Spatio-Temporal Crime Predictions by Leveraging Artificial Intelligence for Citizens Security in Smart Cities

Butt, Umair Muneer; Letchmunan, Sukumar; Hassan, Fadratul Hafinaz; Ali, Mubashir; Baqir, Anees; Koh, Tieng Wei; Sherazi, Hafiz Husnain Raza

doi:10.1109/access.2021.3068306

Cited by 26 publications

(15 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…MIST aims to be a world-class focus for renewable energy and sustainability research, attracting scientists and researchers worldwide. Thus, it formed an interdisciplinary partnership to build infrastructure to strengthen the region's human capital [259].…”

Section: E Smart Peoplementioning

confidence: 99%

A Decade Review on Smart Cities: Paradigms, Challenges and Opportunities

et al. 2022

View full text Add to dashboard Cite

Smart City has been an emerging research domain for Government, Businesses, and researchers in the last few years. The Indian government is also interested and investing lots of funds to develop smart cities. These cities are technology-based and require interdisciplinary research and development for successful implementation. Over the last few decades, various technological interventions have created a tendency to provide smart everyday objects to make human life more comfortable. The emergence of the smart city paradigm is a response to creating a future city that guarantees the well-being and rights of its citizens from the perspective of industrial development: industry, urban planning, environment, and sustainable development. There are several subdomains in the smart city for the research. To work with the different subdomains in a smart city, proper guidance about the background of the smart city is required. This research paper is a guide for the same. This research paper represents a systematic literature review of the smart city domain. This paper carries out a systematic review of research papers published in various well-reputed journals like IEEE, Springer, Elsevier, etc., between 2011 and. This paper will help the government, businesses, and researchers aiming to enhance the smart city concept. Initially, this paper discusses the origin and emergence of this concept, followed by a few definitions and characteristics with the real roadmap and primary supporting pillars of the smart city. This paper discusses a typical architecture having different layers like Sensing, Transportation, Data Management, and Application Layers. There are various supporting technologies and platforms for the smart city; hence implementations are impossible without these technologies and media. This research paper discusses different components of the smart city. A broad literature survey is being done to observe various challenges, opportunities, and future trends in the smart city. This research paper can guide the researchers and provide the research direction in the smart city domain.

show abstract

Section: E Smart Peoplementioning

confidence: 99%

A Decade Review on Smart Cities: Paradigms, Challenges and Opportunities

et al. 2022

View full text Add to dashboard Cite

show abstract

“…One area of deep learning that has received little attention is crime forecasting. Several researchers observe that deep learning is also well suited to deal with the temporal and spatial elements of a problem [ 4 , 5 , 19 ].…”

Section: Related Workmentioning

confidence: 99%

“…We have chosen state-of-the-art New York City crime data [38] that has been used in several research articles. However, we now compare the results of this study under the same experimental setup with Random forest [39], ARIMA [4], SARIMA [5], and ZeroR [40]. To compare the results with state-of-the-art approaches, the same regions of New York City are used.…”

Section: Comparison Of the Proposed Approach With State-of-the-artmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy

et al. 2022

Self Cite

View full text Add to dashboard Cite

The continued urbanization poses several challenges for law enforcement agencies to ensure a safe and secure environment. Countries are spending a substantial amount of their budgets to control and prevent crime. However, limited efforts have been made in the crime prediction area due to the deficiency of spatiotemporal crime data. Several machine learning, deep learning, and time series analysis techniques are exploited, but accuracy issues prevail. Thus, this study proposed a Bidirectional Long Short Term Memory (Bi-LSTM) and Exponential Smoothing (ES) hybrid for crime forecasting. The proposed technique is evaluated using New York City crime data from 2010–2017. The proposed approach outperformed as compared to state-of-the-art Seasonal Autoregressive Integrated Moving Averages (SARIMA) with low Mean Absolute Percentage Error (MAPE) (0.3738, 0.3891, 0.3433,0.3964), Root Mean Square Error (RMSE)(13.146, 13.669, 13.104, 13.77), and Mean Absolute Error (MAE) (9.837, 10.896, 10.598, 10.721). Therefore, the proposed technique can help law enforcement agencies to prevent and control crime by forecasting crime patterns.

show abstract

“…La precisión del modelo se mide considerando diferentes escenarios de tiempo, como el año, (es decir, para cada año), y para la duración total considerada de diez años usando una proporción de 80:20. El 80% de los datos se utilizó para entrenamiento y el 20% para pruebas (Butt, 2021).…”

Section: Iot Para Gestionar Una Smart City?unclassified

Untitled

2021

ECT

View full text Add to dashboard Cite

que promueven en gran medida el intercambio y la gestión de información urbana. Las tecnologías de red emergentes se pueden utilizar para facilitar la construcción de ciudades inteligentes, favoreciendo el desarrollo de los negocios urbanos, la industria y otras organizaciones, así como la gestión del turismo, transporte, seguridad ciudadana, entre otros. Por lo tanto, la realización de una ciudad inteligente mejorará en gran medida la fuerza de desarrollo integral de la ciudad. Analizamos las ventajas de la computación en la niebla, los algoritmos de seguridad, las aplicaciones utilizada, las técnicas, metodologías, métodos de privacidad y seguridad, arquitecturas de software, big data, blockchain y Deep Learnig para proponer una aplicación con una arquitectura que resuelve eficazmente los problemas de la ciudad inteligente.

show abstract

Spatio-Temporal Crime Predictions by Leveraging Artificial Intelligence for Citizens Security in Smart Cities

Cited by 26 publications

References 50 publications

A Decade Review on Smart Cities: Paradigms, Challenges and Opportunities

A Decade Review on Smart Cities: Paradigms, Challenges and Opportunities

Hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy

Untitled

Contact Info

Product

Resources

About