Scalability and Adaptability of Smart Infrastructure Solutions in Baltimore: A Case Study on IoT and AI Integration for Urban Resilience

Soroush Piri

doi:10.20944/preprints202411.1436.v1

Submitted:

18 November 2024

Posted:

19 November 2024

Read the latest preprint version here

Abstract

As urban areas face increasing challenges, integrating smart infrastructure, particularly IoT and AI technologies, has become vital for enhancing resilience. This study focuses on Baltimore as a case study to explore how scalable and adaptable smart infrastructure solutions can address diverse urban needs within a mid-sized U.S. city. Through a comprehensive review of Baltimore’s socioeconomic indicators and the development of a composite resilience score, this paper identifies key factors that facilitate or hinder the scalability and adaptability of smart infrastructure in economically and demographically varied urban contexts. The resilience score provides a quantitative measure of urban resilience, enabling the analysis of trends and dependencies among socioeconomic indicators over time. Findings reveal critical roles for both community engagement and policy support in adapting technologies to local needs, while economic and technical factors influence the scalability of IoT and AI projects. Based on these insights, the study proposes a framework that offers practical guidance for expanding Baltimore’s smart infrastructure in ways that are economically feasible, technically viable, and socially inclusive. This framework aims to assist Baltimore’s policymakers, urban planners, and technologists in advancing resilient, scalable solutions that align with the city's unique infrastructure needs and resource constraints.

Keywords:

Smart Infrastructure

;

Urban Resilience

;

Scalability

;

IoT

;

AI

;

Baltimore

Subject:

Engineering - Civil Engineering

Introduction

Urban areas increasingly face complex challenges in infrastructure management, environmental resilience, and social equity1. Baltimore, Maryland, provides a compelling case study for investigating scalable and adaptable smart infrastructure solutions due to its diverse socioeconomic landscape, historical infrastructure constraints, and ongoing urban development initiatives2. As a mid-sized U.S. city, Baltimore contends with economic disparities that have led to varying levels of infrastructure access and quality across neighborhoods3. These disparities, coupled with aging infrastructure, present significant obstacles for consistent, citywide implementation of IoT and AI technologies. Additionally, Baltimore’s population density, demographic diversity, and concentrated urban areas make it a prime candidate for deploying data-driven solutions that address transportation, public safety, and environmental monitoring4.These factors highlight Baltimore’s need for scalable solutions that can adapt to local variations in economic capacity, technological readiness, and community priorities while fostering urban resilience. Given these challenges, a structured approach is essential to guide the deployment of smart infrastructure solutions. This study adopts a conceptual framework designed to assess both the scalability of IoT and AI technologies and the resilience of urban infrastructure. By introducing this framework early, we can better understand how these technologies can be adapted and integrated into the unique context of Baltimore, addressing both its opportunities and constraints.

The Internet of Things (IoT) refers to interconnected devices that collect and share data in real time5, while Artificial Intelligence (AI) involves algorithms that analyze this data to make predictions or automate decision-making6. IoT devices, such as sensors and connected vehicles, collect real-time data on traffic conditions, which AI algorithms analyze to optimize traffic flow and reduce congestion7. For instance, a study by Telnyx discusses how IoT-enabled traffic monitoring systems gather live data on vehicle counts and pedestrian movements, allowing city planners to make informed decisions to streamline traffic and ease congestion8.

In the UK, AI-powered traffic lights have been trialed to automatically stop cars and allow cyclists to pass during rush hours. Developed by VivaCity, these systems use AI-driven sensors to detect cyclists from up to 30 meters away, changing traffic lights to red for motorists and green for cyclists and pedestrians, thereby enhancing road safety and promoting active travel9. IoT and AI technologies are also instrumental in environmental monitoring, particularly in tracking and mitigating urban pollution10. Smart sensors distributed throughout cities collect data on air quality, which AI systems analyze to identify pollution sources and predict trends. This information enables authorities to implement targeted interventions to improve air quality. These IoT and AI solutions not only enhance urban functionality but play a crucial role in building urban resilience by allowing cities to detect and address issues proactively. For example, AI-based adaptive traffic signal control systems have been developed to manage urban traffic more efficiently, thereby reducing emissions and improving air quality11.

Enhancing public safety is another critical application of IoT and AI in urban environments. Smart surveillance systems equipped with AI can detect unusual activities or hazards, enabling prompt responses to emergencies. The IEEE Public Safety Technology Initiative highlights how IoT integration in smart cities is reducing emergency response times and saving lives by creating a web of real-time data collection and analysis12.Additionally, AI is being used to respond to natural disasters in cities. The Global Initiative on Resilience to Natural Hazards through AI Solutions, a new UN initiative, aims to guide the use of AI in disaster management. AI applications include placing traffic sensors and improving weather forecasts to expedite public alerts and analyze disaster impact using satellite imagery13.

Baltimore could adapt these models to monitor structural health and optimize emergency responses, especially in areas with dense historical architecture and vulnerable communities. Barcelona has established itself as a leader in smart city development by integrating IoT and AI across various urban systems. The city has implemented a comprehensive network of sensors to monitor air quality, noise levels, and traffic conditions in real-time. This data-driven approach enables efficient resource management and informed decision-making, contributing to improved urban living conditions14. New York City has adopted IoT and AI technologies to enhance public safety and infrastructure management. The city utilizes AI-powered surveillance systems to monitor public spaces, detect unusual activities, and respond promptly to emergencies. Additionally, IoT sensors are deployed to monitor structural health of bridges and buildings, facilitating predictive maintenance and reducing the risk of infrastructure failures15.

Tokyo has integrated IoT and AI technologies to bolster its urban resilience, particularly in earthquake preparedness. The city employs AI algorithms to analyze seismic data and predict potential impacts, enabling timely evacuation and resource allocation. IoT devices are also used to monitor infrastructure integrity and environmental conditions, providing real-time information during emergencies16. London has implemented an AI-driven traffic management system that utilizes IoT sensors to monitor traffic flow and congestion levels. The system analyzes real-time data to optimize traffic signals and provide alternative route suggestions, reducing travel times and emissions. This smart infrastructure initiative has significantly improved urban mobility and environmental sustainability17. Building on successful models from cities like New York, Tokyo, and Barcelona, this study explores how Baltimore can leverage smart infrastructure to enhance urban resilience, sustainability, and operational efficiency. However, to successfully implement these technologies, Baltimore requires a tailored approach that considers its specific needs. This study, therefore, explores how scalable and adaptable smart infrastructure solutions, grounded in the unique socioeconomic and infrastructural landscape of Baltimore, can address the city's challenges.

