Text Mining -- Towards Idea Mining: Problem-Solution Phrases Extraction From Text -- Spam Email Categorization with NLP and Using Federated Deep Learning -- SePass: Semantic Password Guessing Using k-nn Similarity Search in Word Embeddings -- DeMRC: Dynamically Enhanced Multi-hop Reading Comprehension Model for Low Data -- ESTD: Empathy Style Transformer with Discriminative Mechanism -- Detection Method of User Behavior Transition on Computer -- Image, Multimedia and Time Series Data Mining -- Ensemble Image Super-resolution CNNs for Small Data and Diverse Compressive Models -- Optimizing MobileNetV2 Architecture Using Split Input and Layer Replications for 3D Face Recognition Task -- GANs for Automatic Generation of Data Plots -- An Explainable Approach to Semantic Link Mining in Multi-sourced Dynamic Data -- Information Mining from Images of Pipeline Based on Knowledge Representation and Reasoning -- Binary Gravitational Subspace Search for Outlier Detection in High Dimensional Data Streams -- Classification, Clustering and Recommendation -- Signal Classification using Smooth Coecients of Multiple Wavelets to Achieve High Accuracy from Compressed Representation of Signal -- On Reducing the Bias of Random Forest -- A collaborative filtering recommendation method integrating user profiles -- A Quality Metric for K-Means Clustering Based on Centroid Locations -- Clustering Method for Touristic Photographic Spots Recommendation -- Personalized Federated Learning with Robust Clustering against Model Poisoning -- A Data-Driven Framework for Driving Style Classification -- Density Estimation in High-Dimensional Spaces: a Multivariate Histogram Approach -- Multi-objective, Optimization, Augmentation, and Database -- Correcting Temporal Overlaps in Process Models Discovered from OLTP Databases -- WDA: A Domain-Aware Database Schema Analysis for improving OBDA-based Event Log Extractions -- A Cricket-based Selection Hyper-heuristic for Many-objective Optimization Problems -- Multi-Objective Optimization Based Feature Selection Using Correlation -- SAME: Sampling Attack in Multiplex Network Embedding -- Cycles Improve Conditional Generators: Synthesis and Augmentation for Data Mining -- Using the Strongest Adversarial Example to Alleviate Robust Overfitting -- Deduplication Over Heterogeneous Attribute Types (D-HAT) -- Others -- Probing Semantic Grounding in Language Models of Code with Representational Similarity Analysis -- Location Data Anonymization Retaining Data Mining Utilization -- A Distributed SAT-based Framework for Closed Frequent Itemset Mining -- Index Advisor via DQN with Invalid Action Mask in Tree-Structured Action Space -- A Hybrid Model for Demand Forecasting Based on the Combination of Statistical and Machine Learning Methods -- A Boosting Algorithm for Training from Only Unlabeled Data -- A Study of the Effectiveness of Correction Factors for Log Transforms in Ensemble Models.

The two-volume set LNAI 13725 and 13726 constitutes the proceedings of the 18th International Conference on Advanced Data Mining and Applications, ADMA 2022, which took place in Brisbane, Queensland, Australia, in November 2022. The 72 papers presented in the proceedings were carefully reviewed and selected from 198 submissions. The contributions were organized in topical sections as follows: Finance and Healthcare; Web and IoT Applications; On-device Application; Other Applications; Pattern Mining; Graph Mining; Text Mining; Image, Multimedia and Time Series Data Mining; Classification, Clustering and Recommendation; Multi-objective, Optimization, Augmentation, and Database; and Others.