2,348 Hits in 4.7 sec

Precise Regression Benchmarking with Random Effects: Improving Mono Benchmark Results [chapter]

Tomas Kalibera, Petr Tuma
2006 Lecture Notes in Computer Science  
Regression Benchmarking  ... 
doi:10.1007/11777830_5 fatcat:pe3bwktgvnfklg7zabv7dubvea

Quality Assurance in Performance: Evaluating Mono Benchmark Results [chapter]

Tomas Kalibera, Lubomir Bulej, Petr Tuma
2005 Lecture Notes in Computer Science  
Regression benchmarking provides means for an automated monitoring of performance, yielding a list of software modifications potentially associated with performance changes.  ...  We focus on locating individual modifications as causes of individual performance changes and present three methods that help narrow down the list of modifications potentially associated with a performance  ...  The authors would like to express their thanks to Jaromir Antoch, Alena Koubkova and Tomas Ostatnicky for their help with mathematical statistics.  ... 
doi:10.1007/11558569_20 fatcat:z3okwif72nbjnpzkso4g2bhd6q

Quantifying Performance Changes with Effect Size Confidence Intervals [article]

Tomas Kalibera, Richard Jones
2020 arXiv   pre-print
Few of these papers evaluated their results with the level of rigour that has come to be expected in other experimental sciences. The uncertainty of measured results was largely ignored.  ...  This poses a hazard to the repeatability, reproducibility and even validity of quantitative results.  ...  in the most precise result for a given experimentation time.  ... 
arXiv:2007.10899v1 fatcat:jxid2du5araz7i6h7es6yqk6bq

A neural network-based method for polypharmacy side effects prediction

Raziyeh Masumshah, Rosa Aghdam, Changiz Eslahchi
2021 BMC Bioinformatics  
Results We propose a neural network-based method for polypharmacy side effects prediction (NNPS) by using novel feature vectors based on mono side effects, and drug–protein interaction information.  ...  We compare NNPS on a benchmark dataset to predict 964 polypharmacy side effects against 5 well-established methods and show that NNPS achieves better results than the results of all 5 methods in terms  ...  To compare the results of NNPS more precisely, we compare it to the results of the Decagon with more details and by some more criteria.  ... 
doi:10.1186/s12859-021-04298-y fatcat:epr5cjs6gzbgpiw22smbgm4zgu

Reducing performance non-determinism via cache-aware page allocation strategies

Michal Hocko, Tomas Kalibera
2010 Proceedings of the first joint WOSP/SIPEW international conference on Performance engineering - WOSP/SIPEW '10  
Real-time systems are hard to dimension and tune with non-determinism.  ...  In performance evaluation via benchmarking and simulation, nondeterminism requires long executions and more complex experiment design.  ...  Acknowledgments The authors would like to thank Filip Pizlo and Jan Vitek for their careful reviews and insightful comments that have helped to improve the paper.  ... 
doi:10.1145/1712605.1712640 dblp:conf/wosp/HockoK10 fatcat:6mwlop2pdvdnpk3sw4d26gxgcy

Effects of gestational exposures to chemical mixtures on birth weight using Bayesian factor analysis in the Health Outcome and Measures of Environment (HOME) Study

Liheng H. Zhuang, Aimin Chen, Joseph M. Braun, Bruce P. Lanphear, Janice M. Y. Hu, Kimberly Yolton, Lawrence C. McCandless
2021 Environmental Epidemiology  
Studying the effects of gestational exposures to chemical mixtures on infant birth weight is inconclusive due to several challenges. One of the challenges is which statistical methods to rely on.  ...  We introduced a novel BFA approach and demonstrated that the precision of the estimates for the mixture-effect is improved in BFA compared with BKMR and MLR.  ...  Meanwhile, BKMR uses nonlinear smoothing techniques, 23 which resulted in less precise effect estimates compared with BFA.  ... 
doi:10.1097/ee9.0000000000000159 pmid:34131620 pmcid:PMC8196215 fatcat:qlmalji5avexrgcidvisyamtau

HMMBinder: DNA-Binding Protein Prediction Using HMM Profile Based Features

Rianon Zaman, Shahana Yasmin Chowdhury, Mahmood A. Rashid, Alok Sharma, Abdollah Dehzangi, Swakkhar Shatabda
2017 BioMed Research International  
Our method was tested on standard benchmark datasets. We experimentally show that our method outperforms the state-of-the-art methods found in the literature.  ...  Similar results could be noticed for auROC, MCC, and sensitivity analysis. Specificity, auROC, and auPR are slightly improved in the experiments with SVM with RBF kernels.  ...  Effect of HMM Based Comparison with Other Methods.  ... 
doi:10.1155/2017/4590609 pmid:29270430 pmcid:PMC5706079 fatcat:rpvpyoaqc5bqpgkjjrs7of6btu

Automated benchmarking and analysis tool

Tomas Kalibera, Jakub Lehotsky, David Majda, Branislav Repcek, Michal Tomcanyi, Antonin Tomecek, Petr Tuma, Jaroslav Urban
2006 Proceedings of the 1st international conference on Performance evaluation methodolgies and tools - valuetools '06  
BEEN has been designed to facilitate automated detection of performance changes during software development (regression benchmarking).  ...  We present the result of project BEEN, a generic tool for automated benchmarking in a heterogeneous distributed environment.  ...  [1] and Mono Regression Benchmarking Project [7] .  ... 
doi:10.1145/1190095.1190101 dblp:conf/valuetools/KaliberaLMRTTTU06 fatcat:74sr3tnbijdjzeuky4ycdxehhm