To systematically evaluate the scalability and resilience of Baltimore’s smart infrastructure, this study employs a conceptual framework that incorporates key criteria addressing both scalability and resilience. The first component, Scalability Factors, focuses on the economic feasibility and technological readiness of IoT and AI technologies. These factors are critical in determining how well these technologies can be expanded and adapted to Baltimore’s diverse socioeconomic and infrastructural landscape. Economic feasibility assesses the cost-effectiveness of scaling smart infrastructure, while technological readiness evaluates the capacity of existing infrastructure to support the integration of new technologies.

The second component involves Resilience Indicators, which are based on various socioeconomic factors that contribute to urban resilience. These indicators include the poverty rate, market hotness, commuting time, median household income, population, unemployment rate, educational enrollment, completed bachelor’s degree rates, household ownership, and insurance coverage. By examining these factors, the study identifies essential dependencies and correlations that influence the design of resilient infrastructure solutions. These indicators highlight the social, economic, and environmental conditions that must be considered when developing infrastructure solutions that can adapt to changing urban needs and foster long-term resilience in Baltimore’s communities.

Methodology

This study employs a mixed-method approach to analyze the scalability and adaptability of smart infrastructure in Baltimore, utilizing both quantitative and spatial data sources. Primary data was sourced from various publicly available datasets, including socio-economic and infrastructure-related indicators such as poverty rate, population, median household income, commuting time, market hotness (days on market), and unemployment rates from the Federal Reserve Bank of St. Louis. Additional datasets on education enrollment, degree attainment, household ownership, commute patterns, and insurance coverage were obtained from the USA Data website. These datasets provided insights into Baltimore’s urban and demographic structure, essential for assessing the potential for scalable smart infrastructure solutions.

1.

Data Collection

Socio-Economic and Infrastructure Data: Key indicators like poverty rate, population, median household income, commuting time for workers, market hotness data and unemployment rates were collected from the Federal Reserve Bank of St. Louis.
Market Hotness Data: Real estate metrics, particularly market hotness (days on market), were included to understand real estate dynamics in Baltimore from the Federal Reserve Bank of St. Louis.
Education and Household Data: Data on total enrollment, completed bachelor’s degrees, and household ownership were gathered was sourced from the USA Data website to assess educational attainment and residential stability, important factors in urban resilience.
Commute and Insurance Data: Information on various commuting modes and insurance coverage (public and private) was sourced from the USA Data website, helping analyze workforce mobility and access to health resources within the city.

2.

Data Preparation

Data Cleaning:

To prepare the dataset for analysis, we conducted several data cleaning steps using the Pandas library18. This process involved handling missing values, standardizing data types, and calculating relevant metrics to ensure consistency and reliability in the data.

1.

Initial Data Inspection: The datasets were loaded and conducted an initial inspection to identify data types, assess the presence of missing values, and obtain summary statistics for the numerical columns.

2.

Date Conversion: Date columns were converted to a datetime format. Any errors in date conversion were coerced to NaT to maintain data integrity.

3.

Handling Missing Values: Missing values in certain fields were filled with context-specific values to ensure completeness.

Data Transformation and Aggregation:

1.: Geospatial Transformation: Latitude and longitude coordinates were transformed into Point geometries using the GeoPandas library19, allowing us to analyze and visualize the spatial distribution of permits within Baltimore County. These coordinates were then converted into a GeoDataFrame, enabling spatial plotting and analysis with Geographic Information System (GIS) tools.
2.: Yearly Aggregation for Resilience Analysis: To assess trends over time, we aggregated indicators by year. This included calculating average values for socio-economic indicators, such as poverty rate, median household income, and insurance coverage, across the study period (2017-2022). This aggregation supported the time-series analysis of resilience indicators, allowing us to observe shifts in socio-economic factors that influence resilience.

3.

Data Analysis

Correlation Analysis: To explore relationships between key socio-economic indicators, a correlation matrix was generated. The analysis helped identify interconnected factors, such as the relationship between income levels and household ownership, or commuting patterns and employment status.

4.

Spatial Analysis

Permit Density Mapping: A spatial analysis of permit activities was conducted to identify high-density areas with significant construction or renovation projects. This spatial concentration was visualized on a map, revealing “hotspots” where IoT and AI technologies could be prioritized due to high infrastructure demands and potential for data collection. The GeoPandas library20 was utilized to handle and analyze geospatial data efficiently.

5.

Comparative Analysis of Socio-Economic Indicators Trends

Trend Analysis Across Key Indicators: By grouping and comparing indicators by year, trends in variables like poverty rate, median income, unemployment, and household ownership were examined. This allowed for the assessment of socio-economic shifts in Baltimore over time, providing insights into factors that influence resilience and adaptability in smart infrastructure.

6.

Calculating the Resilience Score

To quantify Baltimore County’s resilience, a composite resilience score was calculated based on key socio-economic and infrastructural indicators, including poverty rate, market dynamics, commuting time, household income, population, unemployment rate, educational enrollment, insurance coverage, and healthcare accessibility. The process involved three main steps:

Normalization of Indicators: Each indicator was normalized to a scale from 0 to 1 using MinMaxScaler21, a preprocessing tool that standardizes the range of each variable. This approach ensures that all indicators contribute comparably to the resilience score, regardless of their original scales.
Calculation of the Resilience Score: After normalization, the resilience score was calculated as the mean of the normalized indicators, reflecting a balanced measure of resilience. If necessary, specific indicators could be weighted to emphasize their relative importance, though an equal weighting approach was applied here for simplicity.
Integration with Annual Data: The resilience score was computed annually and added to the dataset, allowing for time-series analysis of resilience trends from 2017 to 2022.

7.: Visualization

Spatial Analysis of Permits: A Permit Density Map was generated to visualize the distribution of permit activities across Baltimore County. This analysis aimed to identify high-density areas with significant construction and renovation projects, which could serve as “hotspots” for potential IoT and AI technology prioritization. By visually clustering permit data, the density map provides a straightforward way to target areas with high infrastructure demand, guiding efficient resource allocation for smart infrastructure projects.
Time-Series Analysis of Resilience Scores: A time-series plot of resilience scores from 2017 to 2022 was created, reflecting changes over time and identifying years with significant improvements or setbacks. This visualization highlighted the impacts of socio-economic trends on Baltimore’s resilience, guiding decision-making for scalable smart infrastructure deployment.
Heatmaps of Socio-Economic Indicators: To explore relationships among resilience factors, we generated a correlation heatmap of key socio-economic indicators, including poverty rate, median household income, unemployment, education, and insurance coverage. Using the Seaborn library22, the heatmap was created to display these correlations, with values annotated and color-coded to highlight the strength and direction of relationships between variables. This visualization helped us identify complex interdependencies among indicators, offering insights into how these factors collectively influence resilience within Baltimore County. The heatmap was configured to use a diverging color scale from -1 to 1, allowing for a clear distinction between positive and negative correlations. This approach enabled us to interpret socio-economic trends effectively and provided a visual foundation for understanding the dynamics among resilience indicators.
Time-Series Analysis of Socio-Economic Indicators: A comprehensive time-series analysis was conducted for the period spanning from 2017 to 2022 to evaluate the dynamic changes in socio-economic indicators. This analysis aimed to identify and visualize patterns, trends, and fluctuations over time, shedding light on the years that exhibited notable improvements or declines in key indicators. Such insights are invaluable for understanding the broader socio-economic trajectory of Baltimore County and for pinpointing critical periods that may require further investigation or intervention.

