pedestrians and digital consumer interactions at EDO venues. It highlights the utility of integrating urban mobility and spatial data to model digital consumer behavior, offering potential urban planning and business strategies. By analyzing Melbourne’s city center, we evaluate how factors, such as pedestrian count by sensors on the streets, residential density, the centralities and geometric properties of streets, and place-specific characteristics, influence consumer reviews and ratings on Google Maps. The study employs a random forest machine learning model to predict review volumes and ratings, categorized into high and low classes. The results indicate that pedestrian counts and residential density are key predictors for both metrics, while centrality measures improve the prediction of visitor scores but negatively impact review volume predictions. The geometric features of streets play varying roles across different prediction tasks. The model achieved a 65% F1-score for review volume classifications and a 62% for visitor score. These findings not only provide actionable understanding for urban planners and business stakeholders but also contribute to a deeper understanding of how spatial dynamics affect digital consumer behavior, paving the way for more sustainable urban development and data-driven decision-making.
- Open Access
- 7 October 2020
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 9 (10) , 589
Evaluation of the Space Syntax Measures Affecting Pedestrian Density through Ordinal Logistic Regression Analysis
This paper examines the relationship between pedestrian density and space syntax measures in a university campus using ordinal logistic regression analysis. The pedestrian density assumed as the dependent variable of regression analysis was categorised in low, medium, and high classes by using Jenks natural break classification. The data elements of groups were derived from pedestrian counts performed in 22 gates 132 times. The counting period grouped in nominal categories was assumed as an independent variable. Another independent was one of the 15 derived measures of axial analysis and visual graphic analysis. The statistically significant model results indicated that the integration of axial analysis was the most reasonable measure that explained the pedestrian density. Then, the changes in integration values of current and master plan datasets were analysed using paired sample t-test. The calculated p-value of t-test proved that the master plan would change the campus morphology for pedestrians.
- 7 October 2020
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 9 (10) , 589
Open AccessEvaluation of the Space Syntax Measures Affecting Pedestrian Density through Ordinal Logistic Regression Analysis
This paper examines the relationship between pedestrian density and space syntax measures in a university campus using ordinal logistic regression analysis. The pedestrian density assumed as the dependent variable of regression analysis was categorised in low, medium, and high classes by using Jenks natural break classification. The data elements of groups were derived from pedestrian counts performed in 22 gates 132 times. The counting period grouped in nominal categories was assumed as an independent variable. Another independent was one of the 15 derived measures of axial analysis and visual graphic analysis. The statistically significant model results indicated that the integration of axial analysis was the most reasonable measure that explained the pedestrian density. Then, the changes in integration values of current and master plan datasets were analysed using paired sample t-test. The calculated p-value of t-test proved that the master plan would change the campus morphology for pedestrians.
- 1 October 2019
- Published by International Journal of Engineering and Geoscience in International Journal of Engineering and Geosciences
- Vol. 4 (3) , 141-148
Complexity measures of sports facilities allocation in urban area by metric entropy and public demand compatibility
Sports has an important role for the health of present societies and the next generations as an element of urban design. Sports facilities have strong effects on the social life in urban areas. The facilities supply the communication between the dynamics of the cities and generate synergy in the city life of people interacting with each other for improvement in their lives. Before the construction of the sports facilities, the planners must evaluate the type and size of them in terms of the population of the whole city and, the population of neighboring settlement areas, which use the facility. Entropy can be used as a criterion for the quantitative measure of spatial information on maps. In the study, the location of the sports facilities in Istanbul are compared by using the entropy as a quantitative criterion. As a result, the success of the location selection for the sports facilities in urban areas are estimated by using the entropy as a component. Metric entropy method and applications were carried out by a case study in the city of Istanbul for defining the spatial distribution of sports facility locations with the posts of people including "sports" and sports-related keywords on social media.
- 1 October 2019
- Published by International Journal of Engineering and Geoscience in International Journal of Engineering and Geosciences
- Vol. 4 (3) , 141-148
Complexity measures of sports facilities allocation in urban area by metric entropy and public demand compatibility
Sports has an important role for the health of present societies and the next generations as an element of urban design. Sports facilities have strong effects on the social life in urban areas. The facilities supply the communication between the dynamics of the cities and generate synergy in the city life of people interacting with each other for improvement in their lives. Before the construction of the sports facilities, the planners must evaluate the type and size of them in terms of the population of the whole city and, the population of neighboring settlement areas, which use the facility. Entropy can be used as a criterion for the quantitative measure of spatial information on maps. In the study, the location of the sports facilities in Istanbul are compared by using the entropy as a quantitative criterion. As a result, the success of the location selection for the sports facilities in urban areas are estimated by using the entropy as a component. Metric entropy method and applications were carried out by a case study in the city of Istanbul for defining the spatial distribution of sports facility locations with the posts of people including "sports" and sports-related keywords on social media.
- 1 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Navigation system for blind, hearing and visually impaired people in ITU Ayazaga campus
Navigation systems for impaired people is one of the recent developed applications for hearing or visually impaired people within the context of the in-door navigation technology that compatible with the smart phones. Loud steps is one of the examples of them. The application serves for guiding hearing and visually impaired people with the help of reading voice features of routing to independently around various places. Offices, homes, schools, hospitals, bus stations, airports, public institutions and other social and sport facilities ...etc. are among these destinations. It has been downloaded and used by 130.000 users including more than 20.000 visually impaired people at various institutions in 11 countries. The first implementation of the loud steps in Istanbul Technical University (ITU) was the Faculty of Civil Engineering in Ayazaga Campus area. Subsequently, the application has been established for another 4 buildings including lecture halls and 3 techno park buildings in campus. During the later stages of this project, the establishment of system will be carried out for the remained 12 faculties and 6 institutes located in the campus area. Moreover, outdoor navigation system also established to the campus to make all indoor system integrated for the benefits of hearing or visually impaired people around the whole 2.500.000 square meters campus area. Therefore, ITU Ayazaga Campus has an integrated indoor and outdoor navigation systems which taking these kind of people from any campus entrances using the outdoor navigation systems and to the any halls, lecturer's offices, laboratories, information desk, toilets, elevators also other emergency facilities such as fire exits or fire-escape stairs...etc. providing voice guidance with also visual navigation.
- 1 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Navigation system for blind, hearing and visually impaired people in ITU Ayazaga campus
Navigation systems for impaired people is one of the recent developed applications for hearing or visually impaired people within the context of the in-door navigation technology that compatible with the smart phones. Loud steps is one of the examples of them. The application serves for guiding hearing and visually impaired people with the help of reading voice features of routing to independently around various places. Offices, homes, schools, hospitals, bus stations, airports, public institutions and other social and sport facilities ...etc. are among these destinations. It has been downloaded and used by 130.000 users including more than 20.000 visually impaired people at various institutions in 11 countries. The first implementation of the loud steps in Istanbul Technical University (ITU) was the Faculty of Civil Engineering in Ayazaga Campus area. Subsequently, the application has been established for another 4 buildings including lecture halls and 3 techno park buildings in campus. During the later stages of this project, the establishment of system will be carried out for the remained 12 faculties and 6 institutes located in the campus area. Moreover, outdoor navigation system also established to the campus to make all indoor system integrated for the benefits of hearing or visually impaired people around the whole 2.500.000 square meters campus area. Therefore, ITU Ayazaga Campus has an integrated indoor and outdoor navigation systems which taking these kind of people from any campus entrances using the outdoor navigation systems and to the any halls, lecturer's offices, laboratories, information desk, toilets, elevators also other emergency facilities such as fire exits or fire-escape stairs...etc. providing voice guidance with also visual navigation.