scholarly journals Multi-stage online task assignment driven by offline data under spatio-temporal crowdsourcing

2021 ◽  
Author(s):  
Qi Zhang ◽  
Yingjie Wang ◽  
Zhipeng Cai ◽  
Xiangrong Tong
Keyword(s):  
Task Assignment ◽  
Multi Stage ◽  
Spatio Temporal

Multi-Stage Complex Task Assignment in Spatial Crowdsourcing

2021 ◽  
Author(s):  
Zhao Liu ◽  
Kenli Li ◽  
Xu Zhou ◽  
Ningbo Zhu ◽  
Yunjun Gao ◽  
...  
Keyword(s):  
Task Assignment ◽  
Complex Task ◽  
Spatial Crowdsourcing ◽  
Multi Stage

scholarly journals Growth Optima and Supply-Chain of the Walnut Crop in India

2020 ◽  
Vol 10 (2) ◽  
pp. 708-720
Author(s):  
Bakhtaver Hassan ◽  
Mahua Bhattacharjee ◽  
Shabir A Wani
Keyword(s):  
High Growth ◽  
Efficiency Index ◽  
Marketing Channels ◽  
High Variability ◽  
Primary Data ◽  
Annual Growth Rate ◽  
Compound Annual Growth Rate ◽  
Multi Stage ◽  
Spatio Temporal ◽  
Very High

This paper intends to study the Spatio-temporal growth of the walnut crop in Jammu & Kashmir, which holds a monopoly in walnut production in India. It also aims to assess the efficiency of the existing marketing channels of the walnut-crop in the region. A multi-stage random selection technique was used to collect primary data from three major walnut producing districts to identify the existing marketing channels and estimate their respective efficiencies. Compound-Annual-Growth-rate and Cuddy-Della-Valle index was used to estimate the growth of the walnut crop. Shepherd’s Marketing Efficiency Index was used to estimate the marketing efficiencies of the channels involved in the marketing of the crop. This paper found out very-high variability and slow growth in acreage, very-high variability, and high growth in production as well as in yield-per-hectare of the walnut crop.

scholarly journals Preference-Aware Task Assignment in Spatial Crowdsourcing

2019 ◽  
Vol 33 ◽  
pp. 2629-2636 ◽  
Author(s):  
Yan Zhao ◽  
Jinfu Xia ◽  
Guanfeng Liu ◽  
Han Su ◽  
Defu Lian ◽  
...  
Keyword(s):  
Performance Optimization ◽  
Task Assignment ◽  
Tensor Decomposition ◽  
Spatial Task ◽  
Smart Devices ◽  
Three Dimension ◽  
Spatial Crowdsourcing ◽  
Task Time ◽  
Spatio Temporal ◽  
Temporal Preferences

With the ubiquity of smart devices, Spatial Crowdsourcing (SC) has emerged as a new transformative platform that engages mobile users to perform spatio-temporal tasks by physically traveling to specified locations. Thus, various SC techniques have been studied for performance optimization, among which one of the major challenges is how to assign workers the tasks that they are really interested in and willing to perform. In this paper, we propose a novel preference-aware spatial task assignment system based on workers’ temporal preferences, which consists of two components: History-based Context-aware Tensor Decomposition (HCTD) for workers’ temporal preferences modeling and preference-aware task assignment. We model worker preferences with a three-dimension tensor (worker-task-time). Supplementing the missing entries of the tensor through HCTD with the assistant of historical data and other two context matrices, we recover worker preferences for different categories of tasks in different time slots. Several preference-aware task assignment algorithms are then devised, aiming to maximize the total number of task assignments at every time instance, in which we give higher priorities to the workers who are more interested in the tasks. We conduct extensive experiments using a real dataset, verifying the practicability of our proposed methods.

scholarly journals Mapping Mouse Behavior with an Unsupervised Spatio-temporal Sequence Decomposition Framework

2020 ◽  
Author(s):  
Kang Huang ◽  
Yaning Han ◽  
Ke Chen ◽  
Hongli Pan ◽  
Wenling Yi ◽  
...  
Keyword(s):  
Animal Behavior ◽  
Brain Activity ◽  
Disease Model ◽  
Three Dimensional ◽  
Feature Space ◽  
Rodent Behavior ◽  
Multi Stage ◽  
Motion Features ◽  
Spatio Temporal ◽  
And Behavior

