Filters








3,254 Hits in 7.6 sec

Predictive Multiplicity in Classification [article]

Charles T. Marx, Flavio du Pin Calmon, Berk Ustun
2020 arXiv   pre-print
We introduce formal measures to evaluate the severity of predictive multiplicity and develop integer programming tools to compute them exactly for linear classification problems.  ...  Prediction problems often admit competing models that perform almost equally well. This effect challenges key assumptions in machine learning when competing models assign conflicting predictions.  ...  This research is supported in part by the National Science Foundation under Grants No. CAREER CIF-1845852 and by a Google Faculty Award.  ... 
arXiv:1909.06677v4 fatcat:6dfmvetrvfdkhlhp472bdcwiu4

Learning Optimal Solutions via an LSTM-Optimization Framework [article]

Dogacan Yilmaz, İ. Esra Büyüktahtakın
2022 arXiv   pre-print
In this study, we present a deep learning-optimization framework to tackle dynamic mixed-integer programs.  ...  Specifically, we develop a bidirectional Long Short Term Memory (LSTM) framework that can process information forward and backward in time to learn optimal solutions to sequential decision-making problems  ...  in MPS/NSF under Grant No.  ... 
arXiv:2207.02937v1 fatcat:jx764ljacbfjfdmy7se45d2y4i

Energy management of small-scale PV-battery systems: A systematic review considering practical implementation, computational requirements, quality of input data and battery degradation

Donald Azuatalam, Kaveh Paridari, Yiju Ma, Markus Förstl, Archie C. Chapman, Gregor Verbič
2019 Renewable & Sustainable Energy Reviews  
The existing literature in this area focuses on individual aspects of this problem without a detailed, holistic analysis of the results with regards to practicality in implementation.  ...  Our analysis finds that using a more sophisticated energy management strategy may not necessarily improve the performance and economic viability of the PV-battery system due to the effects of modeling  ...  Furthermore, even faster, near-optimal solutions can be obtained with policy function approximations (PFA) using machine learning.  ... 
doi:10.1016/j.rser.2019.06.007 fatcat:w2psa72fm5hu5hewrwgqlfwavy

A Taxonomy of Railway Track Maintenance Planning and Scheduling: A Review and Research Trends

Mahdieh Sedghi, Osmo Kauppila, Bjarne Bergquist, Erik Vanhatalo, Murat Kulahci
2021 Reliability Engineering & System Safety  
scheduling Bi-Objective Mixed-Integer Linear [18] Programming, Pareto optimal solutions Lidén [22] ✓ ✓ Possession scheduling Mixed Integer Programming Zhang et al. [26] ✓ ✓ Possession scheduling Integer  ...  Linear and integer programming The nature of the decision variables in RTMP&S makes linear or nonlinear programming suitable.  ...  Summary of the literature review Table A1 and Table A2 Table A .1 Summary of the articles with predetermined maintenance policy.  ... 
doi:10.1016/j.ress.2021.107827 fatcat:u7w5th73uvai3ane5b254bpcey

Learning Combined Set Covering and Traveling Salesman Problem [article]

Yuwen Yang, Jayant Rajgopal
2020 arXiv   pre-print
to effectively deal with this problem by providing an opportunity to learn from historical optimal solutions that are derived from the MIP formulation.  ...  We study a combined Set Covering and Traveling Salesman problem and provide a mixed integer programming formulation to solve the problem.  ...  41] , learning where to linearize a mixed integer quadratic problem [42] , learning tactical solutions under imperfect information [43] , and learning as a modeling tool [44] .  ... 
arXiv:2007.03203v1 fatcat:e5g2rckrmra3padchc7wxytw74

Power System Reliability and Maintenance Evolution: A Critical Review and Future Perspectives

Manuel S. Alvarez-Alvarado, Daniel L. Donaldson, Angel A. Recalde, Holguer H. Noriega, Zafar A. Khan, Washington Velasquez, Carlos D. Rodriguez-Gallegos
2022 IEEE Access  
Finally, areas requiring further research are identified alongside emerging trends in power system maintenance, to inform industry practice and support further research.  ...  As societal dependence on power system infrastructure continues to grow, there is an increased need to identify the best practices in the field of power system maintenance planning to ensure the continued  ...  Under this need, authors in [55] , [56] , and [57] use Integer Linear programming to assess generation adequacy in Taiwan, Trinidad-Tobago, and Kuwait, respectively.  ... 
doi:10.1109/access.2022.3172697 fatcat:dskfzzds7zhh7gci4cie32toue

A hybrid machine learning-optimization approach to pricing and train formation problem under demand uncertainty

Atiye Yousefi, Mir Saman Pishvaee
2022 Reserche operationelle  
To this end, we combined an optimization approach with a regression-based machine learning method to provide a reliable and efficient framework for integrated pricing and train formation problem under  ...  Further, in order to deal with the hybrid uncertainty of demand parameter, a robust fuzzy stochastic programming model is proposed.  ...  Machine learning models cannot optimize and they are only predicting factors based on some available information.  ... 
doi:10.1051/ro/2022052 fatcat:7vdgtla32ffgtdzv54m4lxyir4

A Survey on Adaptive Data Rate Optimization in LoRaWAN: Recent Solutions and Major Challenges

