A Joint Passenger Flow Inference and Path Recommender System for Deploying New Routes and Stations of Mass Transit Transportation

2021 ◽  
Vol 16 (1) ◽  
pp. 1-36
Author(s):  
Fandel Lin ◽  
Hsun-Ping Hsieh
Keyword(s):  
Large Scale ◽  
Urban Transportation ◽  
Mass Transit ◽  
Gaussian Mixture ◽  
Comparative Methods ◽  
Geographical Information ◽  
Inference Model ◽  
Timely Manner ◽  
Passenger Flow ◽  
Route Recommendation

In this work, a novel decision assistant system for urban transportation, called Route Scheme Assistant (RSA), is proposed to address two crucial issues that few former researches have focused on: route-based passenger flow (PF) inference and multivariant high-PF route recommendation. First, RSA can estimate the PF of arbitrary user-designated routes effectively by utilizing Deep Neural Network (DNN) for regression based on geographical information and spatial-temporal urban informatics. Second, our proposed Bidirectional Prioritized Spanning Tree (BDPST) intelligently combines the parallel computing concept and Gaussian mixture model (GMM) for route recommendation under users’ constraints running in a timely manner. We did experiments on bus-ticket data of Tainan and Chicago and the experimental results show that the PF inference model outperforms baseline and comparative methods from 41% to 57%. Moreover, the proposed BDPST algorithm's performance is not far away from the optimal PF and outperforms other comparative methods from 39% to 71% in large-scale route recommendations.

scholarly journals Explaining large-scale patterns of vertebrate diversity

2015 ◽  
Vol 11 (7) ◽  
pp. 20150506 ◽  
Author(s):  
John J. Wiens
Keyword(s):  
Species Richness ◽  
Large Scale ◽  
Comparative Methods ◽  
Phylogenetic Comparative Methods ◽  
Metabolic Rates ◽  
Diversification Rates ◽  
Richness Patterns ◽  
Current Species

The major clades of vertebrates differ dramatically in their current species richness, from 2 to more than 32 000 species each, but the causes of this variation remain poorly understood. For example, a previous study noted that vertebrate clades differ in their diversification rates, but did not explain why they differ. Using a time-calibrated phylogeny and phylogenetic comparative methods, I show that most variation in diversification rates among 12 major vertebrate clades has a simple ecological explanation: predominantly terrestrial clades (i.e. birds, mammals, and lizards and snakes) have higher net diversification rates than predominantly aquatic clades (i.e. amphibians, crocodilians, turtles and all fish clades). These differences in diversification rates are then strongly related to patterns of species richness. Habitat may be more important than other potential explanations for richness patterns in vertebrates (such as climate and metabolic rates) and may also help explain patterns of species richness in many other groups of organisms.

The Spatial and Temporal Distribution of Lightning Strikes and Their Relationship with Vegetation Type, Elevation, and Fire Scars in the Northern Territory

2007 ◽  
Vol 20 (7) ◽  
pp. 1161-1173 ◽  
Author(s):  
Musa Kilinc ◽  
Jason Beringer
Keyword(s):  
Large Scale ◽  
Vegetation Type ◽  
Northern Region ◽  
Northern Territory ◽  
Southern Region ◽  
Transitional Period ◽  
Geographical Information ◽  
Coastal Regions ◽  
Fire Scars ◽  
Lightning Strikes

Abstract In this paper the authors explore the spatial and temporal patterns of lightning strikes in northern Australia for the first time. In particular, the possible relationships between lightning strikes and elevation, vegetation type, and fire scars (burned areas) are examined. Lightning data provided by the Bureau of Meteorology were analyzed for a 6-yr period (1998–2003) over the northern, southern, and coastal regions of the Northern Territory (NT) through the use of Geographical Information Systems (GIS) to determine the spatial and temporal characteristics of lightning strikes. It was determined that the highest densities of lightning strikes occurred during the monsoon transitional period (dry to wet) and during the active monsoon periods, when atmospheric moisture is highest. For the period of this study, lightning was far more prevalent over the northern region (1.21 strikes per km2 yr−1) than over the southern (0.58 strikes per km2 yr−1) and coastal regions (0.71 strikes per km2 yr−1). Differences in vegetation cover were suggested to influence the lightning distribution over the northern region of the NT, but no relationship was found in the southern region. Lightning strikes in the southern region showed a positive relationship with elevations above 800 m, but no relationship was found in the northern region, which could be due to the low-lying topography of the area. A comparison of lightning densities between burned and unburned areas showed high variability; however, the authors suggest that, under ideal atmospheric conditions, large-scale fire scars (>500 m) could produce lightning strikes triggered by either enhanced free convection or mesoscale circulations.

scholarly journals Multivariate clustering of reindeer herding districts in Sweden according to range prerequisites for reindeer husbandry

Rangifer ◽  
2009 ◽  
Vol 27 (2) ◽  
pp. 107-119
Author(s):  
Henrik Lundqvist ◽  
Öje Danell
Keyword(s):  
Geographical Information Systems ◽  
Large Scale ◽  
Global Climate ◽  
Meteorological Data ◽  
Principal Component ◽  
Geographical Information ◽  
Reindeer Herding ◽  
Factors Affecting ◽  
Decision Tools ◽  
Forage Value

