Sungwon Jung
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sungwon Jung has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Jaewook Lee
Sejong Univ
4 shared publications - Eun Joo Park
Sungkyunkwan University – Natural Sciences Campus Department of Architecture
3 shared publications Jaewook Lee
3 shared publicationsSeung Wan Hong
3 shared publications- Yong-Wook Jeong
Department of Architecture, Sejong University, 209, Neungdong-ro, Gwangjin-gu, Seoul 05006, Korea
3 shared publications Yoonseok Hwang
2 shared publications
Latest Publications
- 27 March 2026
- Published by Emerald Publishing in Open House International
- Vol. 51 (4) , 1-21
The role of urban environment maintenance in crime prevention: a machine learning analysis of street crime in Manhattan
Purpose: Urban environment maintenance is a critical component of Crime Prevention Through Environmental Design (CPTED), yet its direct impact on crime reduction remains underexplored. Grounded in the Broken Windows Theory, this study investigates the relationship between urban maintenance factors and street crime in Manhattan, New York City. Design/methodology/approach: This research employs a machine learning approach to analyze crime occurrences in relation to urban maintenance indicators. Using a grid-based spatial analysis (250 × 250 meters), we assess over 18,000 citizen-reported complaints from the 311 system spanning five years. Ensemble learning models, including Random Forest and XGBoost, were applied to predict crime occurrence, with SHAP (SHapley Additive exPlanations) analysis used to interpret feature importance. Findings: The results reveal that environmental maintenance factors influencing crime vary significantly depending on local urban conditions. In high-crime areas, specific factors such as illegal parking, homeless presence, and abandoned vehicles exhibit stronger associations with crime rates, whereas noise and sanitation concerns play a more prominent role in low-crime areas. These findings suggest that crime prevention strategies should incorporate region-specific maintenance interventions rather than a one-size-fits-all approach. Originality/value: This study advances the understanding of urban crime prevention by integrating machine learning-based predictive modeling with spatial environmental analysis. By identifying key maintenance factors contributing to crime variations at a granular level, the research provides actionable insights for policymakers, urban planners, and law enforcement agencies seeking to enhance urban safety through targeted environmental management.
- 27 March 2026
- Published by Emerald Publishing in Open House International
- Vol. 51 (4) , 1-21
The role of urban environment maintenance in crime prevention: a machine learning analysis of street crime in Manhattan
Purpose: Urban environment maintenance is a critical component of Crime Prevention Through Environmental Design (CPTED), yet its direct impact on crime reduction remains underexplored. Grounded in the Broken Windows Theory, this study investigates the relationship between urban maintenance factors and street crime in Manhattan, New York City. Design/methodology/approach: This research employs a machine learning approach to analyze crime occurrences in relation to urban maintenance indicators. Using a grid-based spatial analysis (250 × 250 meters), we assess over 18,000 citizen-reported complaints from the 311 system spanning five years. Ensemble learning models, including Random Forest and XGBoost, were applied to predict crime occurrence, with SHAP (SHapley Additive exPlanations) analysis used to interpret feature importance. Findings: The results reveal that environmental maintenance factors influencing crime vary significantly depending on local urban conditions. In high-crime areas, specific factors such as illegal parking, homeless presence, and abandoned vehicles exhibit stronger associations with crime rates, whereas noise and sanitation concerns play a more prominent role in low-crime areas. These findings suggest that crime prevention strategies should incorporate region-specific maintenance interventions rather than a one-size-fits-all approach. Originality/value: This study advances the understanding of urban crime prevention by integrating machine learning-based predictive modeling with spatial environmental analysis. By identifying key maintenance factors contributing to crime variations at a granular level, the research provides actionable insights for policymakers, urban planners, and law enforcement agencies seeking to enhance urban safety through targeted environmental management.
