Filters








1,102 Hits in 5.7 sec

Transport-domain applications of widely used data sources in the smart transportation: A survey [article]

Sina Dabiri, Kevin Heaslip
2018 arXiv   pre-print
For each data source, first, the operational mechanism of the technology for capturing the data is succinctly demonstrated.  ...  Moreover, in order to alleviate the shortcomings pertaining to each single data source and acquire a better understanding of mobility behavior in transportation systems, the data fusion architectures are  ...  One of the main challenges in entry-only AFC systems is the scarcity of alighting information because no facility exists to record the smart card fare data when passengers alight and exit the station.  ... 
arXiv:1803.10902v3 fatcat:tc67qy4x4vbtjb76qi6mbwrqy4

Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey [article]

Julian Wörmann, Daniel Bogdoll, Etienne Bührle, Han Chen, Evaristus Fuh Chuo, Kostadin Cvejoski, Ludger van Elst, Tobias Gleißner, Philip Gottschall, Stefan Griesche, Christian Hellert, Christian Hesels (+34 others)
2022 arXiv   pre-print
However, the subsequent application of these models often involves scenarios that are inadequately represented in the data used for training.  ...  As a consequence, the reliable use of these models, especially in safety-critical applications, is a huge challenge.  ...  By aligning the gradients of a supervised and self-supervised loss in the training phase, during inference the agent can use the gathered meta-knowledge about the imitated supervised loss for self-adaptive  ... 
arXiv:2205.04712v1 fatcat:u2bgxr2ctnfdjcdbruzrtjwot4

The Entry into the U.S. Labor Market of Antebellum European Immigrants, 1840–1860

Joseph P Ferrie
1997 Explorations in economic history (Print)  
White collar, skilled, and semi-skilled immigrants left unskilled jobs more rapidly after arrival than farmers and unskilled workers.  ...  These findings have implications for (1) the accuracy of estimates of immigrant occupational mobility; (2) the size of the human capital transfer resulting from antebellum immigration; and (3)  ...  Comparing the year-of-arrival effects for the I rish and Germans (within either occupation-at-arrival group) will allow us to infer the impact of the second of these influences.  ... 
doi:10.1006/exeh.1997.0674 fatcat:qpthyreyl5h4piflwclzz6xj4y

Full Issue (27.2, Winter 2017)

Journal of Transportation Management Editors
2017 Journal of Transportation Management  
Submissions from practitioners, attorneys or policymakers, co-authoring with academicians, are particularly encouraged in order to increase the interaction between groups.  ...  Articles related to any and all types of organizations, and of local to global scope, will be considered for publication.  ...  people together for training.  ... 
doi:10.22237/jotm/1498867620 fatcat:qvfhhgsmxbhklhd3vby2o4jkwa

Orchestrating the Development Lifecycle of Machine Learning-Based IoT Applications: A Taxonomy and Survey

Bin Qian, Jie Su, Zhenyu Wen, Devki Nandan Jha, Yinhao Li, Yu Guan, Deepak Puthal, Philip James, Renyu Yang, Albert Y. Zomaya, Omer Rana, Lizhe Wang (+2 others)
2020 ACM Computing Surveys  
For supervised cases when a class label is available for training, TML aims to map the input data to the labels by optimising a model, which can be used to infer unseen data at the test stage.  ...  DL models are typically used to model complex unstructured data, e.g., images, audios, time-series data, etc. and are an ideal choice especially with high amount of training data and low requirement on  ...  For example it can be used for boosting semi-supervised data annotation [396] , or it can be integrated with newly collected data for model training.  ... 
doi:10.1145/3398020 fatcat:zzgfcjxjxbhnhf53dmlo63rs3i

ADST: Forecasting Metro Flow using Attention-Based Deep Spatial-Temporal Networks with Multi-Task Learning

Hongwei Jia, Haiyong Luo, Hao Wang, Fang Zhao, Qixue Ke, Mingyao Wu, Yunyun Zhao
2020 Sensors  
Furthermore, we enforce multi-task learning to utilize transition passenger flow volume prediction as an auxiliary task during the training process for generalization.  ...  Through this model, we can not only capture the steady trend, but also the sudden changes of passenger flow.  ...  Acknowledgments: Our sincere thankfulness be tendered to all the reviewers for their valuable comments and helpful suggestions. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s20164574 pmid:32824074 pmcid:PMC7472615 fatcat:ynrvnnerabby5hpnqrcqesv4qa

A Survey of Autonomous Driving: Common Practices and Emerging Technologies [article]

Ekim Yurtsever, Jacob Lambert, Alexander Carballo, Kazuya Takeda
2020 arXiv   pre-print
The paper concludes with an overview of available datasets and tools for ADS development.  ...  These algorithms only use pointcloud data.  ...  Most of the time the ADS can observe a surrounding vehicle only for seconds.  ... 
arXiv:1906.05113v2 fatcat:2hqztllrgjhndbc5aebduvukai

Orchestrating the Development Lifecycle of Machine Learning-Based IoT Applications: A Taxonomy and Survey [article]

