scholarly journals Spatiotemporal Prediction of Theft Risk with Deep Inception-Residual Networks

Smart Cities ◽  
2021 ◽  
Vol 4 (1) ◽  
pp. 204-216
Author(s):  
Xinyue Ye ◽  
Lian Duan ◽  
Qiong Peng
Keyword(s):  
New York ◽  
New York City ◽  
Emergency Service ◽  
Prediction Models ◽  
Smart Cities ◽  
Low Level ◽  
Fine Grained ◽  
Crime Prediction ◽  
High Level ◽  
Better Than

Spatiotemporal prediction of crime is crucial for public safety and smart cities operation. As crime incidents are distributed sparsely across space and time, existing deep-learning methods constrained by coarse spatial scale offer only limited values in prediction of crime density. This paper proposes the use of deep inception-residual networks (DIRNet) to conduct fine-grained, theft-related crime prediction based on non-emergency service request data (311 events). Specifically, it outlines the employment of inception units comprising asymmetrical convolution layers to draw low-level spatiotemporal dependencies hidden in crime events and complaint records in the 311 dataset. Afterward, this paper details how residual units can be applied to capture high-level spatiotemporal features from low-level spatiotemporal dependencies for the final prediction. The effectiveness of the proposed DIRNet is evaluated based on theft-related crime data and 311 data in New York City from 2010 to 2015. The results confirm that the DIRNet obtains an average F1 of 71%, which is better than other prediction models.

scholarly journals Saliency Detection by Multilevel Deep Pyramid Model

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Hai Wang ◽  
Lei Dai ◽  
Yingfeng Cai ◽  
Long Chen ◽  
Yong Zhang
Keyword(s):  
Background Noise ◽  
State Of The Art ◽  
Saliency Detection ◽  
Saliency Map ◽  
Multiple Features ◽  
Low Level ◽  
Pyramid Model ◽  
High Level ◽  
Different Levels ◽  
Better Than

Traditional salient object detection models are divided into several classes based on low-level features and contrast between pixels. In this paper, we propose a model based on a multilevel deep pyramid (MLDP), which involves fusing multiple features on different levels. Firstly, the MLDP uses the original image as the input for a VGG16 model to extract high-level features and form an initial saliency map. Next, the MLDP further extracts high-level features to form a saliency map based on a deep pyramid. Then, the MLDP obtains the salient map fused with superpixels by extracting low-level features. After that, the MLDP applies background noise filtering to the saliency map fused with superpixels in order to filter out the interference of background noise and form a saliency map based on the foreground. Lastly, the MLDP combines the saliency map fused with the superpixels with the saliency map based on the foreground, which results in the final saliency map. The MLDP is not limited to low-level features while it fuses multiple features and achieves good results when extracting salient targets. As can be seen in our experiment section, the MLDP is better than the other 7 state-of-the-art models across three different public saliency datasets. Therefore, the MLDP has superiority and wide applicability in extraction of salient targets.

Distractor-Aware Tracking with Multi-Task and Dynamic Feature Learning

2020 ◽  
pp. 2150031
Author(s):  
Weichun Liu ◽  
Xiaoan Tang ◽  
Chenglin Zhao
Keyword(s):  
Correlation Filter ◽  
Coarse Grained ◽  
Dynamic Feature ◽  
Semantic Features ◽  
Low Level ◽  
Fine Grained ◽  
Semantic Embedding ◽  
Training Stage ◽  
Online Tracking ◽  
High Level

Recently, deep trackers based on the siamese networking are enjoying increasing popularity in the tracking community. Generally, those trackers learn a high-level semantic embedding space for feature representation but lose low-level fine-grained details. Meanwhile, the learned high-level semantic features are not updated during online tracking, which results in tracking drift in presence of target appearance variation and similar distractors. In this paper, we present a novel end-to-end trainable Convolutional Neural Network (CNN) based on the siamese network for distractor-aware tracking. It enhances target appearance representation in both the offline training stage and online tracking stage. In the offline training stage, this network learns both the low-level fine-grained details and high-level coarse-grained semantics simultaneously in a multi-task learning framework. The low-level features with better resolution are complementary to semantic features and able to distinguish the foreground target from background distractors. In the online stage, the learned low-level features are fed into a correlation filter layer and updated in an interpolated manner to encode target appearance variation adaptively. The learned high-level features are fed into a cross-correlation layer without online update. Therefore, the proposed tracker benefits from both the adaptability of the fine-grained correlation filter and the generalization capability of the semantic embedding. Extensive experiments are conducted on the public OTB100 and UAV123 benchmark datasets. Our tracker achieves state-of-the-art performance while running with a real-time frame-rate.