- 6 March 2026
- Published by Emerald Publishing in Archnet-IJAR: International Journal of Architectural Research
- p. 1-22
Pedestrian volume and street crime: a comparative analysis of tourist and residential areas in Manhattan
Purpose: This study investigates the impact of pedestrian volume on street crime by distinguishing between tourist-visited and residential areas using the distribution of tourist points of interest (POIs). It empirically assesses how this spatial classification moderates the pedestrian activity – crime incidence relationship. Design/methodology/approach: This study used street larceny and violent crime as dependent variables and measured pedestrian volume using Google Street View images processed with the YOLOv8 object detection model. It combined pedestrian and POI data to capture contextual effects, and applied negative binomial regression models. Findings: Pedestrian volume was positively associated with both dependent variables. For larceny, the relationship was consistently linear across residential and tourist-visited areas. However, for violent crime, the effect was nonlinear: beyond a certain threshold, increased pedestrian flows were linked to a slower rate of increase in crime. This attenuation of the marginal effect was stronger in residential neighborhoods than in tourist-visited areas, highlighting the role of social composition and community ties in shaping crime outcomes. Practical implications: The study recommends tailoring Crime Prevention Through Environmental Design strategies to both spatial context and crime type, as tourist-visited areas and residential neighborhoods exhibit distinct pedestrian–crime dynamics. Originality/value: Rather than directly identifying pedestrians’ social attributes, this study extends the literature by incorporating the spatial context of tourist concentration into empirical crime analysis. By using tourism POIs as a proxy to estimate tourist presence, it provides a practical approach to explore whether and how pedestrian–crime dynamics vary by urban setting.
- 6 March 2026
- Published by Emerald Publishing in Archnet-IJAR: International Journal of Architectural Research
- p. 1-22
Pedestrian volume and street crime: a comparative analysis of tourist and residential areas in Manhattan
Purpose: This study investigates the impact of pedestrian volume on street crime by distinguishing between tourist-visited and residential areas using the distribution of tourist points of interest (POIs). It empirically assesses how this spatial classification moderates the pedestrian activity – crime incidence relationship. Design/methodology/approach: This study used street larceny and violent crime as dependent variables and measured pedestrian volume using Google Street View images processed with the YOLOv8 object detection model. It combined pedestrian and POI data to capture contextual effects, and applied negative binomial regression models. Findings: Pedestrian volume was positively associated with both dependent variables. For larceny, the relationship was consistently linear across residential and tourist-visited areas. However, for violent crime, the effect was nonlinear: beyond a certain threshold, increased pedestrian flows were linked to a slower rate of increase in crime. This attenuation of the marginal effect was stronger in residential neighborhoods than in tourist-visited areas, highlighting the role of social composition and community ties in shaping crime outcomes. Practical implications: The study recommends tailoring Crime Prevention Through Environmental Design strategies to both spatial context and crime type, as tourist-visited areas and residential neighborhoods exhibit distinct pedestrian–crime dynamics. Originality/value: Rather than directly identifying pedestrians’ social attributes, this study extends the literature by incorporating the spatial context of tourist concentration into empirical crime analysis. By using tourism POIs as a proxy to estimate tourist presence, it provides a practical approach to explore whether and how pedestrian–crime dynamics vary by urban setting.
- 28 February 2024
- Published by Emerald Publishing in Archnet-IJAR: International Journal of Architectural Research
- Vol. 19 (1) , 66-84
Predicting and analysing initiator crime environments based on machine learning for improving urban safety
Purpose: Initiator crimes, also known as near-repeat crimes, occur in places with known risk factors and vulnerabilities based on prior crime-related experiences or information. Consequently, the environment in which initiator crimes occur might be different from more general crime environments. This study aimed to analyse the differences between the environments of initiator crimes and general crimes, confirming the need for predicting initiator crimes.Design/methodology/approach: We compared predictive models using data corresponding to initiator crimes and all residential burglaries without considering repetitive crime patterns as dependent variables. Using random forest and gradient boosting, representative ensemble models and predictive models were compared utilising various environmental factor data. Subsequently, we evaluated the performance of each predictive model to derive feature importance and partial dependence based on a highly predictive model.Findings: By analysing environmental factors affecting overall residential burglary and initiator crimes, we observed notable differences in high-importance variables. Further analysis of the partial dependence of total residential burglary and initiator crimes based on these variables revealed distinct impacts on each crime. Moreover, initiator crimes took place in environments consistent with well-known theories in the field of environmental criminology.Originality/value: Our findings indicate the possibility that results that do not appear through the existing theft crime prediction method will be identified in the initiator crime prediction model. Emphasising the importance of investigating the environments in which initiator crimes occur, this study underscores the potential of artificial intelligence (AI)-based approaches in creating a safe urban environment. By effectively preventing potential crimes, AI-driven prediction of initiator crimes can significantly contribute to enhancing urban safety.
