Falcao A.X., Papa J.P. (eds.) Optimum-path forest: theory, algorithms, and applications

New York: Academic Press, 2022. — 244 p.Optimum-Path Forest: Theory, Algorithms, and Applications was first published in 2008 in its supervised and unsupervised versions with applications in medicine and image classification. Since then, it has expanded to a variety of other applications such as remote sensing, electrical and petroleum engineering, and biology. In recent years, multi-label and semi-supervised versions were also developed to handle video classification problems. The book presents the principles, algorithms, and applications of Optimum-Path Forest, giving the theory and state-of-the-art as well as insights into future directions.Biography of the editorsTheoretical background and related worksThe optimum-path forest framework
Theoretical background
Supervised learning
OPF using complete graph
OPF using k-nn graph
Semisupervised learning
Unsupervised learning
Applications
Supervised
Improvements in training
Improvements in classification
Variations in learning
Biological sciences
Biometrics
Electrical engineering
Geosciences and remote sensing
Image and video analysis
Materials engineering
Medicine
Network security
Feature selection
Petroleum exploration
Other applications
Voice recognition
Semisupervised
Unsupervised
Electrical engineering
Image and video processing
Medicine
Network security
Remote sensing images
Other applications
Conclusions and future trendsReal-time application of OPF-based classifier in Snort IDSIntrusion detection systems
Detection approaches in IDS
Anomaly detection techniques
Types of IDS
Open-source IDS
Snort
Machine learning
Learning methods
Algorithms
Optimum-path forest
Metrics for effectiveness analysis
Methodology
CICIDS data set
Data set balancing
ml_classifiers plugin
Network traffic flow management
Classification of network traffic flows
Plugin configuration
Experiments and results
The first stage of experiments
Naive Bayes
Decision tree
Random forests
Support vector machine
Optimum-path forest
AdaBoost
Comparison of classification techniques
The second stage of experiments
DoS slowloris
DoS SlowHTTPTest
DoS hulk
Port scan
SSH brute force
Final considerations
Future worksOptimum-path forest and active learning approaches for content-based medical image retrievalMethodology
Active learning strategy
Experiments
Results and discussionFunding and acknowledgmentsHybrid and modified OPFs for intrusion detection systems and large-scale problemsModified OPF-based IDS using unsupervised learning and social network concept
Hybrid IDS using unsupervised OPF based on MapReduce approach
Hybrid IDS using modified OPF and selected features
Modified OPF using Markov cluster process algorithm
Modified OPF based on coreset concept
Partitioning step
Sampling step
Enhancement of MOPF using k-medoids algorithmDetecting atherosclerotic plaque calcifications of the carotid artery through optimum-path forestTheoretical background
Computer-aided diagnosis of atherosclerotic lesions
Optimum-path forest
Optimum-path forest classifier
Probabilistic optimum-path forest
Optimum-path forest-based approach for anomaly detection
Fuzzy optimum-path forest
Optimum-path forest based on k-connectivity
Methodology
Data set
Features set
Metrics
Experimental setup
Experimental results
Classification
Statistical analysis
Computational burden
Conclusions and future worksLearning to weight similarity measures with Siamese networks: a case study on optimum-path forestTheoretical background
Optimum-path forest
Training step
Testing step
Siamese networks
Methodology
Proposed approach
Data sets
Experimental setup
Experimental results
BBC News
Caltech Silhouettes
MPEG-
SemeionAn iterative optimum-path forest framework for clusteringRelated work
The iterative optimum-path forest framework
Seed set selection
Clustering by optimum-path forest
Seed recomputation
Returning the forest with lowest total path-cost
Algorithm outline
Application to object delineation
Experimental results
Object delineation by iterative dynamic trees
Analysis of road networks
Experiments on synthetic data sets
Conclusions and future workFuture trends in optimum-path forest classification