The proceedings contain 65 papers. The topics discussed include: grade prediction with neural collaborative filtering;variable-lag granger causality for time series analysis;residual networks behave like boosting algo...
ISBN:
(纸本)9781728144931
The proceedings contain 65 papers. The topics discussed include: grade prediction with neural collaborative filtering;variable-lag granger causality for time series analysis;residual networks behave like boosting algorithms;semantically-aware statistical metrics via weighting kernels;short text embedding for clustering based on word and topic semantic information;a rademacher complexity based method for controlling power and confidence level in adaptive statistical analysis;biased resampling strategies for imbalanced spatio-temporal forecasting;explaining the performance of black box regression models;text summarization by highlighting core content;and least squares and maximum likelihood estimation of sufficient reductions in regressions with matrix valued predictors.
The proceedings contain 71 papers. The topics discussed include: federated feature distillation CLIP for photovoltaic panels defect detection;accurate estimation of cross-excitation in multivariate Hawkes process mode...
ISBN:
(纸本)9798350364941
The proceedings contain 71 papers. The topics discussed include: federated feature distillation CLIP for photovoltaic panels defect detection;accurate estimation of cross-excitation in multivariate Hawkes process models of infectious diseases;deep contrastive active learning for out-of-domain filtering in dialog systems;using annealing to accelerate triangle inequality k-means;adversarial robustness in graph neural networks: recent advances and new frontier;a metaverse platform for air pollution analysis in supporting smart and sustainable city development;validating arbitrary shaped clusters - a survey;MicroPPO: safe power flow management in decentralized micro-grids with proximal policy optimization;and diffusion models for cross-domain image-to-image translation with paired and partially paired datasets.
The proceedings contain 129 papers. The topics discussed include: enhancing recommendation systems with hybrid manifold regularized knowledge graph;enhanced explanations for knowledge-augmented clustering using subgro...
ISBN:
(纸本)9798350345032
The proceedings contain 129 papers. The topics discussed include: enhancing recommendation systems with hybrid manifold regularized knowledge graph;enhanced explanations for knowledge-augmented clustering using subgroup discovery;learning representations through contrastive strategies for a more robust stance detection;exploring deep learning for full-disk solar flare prediction with empirical insights from guided Grad-CAM explanations;instils trust in random forest predictions;predict link between nodes using an ensemble modelling combining depth search algorithm and textual similarity score;enhancing the performance of automated grade prediction in MOOC using graph representation learning;and finite-sample bounds for two-distribution hypothesis tests.
The 2015 datascience and advancedanalytics (DSAA) was held on 19-21 October, 2015 inParis, France. It was fully sponsored by the ieee Computational Intelligence Society and also in partnership with the ACM SIGKDD. D...
详细信息
The 2015 datascience and advancedanalytics (DSAA) was held on 19-21 October, 2015 inParis, France. It was fully sponsored by the ieee Computational Intelligence Society and also in partnership with the ACM SIGKDD. DSAA was the only ieee/ACM jointly sponsored conference truly in datascience, big data and advancedanalytics, providing a premier forum for inter-disciplinary research across statistics, datascience, computational intelligence, and business, and for bridging the gaps between academia and industry.
The proceedings contain 86 papers. The topics discussed include: active semi-supervised classification based on multiple clustering hierarchies;combining static and dynamic features for multivariate sequence classific...
ISBN:
(纸本)9781509052066
The proceedings contain 86 papers. The topics discussed include: active semi-supervised classification based on multiple clustering hierarchies;combining static and dynamic features for multivariate sequence classification;harvester: influence optimization in symmetric interaction networks;a framework for description and analysis of sampling-based approximate triangle counting algorithms;limiting the diffusion of information by a selective PageRank-preserving approach;anomaly detection in automobile control network data with long short-term memory networks;infinite Langevin mixture modeling and feature selection;efficient identification of Tanimoto nearest neighbors;a parallel framework for grid-based bottom-up subspace clustering;impact of query sample selection bias on information retrieval system ranking;learning multifaceted latent activities from heterogeneous mobile data;the semantic knowledge graph: a compact, auto-generated model for real-time traversal and ranking of any relationship within a domain;what would a data scientist ask? automatically formulating and solving predictive problems;behavior-oriented time segmentation for mining individualized rules of mobile phone users;and online experimentation diagnosis and troubleshooting beyond AA validation.