- 28 February 2024
- Published by Emerald Publishing in Archnet-IJAR: International Journal of Architectural Research
- Vol. 19 (1) , 66-84
Predicting and analysing initiator crime environments based on machine learning for improving urban safety
Purpose: Initiator crimes, also known as near-repeat crimes, occur in places with known risk factors and vulnerabilities based on prior crime-related experiences or information. Consequently, the environment in which initiator crimes occur might be different from more general crime environments. This study aimed to analyse the differences between the environments of initiator crimes and general crimes, confirming the need for predicting initiator crimes.Design/methodology/approach: We compared predictive models using data corresponding to initiator crimes and all residential burglaries without considering repetitive crime patterns as dependent variables. Using random forest and gradient boosting, representative ensemble models and predictive models were compared utilising various environmental factor data. Subsequently, we evaluated the performance of each predictive model to derive feature importance and partial dependence based on a highly predictive model.Findings: By analysing environmental factors affecting overall residential burglary and initiator crimes, we observed notable differences in high-importance variables. Further analysis of the partial dependence of total residential burglary and initiator crimes based on these variables revealed distinct impacts on each crime. Moreover, initiator crimes took place in environments consistent with well-known theories in the field of environmental criminology.Originality/value: Our findings indicate the possibility that results that do not appear through the existing theft crime prediction method will be identified in the initiator crime prediction model. Emphasising the importance of investigating the environments in which initiator crimes occur, this study underscores the potential of artificial intelligence (AI)-based approaches in creating a safe urban environment. By effectively preventing potential crimes, AI-driven prediction of initiator crimes can significantly contribute to enhancing urban safety.
- 30 September 2021
- Published by Korean Institute of Information Scientists and Engineers in Journal of KIISE
- Vol. 48 (9) , 1052-1060
An Efficient Document Clustering Method using Space Transformation based on LDA and WMD
기존의 TF-IDF 기반의 문서 클러스터링 기법은 문서의 문맥 정보인 co-occurrence와 word-order에 대한 정보를 충분히 활용하지 못하고, “차원의 저주”로 인해 성능이 저하되는 문제가 있다. 이를 극복하기 위해서 워드 임베딩 벡터를 가중 평균을 하거나, Word Mover‘s Distance(WMD)를 사용한 기법들이 제안되었는데 제안된 기법들은 문서 간 분류에서는 좋은 성능을 보이지만, 문서 집단을 파악해야 하는 문서 클러스터링 에서는 좋은 성능을 보이지 못했다. 따라서 본 연구에서는 LDA를 활용하여 문서집단을 집단의 대표 문서인 토픽 문서로 새롭게 정의하여 토픽 문서를 기반으로 WMD를 계산하는 것으로 기존 문제를 해결한다. 하지만 WMD가 많은 계산량을 필요로 하기 때문에, 이를 해결하기 위해 각 문서를 토픽 문서와의 WMD값을 축으로 하는 저차원 공간으로 매핑하는 하는 것으로 계산량을 줄이면서 충분한 성능을 보이는 공간 변환 기법을 제시한다.
- 30 September 2021
- Published by Korean Institute of Information Scientists and Engineers in Journal of KIISE
- Vol. 48 (9) , 1052-1060
An Efficient Document Clustering Method using Space Transformation based on LDA and WMD
기존의 TF-IDF 기반의 문서 클러스터링 기법은 문서의 문맥 정보인 co-occurrence와 word-order에 대한 정보를 충분히 활용하지 못하고, “차원의 저주”로 인해 성능이 저하되는 문제가 있다. 이를 극복하기 위해서 워드 임베딩 벡터를 가중 평균을 하거나, Word Mover‘s Distance(WMD)를 사용한 기법들이 제안되었는데 제안된 기법들은 문서 간 분류에서는 좋은 성능을 보이지만, 문서 집단을 파악해야 하는 문서 클러스터링 에서는 좋은 성능을 보이지 못했다. 따라서 본 연구에서는 LDA를 활용하여 문서집단을 집단의 대표 문서인 토픽 문서로 새롭게 정의하여 토픽 문서를 기반으로 WMD를 계산하는 것으로 기존 문제를 해결한다. 하지만 WMD가 많은 계산량을 필요로 하기 때문에, 이를 해결하기 위해 각 문서를 토픽 문서와의 WMD값을 축으로 하는 저차원 공간으로 매핑하는 하는 것으로 계산량을 줄이면서 충분한 성능을 보이는 공간 변환 기법을 제시한다.