scholarly journals Crime Prediction with Historical Crime and Movement Data of Potential Offenders Using a Spatio-Temporal Cokriging Method

2020 ◽  
Vol 9 (12) ◽  
pp. 732
Author(s):  
Hongjie Yu ◽  
Lin Liu ◽  
Bo Yang ◽  
Minxuan Lan
Keyword(s):  
Machine Learning ◽  
Data Fusion ◽  
Prediction Models ◽  
Crime Data ◽  
Crime Prediction ◽  
Movement Data ◽  
Environment Variables ◽  
Spatio Temporal ◽  
Fine Resolution ◽  
Better Than

Crime prediction using machine learning and data fusion assimilation has become a hot topic. Most of the models rely on historical crime data and related environment variables. The activity of potential offenders affects the crime patterns, but the data with fine resolution have not been applied in the crime prediction. The goal of this study is to test the effect of the activity of potential offenders in the crime prediction by combining this data in the prediction models and assessing the prediction accuracies. This study uses the movement data of past offenders collected in routine police stop-and-question operations to infer the movement of future offenders. The offender movement data compensates historical crime data in a Spatio-Temporal Cokriging (ST-Cokriging) model for crime prediction. The models are implemented for weekly, biweekly, and quad-weekly prediction in the XT police district of ZG city, China. Results with the incorporation of the offender movement data are consistently better than those without it. The improvement is most pronounced for the weekly model, followed by the biweekly model, and the quad-weekly model. In sum, the addition of offender movement data enhances crime prediction, especially for short periods.

scholarly journals Electrophysiological signatures of hierarchical learning

2021 ◽  
Author(s):  
Meng Liu ◽  
Wenshan Dong ◽  
Shaozheng Qin ◽  
Tom Verguts ◽  
Qi Chen
Keyword(s):  
Cognitive Process ◽  
Human Perception ◽  
Learning Task ◽  
Prediction Errors ◽  
Neural Basis ◽  
Hierarchical Learning ◽  
Low Level ◽  
High Level ◽  
The Brain ◽  
Better Than

AbstractHuman perception and learning is thought to rely on a hierarchical generative model that is continuously updated via precision-weighted prediction errors (pwPEs). However, the neural basis of such cognitive process and how it unfolds during decision making, remain poorly understood. To investigate this question, we combined a hierarchical Bayesian model (i.e., Hierarchical Gaussian Filter, HGF) with electrophysiological (EEG) recording, while participants performed a probabilistic reversal learning task in alternatingly stable and volatile environments. Behaviorally, the HGF fitted significantly better than two control, non-hierarchical, models. Neurally, low-level and high-level pwPEs were independently encoded by the P300 component. Low-level pwPEs were reflected in the theta (4-8 Hz) frequency band, but high-level pwPEs were not. Furthermore, the expressions of high-level pwPEs were stronger for participants with better HGF fit. These results indicate that the brain employs hierarchical learning, and encodes both low- and high-level learning signals separately and adaptively.

scholarly journals Characterization of streptomycin resistance mechanisms among Mycobacterium tuberculosis isolates from patients in New York City.

1996 ◽  
Vol 40 (5) ◽  
pp. 1186-1188 ◽  
Author(s):  
R C Cooksey ◽  
G P Morlock ◽  
A McQueen ◽  
S E Glickman ◽  
J T Crawford
Keyword(s):  
New York ◽  
New York City ◽  
Mycobacterium Tuberculosis ◽  
York City ◽  
Resistance Mechanism ◽  
Ribosomal Protein Gene ◽  
Resistance Mechanisms ◽  
Coding Region ◽  
Low Level

From a collection of 367 isolates of Mycobacterium tuberculosis from patients in New York City in 1994, 45 isolates (12.3%) were resistant in vitro to 2 micrograms or more of streptomycin (SM) per ml. We further evaluated these isolates for levels of SM resistance and for mutations previously associated with resistance in the rpsL (S12 ribosomal protein) gene and the rrs (16S rRNA)-coding region. Twenty-four isolates, representing nine distinct patterns of susceptibility to antituberculosis drugs, were resistant to 500 micrograms of SM per ml and shared a common point mutation at nucleotide 128 in the rpsL gene. This mutation, which substitutes lysine for arginine in the S12 ribosomal binding protein, was not present in isolates with low-level SM resistance or in SM-susceptible control isolates. Among 20 isolates with low-level SM resistance, one possessed a substitution (C-->G865) in the 912 loop of the rrs gene. No mutations in the 530 loop of the rrs coding region were detected, suggesting the presence of an alternative SM resistance mechanism in 19 isolates. Single-strand conformation polymorphisms of mutants were readily detected by a nonradioactive gel screen.

