Abstract
To enhance crime prevention, methods of predicting crime trends are researched. First, the concepts and theories of criminal psychology are analyzed. Second, the Convolutional Neural Network (CNN) principles in deep learning are studied. Third, a 3D-CNN model is established and utilized to construct a crime prediction model. Finally, data mining and cloud computing techniques are employed to store and calculate massive amounts of data. The constructed crime prediction model analyzes the information and data in the cloud computing platform and evaluates the model’s prediction effect on crime trends. Six hundred sets of behavior data are extracted as a training dataset and 100 sets of data as a testing dataset. Results demonstrate that the established 3D-CNN can extract information features from continuous multi-frame cube data and acquire features of spatial–temporal dimensions. When the learning rate is 0.01, the loss value begins to decrease rapidly and then stabilizes. When the learning rate is 0.001, the loss decreases relatively slowly and eventually stabilizes. As the iteration times of CNN increase, the algorithm’s error rate first decreases and then increases. The cloud computing platform can store a large amount of data to facilitate video data calls and analyses. Combining the information and data of past crimes can accurately predict future crime trends.
Similar content being viewed by others
References
Arias-Pujol E, Anguera MT (2020) A mixed methods framework for psychoanalytic group therapy: from qualitative records to a quantitative approach using T-pattern, lag sequential and polar coordinate analyses. Front Psychol 11:1922
Ayrey E, Hayes DJ (2018) The use of three-dimensional convolutional neural networks to interpret LiDAR for forest inventory. Remote Sens 10:649
Bejiga MB, Zeggada A, Nouffidj A, Melgani F (2017) A convolutional neural network approach for assisting avalanche search and rescue operations with UAV imagery. Remote Sens 9:100
Bousefsaf F, Pruski A, Maaoui C (2019) 3D Convolutional neural networks for remote pulse rate measurement and mapping from facial video. Appl Sci 9(20):4364
Brougham PL, Uttley CM (2017) Risk for researchers studying social deviance or criminal behavior. Soc Sci 6:130
Chambon V, Bigenwald A (2019) Criminal responsibility and neuroscience: no revolution yet. Front Psychol 10:1406
de Rafael GH, Fernández-Prados JS (2019) Victimization, social structure and psychosocial variables: the case of Spain in 1999 and 2016. Soc Sci 8:102
Dinh T, Kim Y, Lee HA (2017) Location-based interactive model of internet of things and cloud (IoT-Cloud) for mobile cloud computing applications. Sensors 17:489
Fingelkurts AA, Fingelkurts AA (2017) Information flow in the brain: ordered sequences of metastable states. Information 8:22
Gassen J, Mengelkoch S, Bradshaw HK et al (2020) Does the punishment fit the crime (and immune system)? A potential role for the immune system in regulating punishment sensitivity. Front Psychol 11:1263
Gennaro A, Kipp S, Viol K et al (2020) A phase transition of the unconscious: automated text analysis of dreams in psychoanalytic psychotherapy. Front Psychol 11:1667
Hatton SB (2017) Criminal modus operandi and psychoanalysis as genealogical evidence. Genealogy 1:8
Idsø J, Årethun T (2018) Crime statistics: modeling theft in favour of victims’ choices. Economies 6:25
Kerr J (2018) The art of violent protest and crime prevention. Arts 7:61
Kuang L, Yan X, Tan X et al (2019) Predicting taxi demand based on 3D convolutional neural network and multi-task learning. Remote Sens 11(11):1265
Lee JS, Park S, Jung S (2016) Effect of crime prevention through environmental design (CPTED) measures on active living and fear of crime. Sustainability 8:872
Li Z, Yang C, Liu K, Hu F, Jin B (2016) Automatic scaling hadoop in the cloud for efficient process of big geospatial data. ISPRS Int J Geo Inf 5:173
Li Y, Zhang H, Shen Q (2017) Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sens 9:67
Liang H, Li Q (2016) Hyperspectral imagery classification using sparse representations of convolutional neural network features. Remote Sens 8:99
Lim M, Abdullah A, Jhanjhi N, Supramaniam M (2019) Hidden link prediction in criminal networks using the deep reinforcement learning technique. Computers 8:8
Lin YL, Yen MF, Yu LC (2018) Grid-based crime prediction using geographical features. ISPRS Int J Geo Inf 7(8):298
