Details

Related name

• Yao, Lina [Browse]
• Cai, Taotao [Browse]
• Pan, Shirui [Browse]
• Shen, Tao [Browse]
• Li, Xue [Browse]

Series

• Lecture Notes in Computer Science Ser. [More in this series]
• Lecture Notes in Computer Science Ser. ; v.13726 [More in this series]

Source of description

Description based on publisher supplied metadata and other sources.

Contents

• Intro
• Preface
• Organization
• Contents - Part II
• Contents - Part I
• Text Mining
• Towards Idea Mining: Problem-Solution Phrase Extraction from Text
• 1 Introduction
• 2 Related Work
• 2.1 Problem Formation
• 3 Methodology
• 3.1 Models for Extracting Problem-Solution Phrases
• 4 Experiment
• 4.1 Dataset UCCL1000
• 4.2 Dataset NIPS488
• 4.3 Dataset Summary
• 4.4 Text Preprocessing
• 4.5 Input Representations
• 4.6 Training and Evaluation
• 4.7 Result Analysis
• 5 Discussion
• 6 Future Work
• 7 Conclusion
• References
• Spam Email Categorization with NLP and Using Federated Deep Learning
• 3 Federated Phishing Filter (FPF)
• 3.1 Natural Language Processing
• 3.2 Deep Learning Model for Spam Categorization
• 3.3 Spam Detection and Categorization Model
• 3.4 Federated Learning
• 3.5 Federated Training Models
• 3.6 Federated Averaging (FA)
• 3.7 Federated Averaging Strategies
• 3.8 Equal Weighting (EWS)
• 3.9 Weighted Average (WAS)
• 3.10 Datasets
• 4 Empirical Evaluation
• 4.1 Comparison of EWS and AWS Averaging Strategies
• 4.2 Features Performance Comparison
• 5 Conclusion and Future Work
• SePass: Semantic Password Guessing Using k-nn Similarity Search in Word Embeddings*-12pt
• 3 Semantic Password Guessing
• 3.1 Generation of New Password Candidates
• 3.2 Sorting of the Password Candidates
• 4 Test Bed
• 4.1 Data Sets
• 4.2 Compared Methods
• 4.3 Experimental Set-Up and Evaluation Metric
• 5 Results and Discussion
• 5.1 Accuracy Results
• 5.2 Unseen Base Words
• 6 Conclusion
• DeMRC: Dynamically Enhanced Multi-hop Reading Comprehension Model for Low Data
• 3.1 Sentence Filtering Model
• 3.2 Answer Prediction Model.
• 3.3 Self-training Augmentation Based on External Data
• 4 Experiments
• 4.1 Data Set
• 4.2 Implementation Details
• 5 Results
• ESTD: Empathy Style Transformer with Discriminative Mechanism
• 2.1 NLP for Online Mental Health Assistance
• 2.2 Text Style Transfer
• 2.3 Discriminatory Mechanism
• 3.1 Empathic Expression Calculation
• 3.2 ESTD Framework
• 4 Experiments and Results
• 4.1 Datasets
• 4.2 Baselines
• 4.3 Evaluation Metrics
• 4.4 Ablation Study
• 4.5 Results
• 5 Conclusion
• Detection Method of User Behavior Transition on Computer
• 2.1 Image Classification and Clustering
• 2.2 Search and Operation Automation
• 2.3 User Behavior Analytics
• 3 Detection Method of User Behavior Transition
• 3.1 Overview
• 3.2 Feature Extraction
• 3.3 Time-Series Grouping Function
• 3.4 Time-Series Features Grouping Function
• 3.5 User Behavior Transition Detection Function
• 4.1 Our Dataset
• 4.2 Experiment Results
• 4.3 Discussion
• Image, Multimedia and Time Series Data Mining
• Ensemble Image Super-Resolution CNNs for Small Data and Diverse Compressive Models
• 1.1 Contribution
• 2 Foundational Work and Background
• 2.1 Sparse Representations
• 2.2 Miralon Areal Density Maps
• 3 Proposed Method
• 4 Experimental Results
• 4.1 Training Details
• 4.2 Reconstruction Quality on Testing Images
• 4.3 Application of Miralon Areal Density Maps
• Optimizing MobileNetV2 Architecture Using Split Input and Layer Replications for 3D Face Recognition Task
• 2 Backgrounds
• 2.1 Related Works
• 2.2 Convolutional Neural Network (CNN)
• 3.1 Data Gathering.
• 3.2 Preprocessing
• 3.3 Model Overview
• 3.4 Metrics
• 3.5 Training Configuration
• 3.6 Automatic Model Finding
• 4.1 Comparison Between 2D and 3D Face Recognition Models
• 4.2 Comparison Between RGBD and RGB+D Face Recognition Models
• 4.3 Comparison Between Baseline MobileNetV2 and RGB+D MobileNetV2 with Layer Replication
• 4.4 Comparison Between Our Baseline Model and EffiencientNet on CelebA Dataset
• 5 Conclusion and Future Work
• GANs for Automatic Generation of Data Plots
• 2 Generative Adversarial Networks
• 3 Related Work
• 4 Methodology
• An Explainable Approach to Semantic Link Mining in Multi-sourced Dynamic Data
• 2.1 Knowledge Graph Link Prediction
• 2.2 Semantic Data Integration
• 3 Preliminaries
• 4 Our Approach