To achieve this, the Plotly library was utilized to create highly interactive visualizations. This advanced tool allowed for the development of engaging, user-friendly graphical representations, enabling users to delve into the data with precision and clarity. By facilitating detailed exploration of trends over the six-year period, the visualizations provided stakeholders and researchers with a robust platform to analyze complex datasets and draw meaningful conclusions about the county's socio-economic landscape. This interactive approach ensures that the nuances in data trends are captured and effectively communicated to support informed decision-making.

Results and Discussion

The map reveals areas of concentrated permit activity, likely indicating zones with significant construction or renovation projects. These "hotspots" could represent neighborhoods experiencing rapid development, urban renewal efforts, or economic investment. For city planners and policymakers, these areas may need more infrastructure and public services to accommodate the growing demands of new residents, businesses, and facilities.

The high-density areas offer an ideal setting to deploy smart infrastructure solutions, including IoT and AI technologies, due to the increased infrastructure demands and greater potential for data collection23. Implementing real-time monitoring and predictive analytics in these areas could enhance urban resilience by enabling more responsive and efficient management of resources like traffic flow, public safety, and environmental quality24.

Sparse or lower-density regions might reveal where development has not progressed, possibly due to factors such as economic constraints, lack of incentives, or zoning limitations. These areas could be targeted for pilot smart infrastructure projects to assess the feasibility of improving infrastructure without intensive development25.

Figure 1. Permit Locations Distribution in Baltimore County.

The distribution of permits suggests the impact of zoning and land use policies. The clustered permit activity could indicate zones designated for high-density residential, commercial, or mixed-use purposes. Understanding these patterns helps urban planners identify whether zoning regulations align with the current development trends or need adjustments to support balanced urban growth. The empty spaces or gaps, particularly in the center of the map, may indicate natural features, parks, protected areas, or other non-developable land. These areas could also signify the presence of underdeveloped or economically disadvantaged neighborhoods. Understanding these patterns helps in planning balanced development that maintains green spaces while allowing for growth in designated areas.

The distribution of permits can reveal socio-economic disparities within Baltimore. High-development areas may correlate with economically advantaged neighborhoods or those receiving public and private investment. In contrast, areas with low permit activity might represent communities with fewer economic opportunities or access to resources26. For equitable development, it is essential to engage local communities in low-development areas, understanding the specific barriers they face and working collaboratively to design smart infrastructure solutions that reflect their needs27. Initiatives that support affordable housing, local businesses, and access to transportation in underserved areas can foster balanced growth and social cohesion.

Figure 2. Trend of Medicaid-Insured Population Percentage Over the Years.

The Time-Series plot shows an upward trend in the percentage of the Medicaid-insured population in Baltimore County, Maryland, from 2017 to 2022. After a brief stabilization around 2018-2019, the percentage of Medicaid-insured individuals continues to rise steadily, reaching its highest level in 2022. This trend may indicate increased eligibility or reliance on Medicaid support, possibly due to economic challenges or policy changes that expanded access to Medicaid, emphasizing the growing demand for publicly funded healthcare services in the county.

Figure 3. Trend of Medicare-Insured Population Percentage Over the Years.

This Time-Series plot shows an upward trend in the percentage of the Medicare-insured population in Baltimore County, Maryland, from 2017 to 2022. The steady increase indicates a growing reliance on Medicare insurance, which could reflect an aging population or increased eligibility within the county. The gradual rise suggests a consistent need for Medicare support, highlighting the importance of healthcare infrastructure and services tailored to this demographic.

Figure 4. Trend of Uninsured Population Percentage Over the Years.

The Time-Series plot displays a clear downward trend in the uninsured population percentage in Baltimore County, Maryland, from 2017 to 2019, indicating improved access to health insurance. After 2019, the rate remains relatively stable, with only slight fluctuations. This stabilization suggests that most of the population who were previously uninsured might have obtained coverage, potentially due to policy changes or healthcare programs. However, the small uptick in 2022 may hint at emerging challenges in maintaining coverage levels, warranting attention to prevent a reversal in uninsured rates.

Figure 5. Trend of Total Public Insured Population Over the Years.

The Time-Series plot shows a steady increase in the total public insured population in Baltimore County, Maryland, from 2017 to 2022. This upward trend suggests that more residents are accessing public health insurance options, possibly due to expanded eligibility, increased public awareness, or economic factors encouraging enrollment in public insurance programs. The consistent growth year over year highlights a strengthening in public health insurance coverage, which can positively impact community health and resilience by providing more individuals with access to necessary medical services.

Figure 6. Trend of Total Private Insured Population Over the Years.

This Time-Series plot illustrates fluctuations in the total privately insured population in Baltimore County, Maryland, from 2017 to 2022. Initially, the population remains relatively stable with minor changes from 2017 to 2019, followed by a noticeable dip in 2020. This drop might reflect the economic impact of the COVID-19 pandemic, where job losses and financial instability may have led to a reduction in private insurance coverage. However, there is a significant spike in 2021, possibly due to economic recovery or changes in private insurance policies, followed by a decline in 2022. This trend highlights the variability in private insurance coverage, which could be influenced by economic conditions, employment trends, and policy adjustments affecting access to private health insurance.

Figure 7. Trend of Commute To Work Riding Motorcycle Over the Years.

This Time-Series plot shows a declining trend in the number of people commuting to work by motorcycle in Baltimore County, Maryland, from 2017 to 2022. Starting from a higher count in 2017, the number steadily decreases, reaching a low point in 2020. This drop could be due to various factors, including changes in weather patterns, road safety concerns, or the impact of the COVID-19 pandemic, which reduced commuting overall. In 2021, there’s a slight recovery in motorcycle commuting, but the number declines again in 2022, indicating a continued preference shift away from motorcycle commuting, possibly due to safety or economic reasons.

Figure 8. Trend of Commute to Work Riding Taxi Over the Years.

The Time-Series plot illustrates an upward trend in the number of people commuting to work by taxi in Baltimore County, Maryland, from 2017 to 2022. Starting at a lower count in 2017, the usage of taxis for commuting shows steady growth, with a noticeable increase between 2018 and 2019. Although there was a slight leveling off around 2020, the trend continued to rise in 2021 and 2022, reaching its highest point in 2022. This increase might indicate a growing reliance on alternative commuting options, possibly due to urban mobility changes, increased accessibility of taxi services, or shifts in commuting preferences.

