Machine learning and data mining for emerging trend in cyber dynamics : theories and applications / / edited by Haruna Chiroma, 3 others

• Record Nr.: UNISA996464436503316
• Pubbl/distr/stampa: Cham, Switzerland : , : Springer, , [2021]; ©2021
• ISBN: 3-030-66288-8
• Descrizione fisica: 1 online resource (315 pages) : illustrations
• Disciplina: 354.81150006
• Soggetti: Industries
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Nota di bibliografia: Includes bibliographical references.
• Nota di contenuto: Intro -- Contents -- A Survey of Machine Learning for Network Fault Management -- 1 Introduction -- 2 Network Fault Management -- 3 Pattern Mining-Based Approaches -- 3.1 Episode and Association Rules Mining-Based Approaches -- 3.2 Sequential Pattern Mining-Based Approaches -- 3.3 Clustering-Based Approaches -- 3.4 Summary and Perspective -- 4 Machine Learning-Based Approaches -- 4.1 Artificial Neural Networks-Based Approaches -- 4.2 Decision Tree-Based Approaches -- 4.3 Bayesian Networks-Based Approaches -- 4.4 Support-Vector Machine-Based Approaches -- 4.5 Dependency Graph-Based Approaches -- 4.6 Other Approaches -- 4.7 Summary and Perspective -- 5 Conclusion -- References -- Deep Bidirectional Gated Recurrent Unit for Botnet Detection in Smart Homes -- 1 Introduction -- 2 Deep BGRU Method for Botnet Detection in IoT Networks -- 2.1 Bidirectional Gated Recurrent Unit -- 2.2 The Proposed Method for Selection of Optimal BGRU Hyperparameters -- 2.3 Deep BGRU Classifier for IoT Botnet Detection -- 3 Results and Discussion -- 3.1 Influence of Activation Functions on Classification Performance -- 3.2 Influence of the Number of Epochs on Classification Performance -- 3.3 Influence of the Number of Hidden Layers on Classification Performance -- 3.4 Influence of Hidden Units on Classification Performance -- 3.5 Influence of Batch Size on Classification Performance -- 3.6 Influence of Optimizers on Classification ; Performance -- 3.7 Performance of Deep BGRU-Based Multi-class Classifier -- 4 Conclusion -- References -- Big Data Clustering Techniques: Recent Advances and Survey -- 1 Introduction -- 2 Clustering Techniques -- 2.1 Partitioning Methods -- 2.2 Hierarchical Clustering Methods -- 2.3 Density-Based Methods -- 2.4 Grid-Based Algorithms -- 2.5 Model-Based Methods -- 3 Big Data Clustering Approaches -- 3.1 Data Reduction-Based Methods.; 3.2 Centre-Based Reduction Methods -- 3.3 Parallel Techniques -- 4 Big Data Clustering Applications -- 4.1 Healthcare -- 4.2 Internet of Things (IoT) -- 4.3 Anomaly Detection -- 4.4 Social Media -- 5 Discussion -- 6 Challenges and Future Research Work -- 7 Conclusion -- References -- A Survey of Network Intrusion Detection Using Machine Learning Techniques -- 1 Introduction -- 2 Machine Learning -- 2.1 Supervised Learning -- 2.2 Un-Supervised Learning -- 2.3 Semi-supervised Learning -- 2.4 Reinforcement Learning -- 2.5 Ensemble Learning -- 2.6 Feature Selection -- 3 Machine Learning Based Intrusion Detection System -- 3.1 Intrusion Detection System (IDS) -- 4 Hybrid Intrusion Detection Systems -- 5 Evaluations of Intrusion Detection System -- 5.1 KDD Cup-'99 Dataset -- 5.2 NSL-KDD Dataset -- 5.3 Kyoto 2006 + Dataset -- 5.4 Performance Metrics -- 6 Research Opportunities -- 7 Conclusion -- References -- Indexing in Big Data Mining