Spatio-Temporal Crime HotSpot Detection and Prediction: A Systematic Literature Review

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

doi:10.1109/access.2020.3022808

Cited by 58 publications

(22 citation statements)

References 113 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, this study focused on identifying suitable deep neural architectures for HAR by exploiting the state-of-the-art deep learning paradigm. This SLR is conducted by following the guidelines from papers [34]- [36], [38], [60]. After considering the selection and rejection criteria, 70 articles are selected from Jan 2015 to May 2020 from five scientific databases, including ACM, IEEE, Science Direct, Springer, Taylor & Francis.…”

Section: Discussionmentioning

confidence: 99%

Analysis of Deep Neural Networks for Human Activity Recognition in Videos—A Systematic Literature Review

et al. 2021

Self Cite

View full text Add to dashboard Cite

From the past few decades, Human activity recognition (HAR) is one of the vital research areas in computer vision in which much research is ongoing. The researcher's focus is shifting towards this area due to its vast range of real-life applications to assist in daily living. Therefore, it is necessary to validate its performance on standard benchmark datasets and state-of-the-art systems before applying it in real-life applications. The primary objective of this Systematic Literature Review (SLR) is to collect existing research on video-based human activity recognition, summarize, and analyze the state-of-the-art deep learning architectures regarding various methodologies, challenges, and issues. The top five scientific databases (such as ACM, IEEE, ScienceDirect, SpringerLink, and Taylor & Francis) are accessed to accompany this systematic study by summarizing 70 different research articles on human activity recognition after critical review. Human activity recognition in videos is a challenging problem due to its diverse and complex nature. For accurate video classification, extraction of both spatial and temporal features from video sequences is essential. Therefore, this SLR focuses on reviewing the recent advancements in stratified self-deriving feature-based deep learning architectures. Furthermore, it explores various deep learning techniques available for HAR, challenges researchers to face to build a robust model, and state-of-theart datasets used for evaluation. This SLR intends to provide a baseline for video-based human activity recognition research while emphasizing several challenges regarding human activity recognition accuracy in video sequences using deep neural architectures.

show abstract

Section: Discussionmentioning

confidence: 99%

Analysis of Deep Neural Networks for Human Activity Recognition in Videos—A Systematic Literature Review

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…While the identification of spatial patterns keeps playing its vital role in crime research [28], the spatial-temporal crime patterns have received increasing attention over recent years [29][30][31]. Several reviews about the spatial-temporal methods for crime analysis have been conducted [32,33].…”

Section: Spatial-temporal Analysis Methods In Place-based Crime Researchmentioning

confidence: 99%

Discovering Spatial-Temporal Indication of Crime Association (STICA)

Jiang

Liu

Qin

et al. 2021

IJGI

View full text Add to dashboard Cite

The importance of combining spatial and temporal aspects has been increasingly recognized over recent years, yet pertinent pattern analysis methods in place-based crime research still need further development to explicitly indicate spatial-temporal localities of pertinent factors’ influence ranges. This paper proposes an approach, Spatial-Temporal Indication of Crime Association (STICA), to facilitate identifying the main contributing factors of crime, which are operated at diverse spatial-temporal scales. The method’s rationale is to progressively discern the spatial zones with diverse temporal crime patterns. A specific implementation of the STICA approach, by combining kernel density estimation, k-median-centers clustering, and thematic mapping, is applied to understand the burglary in an urban peninsula, China. The empirical findings include: (1) both the main time-stable and time-varying factors of crime can be indicated with the disparities of temporal crime patterns for different spatial zones based on the STICA results. (2) The spatial range of these factors can enlighten the understanding of interactions for generating crime patterns, especially with regards to how temporally transient and spatially global factors can produce a locally crime-ridden zone through the mediation of stable factors. (3) The STICA results can reveal the spatially contextual effects of stable factors, which are of great value to improve modeling crime patterns. As demonstrated, the STICA approach is effective in exploring contributing factors of crime and has shown great potential for providing a new vision in place-based crime research.

show abstract

“…A variety of techniques are available to obtain statistically significant locations of unusually high or low concentrations (or clusters), commonly referred to as hot and cold spots (Smith et al 2015 ). Spatial clustering techniques are commonly used in the study of human geographic issues such as crime (Butt et al 2020 ). In recent times, however, these methods have been increasingly used in the analysis of physical geographic phenomena such as floods (Brandt et al 2020 ) and urban temperatures (Guerri et al 2021 ).…”

Section: Introductionmentioning

confidence: 99%

Spatial Pattern and Land Surface Features Associated with Cloud-to-Ground Lightning in Bangladesh: An Exploratory Study

et al. 2022

View full text Add to dashboard Cite

Severe weather events such as lightning appear to be a significant threat to humans and property in South Asia, an area known for intense convective activity directly related to the tropical climate of these areas. The current study was conducted in Bangladesh and examined the association between cloud-to-ground (CG) lightning and ground surface properties, with the aim of improving existing knowledge regarding this phenomenon. GLD360 data from 2015 to 2020 were used to describe the seasonal lightning climatology. Elevation, land use and land cover, vegetation and surface heat flux data were used to examine all land surface features possibly associated with CG lightning occurrence. Hot and cold spot spatial patterning was calculated using local indicators of spatial association. Results indicated a strong CG lightning seasonality. CG stroke density varied considerably across seasons with the pre-monsoon exhibiting the highest density. This was followed by occurrences in the monsoon season. The March–June period experienced 73% of the total observed. Elevation appeared to influence the post-monsoon CG stroke, however, its role in the other seasons was more difficult to define. The land cover/lightning index indicated that waterbodies and herbaceous wetlands had more influence than other land cover types, both during the day and at night, and it appeared that latent heat flux played a major role. The CG stroke hot and cold spot locations varied diurnally. The findings suggest that large-scale irrigation practices, especially during the pre-monsoon months, can influence the observed spatiotemporal pattern. The production of hotspot maps could be an initial step in the development of a reliable lightning monitoring system and play a part in increasing public awareness of this issue.

show abstract

Spatio-Temporal Crime HotSpot Detection and Prediction: A Systematic Literature Review

Cited by 58 publications

References 113 publications

Analysis of Deep Neural Networks for Human Activity Recognition in Videos—A Systematic Literature Review

Analysis of Deep Neural Networks for Human Activity Recognition in Videos—A Systematic Literature Review

Discovering Spatial-Temporal Indication of Crime Association (STICA)

Spatial Pattern and Land Surface Features Associated with Cloud-to-Ground Lightning in Bangladesh: An Exploratory Study

Contact Info

Product

Resources

About