325,315 Hits in 5.2 sec

A learning algorithm for change impact prediction

Vincenzo Musco, Antonin Carette, Martin Monperrus, Philippe Preux
2016 Proceedings of the 5th International Workshop on Realizing Artificial Intelligence Synergies in Software Engineering - RAISE '16  
Change impact analysis consists in predicting the impact of a code change in a software application.  ...  We propose an algorithm, called LCIP that learns from past impacts to predict future impacts. To evaluate our system, we consider 7 Java software applications totaling 214,000+ lines of code.  ...  CONTRIBUTION In this section, we describe the Learning Change Impact Prediction (LCIP) algorithm: a new learning algorithm for change impact analysis.  ... 
doi:10.1145/2896995.2896996 dblp:conf/icse/MuscoCMP16 fatcat:qovrrwjxfrhppcjxw5umalfllu

Invited perspectives: How machine learning will change flood risk and impact assessment

Dennis Wagenaar, Alex Curran, Mariano Balbi, Alok Bhardwaj, Robert Soden, Emir Hartato, Gizem Mestav Sarica, Laddaporn Ruangpan, Giuseppe Molinario, David Lallemant
2020 Natural Hazards and Earth System Sciences  
Increasing amounts of data, together with more computing power and better machine learning algorithms to analyse the data, are causing changes in almost every aspect of our lives.  ...  This trend is expected to continue as more data keep becoming available, computing power keeps improving and machine learning algorithms keep improving as well.  ...  Furthermore, we would like to thank the editor (Heidi Kreibich) and the reviewers (Fernando Nardi and an anonymous reviewer) for their contributions to the paper. Financial support.  ... 
doi:10.5194/nhess-20-1149-2020 fatcat:w36mjnxjzrffpc7ozlnzhajnou

Enabling Equal Opportunity in Logistic Regression Algorithm

Sandro Radovanović, Marko Ivić
2021 Management  
Tools: We developed a novel regularization technique for equal opportunity in the logistic regression algorithm.  ...  Compared to the disparate impact constrained logistic regression, our approach has higher prediction accuracy and equal opportunity, while having a lower disparate impact.  ...  Acknowledgments This paper is partially funded by the project ONR-N62909-19-1-2008 (Office of Naval Research): Aggregating computational algorithms and human decision-making preferences in multi-agent  ... 
doi:10.7595/management.fon.2021.0029 fatcat:hnxv47k3mjcdrnmzeuiw4dhlsu

Actionable Interpretation of Machine Learning Models for Sequential Data: Dementia-related Agitation Use Case [article]

Nutta Homdee, John Lach
2020 arXiv   pre-print
Machine learning has shown successes for complex learning problems in which data/parameters can be multidimensional and too complex for a first-principles based analysis.  ...  An implementation of the actionable interpretation is shown with a use case: dementia-related agitation prediction and the ambient environment.  ...  For example, the proposed actionable interpretation can learn the model's prediction is impacted by the decreasing of a predictor.  ... 
arXiv:2009.05097v1 fatcat:zst6dy3z3vevdc6brt7wcbwsya

The Prediction of COVID-19 Using LSTM Algorithms

Myung Hwa Kim, Ju Hyung Kim, Kyoungjin Lee, Gwang-Yong Gim
2021 International Journal of Networked and Distributed Computing (IJNDC)  
CONCLUSION This study proposed a model for applying deep learning on how to predict the economic impact of epidemic trends.  ...  The proposed method is almost the only model for predicting economic impact based on epidemic cases using deep learning. However, there is a threshold for not predicting various economic indicators.  ... 
doi:10.2991/ijndc.k.201218.003 fatcat:dk72sybdnncrpneqzyejtkqwoa

Machine Learning Based Heat Transfer Optimization of Nano-fluid flow in a Helically Coiled Pipe

Awnish Kumar
2021 International Journal for Research in Applied Science and Engineering Technology  
Random Forest algorithm and Support Vector Machine Algorithm to predict the heat transfer efficiency of a flowing nano-fluid in a helically coiled pipe.  ...  These algorithms are used mainly in predictive and optimization purpose. The present study deals with the application of two machine learning algorithms i.e.  ...  A comparative study of various machine learning methods for performance prediction of an evaporative condenser.  ... 
doi:10.22214/ijraset.2021.39576 fatcat:cbiwsghqlncy7gh5szfuj2du6q

Research on E-Commerce Customer Churning Modeling and Prediction

Xue Zhao
2014 Open Cybernetics and Systemics Journal  
In electronic commerce the customer data change is non-linear and time-varying and other characteristics, using a single prediction model to accurately predict e-commerce customer loss is difficult.  ...  In order to improve the prediction accuracy rate of electronic commerce churning, the model first uses the genetic algorithm for the screening of effecting factors, and extracts the important influence  ...  Both of the predicted results are input into the SVM learning, finally the prediction result of a combination model is obtained.  ... 
doi:10.2174/1874110x01408010800 fatcat:lfvzqxwqqvbblfezlajakjb2mu