and Analytics -- 1 Introduction -- 1.1 Objective of the Chapter -- 1.2 Taxonomy of the Chapter -- 2 Index and Indexing -- 2.1 Index Architecture and Indexing Types -- 2.2 Bitmap Index -- 2.3 Dense Index -- 2.4 Sparse Index -- 3 Online Indexes -- 3.1 Online Indexing -- 3.2 Database Cracking -- 3.3 Adaptive Merge -- 3.4 Big Data Analytics Platforms -- 4 Inherent Indexes in MapReduce -- 4.1 Per Document Indexing -- 4.2 Per-Posting List Indexing -- 5 User-Defined Indexing in MapReduce -- 6 Conclusion -- References -- Two-Steps Wrapper-Based Feature Selection in Classification: A Comparison Between Continuous and Binary Variants of Cuckoo Optimisation Algorithm -- 1 Introduction -- 2 Background -- 2.1 Cuckoo Optimisation Algorithm -- 2.2 Binary Cuckoo Optimisation Algorithm -- 2.3 Related Works -- 3 Proposed Wrapper-Based Feature Selection Approaches -- 3.1 BCOA and COA for Feature Selection.; 3.2 A Combined Fitness Function for BCOA and COA Feature Selection -- 4 Experimental Design -- 4.1 Experimental Datasets -- 4.2 Experimental Parameter Settings -- 4.3 Benchmark Approaches -- 5 Results and Discussions -- 5.1 Results of the Proposed BCOA-FS and COA-FS -- 5.2 Results of the Proposed BCOA-2S and COA-2S -- 5.3 Comparison Between Proposed Methods and Classical Methods -- 5.4 Comparison Between Proposed Methods and Other Existing Methods -- 5.5 Comparisons Between BCOA and COA -- 5.6 Further Discussions -- 6 Conclusions and Future Work -- References -- Malicious Uniform Resource Locator Detection Using Wolf Optimization Algorithm and Random Forest Classifier -- 1 Introduction -- 2 Related Works -- 3 Methodology -- 3.1 Method of Data Collection and Preparation -- 3.2 Feature Subset Selection -- 3.3 Meta-Heuristics Algorithms -- 3.4 Classification -- 3.5 Cross-Validation -- 3.6 Evaluation Metric -- 4 Results and Discussion -- 4.1 Modelling and Interpretation -- 4.2 Models Comparison Based on SVM as a Classifier -- 4.3 Models Comparison Based on RF as a Classifier -- 4.4 Comparison with Existing Models -- 5 Conclusion -- References -- Improved Cloud-Based N-Primes Model for Symmetric-Based Fully Homomorphic Encryption Using Residue Number System -- 1 Introduction -- 2 Related Works -- 3 Research Method -- 3.1 Homomorphic Encryption -- 3.2 N-Primes Model -- 3.3 Residue Number System -- 3.4 Proposed ; RNS-Based N-Primes Model for Symmetric FHE -- 4 Results and Discussion -- 5 Conclusion -- Appendix A: Ciphertext -- References -- Big Data Analytics: Partitioned B+-Tree-Based Indexing in MapReduce -- 1 Introduction -- 1.1 Objective of the Chapter -- 2 Literature Review -- 2.1 Inverted Index in MapReduce -- 2.2 User-Defined Indexing in MapReduce -- 3 Methodology -- 3.1 Partitioned B+-Tree -- 3.2 InputSplit as Component of Choice in the HDFS.; 4 Experimental Results and Discussion -- 4.1 The Dataset -- 4.2 Index Building Using the Datasets -- 4.3 Test Queries -- 4.4 The Experiment and Its Setup -- 4.5 Index Creation Performance Evaluation -- 5 Results and Discussions -- 6 Conclusion -- References -- Internet of Vehicle for Two-Vehicle Look-Ahead Convoy System Using State Feedback Control -- 1 Introduction -- 2 System Architecture -- 2.1 IoV Components -- 2.2 IoV Architecture for Two-Vehicle Look-Ahead Convoy -- 2.3 Platform Used for Implementation of the Model -- 3 Modeling of the Two