- Open Access
- 10 July 2021
- Published by MDPI AG in Sustainability
- Vol. 13 (14) , 7715
Theft Prediction Model Based on Spatial Clustering to Reflect Spatial Characteristics of Adjacent Lands
Previous studies have shown that when a crime occurs, the risk of crime in adjacent areas increases. To reflect this, previous grid-based crime prediction studies combined all the cells surrounding the event location to be predicted for use in model training. However, the actual land is continuous rather than a set of independent cells as in a geographic information system. Because the patterns that occur according to the detailed method of crime vary, it is necessary to reflect the spatial characteristics of the adjacent land in crime prediction. In this study, cells with similar spatial characteristics were classified using the Max-p region model (a spatial clustering technique), and the performance was compared to the existing method using random forest (a tree-based machine learning model). According to the results, the F1 score of the model using spatial clustering increased by approximately 2%. Accordingly, there are differences in the physical environmental factors influenced by the detailed method of crime. The findings reveal that crime involving the same offender is likely to occur around the area of the original crime, indicating that a repeated crime is likely in areas with similar spatial features to the area where the crime occurred.
- 10 July 2021
- Published by MDPI AG in Sustainability
- Vol. 13 (14) , 7715
Open AccessTheft Prediction Model Based on Spatial Clustering to Reflect Spatial Characteristics of Adjacent Lands
Previous studies have shown that when a crime occurs, the risk of crime in adjacent areas increases. To reflect this, previous grid-based crime prediction studies combined all the cells surrounding the event location to be predicted for use in model training. However, the actual land is continuous rather than a set of independent cells as in a geographic information system. Because the patterns that occur according to the detailed method of crime vary, it is necessary to reflect the spatial characteristics of the adjacent land in crime prediction. In this study, cells with similar spatial characteristics were classified using the Max-p region model (a spatial clustering technique), and the performance was compared to the existing method using random forest (a tree-based machine learning model). According to the results, the F1 score of the model using spatial clustering increased by approximately 2%. Accordingly, there are differences in the physical environmental factors influenced by the detailed method of crime. The findings reveal that crime involving the same offender is likely to occur around the area of the original crime, indicating that a repeated crime is likely in areas with similar spatial features to the area where the crime occurred.
- Open Access
- 22 February 2021
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 10 (2) , 99
Artificial Neural Network Model Development to Predict Theft Types in Consideration of Environmental Factors
Crime prediction research using AI has been actively conducted to predict potential crimes—generally, crime locations or time series flows. It is possible to predict these potential crimes in detail if crime characteristics, such as detailed techniques, targets, and environmental factors affecting the crime’s occurrence, are considered simultaneously. Therefore, this study aims to categorize theft by performing k-modes clustering using crime-related characteristics as variables and to propose an ANN model that predicts the derived categorizations. As the prediction of theft types allows people to estimate the features of the possibly most frequent thefts in random areas in advance, it enables the efficient deployment of police and the most appropriate tactical measures. Dongjak District was selected as the target area for analysis; thefts in the district showed four types of clusters. Environmental factors, representative elements affecting theft occurrence, were used as input data for a prediction model, while the factors affecting each cluster were derived through multiple linear regression analysis. Based on the results, input variables were selected for the ANN model training per cluster, and the model was implemented to predict theft type based on environmental factors. This study is significant for providing diversity to prediction methods using ANN.
