228 skills found · Page 5 of 8
ManuelMBaumann / Elastic BenchmarksBenchmark problems in 2D and 3D for the elastic wave equation.
fgwei / ICC BenchBenchmark apps for static analyzing inter-component data leakage problem of Android apps.
Mavrovouniotis / E Cvrp Benchmark InstancesElectric Capacitated Vehicle Routing Problem Benchmark Instances
ASU-VDA-Lab / ML For IR DropThese benchmarks were used as a part of the ICCAD23 Contest Problem C ML for static IR drop prediction
chungyc / NinetynineNinety-Nine Haskell Problems. The documentation serves as a standalone list of problems. Includes tests and benchmarks for checking and comparing solutions.
HITsz-TMG / VisionGraphThe benchmark and datasets of the ICML 2024 paper "VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context"
RUCAIBox / ICPC EvalA new benchmark of 118 ICPC problems for evaluating LLM reasoning in competitive coding, featuring realistic ICPC competition scenario, robust local evaluation, and a iterative repair metrics Refine@K
facebookresearch / Relative Pose DatasetWe release a dataset that we have generated from TUM benchmark to evaluate relative pose estimators and therefore facilitate the comparison against future solutions for the relative pose problem.
mrflip / ChimpmarkChimpMARK-2010 is a collection of massive real-world datasets, interesting real-world problems, and simple example code to solve them. Learn Big Data processing, benchmark your cluster, or compete on implementation!
thieu1995 / EnoppyENOPPY: A Python Library for Engineering Optimization Problems
yangdeng-EML / ML MM Benchmark3 physical problems + multiple ML architectures benchmarking
fitbenchmarking / FitbenchmarkingTool for comparing the run time and accuracy of minimizers on fit benchmarking problems
Generative-Engine-Marketing / GEM BenchFirst complete benchmark for Generative Engine Marketing (GEM), an emerging field that focuses on monetizing generative AI by seamlessly integrating advertisements into Large Language Model (LLM) responses. Our work addresses the core problem of ad-injected response (AIR) generation and provides a framework for its evaluation.
nikhilvenkatkumsetty / Financial Time Series Analysis For High Frequency TradingFinancial time-series forecasting has long been a challenging problem because of the inherently noisy and stochastic nature of the market. In the field of High-Frequency Trading (HFT), forecasting for trading purposes is even a more challenging task since an automated inference system is required to be both accurate and fast. In this project, we have implemented a shallow-architecture methodology for the forecasting of financial time-series data, which gives state-of-the-art results. This architecture has been trained and tested on the benchmark Limit Order Book(LOB) FI-2010 dataset, and the corresponding results are compared and analyzed using a variety of measures.
jbussemaker / OpenTurbofanArchitectingOpen-source turbofan architecting benchmark problem
fmrchallenge / Fmrbenchmarkbenchmark problems for research in formal methods for robotics
JuliaDecisionFocusedLearning / DecisionFocusedLearningBenchmarks.jlBenchmark problems for decision-focused learning
hamcruise / FJSP ShutdownCompromising productivity in exchange for energy-saving does not appeal to highly capitalized manufacturing industries. However, we might be able to maintain the same productivity while significantly reducing the energy-consumption. This paper addresses a flexible job shop scheduling problem with a shutdown (on/off) strategy aiming to minimize makespan plus total energy consumption. First, an existing mixed integer linear programming model in the literature is improved and an alternative model is proposed. Second, novel constraint programming and genetic algorithm are proposed. Third, practical operational scenarios are compared and managerial insight is derived. Finally, we provide benchmarking instances, CPLEX codes, and genetic algorithm codes, in order to promote related-research, thus expediting the adoption of energy-efficient scheduling in manufacturing facilities. The computational study demonstrates (1) the proposed models significantly outperform other benchmark models and (2) we can maintain maximum productivity while significantly reducing energy-consumption up to 20%.
yosrinegm / Astronomical Images ClassificationRecently, a massive astronomical dataset is being collected to find answers for a variety of unanswered questions about our universe by virtue of modern sky survey instruments. Unfortunately, it is impossible to work on these massive datasets manually to get effective results so, astronomers are seeking approaches to automate the human error borne processes of manual scanning in order to discover astronomical knowledge and information from these large raw datasets i.e. to classify stars, quasars, galaxies and Supernovae (SNe). The problem here, this is done by hand and it is a very time consuming job as well as it is subject to human bias which differs from person to person. In addition, the manual scanning is infeasible for a huge amount of images. From this point of view, I've selected this concrete astronomical classification problem to investigate applying convolutional Neural Networks (CNNs) algorithm to automate this process and then I compared my results to a reference publication as a benchmark model by using the same well-known public dataset of the Sloan Digital Sky Survey (SDSS).
infomindgithub / Machine Learning Engineer Nanodegree Capstone PROJECT ANALYSIS*****PROJECT SPECIFICATION: Machine Learning Capstone Analysis Project***** This capstone project involves machine learning modeling and analysis of clinical, demographic, and brain related derived anatomic measures from human MRI (magnetic resonance imaging) tests (http://www.oasis-brains.org/). The objectives of these measurements are to diagnose the level of Dementia in the individuals and the probability that these individuals may have Alzheimer's Disease (AD). In published studies, Machine Learning has been applied to Alzheimer’s/Dementia identification from MRI scans and related data in the academic papers/theses in References 10 and 11 listed in the References Section below. Recently, a close relative of mine had to undergo a sequence of MRI tests for cognition difficulties.The motivation for choosing this topic for the Capstone project arose from the desire to understand and analyze potential for Dementia and AD from MRI related data. Cognitive testing, clinical assessments and demographic data related to these MRI tests are used in this project. This Capstone project does not use the MRI "imaging" data and does not focus on AD, focusses only on Dementia. *****Conclusions, Justification, and Reflections***** [Student adequately summarizes the end-to-end problem solution and discusses one or two particular aspects of the project they found interesting or difficult.] The formulation of OASIS data (Ref 1 and 2) in terms of a dementia classification problem based on demographic and clinical data only (and without directly using the MRI image data), is a simplification that has major advantages and appeal. This means the trained model can classify whether an individual has dementia or not with about 87% accuracy, without having to wait for radiological interpretation of MRI scans. This can provide an early alert for intervention and initiation of treatment for those with onset of dementia. The assumption that the combined cross-sectional and longitudinal datasets would lead to dementia label classification of acceptable accuracy came out to be true. The method required careful data cleaning and data preparation work, converting it to a binary classification problem, as outlined in this notebook. At the outset it was not clear which algorithm(s) would be more appropriate for the binary and multi-label classification problem. The approach of spot checking the algorithms early for accuracy led to the determination of a smaller set of algorithms with higher accuracy (e.g. Gadient Boosting and Random Forest) for a deeper dive examination, e.g. use of a k-fold cross-validation approach in classifying the CDR label. The neural network benchmark model accuracy of 78% for binary classification was exceeded by the classification accuracy of the main output of this study, the trained Gradient Boosting and Random Forest classification models. This builds confidence in the latter model for further training with new data and further classification use for new patients.