The proceedings contain 122 papers. The topics discussed include: COSTI: a new classifier for sequences of temporal intervals;multi-instance multi-label learning based on parallel attention and local label manifold co...
ISBN:
(纸本)9781665473309
The proceedings contain 122 papers. The topics discussed include: COSTI: a new classifier for sequences of temporal intervals;multi-instance multi-label learning based on parallel attention and local label manifold correlation;label distribution learning with data augmentation using generative adversarial networks;conformal transformation twin-hyperspheres for highly imbalanced data to binary classification;graph summarization as vertex classification task using graph neural networks vs. bloom filter;improving pairwise rank aggregation via querying for rank difference;safe multi-view co-training for semi-supervised regression;positive-unlabeled domain adaptation;semi-supervised regression with data partitioning and feature mapping;research on mini-batch affinity propagation clustering algorithm;on training and verifying robust autoencoders;DCSF: deep convolutional set functions for classification of asynchronous time series;conditional variational autoencoder with balanced pre-training for generative adversarial networks;few-shot edge classification in graph meta-learning;and adaptive sparse and monotonic attention for transformer-based automatic speech recognition.
The proceedings contain 89 papers. The topics discussed include: Embed2Detect: temporally clustered embedded words for event detection in social media;AMER: automatic behavior modeling and interaction exploration in r...
ISBN:
(纸本)9781665420990
The proceedings contain 89 papers. The topics discussed include: Embed2Detect: temporally clustered embedded words for event detection in social media;AMER: automatic behavior modeling and interaction exploration in recommender system;performance in the courtroom: automated processing and visualization of appeal court decisions in France;detection of novel social bots by ensembles of specialized classifiers;high-precision extraction of emerging concepts from scientific literature;and google dataset search by the numbers.
The proceedings contain 108 papers. The topics discussed include: improving neural networks using slice models for similar classes;embedding for anomaly detection on health insurance claims;AdvPL: adversarial personal...
ISBN:
(纸本)9781728182063
The proceedings contain 108 papers. The topics discussed include: improving neural networks using slice models for similar classes;embedding for anomaly detection on health insurance claims;AdvPL: adversarial personalized learning;vehicle relocation for ride-hailing;an adaptive utilization of convolutional matrix methods of neuron cell segmentation with an application interface to aid the understanding of how memory recall works;improving sentiment analysis in Arabic and English languages by using multi-layer perceptron model (MLP);weakly supervised person search;precision coupon targeting with dynamic customer triage;and ensemble of hierarchical temporal memory for anomaly detection.
The proceedings contain 125 papers. The topics discussed include: matrix factorization approach to behavioral mode analysis from acceleration data;on-line detection of continuous changes in stochastic processes;multi-...
ISBN:
(纸本)9781467382731
The proceedings contain 125 papers. The topics discussed include: matrix factorization approach to behavioral mode analysis from acceleration data;on-line detection of continuous changes in stochastic processes;multi-class learning using data driven ECOC with deep search and re-balancing;improved risk predictions via sparse imputation of patient conditions in electronic medical records;duration models for activity recognition and prediction in buildings using hidden Markov models;exploiting big data in time series forecasting: a cross-sectional approach;detecting human emotion via speech recognition by using speech spectrogram;an effective and economic bi-level approach to ranking and rating spam detection;multi-objective clustering ensemble for high-dimensional data based on strength Pareto evolutionary algorithm;a new consensus function based on dual-similarity measurements for clustering ensemble;and from one star to three stars: upgrading legacy open data using crowdsourcing.
暂无评论