Figure 9. Trend of Commute To Work Riding Bicycle Over the Years.

This Time-Series plot shows the trend of commuting to work by bicycle in Baltimore County, Maryland, from 2017 to 2022. Initially, there is a slight decline from 2017 to 2019, followed by a sharp drop in 2020. This dip might be due to factors such as the COVID-19 pandemic affecting commuting habits. The number of bicycle commuters rebounded in 2021, reaching a higher level before declining again in 2022. This fluctuating pattern suggests changing preferences or external influences impacting the use of bicycles for commuting in recent years.

Figure 10. Trend of Working At Home Over the Years.

This Time-Series plot illustrates a notable increase in the trend of working from home in Baltimore County, Maryland, from 2017 to 2022. Initially, the number remained stable from 2017 to 2019. However, starting in 2020, there is a steep upward trend, reaching the highest point in 2022. This rapid growth likely reflects the impact of the COVID-19 pandemic, which led to a shift towards remote work for many individuals. The sustained rise suggests a lasting change in work patterns, with more people continuing to work from home over the years.

Figure 11. Trend of Commute To Work By Walking Over the Years.

This Time-Series plot shows a fluctuating trend in commuting to work by walking in Baltimore County, Maryland, from 2017 to 2022. There is a gradual decline from 2017, reaching the lowest point in 2020. After this low, the numbers remain stable in 2021, followed by a slight recovery in 2022. This trend may reflect a shift in commuting behaviors, possibly influenced by changes in work location, availability of remote work options, or infrastructure developments affecting walkability in certain areas. The increase in 2022 suggests a partial return to previous commuting habits.

Figure 12. Trend of Commute to Work Driving Alone Over the Years.

The trend of commuting alone to work in Baltimore County shows a steady decrease from 2019 to 2022, after a relatively stable period from 2017 to 2019. This decline could suggest a shift towards alternative commuting methods, potentially influenced by changes in work patterns, increased adoption of remote work, or efforts to reduce solo driving. The trend may reflect broader socioeconomic or policy impacts, including transportation initiatives or rising awareness of environmental sustainability.

Figure 13. Trend of Commute to Work Using Public Transit Over the Years.

The trend in public transit use for commuting in Baltimore County shows a consistent decline from 2017 to 2022, with a notable drop after 2020. This decline may be attributed to factors such as increased remote work, health concerns related to public transportation during the COVID-19 pandemic, or shifts towards other transportation modes. The data suggests a reduced reliance on public transit over the years, highlighting potential areas for transit system evaluation or investment in alternative commuting solutions.

Figure 14. Trend Completed Bachelor Degree Over the Years.

The trend of completed bachelor’s degrees over the years shows a peak in 2020, followed by a steady decline through 2022. This pattern may suggest that 2020 was a notable year for educational achievements, possibly influenced by shifts in educational policies, economic conditions, or societal factors. The subsequent decrease might reflect changes in enrollment rates, economic pressures, or other factors impacting the pursuit or completion of higher education in Baltimore County.

Figure 15. Trend of Total Educational Enrollment Over the Years.

The trend of total educational enrollment shows a consistent decline from 2017 to 2022. This downward trend may indicate a decrease in student enrollment rates, which could be influenced by demographic changes, economic challenges, shifts in population dynamics, or changes in the demand for education within Baltimore County. The steady decline suggests an ongoing trend that could have implications for resource allocation and planning in the education sector.

Figure 16. Trend of Unemployed Persons Over the Years.

The trend of unemployed persons over the years shows a fluctuating pattern. After a slight decline from 2017 to 2019, unemployment spikes significantly in 2020, likely due to economic disruptions, possibly related to the COVID-19 pandemic. Following this peak, there is a steep decline from 2021 to 2022, indicating a recovery in employment levels. This pattern highlights the impact of external economic events on unemployment rates in Baltimore County.

Figure 17. Trend of Population Over the Years.

The trend of population over the years in Baltimore County shows a relatively stable pattern from 2017 to 2019, followed by a sharp increase in 2020. After this jump, the population appears to stabilize, maintaining the elevated level through 2021 and 2022. This sudden increase in 2020 could be due to changes in population dynamics, such as migration, policy changes, or improved data accuracy, which caused a significant shift in recorded population.

Figure 18. Trend of Median Household Income Over the Years.

The trend of population over the years in Baltimore County shows a relatively stable pattern from 2017 to 2019, followed by a sharp increase in 2020. After this jump, the population appears to stabilize, maintaining the elevated level through 2021 and 2022. This sudden increase in 2020 could be due to changes in population dynamics, such as migration, policy changes, or improved data accuracy, which caused a significant shift in recorded population.

Figure 19. Trend of Commuting Time for Workers Over the Years.

The commuting time for workers in Baltimore County initially shows a slight increase from 2017 to 2019, reaching a peak around 2020. However, there is a notable decline from 2020 to 2022. This reduction in commute times in the latter years may be attributed to factors such as an increase in remote work options due to the COVID-19 pandemic, changes in traffic patterns, or other improvements in transportation infrastructure or efficiency. This trend indicates a potential enhancement in work-life balance and reduced travel stress for workers in recent years.

Figure 20. Estimate of People of All Ages in Poverty Over the Years.

The trend in the estimate of people of all ages in poverty over the years for Baltimore County reveals fluctuations that reflect shifting socioeconomic conditions. From 2017 to 2018, there is a sharp increase in the poverty estimate, suggesting potential economic challenges or conditions that may have affected residents’ financial stability during this period. This is followed by a decline and subsequent stabilization from 2019 to 2020, indicating a period where poverty levels appear to have plateaued, potentially signaling economic recovery or stability. However, from 2021 to 2022, the estimate rises significantly, reaching its peak in 2022. This sharp increase could be attributed to recent economic pressures, possibly linked to the effects of the COVID-19 pandemic, which may have intensified financial strain for vulnerable populations. This trend highlights the importance of ongoing socioeconomic support and targeted resources to address poverty in Baltimore County.

Figure 21. Trend of Market Hotness-Median Days on Market Over the Years.

The "Market Hotness - Median Days on Market" trend in Baltimore County shows a fluctuating pattern over the years, suggesting shifts in the real estate market's activity levels. In 2017, the median days on market were relatively high, indicating a slower market with homes staying listed longer. This was followed by a notable decline in 2018, suggesting increased market activity and faster property sales. The trend stabilizes around 2019 but then reaches a low point in 2020, likely reflecting a period of heightened demand and rapid sales, possibly influenced by market dynamics or external factors such as the COVID-19 pandemic.

Figure 22. Correlation Heatmap.

