219,908 Hits in 6.4 sec

Feature Driven and Point Process Approaches for Popularity Prediction

Swapnil Mishra, Marian-Andrei Rizoiu, Lexing Xie
2016 Proceedings of the 25th ACM International on Conference on Information and Knowledge Management - CIKM '16  
To our surprise, Hawkes process with a predictive overlay outperform recent feature-driven and generative approaches on existing tweet data [43] and a new public benchmark on news tweets.  ...  From these observations, we argue that future work on popularity prediction should compare across feature-driven and generative modeling approaches in both classification and regression tasks.  ...  We thank the National Computational Infrastructure (NCI) for providing computational resources, supported by the Australian Government.  ... 
doi:10.1145/2983323.2983812 dblp:conf/cikm/MishraRX16 fatcat:xbqp4um53vfdphbs7moavghr4q

A New Look at AI-Driven NOMA-F-RANs: Features Extraction, Cooperative Caching, and Cache-Aided Computing [article]

Zhong Yang, Yaru Fu, Yuanwei Liu, Yue Chen, Junshan Zhang
2021 arXiv   pre-print
Finally, future trends of AI-driven NOMA-F-RANs, including open research issues and challenges, are identified.  ...  Through case studies, we show the efficacy of AI-enabled methods in terms of F-UEs' latent feature extraction and cooperative caching.  ...  AI-driven Latent Feature Extraction in NOMA-F-RANs In this subsection, we first evaluate the performance of our proposed LSTM solution for F-UEs' task popularity prediction.  ... 
arXiv:2112.01325v1 fatcat:rhga6egpsvgutk3pcewqnhbi4u

Remaining useful life estimation in prognostics using deep convolution neural networks

Xiang Li, Qian Ding, Jian-Qiao Sun
2018 Reliability Engineering & System Safety  
Time window approach is employed for sample preparation in order for better feature extraction by DCNN.  ...  This paper proposes a new data-driven approach for prognostics using deep convolution neural networks (DCNN).  ...  Generally, the existing methods for PHM can be grouped into three main categories, i.e. model-based approaches [4] , data-driven approaches [5] and hybrid approaches [6] .  ... 
doi:10.1016/j.ress.2017.11.021 fatcat:puexmpn56vf5jhfqrfetgeflvy

Data-driven smart charging for heterogeneous electric vehicle fleets

Oliver Frendo, Jérôme Graf, Nadine Gaertner, Heiner Stuckenschmidt
2020 Energy and AI  
In this work we propose a data-driven approach for integrating a machine learning model to predict arbitrary charge profiles into a smart charging algorithm.  ...  Furthermore, an ablation study on regression model features shows the EV's model is not a necessary attribute for accurate charge profile predictions.  ...  The diversity in such sample charging processes underscores the need for data-driven approaches to take into account processes that do not follow the expected theoretical charge profiles.  ... 
doi:10.1016/j.egyai.2020.100007 fatcat:v5ywbqhltbgrnn53fpfpbevvke

IntruDTree: A Machine Learning Based Cyber Security Intrusion Detection Model

Iqbal H. Sarker, Yoosef B. Abushark, Fawaz Alsolami, Asif Irshad Khan
2020 Symmetry  
This model is not only effective in terms of prediction accuracy for unseen test cases but also minimizes the computational complexity of the model by reducing the feature dimensions.  ...  Artificial intelligence, particularly machine learning techniques, can be used for building such a data-driven intelligent intrusion detection system.  ...  For some data points, the value is very low while for some data points, it is much higher, as shown in Figures 1 and 2 .  ... 
doi:10.3390/sym12050754 fatcat:2cnjrwxsobbwflztn7phctnbey

Dynamics-based data science in biology

Jifan Shi, Kazuyuki Aihara, Luonan Chen
2021 National Science Review  
We review three applications on detecting the tipping-points of diseases, quantifying cell's potency, and predicting time-series, to show the importance of dynamics-based data-science.  ...  With the increasingly accumulated bio-data, dynamics-based data-science has been progressing as an efficient way to reveal mechanisms of dynamical biological processes.  ...  Taken together, we conclude the principles and advantages of dynamics-based data-driven approaches as explicable, quantifiable, and generalizable.  ... 
doi:10.1093/nsr/nwab029 pmid:34691649 pmcid:PMC8288307 fatcat:lpi333yslfavdmqtkh3jnbfgfq

An Incremental Learning Based Edge Caching System: From Modeling to Evaluation

Guangping Xu, Bo Tang, Liming Yuan, Yanbing Xue, Zan Gao, Salwa Mostafa, Chi Wan Sung
2020 IEEE Access  
Inspired by the success of incremental learning approaches in processing massive data in real time, we propose an incremental learning based framework at an edge caching server.  ...  The distribution of data popularity is highly skewed and changing over time. Besides, the access pattern of the user requests also varies over time.  ...  Meanwhile, it lets the IL predictor to predict whether the object will be in top-K popularity or not. The IL predictor first looks up features x t i from feature table and then make a prediction.  ... 
doi:10.1109/access.2020.2965249 fatcat:zlwdgn35hrblblzyfbhgaz6i3e

Perspective: Materials informatics and big data: Realization of the "fourth paradigm" of science in materials science