• 4.1 Our Framework
• 4.2 KG-Based Integration
• 4.3 Rule-Based Link Prediction
• 5 An Application Case
• 6 Evaluation
• 6.1 Static Link Prediction
• 6.2 Dynamic Link Prediction
• Information Mining from Images of Pipeline Based on Knowledge Representation and Reasoning
• 2.1 Pipeline Defects Identification
• 2.2 Ontology for Knowledge Formalization
• 3 PDI Ontology Construction
• 3.1 Knowledge Resource
• 3.2 Ontology Development for PDI
• 3.3 Reasoning Rules for PDI
• 4 Case Study
• 4.1 Selected Pipeline Images with Common Defect Types
• 4.2 The Attribute Information of Pipeline Images
• 4.3 Mapping Rules for Images Instantiation in PDI Ontology
• 4.4 Knowledge Reasoning
• 4.5 Discussion
• Binary Gravitational Subspace Search for Outlier Detection in High Dimensional Data Streams
• 3 Problem Formulation.
• 4 Binary Gravitational Subspace Search for Outlier Detection in High Dimensional Data Streams
• 4.1 Subspace Search with Adapted Binary GSA
• 4.2 Solution Overview
• 5 Experimental Study and Results Analysis
• 5.1 Experimentation Setting
• 5.2 Results and Analysis
• 6 Conclusion and Future Works
• Classification, Clustering and Recommendation
• Signal Classification Using Smooth Coefficients of Multiple Wavelets to Achieve High Accuracy from Compressed Representation of Signal
• 2 Wavelets
• 2.1 DWT
• 2.2 MDWT
• 2.3 Energy Distribution
• 3 Proposed Technique
• 3.1 Advantages
• 3.2 Steps in the Proposed Technique: MWCSC
• 4.1 Classification Methods Used
• 4.2 Arrowhead Data
• 4.3 Mallat Data
• 4.4 Ford Data
• On Reducing the Bias of Random Forest
• 2 The Proposed Technique
• 3 Experimental Results
• 4 Conclusion
• A Collaborative Filtering Recommendation Method with Integrated User Profiles*-12pt
• 2 Proposed Method
• 2.1 User Profile Labeling System
• 2.2 User Profile Construction and Similarity Calculation
• 2.3 User Clustering
• 2.4 Collaborative Filtering
• 3 Performance Analysis
• 3.1 Experimental Method
• 3.2 Experimental Result
• A Quality Metric for K-Means Clustering Based on Centroid Locations
• 3 New Quality Metrics
• 3.1 Reduced 2R Metric
• 3.2 Implicit Assumptions in K-Means Algorithm
• 3.3 Covariant Metric (MC)
• 3.4 Quantifying Index Performance
• 4 Experiments on Synthetic Data
• 4.1 Data Generation
• 4.2 Analysis of Synthetic Data
• 4.3 Results and Discussion
• 5 Experiments on Real Data
• 5.1 Variable Selection
• 5.2 Data Sets
• 6 Comparison with Other Indexes
• 7 Limitations.
• 8 Conclusion
• Clustering Method for Touristic Photographic Spots Recommendation
• 3 Our Approach
• 3.1 Global Clustering
• 3.2 Local Clustering
• 3.3 Indexes and Validation
• 3.4 TPS Qualification
• 4.1 Data Processing
• 4.2 Global Clustering Comparison
• 4.3 Local Clustering Comparison
• 4.4 Spot Qualification
• Personalized Federated Learning with Robust Clustering Against Model Poisoning
• 2.1 PFL
• 2.2 Robust Clustering
• 2.3 Model Poisoning and Anomaly Detection
• 3.1 PFL
• 3.2 LOF
• 3.3 Proposed Method
• 4 Algorithm
• 5 Experiments
• 5.1 Experimental Settings
• 5.2 Experimental Study
• A Data-Driven Framework for Driving Style Classification
• 2 State of the Art
• 3 Problem Statement
• 4 Proposed Solution
• 4.1 Dataset Description
• 4.2 Pre-processing
• 4.3 Feature Engineering
• 4.4 Neural Architecture Search
• 5.1 Selection of Time-Window for Aggregation
• 5.2 Comparison of Different Models
• 6 Conclusion and Future Work
• Density Estimation in High-Dimensional Spaces: A Multivariate Histogram Approach
• 2 Background and Related Work
• 2.1 Basic Concepts
• 2.2 Approaches to Density Estimation
• 2.3 Applications in Research
• 2.4 Example: Density of the Old Faithful Dataset
• 3 A Multivariate Histogram-Based Approach
• 3.1 Define Hypergrid
• 3.2 Calculate Relative Frequencies
• 3.3 Calculate Hypervolumes and Density Estimates
• 3.4 Estimate Density for Datasets with Missing Values
• 4 Evaluation and Results
• 4.1 Computational Performance
• 4.2 Measuring Density with Categorical Variables
• 4.3 Measuring Density with Missing Values.
• 5 Conclusions.

Show 237 more Contents items

ISBN

9783031221378 ((electronic bk.))

Statement on language in description

Princeton University Library aims to describe library materials in a manner that is respectful to the individuals and communities who create, use, and are represented in the collections we manage. Read more...