Poverty Rate

The Poverty Rate shows a strong positive correlation with Medicaid-insured Individuals Percentage (0.87) and a moderate correlation with Total Public Insured Population (0.84). This suggests that areas with higher poverty rates have a higher proportion of residents reliant on public insurance programs, reflecting potential economic and healthcare access challenges in these communities. There is a negative correlation with Total Enrollment (-0.81) and Total Private Insured Population (-0.63), indicating that higher poverty rates may be associated with lower educational enrollment and a lower percentage of private insurance coverage.

Market Hotness - Median Days on Market

Market Hotness has a moderate positive correlation with Uninsured Individuals Percentage (0.86). This suggests that areas where properties stay on the market longer may also have a higher percentage of uninsured individuals, possibly due to economic challenges or lower healthcare accessibility. It is negatively correlated with Total Public Insured Population (-0.62) and Medicaid-insured Individuals Percentage (-0.62), indicating that areas with quicker real estate transactions might have a higher percentage of public health insurance users.

Commuting Time for Workers

Commuting Time has a strong positive correlation with Commute to Work Using Public Transit (0.86) and Commute to Work Driving Alone (0.80). This reflects a general trend that longer commutes might be associated with public transit use and driving alone. There is a negative correlation with Total Public Insured Population (-0.77) and Total Private Insured Population (-0.78), suggesting that areas with longer commutes might have fewer insured individuals, potentially due to economic factors or a lack of accessible healthcare options near work locations.

Median Household Income

Median Household Income has a strong positive correlation with Total Private Insured Population (0.92) and Total Enrollment (0.95), implying that higher income areas tend to have more private insurance coverage and educational enrollment. It has a strong negative correlation with Medicaid-insured Individuals Percentage (-0.88) and Uninsured Individuals Percentage (-0.65), indicating that higher income areas tend to have fewer residents relying on Medicaid or who are uninsured.

Population

Population is strongly positively correlated with Household Ownership (0.84) and Total Public Insured Population (0.84), suggesting that higher population areas might have higher rates of homeownership and public insurance coverage. It is moderately negatively correlated with Total Enrollment (-0.9) and Total Private Insured Population (-0.77), which could imply that densely populated areas may have less access to educational resources and private insurance options.

Unemployed Persons

Unemployment has a positive correlation with Medicaid-insured Individuals Percentage (0.91) and Total Public Insured Population (0.93). This could imply that areas with higher unemployment rates have more residents reliant on public insurance, possibly due to income constraints. It has a negative correlation with Median Household Income (-0.3) and Total Private Insured Population (-0.28), reflecting economic challenges that might affect access to private insurance.

Total Enrollment

Total Enrollment has a very high positive correlation with Median Household Income (0.95) and Total Private Insured Population (0.88), indicating that areas with higher educational enrollment are often associated with higher income and private insurance coverage.It has a strong negative correlation with Medicaid-insured Individuals Percentage (-0.97) and Uninsured Individuals Percentage (-0.9), which suggests that higher enrollment may be inversely related to reliance on public insurance or lack of insurance.

Completed Bachelor

Completed Bachelor rates have a moderate positive correlation with Commute To Work Using Public Transit (0.43) and a negative correlation with Commute To Work By Walking (-0.63). This implies that higher education levels may be associated with public transit use, while areas with higher walkability might have lower rates of bachelor’s degree attainment.There is a strong positive correlation with Total Private Insured Population (0.65) and Median Household Income (0.6), indicating that areas with higher educational attainment tend to have higher income and access to private insurance.

Household Ownership

Household Ownership has a strong positive correlation with Population (0.84) and Total Public Insured Population (0.94), suggesting that areas with higher population might also have higher homeownership and public insurance coverage.It is negatively correlated with Total Enrollment (-0.96) and Completed Bachelor (-0.4), which could indicate that areas with higher homeownership might have lower educational enrollment and lower bachelor’s degree attainment.

Insurance Coverage

Total Private Insured Population is strongly positively correlated with Median Household Income (0.92) and negatively correlated with Medicaid-insured Individuals Percentage (-0.72). This suggests that higher private insurance coverage aligns with higher income levels and lower reliance on Medicaid. Total Public Insured Population has strong positive correlations with Medicaid-insured Individuals Percentage (0.98) and Medicare-insured Individuals Percentage (0.9), indicating a strong relationship between public insurance categories. Uninsured Individuals Percentage is positively correlated with Market Hotness (0.85) and negatively with Total Public Insured Population (-0.7). This may suggest that areas with fewer public insurance users have higher uninsured rates and properties that stay longer on the market.

The high degree of correlations in certain areas indicates dependencies that are important for designing resilient infrastructure. For example:

1.: Income and Insurance: The strong links between income levels, insurance types, and educational enrollment suggest that policies focusing on improving economic conditions could positively impact insurance accessibility and educational opportunities.
2.: Healthcare Coverage and Economic Conditions: The correlation between poverty, Medicaid reliance, and unemployment emphasizes the importance of economically sensitive healthcare solutions. This insight can guide strategies to scale public insurance support in economically challenged areas.
3.: Transportation and Workforce Dynamics: The relationships between commuting patterns, household income, and educational attainment highlight how transportation infrastructure may impact economic and educational access. Prioritizing transit accessibility in high-density or low-income areas can improve overall workforce resilience and economic adaptability.

Educational Enrollment and Social Mobility: Higher educational enrollment is associated with higher household income and lower poverty and unemployment rates. This correlation underscores the potential impact of educational investment on urban resilience, suggesting that policies promoting access to education can strengthen community resilience.

Figure 23. Trend of Resilience Score Over the Years in Baltimore County.

Between 2017 and 2019, the resilience score shows a steady, though gradual, increase. This suggests that during these years, the factors contributing to resilience—such as economic, educational, and healthcare indicators—experienced only modest improvements. These incremental changes likely reflect positive developments within Baltimore's infrastructure, employment, or community well-being, though they did not lead to significant shifts in overall resilience. From 2019 to 2021, there is a sharp increase in the resilience score, reaching its peak in 2021. This period likely saw substantial improvements in several key indicators, potentially due to socioeconomic or policy changes that positively impacted factors such as insurance coverage, educational attainment, household income, or employment levels.

This marked rise in resilience may indicate that specific policies or community initiatives were particularly effective in strengthening Baltimore’s resilience during these years. In 2022, the resilience score shows a slight decline. This dip may reflect a minor setback or decrease in one or more resilience indicators, suggesting that a particular economic or social challenge affected the city’s resilience. However, the decline is not significant, indicating that the overall resilience remains high compared to the initial 2017 level, despite this recent challenge.

The factors influencing these trends are worth exploring further. The sharp increase in 2020 and 2021 could be attributed to policy interventions, economic growth, or community programs that improved conditions related to healthcare access, education, or employment opportunities. Additionally, the COVID-19 pandemic, particularly during 2020 and 2021, likely played a role in shaping the resilience indicators. Public health initiatives and economic relief measures introduced during the pandemic may have contributed to the substantial rise in resilience during these years. However, challenges that emerged in the pandemic's aftermath may have contributed to the slight dip seen in 2022.