Liu Y, Chen M (2021) Applying text similarity algorithm to analyze the triangular citation behavior of scientists. Appl Soft Comput 107:107362. https://doi.org/10.1016/j.asoc.2021.107362
Liu L, Chui WH, Chen Y (2018) Violent and non-violent criminal behavior among young Chinese drug users: a mixed methods study. Int J Environ Res Public Health 15:432
Ma X, Dai Z, He Z, Ma J, Wang Y, Wang Y (2017) Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction. Sensors 17:818
Ma C, Zhang Y, Wang A, Wang Y, Chen G (2018) Traffic command gesture recognition for virtual urban scenes based on a spatiotemporal convolution neural network. ISPRS Int J Geo Inf 7:37
Mei S, Yuan X, Ji J, Zhang Y, Wan S, Du Q (2017) Hyperspectral image spatial super-resolution via 3D full convolutional neural network. Remote Sens 9:1139
Mihinjac M, Saville G (2019) Third-generation crime prevention through environmental design (CPTED). Soc Sci 8:182
Park JH, Park JH (2017) Blockchain security in cloud computing: use cases, challenges, and solutions. Symmetry 9:164
Pecino-Latorre MM, Pérez-Fuentes MC, Patró-Hernández RM (2019a) Homicide profiles based on crime scene and victim characteristics. Int J Environ Res Public Health 16:3629
Pecino-Latorre MM, Pérez-Fuentes MC, Patró-Hernández RM, Santos-Hermoso J (2019b) Expressiveness and instrumentality of crime scene behavior in spanish homicides. Int J Environ Res Public Health 16:4526
Qi W, Zhang X, Wang N et al (2019) a spectral-spatial cascaded 3D convolutional neural network with a convolutional long short-term memory network for hyperspectral image classification. Remote Sens 11(20):2363
Ran L, Zhang Y, Zhang Q, Yang T (2017) Convolutional neural network-based robot navigation using uncalibrated spherical images. Sensors 17:1341
Reed CL, Moody EJ, Mgrublian K et al (2020) Body matters in emotion: restricted body movement and posture affect expression and recognition of status-related emotions. Front Psychol 11:1961
Schruijer S (2018) The role of collusive dynamics in the occurrence of organizational crime: a psychoanalytically informed social psychological perspective. Adm Sci 8:24
Shahrivari S (2014) Beyond batch processing: towards real-time and streaming big data. Computers 3:117–129
Shen C-W, Min C, Wang C-C (2019) Analyzing the trend of O2O commerce by bilingual text mining on social media. Comput Hum Behav 101:474–483. https://doi.org/10.1016/j.chb.2018.09.031
Srivastava S, Saxena S, Buyya R, Kumard M, Shankare A, Bhushan B (2021) CGP: cluster-based gossip protocol for dynamic resource environment in cloud. Simul Model Pract Theory 108:102275
Tang Y, Zhu X, Guo W, Ye X, Hu T, Fan Y, Zhang F (2017) Non-homogeneous diffusion of residential crime in urban China. Sustainability 9:934
Tom-Jack QT, Bernstein JM, Loyola LC (2019) The role of geoprocessing in mapping crime using hot streets. ISPRS Int J Geo Inf 8:540
Ullah FUM, Ullah A, Muhammad K et al (2019) Violence detection using spatiotemporal features with 3D convolutional neural network. Sensors 19(11):2472
Wang H, Wang Y, Zhang Q, Xiang S, Pan C (2017) Gated convolutional neural network for semantic segmentation in high-resolution images. Remote Sens 9:446
Wang L, Lee G, Williams I (2019a) The spatial and social patterning of property and violent crime in toronto neighbourhoods: a spatial-quantitative approach. ISPRS Int J Geo Inf 8:51
Wang Z, Liu L, Zhou H, Lan M (2019b) Crime geographical displacement: testing its potential contribution to crime prediction. ISPRS Int J Geo Inf 8:383
Wu SM, Chen T-C, Wu YJ, Lytras M (2018) smart cities in taiwan: a perspective on big data applications. Sustainability 10:106
Yu Y, Lin H, Meng J, Zhao Z (2016) Visual and textual sentiment analysis of a microblog using deep convolutional neural networks. Algorithms 9:41
Acknowledgements
This project was supported by Ministry of Education humanities and social sciences youth fund project (18YJC820067) and Key Project of Education Department of Anhui Province (gxyqZD2019138).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wu, Y. The impact of criminal psychology trend prediction based on deep learning algorithm and three-dimensional convolutional neural network. J Ambient Intell Human Comput (2021). https://doi.org/10.1007/s12652-021-03455-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12652-021-03455-8