Bin Qian, Jie Su, Zhenyu Wen, Devki Nandan Jha, Yinhao Li, Yu Guan, Deepak Puthal, Philip James, Renyu Yang, Albert Y. Zomaya, Omer Rana, Lizhe Wang (+2 others)
2020 arXiv   pre-print
We outline core roadmap and taxonomy, and subsequently assess and compare existing standard techniques used in individual stage.  ...  Machine Learning (ML) and Internet of Things (IoT) are complementary advances: ML techniques unlock complete potentials of IoT with intelligence, and IoT applications increasingly feed data collected by  ...  For example it can be used for boosting semi-supervised data annotation [396] , or it can be integrated with newly collected data for model training.  ... 
arXiv:1910.05433v5 fatcat:ffvjipmylve6feuzdbav2syxfu

A Survey of Autonomous Driving: Common Practices and Emerging Technologies

Ekim Yurtsever, Jacob Lambert, Alexander Carballo, Kazuya Takeda
2020 IEEE Access  
The paper concludes with an overview of available datasets and tools for ADS development.  ...  All of the mentioned methods follow direct supervised training strategies. As such, ground truth is required for training.  ...  TABLE 7 . 7 Average Precision (AP) in % on the KITTI 3D object detection test set car class, ordered based on moderate category accuracy. These algorithms only use pointcloud data.  ... 
doi:10.1109/access.2020.2983149 fatcat:t3w7nopogvbhvbbkgpk3dknn5u

Exploiting geographic dependencies for real estate appraisal

Yanjie Fu, Hui Xiong, Yong Ge, Zijun Yao, Yu Zheng, Zhi-Hua Zhou
2014 Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '14  
Also, we use a linear model to fuse these three influential factors and predict estate investment values.  ...  However, with the development of new ways of collecting estate-related mobile data, there is a potential to leverage geographic dependencies of estates for enhancing estate appraisal.  ...  Since a taxi could not send passengers into a POI directly, the drop-off point usually is not the same with the destination. A passenger often walks a short distance to reach the destination.  ... 
doi:10.1145/2623330.2623675 dblp:conf/kdd/FuXGYZZ14 fatcat:4r3z2rmnybez7dmhlyvhtslxpm

Contextual Awareness in Human-Advanced-Vehicle Systems: A Survey

Raul Fernandez-Rojas, Anthony Perry, Hemant Singh, Benjamin Campbell, Saber Elsayed, Robert Hunjet, Hussein Abbass
2019 IEEE Access  
This paper uses a human-AVSs (HAVSs) lens to polarize the literature in a coherent form suitable for designing distributed HAVSs.  ...  systems as the enabling technology for recommender systems to operate autonomously.  ...  They use a game theoretic approach whereby SUs are only allowed to transmit after a PU's packet has reached its destination.  ... 
doi:10.1109/access.2019.2902812 fatcat:ieqvknlscjgfthy3snql53ohzi

Deep Learning for Spatio-Temporal Data Mining: A Survey [article]

Senzhang Wang, Jiannong Cao, Philip S. Yu
2019 arXiv   pre-print
We first categorize the types of spatio-temporal data and briefly introduce the popular deep learning models that are used in STDM.  ...  As the number, volume and resolution of spatio-temporal datasets increase rapidly, traditional data mining methods, especially statistics based methods for dealing with such data are becoming overwhelmed  ...  The second largest problem category is representation learning, which aims to learning feature representations for various ST data in an unsupervised or semi-supervised way.  ... 
arXiv:1906.04928v2 fatcat:4zrdtgkvirfuniq3rb2gl7ohpy

Optimizing Passenger On-Vehicle Experience through Simulation and Multi-Agent Multi-Criteria Mobility Planning

Rongye Shi
2019
Second, to plan for passengers' mobility concerning the influence among passengers as well as multiple service preferences is computationally intensive, especially on a city scale.  ...  First, a model or a simulator that captures not only the road traffic, but also the behaviors of passengers and other relevantfactors is a prerequisite for this research but has seldom been developed previously  ...  Summary This chapter describes a semi-supervised self-training method for filling the missing destination features in the entry-only data.  ... 
doi:10.1184/r1/8218700 fatcat:qvlezw6ykndlfjlsdyzhrwhi7e

VOLUME 11 : 2013

Malaysia Institute of Planners
2016 PLANNING MALAYSIA JOURNAL  
A special thank you to the Kuala Lumpur City Hall for the scholarship awarded to the second author.  ...  Appreciation to Malaysia Federal Department of Town and Country Planning, Royal Malaysia Police for providing data and information for this research.  ...  Data entry and cleaning have found that some 1000 samples were useful and meaningful for data analysis purposes.  ... 
doi:10.21837/pmjournal.v11.i3.366 fatcat:zpkmk7637jdzbdhocittv6ttti

Universal Approximation of Edge Density in Large Graphs [article]

Marc Boullé
2015 arXiv   pre-print
It is able to extract insightful patterns in the unsupervised learning setting and to provide state of the art accuracy when used as a preparation step for supervised learning.  ...  We use a model selection technique with data-dependent prior and obtain an exact evaluation criterion for the posterior probability of edge density estimation models.  ...  They all used both the content and link data in a semi-supervised learning setting, on top of classifiers among which SVM, random forests and naive Bayes.  ... 
arXiv:1508.01340v1 fatcat:2doylqhwyjco5jcl4fupo7aswi
« Previous Showing results 1 — 15 out of 1,102 results