Limitation

This study’s analysis relies on socio-economic and infrastructural data spanning from 2017 to 2022. While this period provides valuable insights into recent trends and challenges, it also limits our ability to capture longer-term patterns or assess the potential impacts of ongoing policy changes that may not yet be reflected in the data. Additionally, some socio-economic shifts, such as the post-pandemic recovery, may only begin to show broader effects outside this timeframe. Future studies could benefit from a broader dataset extending past 2022, allowing for more comprehensive trend analysis and an assessment of the continuity or change in emerging patterns.

Conclusion and Recommendations

The analysis of Baltimore County's socio-economic and infrastructural indicators reveals valuable insights into its development patterns, resilience, and challenges. High-density zones identified through permit activities suggest ideal locations for deploying smart infrastructure, such as IoT to enhance urban resilience via real-time monitoring and resource management. In contrast, sparse development areas offer opportunities for cost-effective pilot projects. Time-series analyses of socio-economic indicators, such as public insurance coverage, poverty rates, and commuting patterns, highlight the county's response to policy shifts and external events like COVID-19. Trends in public insurance coverage indicate increased reliance on healthcare resources due to economic pressures, while shifts in commuting behavior suggest a rise in remote work, potentially reducing commuting infrastructure demand. Between 2017 and 2021, the resilience score rose steadily, likely due to improved healthcare access, employment, and education, with a minor decline in 2022 indicating emerging challenges. Based on these findings, recommendations include prioritizing smart infrastructure in high-density areas to maximize impact, expanding healthcare accessibility in economically disadvantaged neighborhoods, and investing in alternative commuting options like bike-sharing and pedestrian-friendly pathways. In low-development areas, promoting digital literacy and public Wi-Fi access can foster economic empowerment. Implementing resilience metrics and public dashboards will enhance transparency and proactive resource management, while partnerships with state agencies can support ongoing resilience monitoring. Continued tracking of socio-economic indicators and further research into local policy impacts and neighborhood-specific needs will help refine strategies, fostering a sustainable and resilient Baltimore County for the future.

Notes

1	Sara Meerow, Pani Pajouhesh, and Thaddeus R. Miller, “Social Equity in Urban Resilience Planning,” Local Environment 24, no. 9 (September 2, 2019): 793–808, https://doi.org/10.1080/13549839.2019.1645103.
	Caitlin DeClercq et al., “A Novel Approach to Locating Community Clinics to Promote Health Care Accessibility and Reduce Health Disparities in Baltimore, Maryland,” Inquiry: A Journal of Medical Care Organization, Provision and Financing 60 (May 13, 2023): 00469580221135953, https://doi.org/10.1177/00469580221135953.
	Brett Theodos et al., “Neighborhood Investment Flows in Baltimore: With a Case Study on the East Baltimore Development Initiative,” Urban Institute, September 29, 2020, https://www.urban.org/research/publication/neighborhood-investment-flows-baltimore-case-study-east-baltimore-development-initiative; “Drilling Down in Baltimore’s Neighborhoods,” The Abell Foundation (blog), accessed November 13, 2024, https://abell.org/publication/drilling-down/; “New Report from Johns Hopkins Finds Stark Transit Inequity in Baltimore \| Hub,” accessed November 13, 2024, https://hub.jhu.edu/2021/10/07/transit-inequity-baltimore/.
	“Mayor Scott, BCIT Release Five-Year Plan to Address the City’s Digital Divide,” Mayor Brandon M. Scott, December 13, 2023, https://mayor.baltimorecity.gov/news/press-releases/2023-12-13-mayor-scott-bcit-release-five-year-plan-address-citys-digital-divide.
	“What Is the Internet of Things (IoT)? \| IBM,” accessed November 13, 2024, https://www.ibm.com/topics/internet-of-things.
	“What Is Artificial Intelligence (AI)? \| IBM,” August 9, 2024, https://www.ibm.com/topics/artificial-intelligence.
	Soroush Piri, “Smart Infrastructure Integration for Enhanced Urban Resilience: A Transdisciplinary Approach,” SSRN Scholarly Paper (Rochester, NY: Social Science Research Network, April 29, 2024), https://doi.org/10.2139/ssrn.4811269.
	“IoT for Monitoring Traffic Tackles Urban Traffic Issues,” Telnyx, accessed November 9, 2024, https://telnyx.com/resources/iot-monitoring-traffic.
	“New AI Traffic Lights Being Tested Give Priority to Cyclists over Cars in Hope to ‘encourage More People to Cycle’ \| The Irish Sun,” accessed November 9, 2024, https://www.thesun.ie/motors/13799094/ai-traffic-lights-stop-cars-cyclists/?utm_source=chatgpt.com.
	Md Eshrat E. Alahi et al., “Integration of IoT-Enabled Technologies and Artificial Intelligence (AI) for Smart City Scenario: Recent Advancements and Future Trends,” Sensors (Basel, Switzerland) 23, no. 11 (May 30, 2023): 5206, https://doi.org/10.3390/s23115206.