Computing and Data Challenges in Climate Change

Katherine Yelick
2020 2020 IEEE 27th International Conference on High Performance Computing, Data, and Analytics (HiPC)  
High Performance Computing has been a critical tool in understanding predicting climate change, and exascale computing combined with advances in mathematical modeling and parallel algorithm will lead to  ...  algorithms and machine learning.  ...  algorithms and machine learning.  ... 
doi:10.1109/hipc50609.2020.00009 fatcat:2e5ftxitlfgqppbvghj264wqvi

Climate Informatics: Accelerating Discovering in Climate Science with Machine Learning

Claire Monteleoni, Gavin A. Schmidt, Scott McQuade
2013 Computing in science & engineering (Print)  
T he impacts of present and potential future climate change pose important scientific and societal challenges.  ...  The impact of machine learning on climate science has the potential to be similarly profound.  ...  Acknowledgments Thanks to Shailesh Saroha and Eva Asplund for their work aiding our research. 1  ... 
doi:10.1109/mcse.2013.50 fatcat:r5qb7bghr5gahmsmfcr3zv7kyu

State-Aware Rate Adaptation for UAVs by Incorporating On-Board Sensors [article]

Shiyue He, Wei Wang, Hang Yang, Yang Cao, Tao jiang, Qian Zhang
2019 arXiv   pre-print
To make full use of the sensor data, we introduce a learning-based prediction module by leveraging the internal state to dynamically store temporal features under variable flight states.  ...  However, the above protocols still have limitation under constantly changing flight states and environments for air-to-ground links.  ...  StateRate employs a deep learning architecture that learns to choose the optimal MCS when the state of the UAV changes dynamically.  ... 
arXiv:1910.09184v1 fatcat:2v4zzjrllna3npe456ibf7fit4

On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning [article]

Hoda Heidari, Vedant Nanda, Krishna P. Gummadi
2019 arXiv   pre-print
We propose an effort-based measure of fairness and present a data-driven framework for characterizing the long-term impact of algorithmic policies on reshaping the underlying population.  ...  Most existing notions of algorithmic fairness are one-shot: they ensure some form of allocative equality at the time of decision making, but do not account for the adverse impact of the algorithmic decisions  ...  • We investigated the long-term impact of algorithmic models-in terms of how they reshape the underlying population-by modeling individuals' responses through social learning. • We proposed measuring the  ... 
arXiv:1903.01209v2 fatcat:ckw77tagengh7e7sk6b5tf7yaa

Interacting with Predictions

Josua Krause, Adam Perer, Kenney Ng
2016 Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems - CHI '16  
Our system is then evaluated using a case study involving a team of data scientists improving predictive models for detecting the onset of diabetes from electronic medical records.  ...  In addition, our support for localized inspection allows data scientists to understand how and why specific datapoints are predicted as they are, as well as support for tweaking feature values and seeing  ...  For each impactful feature, the original data value is shown as well as the suggested change and what the resulting predicted risk would be if such a change was made.  ... 
doi:10.1145/2858036.2858529 dblp:conf/chi/KrausePN16 fatcat:qdi3tnbw7fbn5c3wrrkgq6au4u

Online Incremental Machine Learning Platform for Big Data-Driven Smart Traffic Management

Dinithi Nallaperuma, Rashmika Nawaratne, Tharindu Bandaragoda, Achini Adikari, Su Nguyen, Thimal Kempitiya, Daswin De Silva, Damminda Alahakoon, Dakshan Pothuhera
2019 IEEE transactions on intelligent transportation systems (Print)  
Index Terms-Smart traffic management, concept drift, unsupervised incremental learning, deep learning, deep reinforcement learning, impact propagation, traffic optimization, traffic forecasting, traffic  ...  It is timely and pertinent that ITS harness the potential of an artificial intelligence (AI) to develop the big data-driven smart traffic management solutions for effective decision-making.  ...  machine learning algorithms and prediction schemes for nonrecurrent traffic incidents that impact an entire road network. b) a majority of existing approaches focus on freeways and highways, with very  ... 
doi:10.1109/tits.2019.2924883 fatcat:enaochz3vverdhfeg2poazc6ai

Priority-based Post-Processing Bias Mitigation for Individual and Group Fairness [article]

Pranay Lohia
2021 arXiv   pre-print
Our novel framework establishes it by using a user segmentation algorithm to capture the consumption strategy better.  ...  We establish this proposition by a case study on tariff allotment in a smart grid.  ...  Disparate impact (DI) is a standard measure for group fairness. Pre-processing, in-processing, and post-processing are three stages for performing debiasing in the machine learning model.  ... 
arXiv:2102.00417v1 fatcat:trvhea4tsvct7gkxtkbfjvajfe

Prediction of Urban and Rural Tourism Economic Forecast Based on Machine Learning

Wusheng Zhou, Bai Yuan Ding
2021 Scientific Programming  
The quasi-prediction of tourism revenue can drive the development of a series of related industries and accelerate the development of the domestic economy.  ...  The traditional cointegration analysis method is to extract the promotion characteristics of tourism income to the local economy and construct a tourism income prediction model, but it cannot accurately  ...  From the perspective of predictive ability, machine learning is a predictive method with strong applicability, good accuracy, and high efficiency.  ... 
doi:10.1155/2021/4072499 fatcat:u37r6pevvvfalm34xlfmj3c33i
« Previous Showing results 1 — 15 out of 325,315 results