Model predicts cognitive health risks based on smartphone usage patterns.
problem Identifying cognitive health risks through smartphone usage.
method Structured models of smartphone interactions analyzed over 12 weeks.
result AUROC of 0.79 in discriminating between healthy and symptomatic subjects.
Proposes AtCoR for predicting bike station usage, improving station network reconfiguration.
problem Challenges in predicting new bike stations due to lack of historical data.
method AtCoR algorithm that predicts both existing and new bike stations using station-centered heatmaps and historical correlations.
result AtCoR outperforms existing models in predicting bike station usage.
Method learns software resource usage from snapshots.
problem Challenges in learning time-varying, correlated resource usage.
method Graph structured Schrödinger bridge problem for nonparametric learning.
result Predicts most-likely resource distributions.
Neural networks predict EV charging station usage from network layout.
problem Designing optimal EV charging station networks.
method Used neural networks to predict usage from station layout.
result Quickly estimates average usage statistics from proposed station placements.
Method predicts hardware resource usage by control software with guaranteed linear convergence.
problem Predicting time-varying hardware resource availability in control software.
method Path structured multimarginal Schrödinger bridge (MSBP) for learning stochastic resource usage.
result Guaranteed linear convergence to accurate prediction of hardware resource utilization.
AppsPred predicts smartphone app usage based on context.
problem Predicting personalized usage behavior of smartphone apps based on contexts.
method Random Forest machine learning technique considering multi-dimensional contexts.
result AppsPred significantly outperforms other machine learning approaches in predicting smartphone apps.
Crowdsourcing generated useful hypotheses for predicting residential energy usage.
problem Predicting residential electric energy usage using crowdsourced data.
method Crowdsourced questions and answers were used to build a predictive model of monthly electric energy consumption.
result The crowd can generate useful hypotheses for predicting energy usage, even with sparse data.
This study uses LSTM and SARIMA models to forecast CPU usage in cloud computing.
problem Predicting future CPU usage in cloud computing centers.
method Used LSTM and SARIMA models to forecast CPU usage over short and long time scales.
result SARIMA model performed better for long-term predictions but LSTM was more robust.
Context2Name predicts natural names from minified code, improving code readability.
problem Minified code makes it hard to understand natural names in JavaScript.
method Combines static analysis and neural networks to predict natural names.
result Successfully predicts 47.5% of all minified identifiers in real-world code.
Deep learning detects inaccurate smart meters for resource savings.
problem Detecting and replacing inaccurate smart meters to save resources.
method Developed a deep-learning method using LSTM and CNN to predict electricity usage trajectories.
result High accuracy in detecting inaccurate meters for practical usage.
New features from early battery cycles predict lifetime with high accuracy.
problem Accurately predicting battery lifetime under varying conditions is challenging due to manufacturing variability and usage-dependent degradation.
method Extracted features from regularly scheduled reference performance tests and used them to predict battery lifetime using a hierarchical Bayesian regression model.
result Demonstrated a lifetime prediction of in-distribution cells with 15.1% mean absolute percentage error using only the first 15% of data.
DCN combines DNN and cross network for efficient ad click prediction.
problem Efficiently learn feature interactions in prediction models.
method Deep & Cross Network (DCN) that explicitly applies feature crossing at each layer.
result Demonstrated superior performance in model accuracy and memory usage.
Traditional recommendation systems rely on past usage data in order to generate new recommendations. Those approaches fail to generate sensible recommendations for new users and items into the system due to missing information about their past interactions. In this paper, we propose a solution for successfully addressi…
The paper identifies when larger models improve predictions and proposes a switcher model.
problem Understanding when larger models benefit from added complexity.
method Numerical studies on T5 architecture to analyze predictive uncertainty and model performance.
result Large models improve on examples where small models are uncertain, but not on certain examples.
Develops S-EFE for analyzing grouped data, improving word usage interpretation.
problem Analyzing how words are used differently across related groups of data.
method Structured exponential family embeddings (S-EFE) with hierarchical modeling and amortization.
result S-EFE enables group-specific interpretation of word usage and outperforms EFE.
A new method for time-series data provides guaranteed coverage and adapts to non-exchangeable data.
problem Guaranteed coverage for time-series data prediction intervals.
method Sequential Conformalized Density Regions (SCDR) using quantile random forest.
result SCDR achieves guaranteed asymptotic coverage and outperforms existing methods in simulations.