Rachel Kufakunesu, Gerhard P. Hancke, Adnan M. Abu-Mahfouz
2020 Sensors  
First, we provide an overview of LoRaWAN network performance that has been explored and documented in the literature and then focus on recent solutions for ADR as an optimization approach to improve throughput  ...  LoRaWAN is built to optimize LPWANs for battery lifetime, capacity, range, and cost.  ...  scheduling  [32] Scalability Machine Learning MATLAB Variable Hysteresis   [33] Scalability Integer Linear Programming    [34] Scalability NS-3 [35] Scalability Mathematical  ... 
doi:10.3390/s20185044 pmid:32899454 fatcat:nrruddlhrzd7rdx4sxkmpn3bje

Smart "Predict, then Optimize" [article]

Adam N. Elmachtoub, Paul Grigas
2020 arXiv   pre-print
By and large, machine learning tools are intended to minimize prediction error and do not account for how the predictions will be used in the downstream optimization problem.  ...  Our SPO+ loss function can tractably handle any polyhedral, convex, or even mixed-integer optimization problem with a linear objective.  ...  Data-driven inverse optimization with imperfect information. Mathematical Programming 167(1) 191- 234. Molchanov, Ilya. 2005. Theory of random sets, vol. 19. Springer.  ... 
arXiv:1710.08005v5 fatcat:a3fbloeyznaovhasvswexbzncq

Recent Techniques Used in Home Energy Management Systems: A Review

Isaías Gomes, Karol Bot, Maria da Graça Ruano, António Ruano
2022 Energies  
The so-called home energy management systems (HEMS) emerge as a solution.  ...  In addition, the techniques are divided into four broad categories: traditional techniques, model predictive control, heuristics and metaheuristics, and other techniques.  ...  Mixed-Integer Linear Programming Mixed-integer linear programming (MILP) refers to optimization techniques where the objective function is given by a linear function and subject to linear constraints but  ... 
doi:10.3390/en15082866 fatcat:nrhf6bc6frdttbnerk6lrwlcbe

Large-Scale Optimization-Based Classification Models in Medicine and Biology

Eva K. Lee
2007 Annals of Biomedical Engineering  
To illustrate the power and flexibility of the classification model and solution engine, and its multi-group prediction capability, application of the predictive model to a broad class of biological and  ...  a safeguard against over-training (which tends to lead to high misclassification rates from the resulting predictive rule); and (5) successive multi-stage classification capability to handle data points  ...  modeled as mixed integer programs.  ... 
doi:10.1007/s10439-007-9317-7 pmid:17503186 fatcat:f24xlrwqnnamzf6gppendii7b4

A Survey of Anticipatory Mobile Networking: Context-Based Classification, Prediction Methodologies, and Optimization Techniques [article]

Nicola Bui, Matteo Cesana, S. Amir Hosseini, Qi Liao, Ilaria Malanchini, Joerg Widmer
2017 arXiv   pre-print
In particular, we identify the main prediction and optimization tools adopted in this body of work and link them with objectives and constraints of the typical applications and scenarios.  ...  A growing trend for information technology is to not just react to changes, but anticipate them as much as possible.  ...  Mixed-Integer Linear Programming (MILP) approach.  ... 
arXiv:1606.00191v3 fatcat:me4ufu7gsjcmtcrs3m6g4jf2am

Energy Management in Microgrids with Renewable Energy Sources: A Literature Review

Yimy E. García Vera, Rodolfo Dufo-López, José L. Bernal-Agustín
2019 Applied Sciences  
This paper presents a literature review of energy management in microgrid systems using renewable energies, along with a comparative analysis of the different optimization objectives, constraints, solution  ...  The integration of these systems is carried out in a distributed manner via microgrid systems; this provides a set of technological solutions that allows information exchange between the consumers and  ...  Some of the classic optimization methods include mixed integer linear and non-linear programming.  ... 
doi:10.3390/app9183854 fatcat:i3kkxrvxkzfkrikaylmdrbizpi

Machine Intelligence Techniques for Next-Generation Context-Aware Wireless Networks [article]

Tadilo Endeshaw Bogale, Xianbin Wang, Long Bao Le
2018 arXiv   pre-print
At the same time, generation and consumption of wireless data are becoming increasingly distributed with ongoing paradigm shift from people-centric to machine-oriented communications, making the operation  ...  Towards this end, this article provides a comprehensive survey on the utilization of AI integrating machine learning, data analytics and natural language processing (NLP) techniques for enhancing the efficiency  ...  To solve the problems, mixed integer linear programming (MILP), ant colony optimization (ACO) and genetic algorithm (GA) have been applied.  ... 
arXiv:1801.04223v1 fatcat:5hrwouh6mrenvjnbqqwcbr5b3i

At-stop control measures in public transport: Literature review and research agenda

K. Gkiotsalitis, O. Cats
2021 Transportation Research Part E: Logistics and Transportation Review  
A B S T R A C T In this literature review, we systematically review studies on public transit control with a specific focus on at-stop measures.  ...  Control methods, that have attracted more attention in recent years due to the advancements in automation and data availability, aim at alleviating the negative effects of service variability because of  ...  Given this emergence of Big data, short-term prediction techniques often involve the application of machine learning techniques (e.g. Li et al., 2017; Toqué et al., 2017) .  ... 
doi:10.1016/j.tre.2020.102176 fatcat:oirobgtkfbgm3f3ltyf2ngyi6u
« Previous Showing results 1 — 15 out of 3,254 results