AbstractObjective quantification of animal behavior is crucial to understanding the relationship between brain activity and behavior. For rodents, this has remained a challenge due to the high-dimensionality and large temporal variability of their behavioral features. Inspired by the natural structure of animal behavior, the present study uses a parallel, and multi-stage approach to decompose motion features and generate an objective metric for mapping rodent behavior into the animal feature space. Incorporating a three-dimensional (3D) motion-capture system and unsupervised clustering into this approach, we developed a novel framework that can automatically identify animal behavioral phenotypes from experimental monitoring. We demonstrate the efficacy of our framework by generating an “autistic-like behavior space” that can robustly characterize a transgenic mouse disease model based on motor activity without human supervision. The results suggest that our framework features a broad range of applications, including animal disease model phenotyping and the modeling of relationships between neural circuits and behavior.

scholarly journals Local-aware spatio-temporal attention network with multi-stage feature fusion for human action recognition

2021 ◽  
Author(s):  
Yaqing Hou ◽  
Hua Yu ◽  
Dongsheng Zhou ◽  
Pengfei Wang ◽  
Hongwei Ge ◽  
...  
Keyword(s):  
Action Recognition ◽  
Feature Fusion ◽  
Human Action Recognition ◽  
Human Action ◽  
Spatial Network ◽  
Stream Networks ◽  
Human Actions ◽  
Attention Network ◽  
Multi Stage ◽  
Spatio Temporal

AbstractIn the study of human action recognition, two-stream networks have made excellent progress recently. However, there remain challenges in distinguishing similar human actions in videos. This paper proposes a novel local-aware spatio-temporal attention network with multi-stage feature fusion based on compact bilinear pooling for human action recognition. To elaborate, taking two-stream networks as our essential backbones, the spatial network first employs multiple spatial transformer networks in a parallel manner to locate the discriminative regions related to human actions. Then, we perform feature fusion between the local and global features to enhance the human action representation. Furthermore, the output of the spatial network and the temporal information are fused at a particular layer to learn the pixel-wise correspondences. After that, we bring together three outputs to generate the global descriptors of human actions. To verify the efficacy of the proposed approach, comparison experiments are conducted with the traditional hand-engineered IDT algorithms, the classical machine learning methods (i.e., SVM) and the state-of-the-art deep learning methods (i.e., spatio-temporal multiplier networks). According to the results, our approach is reported to obtain the best performance among existing works, with the accuracy of 95.3% and 72.9% on UCF101 and HMDB51, respectively. The experimental results thus demonstrate the superiority and significance of the proposed architecture in solving the task of human action recognition.

scholarly journals Spatio-Temporal Heterogeneity of Schistosomiasis in China Based on Multi-stage, Continuous Downscaling of Sentinel Monitoring

2021 ◽  
Author(s):  
Yan-Feng Gong ◽  
Jia-Xin Feng ◽  
Zhuo-Wei Luo ◽  
Jing-Bo Xue ◽  
Zhao-Yu Guo ◽  
...  
Keyword(s):  
Temporal Trends ◽  
Poisson Model ◽  
Sichuan Province ◽  
Dongting Lake ◽  
Hunan Province ◽  
Jiangxi Province ◽  
Temporal Heterogeneity ◽  
Multi Stage ◽  
Spatio Temporal ◽  
Human Infections