HIVE-COTE v1.0 improves time series classification with enhanced usability.
problem Improving time series classification accuracy and usability.
method Presented a walkthrough guide and extensive experimental evaluation of HIVE-COTE v1.0.
result HIVE-COTE v1.0 outperforms three recently proposed algorithms in predictive performance and resource usage.
Bayesian approach predicts battery health under varied conditions.
problem Accurately predicting battery health for reliable operation and investment valuation.
method Gaussian process regression with Bayesian non-parametric feature selection.
result Method accurately predicts battery capacity fade with low error.
Model predicts web page parallelism for improved browser performance and energy.
problem Improving browser performance and energy usage through parallelism.
method Supervised learning model using web page primitives and parallelism features.
result Model predicts parallelism and optimizes performance and energy usage.
Efficiently trains GCNs with reduced time and memory usage.
problem Hard training of GCNs over large graph datasets.
method Layer-wise and learned efficient training framework (L2-GCN). result Significantly reduces training time and memory usage.
Efficient neural network improves disaggregation of home energy usage.
problem Estimating power consumption of individual appliances from total home power.
method Fully convolutional neural network architecture with improved computational efficiency.
result Achieves state-of-the-art disaggregation performance with reduced training and prediction times.
Extends conformal prediction for controlling expected risk of monotone loss functions.
problem Controlling expected risk of monotone loss functions.
method Generalizes split conformal prediction with coverage guarantee, extending to distribution shift, quantile risk, multiple, adversarial, and expectations of U-statistics.
result Tight up to an O(1/n) factor, with worked examples in computer vision and natural language processing. Unihedge uses HTAX to create unlimited liquidity in prediction markets.
problem Limited liquidity and information incorporation issues in prediction markets.
method Introduces HTAX prediction markets with DPM derivatives and new incentive mechanisms.
result Unlimited liquidity and improved information incorporation in prediction markets.
Proposes a game-theoretic framework to motivate energy-efficient behavior in smart buildings.
problem Improving energy efficiency in smart building infrastructure through occupant behavior.
method Introduces a novel game-theoretic framework with human interaction, incorporating utility learning and deep neural networks.
result Demonstrates highly accurate prediction of occupant energy resource usage and explainable decision-making.
Mixed dimension embeddings reduce memory usage in recommendation systems.
problem Space-intensive embedding representations in recommendation systems.
method Mixed dimension embeddings where vector dimension scales with query frequency.
result Significant reduction in memory usage with minimal performance loss.
This study analyzes how weather impacts bike sharing usage in Washington D.C.
problem Understanding how weather affects bike sharing usage patterns.
method Gathered bike usage and weather data, used k-means clustering algorithm to identify clusters.
result Weather significantly impacts bike usage, with temperature and precipitation being the most influential factors.
Improves full conformal prediction for stochastic non-conformity measures.
problem Inability of existing conditions to guarantee full conformal prediction validity under stochastic settings.
method Introduces a new sufficient condition: Conditional Independence & Permutation Invariance in Distribution.
result Corrects the insufficient condition and provides a new sufficient condition for full conformal prediction validity.
Paper explores how black box models can deviate from average performance.
problem Understanding and interpreting predictions from sophisticated black box models.
method Two general approaches to provide interpretable descriptions of black box classification model performance.
result Identifies regions where black box models deviate significantly from their average performance.
Deep Rule Forests identifies drug-drug and drug-disease interactions causing AKI.
problem Identifying drug-drug and drug-disease interactions leading to AKI.
method Deep Rule Forests (DRF) algorithm discovering rules from multilayer tree models.
result DRF model outperforms other algorithms in prediction accuracy and interpretability.
Paper presents AETN for efficient user modeling from mobile app usage.
problem Efficient user modeling from mobile app usage with reduced manual effort.
method AutoEncoder-coupled Transformer Network (AETN).
result AETN achieves effective user embeddings with reduced manual effort.
Band-limited training reduces resource usage without sacrificing accuracy.
problem Resource constraints in training Convolutional Neural Networks (CNNs).
method Artificially constraining the frequency spectra of convolutional filters during training.
result CNNs can leverage lower-frequency components effectively, reducing resource usage.
New method for faster TPM from multivariate time series.
problem Mining predictive complex temporal patterns from multivariate time series.
method Fast Temporal Pattern Mining with Extended Vertical Lists.
result Significantly faster performance than previous algorithm.
