Spatiotemporal Prediction of Theft Risk with Deep Inception-Residual Networks

Ye, Xinyue; Duan, Lian; Peng, Qiong

doi:10.3390/smartcities4010013

Cited by 11 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…High values for the precision and recall show the acceptable performance of the YOLO v4, R-FCN ResNet101, Faster R-CNN Inception V2 models for the detection of visible mechanical damage in sugar beet. The F1-score, as a harmonic mean of precision and recall of a model, shows how robust the performance of a model is [29]. In this study, the YOLO v4 model shows better performance compared to the other developed networks.…”

Section: Resultsmentioning

confidence: 57%

Sugar Beet Damage Detection during Harvesting Using Different Convolutional Neural Network Models

2021

View full text Add to dashboard Cite

Mechanical damages of sugar beet during harvesting affects the quality of the final products and sugar yield. The mechanical damage of sugar beet is assessed randomly by operators of harvesters and can depend on the subjective opinion and experience of the operator due to the complexity of the harvester machines. Thus, the main aim of this study was to determine whether a digital two-dimensional imaging system coupled with convolutional neural network (CNN) techniques could be utilized to detect visible mechanical damage in sugar beet during harvesting in a harvester machine. In this research, various detector models based on the CNN, including You Only Look Once (YOLO) v4, region-based fully convolutional network (R-FCN) and faster regions with convolutional neural network features (Faster R-CNN) were developed. Sugar beet image data during harvesting from a harvester in different farming conditions were used for training and validation of the proposed models. The experimental results showed that the YOLO v4 CSPDarknet53 method was able to detect damage in sugar beet with better performance (recall, precision and F1-score of about 92, 94 and 93%, respectively) and higher speed (around 29 frames per second) compared to the other developed CNNs. By means of a CNN-based vision system, it was possible to automatically detect sugar beet damage within the sugar beet harvester machine.

show abstract

Section: Resultsmentioning

confidence: 57%

Sugar Beet Damage Detection during Harvesting Using Different Convolutional Neural Network Models

2021

View full text Add to dashboard Cite

show abstract

“…(2017), and Ye et al. (2021) state that 311 reports are different from location to location, and this variation can represent information about census tracts.…”

Section: The Proposed Stftis Modelmentioning

confidence: 99%

STFTiS: Introducing a spatio‐temporal FTiS model to investigate the level of citizens' satisfaction of 311 non‐emergency services

Mohammadi

Taleai

Alizadeh

et al. 2022

Transactions in GIS

View full text Add to dashboard Cite

Using the 311 service, citizens can help the government gain a deeper understanding of citizens' needs by reporting the status of municipal services. This study proposes the STFTiS model to examine the level of citizens' satisfaction by investigating the spatio‐temporal patterns of 311 reports provided by citizens regarding municipal services. The main novelty of the proposed STFTiS model is its ability to integrate the spatial domain into the traditional FTiS (frequency, time interval, and satisfaction) model. For this purpose, Moran's I index was used to cluster the 311 reports from a spatial perspective. Afterward, the reports were clustered based on the spatial labels and the parameters of time interval and frequency. A fuzzy time series and an autoregressive moving average prediction model have been combined to find the best temporal window for association rule mining. The proposed model was applied to a database of the Boston 311 service. The results from interpreting clusters indicate that Boston's citizens are most interested in government responses to address Transportation and Inspection Service issues. Besides, the most important rule states a strong relationship between the Mayor's 24‐Hour Hotline and Inspection Service reports, with 86% support and 95.7% confidence. The evaluation shows that the STFTiS model has significantly improved the results of the non‐spatial FTiS model. The results can be used by policymakers to effectively manage citizens' needs and provide necessary on‐demand support by discovering the most critical needs of citizens.

show abstract

“…OpenStreetMap is a collaborative project that creates a free editable geographic database of the world. 17 In fine-grained crime analysis such as hot spot prediction, geographical information such as road network can be obtained from such data source [14,147,156]. Some researchers have explored visual data in crime prediction [156], such as Google Street View data, which provide more than 10 million miles of street view imagery across 83 countries.…”

Section: Open Source Indicatorsmentioning

confidence: 99%

“…Due to the low regularity of crime data in both space and time, the authors preprocessed the crime data to select appropriate spatio-temporal scales for prediction and proposed different data regularization methods for spatial and temporal dimensions. Furthermore, to address the problem of the sparsity of crime events in space and time, Ye et al [147] proposed a deep inception-residual network (DIRNet) to conduct theft-related crime prediction based on crime and 311 data. This framework consists of convolutional layers and inception layers to extract spatiotemporal dependencies from crime and 311 data, respectively.…”

Section: Feedforward Neural Network Based Approachesmentioning

confidence: 99%

“…CNN is designed to automatically learn spatial hierarchies of features through backpropagation by using multiple building blocks, such as convolution layers, pooling layers. Compared to limited research on CNNs in civil unrest prediction more studies have explored CNNs in crime prediction [37,52,128,147,156]. This is mainly because that the spatial granularity of criminal events is usually smaller than civil unrest.…”

Section: Deep Learning Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Societal Event Forecasting with Deep Learning

Deng¹,

Ning²

2021

Preprint

View full text Add to dashboard Cite

Population-level societal events, such as civil unrest and crime, often have a significant impact on our daily life. Forecasting such events is of great importance for decision-making and resource allocation. Event prediction has traditionally been challenging due to the lack of knowledge regarding the true causes and underlying mechanisms of event occurrence. In recent years, research on event forecasting has made significant progress due to two main reasons: (1) the development of machine learning and deep learning algorithms and (2) the accessibility of public data such as social media, news sources, blogs, economic indicators, and other meta-data sources. The explosive growth of data and the remarkable advancement in software/hardware technologies have led to applications of deep learning techniques in societal event studies. This paper is dedicated to providing a systematic and comprehensive overview of deep learning technologies for societal event predictions. We focus on two domains of societal events: civil unrest and crime. We first introduce how event forecasting problems are formulated as a machine learning prediction task. Then, we summarize data resources, traditional methods, and recent development of deep learning models for these problems. Finally, we discuss the challenges in societal event forecasting and put forward some promising directions for future research.

show abstract

Spatiotemporal Prediction of Theft Risk with Deep Inception-Residual Networks

Cited by 11 publications

References 27 publications

Sugar Beet Damage Detection during Harvesting Using Different Convolutional Neural Network Models

Sugar Beet Damage Detection during Harvesting Using Different Convolutional Neural Network Models

STFTiS: Introducing a spatio‐temporal FTiS model to investigate the level of citizens' satisfaction of 311 non‐emergency services

A Survey on Societal Event Forecasting with Deep Learning

Contact Info

Product

Resources

About