	C. Ashokkumar et al., “Urban Traffic Management for Reduced Emissions: AI-Based Adaptive Traffic Signal Control,” in 2024 2nd International Conference on Sustainable Computing and Smart Systems (ICSCSS), 2024, 1609–15, https://doi.org/10.1109/ICSCSS60660.2024.10625356.
	“Smart City Integration: How IoT Is Reducing Emergency Response Times and Saving Lives - IEEE Public Safety Technology Initiative,” accessed November 9, 2024, https://publicsafety.ieee.org/topics/smart-city-integration-how-iot-is-reducing-emergency-response-times-and-saving-lives.
	“How AI Is Being Used to Respond to Natural Disasters in Cities \| TIME,” accessed November 9, 2024, https://time.com/7171445/ai-natural-disaster-cities/?utm_source=chatgpt.com.
	“Data-Driven Smart Sustainable Cities of the Future: Urban Computing and Intelligence for Strategic, Short-Term, and Joined-up Planning \| Computational Urban Science,” accessed November 9, 2024, https://link.springer.com/article/10.1007/s43762-021-00008-9.
	“Artificial Intelligence in Smart Cities—Applications, Barriers, and Future Directions: A Review,” accessed November 9, 2024, https://www.mdpi.com/2624-6511/7/3/57.
	“Technological Innovations for Enhancing Disaster Resilience in Smart Cities: A Comprehensive Urban Scholar’s Analysis,” accessed November 9, 2024, https://www.mdpi.com/2071-1050/15/15/12036.
	Simon Elias Bibri et al., “Environmentally Sustainable Smart Cities and Their Converging AI, IoT, and Big Data Technologies and Solutions: An Integrated Approach to an Extensive Literature Review,” Energy Informatics 6, no. 1 (April 5, 2023): 9, https://doi.org/10.1186/s42162-023-00259-2.
	“Pandas - Python Data Analysis Library,” accessed November 13, 2024, https://pandas.pydata.org/about/citing.html.
	Kelsey Jordahl et al., “Geopandas/Geopandas: V0.8.1” (Zenodo, July 15, 2020), https://doi.org/10.5281/ZENODO.3946761.
	Jordahl et al.
	“Sklearn.Preprocessing.MinMaxScaler — Scikit-Learn 0.15-Git Documentation,” accessed November 13, 2024, https://scikit-learn.org/0.15/modules/generated/sklearn.preprocessing.MinMaxScaler.html.
	Michael Waskom, “Seaborn: Statistical Data Visualization,” Journal of Open Source Software 6, no. 60 (April 6, 2021): 3021, https://doi.org/10.21105/joss.03021.
	Andrew Hudson-Smith et al., “Urban IoT: Advances, Challenges, and Opportunities for Mass Data Collection, Analysis, and Visualization,” in Urban Informatics, ed. Wenzhong Shi et al. (Singapore: Springer, 2021), 701–19, https://doi.org/10.1007/978-981-15-8983-6_38.
	Lars Baumgärtner et al., “Smart Street Lights and Mobile Citizen Apps for Resilient Communication in a Digital City” (arXiv, August 27, 2019), https://doi.org/10.48550/arXiv.1908.10233; Naser Hossein Motlagh et al., “Towards Large-Scale IoT Deployments in Smart Cities: Requirements and Challenges,” in Learning Techniques for the Internet of Things, ed. Praveen Kumar Donta, Abhishek Hazra, and Lauri Lovén (Cham: Springer Nature Switzerland, 2024), 105–29, https://doi.org/10.1007/978-3-031-50514-0_6; “(PDF) IoT-Driven Smart Cities: Enhancing Urban Sustainability and Quality of Life,” ResearchGate, accessed November 18, 2024, https://www.researchgate.net/publication/374090800_IoT-Driven_Smart_Cities_Enhancing_Urban_Sustainability_and_Quality_of_Life; “(PDF) The Role of IoT in Transforming Smart Cities: Enhancing Urban Infrastructure and Sustainability Through Technology,” accessed November 18, 2024, https://www.researchgate.net/publication/384285980_The_Role_of_IoT_in_Transforming_Smart_Cities_Enhancing_Urban_Infrastructure_and_Sustainability_Through_Technology.
	Steffen Lehmann, “Sustainable Urbanism: Towards a Framework for Quality and Optimal Density?,” Future Cities and Environment 2, no. 1 (August 5, 2016): 8, https://doi.org/10.1186/s40984-016-0021-3; Serio Angelo Maria Agriesti, Ralf-Martin Soe, and Muhammad Atiullah Saif, “Framework for Connecting the Mobility Challenges in Low Density Areas to Smart Mobility Solutions: The Case Study of Estonian Municipalities,” European Transport Research Review 14, no. 1 (July 21, 2022): 32, https://doi.org/10.1186/s12544-022-00557-y.
	“(PDF) Up-Zoning New York City’s Mixed-Use Neighborhoods: Property-Led Economic Development and the Anatomy of a Planning Dilemma,” ResearchGate, accessed November 18, 2024, https://www.researchgate.net/publication/249694367_Up-Zoning_New_York_City%27s_Mixed-Use_Neighborhoods_Property-Led_Economic_Development_and_the_Anatomy_of_a_Planning_Dilemma.
	“(PDF) Evaluating the Impact of Community Engagement in Urban Planning on Sustainable Development,” ResearchGate, accessed November 18, 2024, https://www.researchgate.net/publication/376995168_Evaluating_the_impact_of_community_engagement_in_urban_planning_on_sustainable_development; “(PDF) Building Engaged Communities—A Collaborative Leadership Approach,” ResearchGate, accessed November 18, 2024, https://www.researchgate.net/publication/328948672_Building_Engaged_Communities-A_Collaborative_Leadership_Approach.