- 22 February 2021
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 10 (2) , 99
Open AccessArtificial Neural Network Model Development to Predict Theft Types in Consideration of Environmental Factors
Crime prediction research using AI has been actively conducted to predict potential crimes—generally, crime locations or time series flows. It is possible to predict these potential crimes in detail if crime characteristics, such as detailed techniques, targets, and environmental factors affecting the crime’s occurrence, are considered simultaneously. Therefore, this study aims to categorize theft by performing k-modes clustering using crime-related characteristics as variables and to propose an ANN model that predicts the derived categorizations. As the prediction of theft types allows people to estimate the features of the possibly most frequent thefts in random areas in advance, it enables the efficient deployment of police and the most appropriate tactical measures. Dongjak District was selected as the target area for analysis; thefts in the district showed four types of clusters. Environmental factors, representative elements affecting theft occurrence, were used as input data for a prediction model, while the factors affecting each cluster were derived through multiple linear regression analysis. Based on the results, input variables were selected for the ANN model training per cluster, and the model was implemented to predict theft type based on environmental factors. This study is significant for providing diversity to prediction methods using ANN.
- 1 October 2020
- Published by Elsevier in Automation in Construction
- Vol. 118
Performance evaluation of building designs with BIM-based spatial patterns
- 1 October 2020
- Published by Elsevier in Automation in Construction
- Vol. 118
Performance evaluation of building designs with BIM-based spatial patterns
- Open Access
- 9 September 2020
- Published by MDPI AG in Sustainability
- Vol. 12 (18) , 7419
Using Eye-Tracking Technology to Measure Environmental Factors Affecting Street Robbery Decision-Making in Virtual Environments
There is a lack of quantitative data regarding how offenders make decisions about committing a crime or how situational factors influence such decisions. Detailed crime data on decision-making among criminals are required to improve the accuracy of research. Demonstrating a new methodology for assessing the factors impacting criminal decision-making among street robbery offenders, this study identifies visual data that influence criminal decision-making, and verifies the significance of the measured data. To this end, this study first identified and organized the physical aspects affecting criminal decision-making based on the Crime Prevention Through Environmental Design (CPTED) literature. Next, participants were informed of a street crime scenario and asked to replicate the behaviors of criminals in the virtual environment of Grand Theft Auto 5. Factors affecting criminals’ decision-making were then quantitatively assessed using eye-tracking technology. Multivariate logistic regression analysis was used to verify the significance of the measured data. Results show that windows placed adjacent to the street, balconies and verandas, and signs indicating territoriality have a significant effect on criminals’ decision-making. Confirming the influence of CPTED factors on the occurrence of street robbery, this study advances a new way of acquiring quantitative data through eye-tracker technology, a method hitherto unexplored by existing research on street robbery.
- 9 September 2020
- Published by MDPI AG in Sustainability
- Vol. 12 (18) , 7419
Open AccessUsing Eye-Tracking Technology to Measure Environmental Factors Affecting Street Robbery Decision-Making in Virtual Environments
There is a lack of quantitative data regarding how offenders make decisions about committing a crime or how situational factors influence such decisions. Detailed crime data on decision-making among criminals are required to improve the accuracy of research. Demonstrating a new methodology for assessing the factors impacting criminal decision-making among street robbery offenders, this study identifies visual data that influence criminal decision-making, and verifies the significance of the measured data. To this end, this study first identified and organized the physical aspects affecting criminal decision-making based on the Crime Prevention Through Environmental Design (CPTED) literature. Next, participants were informed of a street crime scenario and asked to replicate the behaviors of criminals in the virtual environment of Grand Theft Auto 5. Factors affecting criminals’ decision-making were then quantitatively assessed using eye-tracking technology. Multivariate logistic regression analysis was used to verify the significance of the measured data. Results show that windows placed adjacent to the street, balconies and verandas, and signs indicating territoriality have a significant effect on criminals’ decision-making. Confirming the influence of CPTED factors on the occurrence of street robbery, this study advances a new way of acquiring quantitative data through eye-tracker technology, a method hitherto unexplored by existing research on street robbery.