The 51 reindeer herding districts in Sweden vary in productivity and prerequisites for reindeer herding. In this study we characterize and group reindeer herding districts based on relevant factors affecting reindeer productivity, i.e. topography, vegetation, forage value, habitat fragmentation and reachability, as well as season lengths, snow fall, ice-crust probability, and insect harassment, totally quantified in 15 variables. The herding districts were grouped into seven main groups and three single outliers through cluster analyses. The largest group, consisting of 14 herding districts, was further divided into four subgroups. The range properties of herding districts and groups of districts were characterized through principal component analyses. By comparisons of the suggested grouping of herding districts with existing administrative divisions, these appeared not to coincide. A new division of herding districts into six administrative sets of districts was suggested in order to improve administrative planning and management of the reindeer herding industry. The results also give possibilities for projections of alterations caused by an upcoming global climate change. Large scale investigations using geographical information systems (GIS) and meteorological data would be helpful for administrative purposes, both nationally and internationally, as science-based decision tools in legislative, economical, ecological and structural assessments. Abstract in Swedish / Sammanfattning: Multivariat gruppering av svenska samebyar baserat på renbetesmarkernas grundförutsettningar Svenska renskötselområdet består av 51 samebyar som varierar i produktivitet och förutsättningar för renskötsel. Vi analyserade variationen mellan samebyar med avseende på 15 variabler som beskriver topografi, vegetation, betesvärde, fragmentering av betesmarker, klimat, skareförekomst och aktivitet av parasiterande insekter och vi föreslår en indelning av samebyar i tio grupper. Den största gruppen, som bestod av 14 samebyar, delades vidare in i 4 undergrupper. Klusteranalyser med 4 olika linkage-varianter användes till att gruppera samebyarna. Principalkomponentsanalys användes för att kartlägga undersökta variabler och de resulterande samebygruppernas karaktär. Samebygrupperna följde inte länsgränser och tre samebyar föll ut som enskilda grupper. Denna undersökning ger underlag för jämförelser mellan samebyar med beaktande av likheter och olikheter i fråga om produktivitet och funktionella särdrag istället för länsgränser och historik. Vi föreslår en ny administrativ indelning i sex områden som skulle kunna fungera som ett alternativt underlag för planering och beslut som rör produktionsaspekter i rennäringen. Resultaten ger också underlag för förutsägelser av förändringar i samebyars produktionsförutsättningar till följd av klimatförändringar.

scholarly journals Deep-Learning-Based Road Crack Detection Frameworks for Dashcam-captured Images under Different Illumination Conditions

2021 ◽  
Author(s):  
Da-Ren Chen ◽  
Wei-Min Chiu
Keyword(s):  
Object Detection ◽  
Large Scale ◽  
Crack Detection ◽  
State Of The Art ◽  
Gaussian Mixture Models ◽  
Gaussian Mixture ◽  
Machine Learning Techniques ◽  
Detection Accuracy ◽  
The Road ◽  
Art Object

Abstract Machine learning techniques have been used to increase detection accuracy of cracks in road surfaces. Most studies failed to consider variable illumination conditions on the target of interest (ToI), and only focus on detecting the presence or absence of road cracks. This paper proposes a new road crack detection method, IlumiCrack, which integrates Gaussian mixture models (GMM) and object detection CNN models. This work provides the following contributions: 1) For the first time, a large-scale road crack image dataset with a range of illumination conditions (e.g., day and night) is prepared using a dashcam. 2) Based on GMM, experimental evaluations on 2 to 4 levels of brightness are conducted for optimal classification. 3) the IlumiCrack framework is used to integrate state-of-the-art object detecting methods with CNN to classify the road crack images into eight types with high accuracy. Experimental results show that IlumiCrack outperforms the state-of-the-art R-CNN object detection frameworks.

Terminating Architecture: Mega-Development in Hong Kong

2013 ◽  
Vol 30 (7-8) ◽  
pp. 277-289
Author(s):  
Li Shiqiao
Keyword(s):  
Hong Kong ◽  
Scale Development ◽  
Large Scale ◽  
Mass Transit ◽  
Development Projects ◽  
Financial Viability ◽  
Property Market ◽  
Railway Stations ◽  
Railway Systems ◽  
Physical Features

This paper examines large development projects as a function of finance in the context of Hong Kong, taking Kowloon Station as an exceptionally revealing case. Hong Kong's property market is one of the most established in Asia, and it points to the ways in which large-scale development schemes proliferate along efficient and affordable mass transit railway systems with great speed and success. At Kowloon Station, finance redefines architecture; instead of focusing on aesthetics and community, it is now promoting standardization, market visibility and semantic control. The financial viability of these developments depends entirely on these new goals; mega-developments such as Kowloon Station – and those in other parts of Asia – are successful in inventing major mass transit railway stations as terminals, in capturing commuters within spatial enclosures surrounded by barrier-like physical features, and in terminating architecture as it has long been established as a discipline. Mega-development is increasingly reinventing the contemporary Asian city.