Look-Ahead Vehicle Convoy Strategy -- 4 Vehicle Dynamic -- 4.1 SFC Design Using Pole-Placement Approach -- 4.2 Design Procedure of the SFC via Pole Placement Technique -- 4.3 Controllability System Test -- 5 Result and Discussion -- 6 Conclusion and Future Work -- References -- Vehicle Following Control with Improved Information Flow Using Two-Vehicle-Look-Ahead-Plus-Rear-Vehicle Topology -- 1 Introduction -- 2 Single-Vehicle External Dynamics -- 2.1 Aerodynamic Drag -- 2.2 Viscous Friction Drag -- 2.3 Rolling Resistance Force -- 2.4 Simplified Vehicle Dynamics -- 3 Following Vehicle Convoy Dynamics -- 4 Turning of Gains and Simulation -- 5 Results and Discussion -- 5.1 Comparison of the One-Vehicle Look-Ahead and Two-Vehicle Look-Ahead Against the Proposed Topology -- 6 Conclusion and Further Work -- References -- Extended Risk-Based Context-Aware Model for Dynamic Access Control in Bring Your Own Device Strategy -- 1 Introduction -- 2 Background -- 2.1 Dynamic Access Control in BYOD Strategy -- 2.2 Bayesian Network -- 3 Related Work -- 3.1 Risk Evaluation Model -- 3.2 Context-Aware Access Control Model -- 3.3 Finding from Related Work -- 4 Proposed ExtSRAM Model -- 4.1 Contextual Risk Factors -- 4.2 Enterprise Environment -- 5 ExtSRAM Process Flow -- 5.1 Assumptions on ExtSRAM Model.; 5.2 ExtSRAM Methodology -- 6 Theoretical Validation of the Model -- 6.1 Soundness of ExtSRAM -- 6.2 Completeness of ExtSRAM -- 7 Future Research Directions -- 8 Conclusion -- References.

Information Processing in Cells and Tissues [[electronic resource] ] : 9th International Conference, IPCAT 2012, Cambridge, UK, March 31 -- April 2, 2012, Proceedings / / edited by Michael A. Lones, Stephen L. Smith, Sarah Teichmann, Felix Naef, Jonathan Oliver, Martin Albrecht Trefzer

• Record Nr.: UNISA996466267303316
• Pubbl/distr/stampa: Berlin, Heidelberg : , : Springer Berlin Heidelberg : , : Imprint : Springer, , 2012
• ISBN: 3-642-28792-1
• Edizione: [1st ed. 2012.]
• Descrizione fisica: 1 online resource (XII, 278 p. 120 illus.)
• Collana: Theoretical Computer Science and General Issues, , 2512-2029 ; ; 7223
• Disciplina: 616.02/77
• Soggetti: Bioinformatics; Computer science; Computer science—Mathematics; Pattern recognition systems; Computational and Systems Biology; Theory of Computation; Mathematical Applications in Computer Science; Automated Pattern Recognition
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Note generali: International conference proceedings.
• Nota di bibliografia: Includes bibliographical references and author index.
• Sommario/riassunto: This book constitutes the refereed proceedings of the 9th International Conference on Information in Cells and Tissues, IPCAT 2012, held in Cambridge, UK, in March/April 2012. The 13 revised full papers presented together with 26 extended abstracts were carefully reviewed and selected from numerous submissions. The papers cover a wide range of topics in disciplines related to genetic and epigenetic networks, transcriptomics and gene regulation, signalling pathways and responses, protein structure and metabolic networks, patterning and rhythm generation, neural modelling and neural networks, biomedical modelling and signal processing, information processing and representation, and algorithmic approaches in computational biology.