| Description |
1 online resource (563 p.) |
| Series |
Computing and Networks Ser |
|
Computing and Networks Ser
|
| Contents |
Intro -- Title -- Copyright -- Contents -- About the Editors -- Book preface -- 1 Toward graph data science -- 1.1 Introduction -- 1.2 Concept of graph -- 1.3 Graph travels on analysis -- 1.4 Graph plotting -- 1.5 Network graph of an ETFL ARK Funds -- 1.6 Twitch verse -- 1.6.1 Use of graph theory mechanisms for solving data science problems -- 1.7 Data visualization techniques -- 1.8 Present research ongoing -- 1.9 Next 60 years of data science -- 1.10 Scientific data analytics tested empirically -- 1.11 Conclusion -- 1.12 Future work -- References |
|
2 Data science: the Artificial Intelligence (AI) algorithms-inspired use cases -- 2.1 Introduction -- 2.2 The evolution and elevation of data science -- 2.3 Anomaly detection -- 2.3.1 Binary and multiclass classification -- 2.3.2 Personalization -- 2.4 Fraud detection -- 2.4.1 Challenges to fraud detection -- 2.4.2 Best practices for observability with fraud models -- 2.4.3 Important metrics -- 2.4.4 Performance degradation -- 2.4.5 Overcoming the drift problem -- 2.5 AI-enabled fake news detection -- 2.6 AI-inspired credit card fraud detection -- 2.7 AI-empowered forest fire prediction |
|
2.8 AI-induced breast cancer (BC) detection -- 2.8.1 Phase 0 -- preparation of data -- 2.8.2 Phase 1: data investigation -- 2.8.3 Phase 2: data categories -- 2.8.4 Phase 3: feature scaling -- 2.8.5 Phase 4: ML model selection -- 2.8.6 Phase 5 -- model evaluation -- 2.8.7 Phase 6 -- model optimization -- 2.9 Stopping cyber attacks by AI algorithms -- 2.10 ML for cyber security -- 2.11 Network protection -- 2.12 Endpoint detection and response (EDR) -- 2.13 Threat detection by EDR -- 2.14 Containment -- 2.15 Application security -- 2.16 User behavior -- 2.17 Process behavior |
|
2.18 The modern data architecture (MDA) -- 2.18.1 Smart applications -- 2.18.2 Smarter edge -- 2.18.3 Faster, more accurate, and easier management -- 2.19 The Kafka platform for data scientists -- 2.20 Kafka APIs -- 2.21 Conclusion -- References -- 3 Accelerating graph analytics -- 3.1 Introduction -- 3.2 Graph analytics methods to deliver smarter AI -- 3.2.1 Semi supervised learning with graph algorithms -- 3.3 Data preparation -- 3.4 Steps to get started with graph machine learning model -- 3.4.1 Structured query-oriented knowledge graphs -- 3.4.2 Query-based feature engineering |
|
3.4.3 Extending the use of graph algorithms -- 3.4.4 Approaches based on local similarity -- 3.4.5 Approaches that are based on global similarity -- 3.4.6 Approaches based on quasi-local similarity -- 3.5 Graph embeddings -- 3.5.1 Why graph embeddings are needed? -- 3.5.2 GNN and native learning -- 3.5.3 Based on the graph type -- 3.6 Applications -- 3.6.1 Classification of text -- 3.6.2 Translation by a neural computer -- 3.6.3 Image classification is a technique used in the field of image manipulation -- 3.6.4 Object detection is a feature that allows detecting of objects in the environment |
| Summary |
Graph analytics are being empowered through novel analytics techniques to explore and pinpoint beneficial relationships between different entities such as organizations, people and transactions. This edited book presents the various aspects and importance of graph data science, with contributions by authors from academia and industry |
| Notes |
Description based upon print version of record |
|
3.6.5 Semantic segmentation is the process of separating words based on their semantic meaning |
| Form |
Electronic book
|
| Author |
Kumar, Abhishek
|
|
García Díaz, Vicente
|
|
Muthuraman Sundar, Nachamai
|
| ISBN |
9781839534898 |
|
1839534893 |
|