Bayesian model predicts public transport usage during events.
problem Difficulty in predicting transportation disruptions during special events.
method Bayesian additive model with Gaussian process components, using smart card records and web data.
result Model outperforms baselines by up to 26% in R2 and explains individual event components.
Paper proposes transparent reporting of algorithmic energy usage to promote environmental sustainability.
problem Need for transparent reporting of algorithmic energy usage for environmental sustainability.
method Developed a Python package to make analyses of energy usage accessible to individual researchers, localized to specific power grids, and compared with global benchmarks.
result Demonstrated the use of automatically-generated Energy Usage Reports in model-choice for machine learning.
Graphical Lasso algorithm segments occupants' energy usage behaviors in HC-CP systems.
problem Improving sustainability and energy efficiency in HC-CP systems.
method Introduced a gamification framework and applied Graphical Lasso for energy usage segmentation.
result Characterized different energy usage behaviors in HC-CP systems.
Study examines how imputation accuracy affects prediction accuracy in regression problems with missing covariates.
problem Missing covariates in regression or classification problems.
method Simulation and empirical analysis using UCI datasets and statistical inference.
result Imputation accuracy impacts prediction accuracy, especially with Machine Learning methods.
Random Forest permutation importance measure is asymptotically unbiased in sparse regression models.
problem Challenges in selecting informative variables in high-dimensional regression problems.
method Theoretical guarantees and asymptotic unbiasedness of permutation importance measure under specific assumptions.
result Permutation importance measure in Random Forest is asymptotically unbiased.
Investigations have been performed into using clustering methods in data mining time-series data from smart meters. The problem is to identify patterns and trends in energy usage profiles of commercial and industrial customers over 24-hour periods, and group similar profiles. We tested our method on energy usage data p…
Random weights in GNNs match learned weights in performance.
problem Feature rank collapse in GNNs.
method Replacing learned weights with random weights.
result Random weights achieve comparable performance to learned weights, reducing training time and memory usage.
DBMs model Fitbit usage patterns revealing two distinct weekly usage habits.
problem Challenges in modeling activity tracker data due to unlabeled data.
method Deep Boltzmann Machines (DBMs) for unsupervised learning of weekly usage patterns.
result Two distinct weekly usage patterns identified: frequent Monday-Tuesday use and consistent weekly use.
Random forest predicts catastrophe bond spreads with 93% accuracy.
problem Predicting spreads in the primary catastrophe bond market.
method Random forest approach using all information in offering circulars.
result Random forest explains 93% of spread variability, significantly better than linear regression (47%).
New method improves model predictions for complex systems.
problem Applying high-dimensional, nonlinear models requires fitting accurate data.
method Supermodeling with sensitivity analysis to reduce coupling coefficients.
result Supermodeling outperforms Approximate Bayesian Computation for chaotic systems.
Survey of mobility studies using mobile phone data.
problem Understanding human mobility patterns.
method Data Science techniques applied to mobile phone datasets.
result Applications in urban planning, data traffic prediction, etc.
RNNs improve predictive precompute for faster user interface response times.
problem Improving user interface response times in mobile and web applications.
method Application of recurrent neural networks (RNNs) for predictive precompute.
result RNN models improve prediction accuracy and reduce computational cost.
Recently, a technique called Layer-wise Relevance Propagation (LRP) was shown to deliver insightful explanations in the form of input space relevances for understanding feed-forward neural network classification decisions. In the present work, we extend the usage of LRP to recurrent neural networks. We propose a specif…
Sequence-to-sequence models predict resource usage for co-scheduled jobs in data centers.
problem Challenges in co-scheduling jobs due to resource interference and inefficiencies.
method Sequence-to-sequence models based on recurrent neural networks for workload interference prediction.
result Models accurately forecast resource usage trends from job profiles, improving scheduling decisions.
This work uses conformal prediction to quantify uncertainty in large language models for multiple-choice questions.
problem Ensuring robustness and reliability of large language models in high-stakes applications.
method Conformal prediction applied to multi-choice question answering.
result Uncertainty estimates from conformal prediction are closely related to prediction accuracy.
A new model improves homogeneity in burn patient reimbursement.
problem Incomplete homogeneity checks for burn patients using LOS as a proxy.
method Cost-sensitive decision tree model considering patient-level cost and severity of burn.
result Identified groups with increased homogeneity compared to current HRG groups.