Emotional and Subjective Volunteered Geographical Information

2017 ◽  
pp. 97-112 ◽  
Author(s):  
Jiri Panek
Keyword(s):  
Data Mining ◽  
Social Networks ◽  
Spatial Data ◽  
Large Scale ◽  
Geographical Information ◽  
Emotional Information ◽  
Spatial Features ◽  
Spatial Locations ◽  
The City

Crowdsroucing of emotional information can take many forms, from social networks data mining to large-scale surveys. The author presents the case-study of emotional mapping in Ostrava´s district Ostrava-Poruba, Czech Republic. Together with the local administration, the author crowdsourced the emotional perceptions of the location from almost 400 citizens, who created 4,051 spatial features. Additional to the spatial data there were 1,244 comments and suggestions for improvements in the district. Furthermore, the author is looking for patterns and hot-spots within the city and if there are any relevant linkages between certain emotions and spatial locations within the city.

scholarly journals The translation of an evidence-based preschool physical activity intervention from in-person to online delivery of professional development to preschool teachers

2019 ◽  
Vol 9 (6) ◽  
pp. 1186-1196 ◽  
Author(s):  
Ruth P Saunders ◽  
Michaela A Schenkelberg ◽  
Christina Moyer ◽  
Erin K Howie ◽  
William H Brown ◽  
...  
Keyword(s):  
Professional Development ◽  
Large Scale ◽  
Physical Activity Intervention ◽  
Preschool Teachers ◽  
Controlled Trial ◽  
Development Program ◽  
Evidence Based ◽  
Timely Manner ◽  
Online Delivery ◽  
Randomized Controlled

An intervention shown to be effective in a randomized controlled trial can be translated into an online professional development program and disseminated on a large scale in a timely manner.

scholarly journals Sensor Selection for Decentralized Large-Scale Multi-Target Tracking Network

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4115 ◽  
Author(s):  
Feng Lian ◽  
Liming Hou ◽  
Bo Wei ◽  
Chongzhao Han
Keyword(s):  
Target Tracking ◽  
Large Scale ◽  
Sequential Monte Carlo ◽  
Signal To Noise Ratio ◽  
Computational Cost ◽  
Gaussian Mixture ◽  
Descent Method ◽  
Sensor Selection ◽  
Multi Target Tracking ◽  
Finite Set

A new optimization algorithm of sensor selection is proposed in this paper for decentralized large-scale multi-target tracking (MTT) network within a labeled random finite set (RFS) framework. The method is performed based on a marginalized δ-generalized labeled multi-Bernoulli RFS. The rule of weighted Kullback-Leibler average (KLA) is used to fuse local multi-target densities. A new metric, named as the label assignment (LA) metric, is proposed to measure the distance for two labeled sets. The lower bound of LA metric based mean square error between the labeled multi-target state set and its estimate is taken as the optimized objective function of sensor selection. The proposed bound is obtained by the information inequality to RFS measurement. Then, we present the sequential Monte Carlo and Gaussian mixture implementations for the bound. Another advantage of the bound is that it provides a basis for setting the weights of KLA. The coordinate descent method is proposed to compromise the computational cost of sensor selection and the accuracy of MTT. Simulations verify the effectiveness of our method under different signal-to- noise ratio scenarios.

scholarly journals Quantifying the Polygenic Architecture of the Human Cerebral Cortex: Extensive Genetic Overlap between Cortical Thickness and Surface Area

2020 ◽  
Vol 30 (10) ◽  
pp. 5597-5603 ◽  
Author(s):  
Dennis van der Meer ◽  
Oleksandr Frei ◽  
Tobias Kaufmann ◽  
Chi-Hua Chen ◽  
Wesley K Thompson ◽  
...  
Keyword(s):  
Surface Area ◽  
Cortical Thickness ◽  
Large Scale ◽  
Gaussian Mixture ◽  
Total Surface Area ◽  
Brain Morphology ◽  
Genetic Determinants ◽  
Genetic Predictors ◽  
Genetic Overlap ◽  
Causal Variants

Abstract The thickness of the cerebral cortical sheet and its surface area are highly heritable traits thought to have largely distinct polygenic architectures. Despite large-scale efforts, the majority of their genetic determinants remain unknown. Our ability to identify causal genetic variants can be improved by employing brain measures that better map onto the biology we seek to understand. Such measures may have fewer variants but with larger effects, that is, lower polygenicity and higher discoverability. Using Gaussian mixture modeling, we estimated the number of causal variants shared between mean cortical thickness and total surface area, as well as the polygenicity and discoverability of regional measures. We made use of UK Biobank data from 30 880 healthy White European individuals (mean age 64.3, standard deviation 7.5, 52.1% female). We found large genetic overlap between total surface area and mean thickness, sharing 4016 out of 7941 causal variants. Regional surface area was more discoverable (P = 2.6 × 10−6) and less polygenic (P = 0.004) than regional thickness measures. These findings may serve as a roadmap for improved future GWAS studies; knowledge of which measures are most discoverable may be used to boost identification of genetic predictors and thereby gain a better understanding of brain morphology.

Sign in / Sign up

Export Citation Format

Share Document