- Open Access
- 22 December 2019
- Published by MDPI AG in Sustainability
- Vol. 12 (1) , 109
Artificial Neural Network-Based Residential Energy Consumption Prediction Models Considering Residential Building Information and User Features in South Korea
When researching the energy consumption of residential buildings, it is becoming increasingly important to consider how residents use energy. With the advancement of computing power and data analysis techniques, it is now possible to analyze user information using big data techniques. Here, we endeavored to integrate user information with the physical characteristics of residential buildings to analyze how these elements impact energy consumption. Regression analysis was conducted to accurately identify the impact of each element on energy consumption. It was found that six elements were influential in all seasons: the number of exterior walls, housing direction, housing area, number of years occupied, number of household members, and the occupation of the household head. The elements that had an impact in each period were then derived. Based on the results of the regression analysis, input variables for the training of an artificial neural network (ANN) model were selected for each period, and residential energy consumption prediction models were implemented based on actual consumption. The elements identified as those affecting energy consumption, through regression analysis, can be used for implementing prediction models with advanced forms. This study is significant in that we derived influential elements from an integrative perspective.
- 22 December 2019
- Published by MDPI AG in Sustainability
- Vol. 12 (1) , 109
Open AccessArtificial Neural Network-Based Residential Energy Consumption Prediction Models Considering Residential Building Information and User Features in South Korea
When researching the energy consumption of residential buildings, it is becoming increasingly important to consider how residents use energy. With the advancement of computing power and data analysis techniques, it is now possible to analyze user information using big data techniques. Here, we endeavored to integrate user information with the physical characteristics of residential buildings to analyze how these elements impact energy consumption. Regression analysis was conducted to accurately identify the impact of each element on energy consumption. It was found that six elements were influential in all seasons: the number of exterior walls, housing direction, housing area, number of years occupied, number of household members, and the occupation of the household head. The elements that had an impact in each period were then derived. Based on the results of the regression analysis, input variables for the training of an artificial neural network (ANN) model were selected for each period, and residential energy consumption prediction models were implemented based on actual consumption. The elements identified as those affecting energy consumption, through regression analysis, can be used for implementing prediction models with advanced forms. This study is significant in that we derived influential elements from an integrative perspective.
- Open Access
Prediction Model Based on an Artificial Neural Network for User-Based Building Energy Consumption in South Korea
The evaluation of building energy consumption is heavily based on building characteristics and thus often deviates from the true consumption. Consequently, user-based estimation of building energy consumption is necessary because the actual consumption is greatly affected by user characteristics and activities. This work aims to examine the variation in energy consumption as a function of user activities within the same building, and to employ an artificial neural network (ANN) to predict user-based energy consumption. The study exploited the actual 24-h schedules of 5240 single-person households and computed the respective energy consumption using EnergyPlus V 8.8.0 software. The calculated values were clustered according to gender, age, occupation, income, educational level, and occupancy period and the difference among them was analyzed. The simulation results showed that for single-person households in Korea, females used more energy than males did, and the difference increased with age. Furthermore, unemployed and low-income individuals consumed more energy whereas consumption was inversely proportional to the educational level. Energy consumption increased with the occupancy period. Based on the simulation results and six user characteristics, the ANN model indicated a correlation between user characteristics and energy usage. This study analyzed the differences in energy usage depending on user activity and characteristics that affect building energy consumption.
Open AccessPrediction Model Based on an Artificial Neural Network for User-Based Building Energy Consumption in South Korea
The evaluation of building energy consumption is heavily based on building characteristics and thus often deviates from the true consumption. Consequently, user-based estimation of building energy consumption is necessary because the actual consumption is greatly affected by user characteristics and activities. This work aims to examine the variation in energy consumption as a function of user activities within the same building, and to employ an artificial neural network (ANN) to predict user-based energy consumption. The study exploited the actual 24-h schedules of 5240 single-person households and computed the respective energy consumption using EnergyPlus V 8.8.0 software. The calculated values were clustered according to gender, age, occupation, income, educational level, and occupancy period and the difference among them was analyzed. The simulation results showed that for single-person households in Korea, females used more energy than males did, and the difference increased with age. Furthermore, unemployed and low-income individuals consumed more energy whereas consumption was inversely proportional to the educational level. Energy consumption increased with the occupancy period. Based on the simulation results and six user characteristics, the ANN model indicated a correlation between user characteristics and energy usage. This study analyzed the differences in energy usage depending on user activity and characteristics that affect building energy consumption.