Performance of variable and function selection methods for estimating the non-linear health effects of correlated chemical mixtures: a simulation study [article]

Nina Lazarevic, Luke D. Knibbs, Peter D. Sly, Adrian G. Barnett
2019 arXiv   pre-print
In a simulation study, we assessed the performance of Bayesian kernel machine regression (BKMR), Bayesian additive regression trees (BART), Bayesian structured additive regression with spike-slab priors  ...  Penalised regression methods that assume linearity, such as lasso, may not be suitable for studies of environmental chemicals hypothesised to have non-monotonic relationships with outcomes.  ...  As an oracle (i.e., benchmark) method, we fitted GAMs to the true model of four phenols (R package mgcv, version 1.8-23, with restricted maximum likelihood smoothing parameter estimation). 35 Results  ... 
arXiv:1908.01583v1 fatcat:gvsnohqkmbfrnjzq3ezrnmxwoa

RGB cameras failures and their effects in autonomous driving applications [article]

Francesco Secci, Andrea Ceccarelli
2022 arXiv   pre-print
The resulting misbehaviors with respect to operating with clean images allow a better understanding of failures effects and the related safety risks in image-based applications.  ...  To support the definition of safe and robust vehicle architectures and intelligent systems, in this paper we define the failure modes of a vehicle camera, together with an analysis of effects and known  ...  KITTI includes a benchmark to measure object detection performance based on the average precision AP [77] .  ... 
arXiv:2008.05938v3 fatcat:f2glidprlvdpnbjxq6crxcv36u

A comparison of reweighting estimators of average treatment effects in real world populations

Chen-Yen Lin, Eloise Kaizar, Douglas Faries, Joseph Johnston
2021 Pharmaceutical statistics  
in whether results observed in idealized trial settings will translate into comparable outcomes in real world settings-that is, into so-called "real world" effectiveness.  ...  Our results suggest an optimal approach to estimation depends on the characteristics of source and target populations, including degree of selection bias and treatment effect heterogeneity.  ...  γ = 2, we find it helpful for improving our intuition.  ... 
doi:10.1002/pst.2106 pmid:33675139 fatcat:cj57bkerorfujgd5y5eminx3re

LAReQA: Language-agnostic answer retrieval from a multilingual pool [article]

Uma Roy, Noah Constant, Rami Al-Rfou, Aditya Barua, Aaron Phillips, Yinfei Yang
2020 arXiv   pre-print
We find that augmenting training data via machine translation is effective, and improves significantly over using mBERT out-of-the-box.  ...  We present LAReQA, a challenging new benchmark for language-agnostic answer retrieval from a multilingual candidate pool.  ...  While mBERT exhibits some strong crosslingual alignment out of the box, our results show that this can be improved greatly by using cross-lingual objectives, as in X-X-mono and X-Y.  ... 
arXiv:2004.05484v1 fatcat:75ilkbbezzhdvnqm4xzultmldu

An Unsupervised Approach to Anomaly Detection in Music Datasets

Yen-Cheng Lu, Chih-Wei Wu, Chang-Tien Lu, Alexander Lerch
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
The model integrates categorical regression and robust estimation techniques to infer anomalous scores in music clips.  ...  The proposed method introduces a preliminary framework for anomaly detection in music data that can serve as a useful tool to improve data integrity in the future.  ...  Benchmark Methods We compared the results obtained using our approach with those of three unsupervised benchmark methods.  ... 
doi:10.1145/2911451.2914700 dblp:conf/sigir/LuWLL16 fatcat:dogpxumtoraopfv32dejpvmf6u

On the Interaction Effects Between Prediction and Clustering [article]

Matt Barnes, Artur Dubrawski
2018 arXiv   pre-print
Empirical results on benchmark datasets validate our theoretical results and demonstrate how scaling techniques provide solutions to new classes of problems.  ...  We precisely answer these questions by providing theoretical properties which hold in various settings, and prove that expected out-of-cluster loss behavior rapidly decays with even minor clustering errors  ...  effects closely aligns with our theoretical results.  ... 
arXiv:1807.06713v2 fatcat:b3gcp6h7gvhyxcnhazs2a52dy4

How accurate are yield estimates from crop cuts? Evidence from smallholder maize farms in Ethiopia

Frederic Kosmowski, Jordan Chamberlin, Hailemariam Ayalew, Tesfaye Sida, Kibrom Abay, Peter Craufurd
2021 Food Policy  
We find that randomly positioned quadrants outperform systematic sampling schemes: the random octant had the best accuracy and was the most cost-effective.  ...  We compare yield from a full plot harvest with farmer assessments and with estimates from a variety of field sampling protocols: W-walk, transect, random quadrant, random octant, center quadrant, and 3  ...  Taking Maize Agronomy to Scale in Africa (TAMASA) project (investment number INV-008260), and the CGIAR Research Program on Maize Agri Food System (CRP MAIZE-AFS) led by the International Maize and Wheat Improvement  ... 
doi:10.1016/j.foodpol.2021.102122 pmid:34898811 pmcid:PMC8639447 fatcat:qx6ewof7fnfovgcc2snfu4oi24
« Previous Showing results 1 — 15 out of 2,348 results