Abstract Background: There is a continuous decline in the prevalence of schistosomiasis and the number of Schistosoma japonicum infections in humans and livestock in China. However, there are a large number of factors that have not been resolved and which may contribute to future transmission of schistosomiasis. These include a range of sources for S. japonicum infection, difficulty in management of S. japonicum sources of infection, frequent emergence and re-emergence of Oncomelania hupensis snail habitats, and the problematic elimination of snail habitats. These factors challenge progress towards the elimination of schistosomiasis in China.Methods: Based on multi-stage continuous downscaling of sentinel monitoring, county-based schistosomiasis surveillance data were captured from the national schistosomiasis surveillance sites of China from 2005 to 2019. The data included S. japonicum infections in humans, livestock, and O. hupensis. The spatio-temporal trends for schistosomiasis were detected using a Joinpoint regression model, with a standard deviational ellipse (SDE) tool, which determined the central tendency and dispersion in spatial distribution of schistosomiasis. Further, spatio-temporal clusters of S. japonicum infections in humans, livestock, and O. hupensis were evaluated by Poisson model. Results: The prevalence of S. japonicum human infections was reduced from 2.06% to zero based on the national schistosomiasis surveillance sites of China during the period from 2005 to 2019, with a reduction from 9.42% to zero for the prevalence of S. japonicum infections in livestock, and from 0.26% to zero for the prevalence of S. japonicum infections in O. hupensis. The decline in prevalence of S. japonicum infections in humans, livestock, and O. hupensis was statistically significant from 2005 to 2019 (P < 0.01). There was an exception to the decline in S. japonicum infections in livestock during the period from 2008 to 2012. Using an SDE tool, schistosomiasis-affected regions were reduced yearly from 2005 to 2014 in the endemic provinces of Hunan, Hubei, Jiangxi, and Anhui, as well as in the Poyang and Dongting Lake regions. Poisson model revealed 11 clusters of S. japonicum human infections, six clusters of S. japonicum infections in livestock, and nine clusters of S. japonicum infections in O. hupensis. The clusters of human infection were found to be highly consistent with clusters of S. japonicum infections in livestock and O. hupensis. These clusters were in the five provinces of Hunan, Hubei, Jiangxi, Anhui, and Jiangsu, as well as along the middle and lower reaches of the Yangtze River. Humans, livestock, and O. hupensis infections with S. japonicum were mainly concentrated in the north of the Hunan Province, south of the Hubei Province, north of the Jiangxi Province, and southwestern portion of Anhui Province. In the two mountainous provinces of Sichuan and Yunnan; human, livestock, and O. hupensis infections with S. japonicum were mainly concentrated in the northwestern portion of the Yunnan Province, the Daliangshan area in the south of Sichuan Province, and the hilly regions in the middle of Sichuan Province. Conclusions: This study demonstrate a significant spatio-temporal heterogeneity of schistosomiasis in China. A remarkable decline in endemic schistosomiasis was observed between 2005 and 2019. However, there continues to be a long-term risk of schistosomiasis transmission in local areas, with high-risk areas primarily located in the Poyang Lake and Dongting Lake regions, with frequent acute S. japonicum infections. Using a One Health approach, further reinforcement of an integrated schistosomiasis control strategy, with an emphasis on the sources of S. japonicum infection, is required to facilitate the elimination of schistosomiasis in China by 2030.

scholarly journals A satellite-based spatio-temporal machine learning model to reconstruct daily PM2.5 concentrations across Great Britain

2020 ◽  
Author(s):  
Rochelle Schneider dos Santos ◽  
Ana Vicedo-Cabrera ◽  
Francesco Sera ◽  
Massimo Stafoggia ◽  
Kees de Hoogh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Great Britain ◽  
Temporal Resolution ◽  
Fine Particulate Matter ◽  
Epidemiological Studies ◽  
Learning Model ◽  
Additional Information ◽  
Multi Stage ◽  
Machine Learning Model ◽  
Spatio Temporal

Epidemiological studies on health effects of air pollution usually rely on measurements from fixed ground monitors, which provide limited spatio-temporal coverage. Data from satellites, reanalysis and chemical transport models offer additional information used to reconstruct pollution concentrations at high spatio-temporal resolution. The aim of this study is to develop a multi-stage satellite-based machine learning model to estimate daily fine particulate matter (PM2.5) levels across Great Britain during 2008-2018. This high-resolution model consists of random forest (RF) algorithms applied in four stages. Stage-1 augments monitor-PM2.5 series using co-located PM10 measures. Stage-2 imputes missing satellite aerosol optical depth observations using atmospheric reanalysis models. Stage-3 integrates the output from previous stages with spatial and spatio-temporal variables to build a prediction model for PM2.5. Stage-4 applies Stage-3 models to estimate daily PM2.5 concentrations over a 1-km grid. The RF architecture performed well in all stages, with results from Stage-3 showing an average cross-validated R2 of 0.767 and minimal bias. The model performed better over the temporal scale when compared to the spatial component, but both presented good accuracy with an R2 of 0.795 and 0.658, respectively. The high spatio-temporal resolution and relatively high precision allows this dataset (approximately 950 million points) to be used in epidemiological analyses to assess health risks associated with both short- and long-term exposures to PM2.5.

Sign in / Sign up

Export Citation Format

Share Document