References

Agriesti, Serio Angelo Maria, Ralf-Martin Soe, and Muhammad Atiullah Saif. “Framework for Connecting the Mobility Challenges in Low Density Areas to Smart Mobility Solutions: The Case Study of Estonian Municipalities.” European Transport Research Review 14, no. 1 (July 21, 2022): 32. [CrossRef]
Alahi, Md Eshrat E., Arsanchai Sukkuea, Fahmida Wazed Tina, Anindya Nag, Wattanapong Kurdthongmee, Korakot Suwannarat, and Subhas Chandra Mukhopadhyay. “Integration of IoT-Enabled Technologies and Artificial Intelligence (AI) for Smart City Scenario: Recent Advancements and Future Trends.” Sensors (Basel, Switzerland) 23, no. 11 (May 30, 2023): 5206. [CrossRef]
“Artificial Intelligence in Smart Cities—Applications, Barriers, and Future Directions: A Review.”. Available online: https://www.mdpi.com/2624-6511/7/3/57 (accessed on 9 November 2024).
Ashokkumar, C., D. Abitha Kumari, S. Gopikumar, N. Anuradha, R. Santhana Krishnan, and Sakthidevi. I. “Urban Traffic Management for Reduced Emissions: AI-Based Adaptive Traffic Signal Control.” In 2024 2nd International Conference on Sustainable Computing and Smart Systems (ICSCSS), 1609–15, 2024. [CrossRef]
Baumgärtner, Lars, Jonas Höchst, Patrick Lampe, Ragnar Mogk, Artur Sterz, Pascal Weisenburger, Mira Mezini, and Bernd Freisleben. “Smart Street Lights and Mobile Citizen Apps for Resilient Communication in a Digital City.” arXiv, August 27, 2019. [CrossRef]
Bibri, Simon Elias, Alahi Alexandre, Ayyoob Sharifi, and John Krogstie. “Environmentally Sustainable Smart Cities and Their Converging AI, IoT, and Big Data Technologies and Solutions: An Integrated Approach to an Extensive Literature Review.” Energy Informatics 6, no. 1 (April 5, 2023): 9. [CrossRef]
“Data-Driven Smart Sustainable Cities of the Future: Urban Computing and Intelligence for Strategic, Short-Term, and Joined-up Planning | Computational Urban Science.”. Available online: https://link.springer.com/article/10.1007/s43762-021-00008-9 (accessed on 9 November 2024).
DeClercq, Caitlin, Mohammad Gharipour, Salman Mohagheghi, Andrew Tot Bui, Naomi Wong Hemme, and Eric Johnson. “A Novel Approach to Locating Community Clinics to Promote Health Care Accessibility and Reduce Health Disparities in Baltimore, Maryland.” Inquiry: A Journal of Medical Care Organization, Provision and Financing 60 (May 13, 2023): 00469580221135953. [CrossRef]
“How AI Is Being Used to Respond to Natural Disasters in Cities | TIME.”. Available online: https://time.com/7171445/ai-natural-disaster-cities/?utm_source=chatgpt.com (accessed on 9 November 2024).
Hudson-Smith, Andrew, Duncan Wilson, Steven Gray, and Oliver Dawkins. “Urban IoT: Advances, Challenges, and Opportunities for Mass Data Collection, Analysis, and Visualization.” In Urban Informatics, edited by Wenzhong Shi, Michael F. Goodchild, Michael Batty, Mei-Po Kwan, and Anshu Zhang, 701–19. Singapore: Springer, 2021. [CrossRef]
Jordahl, Kelsey, Joris Van Den Bossche, Martin Fleischmann, Jacob Wasserman, James McBride, Jeffrey Gerard, Jeff Tratner, et al. “Geopandas/Geopandas: V0.8.1.” Zenodo, July 15, 2020. [CrossRef]
Lehmann, Steffen. “Sustainable Urbanism: Towards a Framework for Quality and Optimal Density?” Future Cities and Environment 2, no. 1 (August 5, 2016): 8. [CrossRef]
Mayor Brandon M. Scott. “Mayor Scott, BCIT Release Five-Year Plan to Address the City’s Digital Divide,”. Available online: https://mayor.baltimorecity.gov/news/press-releases/2023-12-13-mayor-scott-bcit-release-five-year-plan-address-citys-digital-divide (accessed on 13 December 2023).
Meerow, Sara, Pani Pajouhesh, and Thaddeus R. Miller. “Social Equity in Urban Resilience Planning.” Local Environment 24, no. 9 (September 2, 2019): 793–808. [CrossRef]
Motlagh, Naser Hossein, Martha Arbayani Zaidan, Roberto Morabito, Petteri Nurmi, and Sasu Tarkoma. “Towards Large-Scale IoT Deployments in Smart Cities: Requirements and Challenges.” In Learning Techniques for the Internet of Things, edited by Praveen Kumar Donta, Abhishek Hazra, and Lauri Lovén, 105–29. Cham: Springer Nature Switzerland, 2024. [CrossRef]
“New AI Traffic Lights Being Tested Give Priority to Cyclists over Cars in Hope to ‘encourage More People to Cycle’ | The Irish Sun.”. Available online: https://www.thesun.ie/motors/13799094/ai-traffic-lights-stop-cars-cyclists/?utm_source=chatgpt.com (accessed on 9 November 2024).
“New Report from Johns Hopkins Finds Stark Transit Inequity in Baltimore | Hub.”. Available online: https://hub.jhu.edu/2021/10/07/transit-inequity-baltimore/ (accessed on 13 November 2024).
“Pandas - Python Data Analysis Library.”. Available online: https://pandas.pydata.org/about/citing.html (accessed on 13 November 2024).
“(PDF) The Role of IoT in Transforming Smart Cities: Enhancing Urban Infrastructure and Sustainability Through Technology.”. Available online: https://www.researchgate.net/publication/384285980_The_Role_of_IoT_in_Transforming_Smart_Cities_Enhancing_Urban_Infrastructure_and_Sustainability_Through_Technology (accessed on 18 November 2024).
Piri, Soroush. “Smart Infrastructure Integration for Enhanced Urban Resilience: A Transdisciplinary Approach.” SSRN Scholarly Paper. Rochester, NY: Social Science Research Network, April 29, 2024. [CrossRef]
ResearchGate. “(PDF) Building Engaged Communities—A Collaborative Leadership Approach.”. Available online: https://www.researchgate.net/publication/328948672_Building_Engaged_Communities-A_Collaborative_Leadership_Approach (accessed on 18 November 2024).
ResearchGate. “(PDF) Evaluating the Impact of Community Engagement in Urban Planning on Sustainable Development.”. Available online: https://www.researchgate.net/publication/376995168_Evaluating_the_impact_of_community_engagement_in_urban_planning_on_sustainable_development (accessed on 18 November 2024).
ResearchGate. “(PDF) IoT-Driven Smart Cities: Enhancing Urban Sustainability and Quality of Life.”. Available online: https://www.researchgate.net/publication/374090800_IoT-Driven_Smart_Cities_Enhancing_Urban_Sustainability_and_Quality_of_Life (accessed on 18 November 2024).
ResearchGate. “(PDF) Up-Zoning New York City’s Mixed-Use Neighborhoods: Property-Led Economic Development and the Anatomy of a Planning Dilemma.”. Available online: https://www.researchgate.net/publication/249694367_Up-Zoning_New_York_City%27s_Mixed-Use_Neighborhoods_Property-Led_Economic_Development_and_the_Anatomy_of_a_Planning_Dilemma (accessed on 18 November 2024).
“Sklearn.Preprocessing.MinMaxScaler — Scikit-Learn 0.15-Git Documentation.”. Available online: https://scikit-learn.org/0.15/modules/generated/sklearn.preprocessing.MinMaxScaler.html (accessed on 13 November 2024).
“Smart City Integration: How IoT Is Reducing Emergency Response Times and Saving Lives - IEEE Public Safety Technology Initiative.”. Available online: https://publicsafety.ieee.org/topics/smart-city-integration-how-iot-is-reducing-emergency-response-times-and-saving-lives (accessed on 9 November 2024).
“Technological Innovations for Enhancing Disaster Resilience in Smart Cities: A Comprehensive Urban Scholar’s Analysis.”. Available online: https://www.mdpi.com/2071-1050/15/15/12036 (accessed on 9 November 2024).
Telnyx. “IoT for Monitoring Traffic Tackles Urban Traffic Issues.”. Available online: https://telnyx.com/resources/iot-monitoring-traffic (accessed on 9 November 2024).
The Abell Foundation. “Drilling Down in Baltimore’s Neighborhoods.”. Available online: https://abell.org/publication/drilling-down/ (accessed on 13 November 2024).
Theodos, Brett, Eric Hangen, Brady Meixell, and Lionel Foster. “Neighborhood Investment Flows in Baltimore: With a Case Study on the East Baltimore Development Initiative.” Urban Institute, September 29, 2020. Available online: https://www.urban.org/research/publication/neighborhood-investment-flows-baltimore-case-study-east-baltimore-development-initiative.
Waskom, Michael. “Seaborn: Statistical Data Visualization.” Journal of Open Source Software 6, no. 60 (April 6, 2021): 3021. [CrossRef]
“What Is Artificial Intelligence (AI)? | IBM,”. Available online: https://www.ibm.com/topics/artificial-intelligence (accessed on 9 August 2024).
“What Is the Internet of Things (IoT)? | IBM.”. Available online: https://www.ibm.com/topics/internet-of-things (accessed on 13 November 2024).

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

Copyright: This open access article is published under a Creative Commons CC BY 4.0 license, which permit the free download, distribution, and reuse, provided that the author and preprint are cited in any reuse.