Ankit Agrawal, Alok Choudhary
2016 APL Materials  
models (property prediction) and inverse models (materials discovery).  ...  In this article, we look at how data-driven techniques are playing a big role in deciphering processing-structure-property-performance relationships in materials, with illustrative examples of both forward  ...  FA9550-12-1-0458, NIST Award No. 70NANB14H012, and DARPA Award No. N66001-15-C-4036.  ... 
doi:10.1063/1.4946894 fatcat:mkjbsjcsqjgo7lmbuknsgq7f34

Data-driven Soft Sensors in the process industry

Petr Kadlec, Bogdan Gabrys, Sibylle Strandt
2009 Computers and Chemical Engineering  
This paper discusses characteristics of the process industry data which are critical for the development of data-driven Soft Sensors.  ...  In the last two decades Soft Sensors established themselves as a valuable alternative to the traditional means for the acquisition of critical process variables, process monitoring and other tasks which  ...  Nonetheless, model-driven Soft Sensors are popular as a support for inferential control.  ... 
doi:10.1016/j.compchemeng.2008.12.012 fatcat:d7kxy4a2fbhanpc74yhfrg6jma

Parsimonious Network based on Fuzzy Inference System (PANFIS) for Time Series Feature Prediction of Low Speed Slew Bearing Prognosis [article]

Wahyu Caesarendra, Mahardhika Pratama, Tegoeh Tjahjowidodo, Kiet Tieud, Buyung Kosasih
2018 arXiv   pre-print
The method is applied to normal-to-failure bearing vibration data collected for 139 days and to predict the time-domain features of vibration slew bearing signals.  ...  The prognostic approaches are described comprehensively to provide a better idea on how to select an appropriate prognosis method for specific needs.  ...  a data-driven approach.  ... 
arXiv:1802.09332v1 fatcat:xk7tfgtlafc6rorgoq3xo5pymy

Guest Editorial: Data-Driven Management of Complex Systems Through Plant-Wide Performance Supervision

Okyay Kaynak, Steven Ding, Ahmet Palazoglu, Hao Luo
2021 IEEE Transactions on Industrial Informatics  
In "A data-driven approach of product quality prediction for complex production systems [item 12) in the Appendix]," the authors proposed a data-driven approach based on a parallel deep factorization machine  ...  The reasons behind such popularity of data-driven techniques are twofold.  ... 
doi:10.1109/tii.2020.3023259 fatcat:2x44ydldbreqdcyejz5jui7q24

Advanced RF and Microwave Design Optimization: A Journey and a Vision of Future Trends

Jose E. Rayas-Sanchez, Slawomir Koziel, John W. Bandler
2021 IEEE Journal of Microwaves  
optimization, and formal cognition-driven space mapping approaches, assisted by Bayesian and machine learning techniques.  ...  To address these major challenges, we venture into the development of sophisticated optimization approaches, exploiting confined and dimensionally reduced surrogate vehicles, automated feature-engineering-based  ...  Gray lines correspond to 500 EM-simulated random samples for MC analysis, circles mark the feature points predicted by the surrogate.  ... 
doi:10.1109/jmw.2020.3034263 fatcat:a64hobxhfzhe3f2stmhkewvgca

Data-Driven Prediction System of Dynamic People-Flow in Large Urban Network Using Cellular Probe Data

Xiaoxuan Chen, Xia Wan, Fan Ding, Qing Li, Charlie McCarthy, Yang Cheng, Bin Ran
2019 Journal of Advanced Transportation  
In addition, it is hard to validate the prediction method at a large scale. This paper proposed a data-driven method for dynamic people-flow prediction, which contains four models.  ...  The experimental result shows that the proposed people-flow prediction system could provide prediction precision of 76.8% and 70% for outbound and inbound people, respectively.  ...  Authors' Contributions Xiaoxuan Chen, Xia Wan, Fan Ding, and Bin Ran contributed to study conception and design; Xiaoxuan Chen and Fan Ding contributed to data collection; Xiaoxuan Chen, Qing Li, and Charlie  ... 
doi:10.1155/2019/9401630 fatcat:p7vyfk2oijdnppnqnjrwab6a2u

Soft metrology based on machine learning: A review

Marcela Vallejo, Carolina de la Espriella, Juliana Andrea Gómez-Santamaría, Andres Felipe Ramirez Barrera, Edilson Delgado-Trejos
2019 Measurement science and technology  
This study does not delve into developments and applications for human and social sciences, although the proposed definition considers the use that this term has had in these areas.  ...  For this purpose, the literature on indirect measurement techniques and systems has been reviewed, encompassing recent as well as a few older key documents to present a time line of development and map  ...  Additionally, the authors would like to thank the Measurement Analysis and Decision Support Laboratory (AMYSOD Lab) of Parque i, Medellin, Colombia.  ... 
doi:10.1088/1361-6501/ab4b39 fatcat:dw6ahml7ofhrbcz43nx7643yaq

Minimizing False Negatives of Measles Prediction Model: An Experimentation of Feature Selection Based On Domain Knowledge and Random Forest Classifier

2019 International Journal of Engineering and Advanced Technology  
developmentof measles prediction model by incorporating both the domain knowledge and the data-driven approaches, in particular, the Random Forest classifier.The domain expert has earlier on set the important  ...  features based uponhisprior knowledgeon measles for the purpose of minimizing the size of features.  ...  Li et al. (2018) has also performed similar experiment for oral disease prediction and deduced that the approach helps in removing irrelevant features and improving prediction accuracy.  ... 
doi:10.35940/ijeat.a2640.109119 fatcat:bvsef62fxvbq3iyaqwwp3eelbi
« Previous Showing results 1 — 15 out of 219,908 results