Machine Learning and Knowledge Discovery in Databases: European Conference, Ecml Pkdd 2018, Dublin, Ireland, September 10-14, 2018, Proceedings, Part

ISBN-13: 9783030109967 / Angielski / Miękka / 2019 / 706 str.

Ulf Brefeld; Edward Curry; Elizabeth Daly

Spis treści

ADS Data Science Applications.- Neural Article Pair Modeling for Wikipedia Sub-article Matching.- LinNet: Probabilistic Lineup Evaluation Through Network Embedding.- Improving Emotion Detection with Sub-clip Boosting.- Machine Learning for Targeted Assimilation of Satellite Data.- From Empirical Analysis to Public Policy: Evaluating Housing Systems for Homeless Youth.- Discovering Groups of Signals in In-Vehicle Network Traces for Redundancy Detection and Functional Grouping.- ADS E-commerce.- SPEEDING up the Metabolism in E-commerce by Reinforcement Mechanism DESIGN.- Intent-aware Audience Targeting for Ride-hailing Service.- A Recurrent Neural Network Survival Model: Predicting Web User Return Time.- Implicit Linking of Food Entities in Social Media.- A Practical Deep Online Ranking System in E-commerce Recommendation.- ADS Engineering and Design.- ST-DenNetFus: A New Deep Learning Approach for Network Demand Prediction.- Automating Layout Synthesis with Constructive Preference Elicitation.- Configuration of Industrial Automation Solutions Using Multi-relational Recommender Systems.- Learning Cheap and Novel Flight Itineraries.- Towards Resource-Efficient Classifiers for Always-On Monitoring.- ADS Financial / Security.- Uncertainty Modelling in Deep Networks: Forecasting Short and Noisy Series.- Using Reinforcement Learning to Conceal Honeypot Functionality.- Flexible Inference for Cyberbully Incident Detection.- Solving the \false positives" problem in fraud prediction - Automated Data Science at an Industrial Scale.- Learning Tensor-based Representations from Brain-Computer Interface Data for Cybersecurity.- ADS Health.- Can We Assess Mental Health through Social Media and Smart Devices? Addressing Bias in Methodology and Evaluation.- AMIE: Automatic Monitoring of Indoor Exercises.- Rough Set Theory as a Data Mining Technique: A Case Study in Epidemiology and Cancer Incidence Prediction.- Selecting Influenza Mitigation Strategies Using Bayesian Bandits.- Hypotensive Episode Prediction in ICUs via Observation Window Splitting.- Equipment Health Indicator Learning using Deep Reinforcement Learning.- ADS Sensing/Positioning.- PBE: Driver Behavior Assessment Beyond Trajectory Profiling.- Accurate WiFi-based Indoor Positioning with Continuous Location Sampling.- Human Activity Recognition with Convolutional Neural Networks.- Urban sensing for anomalous event detection.- Combining Bayesian Inference and Clustering for Transport Mode Detection from Sparse and Noisy Geolocation Data.- CentroidNet: A Deep Neural Network for Joint Object Localization and Counting.- Deep Modular Multimodal Fusion on Multiple Sensors for Volcano Activity Recognition.- Nectar Track.- Matrix Completion under Interval Uncertainty.- A two-step approach for the prediction of mood levels based on diary data.- Best Practices to Train Deep Models on Imbalanced Datasets - A Case Study on Animal Detection in Aerial Imagery.- Deep Query Ranking for Question Answering over Knowledge Bases.- Machine Learning Approaches to Hybrid Music Recommender Systems.- Demo Track.- IDEA: An Interactive Dialogue Translation Demo System Using Furhat Robots.- RAPID: Real-time Analytics Platform for Interactive Data Mining.- COBRASTS: A new approach to Semi-Supervised Clustering of Time Series.- pysubgroup: Easy-to-use Subgroup Discovery in Python.- An Advert Creation System for Next-Gen Publicity.- VHI : Valve Health Identification for the Maintenance of Subsea Industrial Equipment.- Tiler: Software for Human-Guided Data Exploration.- ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio.- ClaRe: Classification and Regression Tool for Multivariate Time Series.- Industrial Memories: Exploring the Findings of Government Inquiries with Neural Word Embedding and Machine Learning.- Monitoring Emergency First Responders' Activities via Gradient Boosting and Inertial Sensor Data.- Visualizing Multi-Document Semantics via Open Domain Information Extraction.