Development of a Hybrid Model for Dynamic Travel-Time Prediction

2003 ◽  
Vol 1855 (1) ◽  
pp. 22-31 ◽  
Author(s):  
Chandra Mouly Kuchipudi ◽  
Steven I. J. Chien
Keyword(s):  
New York ◽  
Travel Time ◽  
Hybrid Model ◽  
Prediction Models ◽  
New York State ◽  
State Variables ◽  
Travel Time Prediction ◽  
Time Prediction ◽  
Historic Data ◽  
Better Than

Travel-time prediction has been an interesting research subject for decades, and various prediction models have been developed. A prediction model was derived by integrating path-based and link-based prediction models. Prediction results generated by the hybrid model and their accuracy are compared with those generated by the path-based and link-based models individually. The models were developed with real-time and historic data collected from the New York State Thruway by the Transportation Operations Coordinating Committee. In these models, the Kalman filtering algorithm is applied for travel-time prediction because of its significance in continuously updating the state variables as new observations. The experimental results reveal that the travel times predicted with the path-based model are better than those predicted with the link-based model during peak periods, and vice versa. The hybrid model derives results from the best model at a given time, thus optimizing the performance. A prototype prediction system was developed on the World Wide Web.

scholarly journals A Privacy-Preserving Attribute-Based Encryption System for Data Sharing in Smart Cities

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Xieyang Shen ◽  
Chuanhe Huang ◽  
Danxin Wang ◽  
Jiaoli Shi
Keyword(s):  
Data Sharing ◽  
Service Providers ◽  
Smart Cities ◽  
Information Leakage ◽  
Cloud Service ◽  
Data Access ◽  
Smart Devices ◽  
Fine Grained ◽  
Data Access Control ◽  
High Level

Information leakage and efficiency are the two main concerns of data sharing in cloud-aided IoT. The main problem is that smart devices cannot afford both energy and computation costs and tend to outsource data to a cloud server. Furthermore, most schemes focus on preserving the data stored in the cloud but omitting the access policy is typically stored in unencrypted form. In this paper, we proposed a fine-grained data access control scheme based on CP-ABE to implement access policies with a greater degree of expressiveness as well as hidden policies from curious cloud service providers. Moreover, to mitigate the extra computation cost generated by complex policies, an outsourcing service for decryption can be used by data users. Further experiments and extensive analysis show that we significantly decrease the communication and computation overhead while providing a high-level security scheme compared with the existing schemes.

scholarly journals Knowledge Graph Representation Fusion Framework for Fine-Grained Object Recognition in Smart Cities

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Yang He ◽  
Ling Tian ◽  
Lizong Zhang ◽  
Xi Zeng
Keyword(s):  
Knowledge Representation ◽  
Image Classification ◽  
Visual Information ◽  
Smart Cities ◽  
Image Features ◽  
Graph Representation ◽  
Knowledge Graph ◽  
Fine Grained ◽  
High Level ◽  
Traditional Approaches

Autonomous object detection powered by cutting-edge artificial intelligent techniques has been an essential component for sustaining complex smart city systems. Fine-grained image classification focuses on recognizing subcategories of specific levels of images. As a result of the high similarity between images in the same category and the high dissimilarity in the same subcategories, it has always been a challenging problem in computer vision. Traditional approaches usually rely on exploring only the visual information in images. Therefore, this paper proposes a novel Knowledge Graph Representation Fusion (KGRF) framework to introduce prior knowledge into fine-grained image classification task. Specifically, the Graph Attention Network (GAT) is employed to learn the knowledge representation from the constructed knowledge graph modeling the categories-subcategories and subcategories-attributes associations. By introducing the Multimodal Compact Bilinear (MCB) module, the framework can fully integrate the knowledge representation and visual features for learning the high-level image features. Extensive experiments on the Caltech-UCSD Birds-200-2011 dataset verify the superiority of our proposed framework over several existing state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document