Spatial sensitivity analysis for urban hotspots using cell phone traces

Wu, Jiahui; Frı́as-Martı́nez, Enrique; Frías-Martínez, Vanessa

doi:10.1177/2399808320985843

Cited by 3 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hotspots or high-traffic communication areas [21] have a high activity and density compared to the other areas in a smart city [22]. Hotspot analysis is a classical problem concerned with spatial analysis [23]. Telecommunication operators and companies always care to identify the hotspots in a city to improve the quality of service.…”

Section: Problem Statementmentioning

confidence: 99%

City Hotspot Identification Using Smart Cyber-Physical Social System

Amin,

He,

Choi

2024

IEEE Access

View full text Add to dashboard Cite

Recently, the concept of smart cities has become popular and got researchers' attention because it helps to improve citizens' lives by providing valuable services, for instance, smart transportation, smart homes, telecommunication, infrastructure, etc. Hotspot analysis is a classic problem concerned with spatial analysis. Telecommunication operators and companies always care to identify the Hotspots in the city. The hotspots are the places with very high communication strength relative to others. It is evident from the current literature that cyber physics social systems (CPSS) are useful in the identification of hotspots in a smart city. However, big data storage, analysis, processing, accuracy, and robustness are the key concerns. Thus herein, we propose a smart cyber-physical-social system for the analysis of hotspots using telecom data. Herein, our proposed CPS model is comprised of three layers and each layer has different functionality. In our proposed model, initially, raw Call Detail Data (CDR) data is collected at the data collection layer. Then smart CPSS passed it to the next layer. In the Data processing layer, CPSS performs pre-processing, data storage, and analysis. Then, it constructs a graph and performs a social network analysis (SNA). Herein, different from traditional centrality measures, we suggest Eigenvector and kshell as social network similarity and Jaccard, cosine, as social behavioral measures. Herein, the process of city hotspot identification is performed, followed by SNA, which is conducted by quantifying the importance of each hotspot based on metrics. Finally, our proposed smart CPSS model accurately identifies Top-Ten hotspots. In this study, we use five-day data and compare the changes in the hotspot patterns. We validate our findings of hotspots with the original dataset and confirm the robustness and accuracy using autocorrelation and cross-correlation functions.INDEX TERMS Cyber-Physical Social Systems (CPSS), Cyber-Physical Systems (CPS), Smart City, Big Data.

show abstract

Section: Problem Statementmentioning

confidence: 99%

City Hotspot Identification Using Smart Cyber-Physical Social System

Amin,

He,

Choi

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Kadar and Pletikosa extracted footfall from checkins, subway and taxi data, along with other census and POI features, to predict the number of crimes for a given census tract in the next year [25]; De Nedai et al proposed a spatially filtered Bayesian Negative Binomial model to study how social, built environment and footfall influence criminal activity [16]; Rumi et al proposed a set of footfall dynamic features computed from Foursquare check-ins including visitor count, visitor entropy and homegeneity or region popularity, and showed that these features improved the performance of short-term crime prediction for certain types of crime with F1-score increases of up to 2% [38]; and Stec et al showed that deep learning architectures that use footfall from public transit, together with weather conditions that have been reported to affect crime, enhance the accuracy of crime predictions [40]. In addition to footfall, Wu et al quantified urban spatial structure using human mobility to predict number of crimes for municipalities in the next year [49,50].…”

Section: Modeling Crime With Human Mobilitymentioning

confidence: 99%

“…Another mobility feature used in crime prediction contexts is the origin-destination matrix (OD) that characterizes human mobility (flows) between census tracts. Human mobility data has been used to characterize human behaviors in the built environment [23][24][25][26][27], for public safety [10,14], during epidemics and disasters [28][29][30][31][32][33][34][35], as well as to support decision making for socio-economic development [36][37][38][39][40][41]. In this paper, we will focus on deep learning crime prediction models that exploit the predictive power past crime data and OD mobility matrices [10].…”

Section: Crime Prediction With Mobility Patternsmentioning

confidence: 99%

Enhancing short-term crime prediction with human mobility flows and deep learning architectures

Abrar

Awasthi

et al. 2022

EPJ Data Sci.

Self Cite

View full text Add to dashboard Cite

Place-based short-term crime prediction models leverage the spatio-temporal patterns of historical crimes to predict aggregate volumes of crime incidents at specific locations over time. Under the umbrella of the crime opportunity theory, that suggests that human mobility can play a role in crime generation, increasing attention has been paid to the predictive power of human mobility in place-based short-term crime models. Researchers have used call detail records (CDR), data from location-based services such as Foursquare or from social media to characterize human mobility; and have shown that mobility metrics, together with historical crime data, can improve short-term crime prediction accuracy. In this paper, we propose to use a publicly available fine-grained human mobility dataset from a location intelligence company to explore the effects of human mobility features on short-term crime prediction. For that purpose, we conduct a comprehensive evaluation across multiple cities with diverse demographic characteristics, different types of crimes and various deep learning models; and we show that adding human mobility flow features to historical crimes can improve the F1 scores for a variety of neural crime prediction models across cities and types of crimes, with improvements ranging from 2% to 7%. Our analysis also shows that some neural architectures can slightly improve the crime prediction performance when compared to non-neural regression models by at most 2%.

show abstract

Analysis of Performance Improvements and Bias Associated with the Use of Human Mobility Data in COVID-19 Case Prediction Models

Abrar,

Awasthi,

Smolyak

et al. 2023

ACM J. Comput. Sustain. Soc.

View full text Add to dashboard Cite

The COVID-19 pandemic has mainstreamed human mobility data into the public domain, with research focused on understanding the impact of mobility reduction policies as well as on regional COVID-19 case prediction models. Nevertheless, current research on COVID-19 case prediction tends to focus on performance improvements, masking relevant insights about when mobility data does not help, and more importantly, why, so that it can adequately inform local decision making. In this paper, we carry out a systematic analysis to reveal the conditions under which human mobility data provides (or not) an enhancement over individual regional COVID-19 case prediction models that do not use mobility as a source of information. Our analysis - focused on US county-based COVID-19 case prediction models - shows that (1) at most, 60% of counties improve their performance after adding mobility data; (2) that the performance improvements are modest, with median correlation improvements of approximately 0.13; (3) that improvements were lower for counties with higher Black, Hispanic, and other non-White populations as well as low-income and rural populations, pointing to potential bias in the mobility data negatively impacting predictive performance; and that (4) different mobility datasets, predictive models and training approaches bring about diverse performance improvements.

show abstract

Spatial sensitivity analysis for urban hotspots using cell phone traces

Cited by 3 publications

References 29 publications

City Hotspot Identification Using Smart Cyber-Physical Social System

City Hotspot Identification Using Smart Cyber-Physical Social System

Enhancing short-term crime prediction with human mobility flows and deep learning architectures

Analysis of Performance Improvements and Bias Associated with the Use of Human Mobility Data in COVID-19 Case Prediction Models

Contact Info

Product

Resources

About