Track 1: Advances in High Performance Computing

Algorithms: 

1. Algorithmic Techniques to Improve Energy and Power Efficiency 
2. Quantum and Bio-Inspired Algorithms
3. Resilient and Fault Tolerant Algorithms 
4. Parallel Algorithms for Numerical Linear Algebra
5. Concurrent Algorithms and Data Structures
6. Load Balancing, Scheduling and Resource Management
7. Large Scale Graph Analytics
8. Streaming Algorithms

Architectures:

1. Interconnection Networks and Architectures
2. Cache/Memory Architecture for High Performance Computing
3. High Performance/Scalable Storage Systems
4. Power-Efficient and Reconfigurable Architectures
5. Quantum and Bio-Inspired Architectures
6. Software Support and Advanced Micro-architecture Techniques
7. Resilient and Fault Tolerant Architectures

  Applications:

1. Big Data Computing and Applications
2. Cross-Cutting Methods such as Co-Design of Parallel Algorithms, Software, and Architectures
3. Emerging Applications such as Biotechnology, IoT, and Nanotechnology
4. Hardware Acceleration for Parallel Applications
5. Parallelism in Scientific Data Visualization and Visual Analytics
6. Scientific/Engineering/Industrial Applications and Workloads
7. Scalable Graph and other Irregular Applications 
8. Design of Simulation Applications and Peta- and Exascale Applications

Systems Software:

1. Big Data Analytics Systems and Software Architectures
2. Compiler Technologies for High-Performance Computing
3. Exascale Computing, Cloud Platforms, Data Center Architectures and Services
4. Parallel Languages, Programming Environments and Performance Assessment
5. Operating Systems for Scalable High Performance Computing
6. Hybrid Parallel Programming with GPUs and Accelerators
7. Dealing with Uncertainties, Resilient/Fault-Tolerant Systems

Track 2: Advances in Machine Learning

Model Selection:

1. Learning using Ensemble and Boosting Strategies
2. Active Machine Learning
3. Manifold Learning
4. Fuzzy Learning
5. Kernel Based Learning
6. Genetic Learning
7. Hybrid Models

Evolutionary Parameter Estimation:

1. Fuzzy Approaches to Parameter Estimation
2. Genetic Optimization
3. Bayesian Estimation Approaches
4. Boosting Approaches to Transfer Learning
5. Heterogeneous Information Networks
6. Recurrent Neural Networks
7. Influence Maximization
8. Co-evolution of time sequences

Graphs and Social Networks:

1. Social Group Evolution - Dynamic Modelling
2. Adaptive and Dynamic Shrinking
3. Pattern Summarization
4. Graph Embeddings
5. Graph Mining Methods
6. Structure Preserving Embedding
7. Non-Parametric
8. Models for Sparse Networks
9. Forecasting
10. Nested Multi-Instance Learning

Large Scale Machine Learning:

1. Large Scale Item Categorization
2. Machine Learning over the Cloud
3. Anomaly Detection in Streaming Heterogeneous Datasets
4. Signal Analysis
5. Learning Paradigms
6. Clustering, Classification and Regression Methods
7. Supervised, Semi-Supervised and Unsupervised Learning
8. Algebra, Calculus, Matrix and Tensor Methods in Context of Machine Learning
9. Reinforcement Learning
10. Optimization Methods
11. Parallel and Distributed Learning

Track 3: Advances in Deep Learning

1. Inference Dependencies on Multi-Layered Networks
2. Recurrent Neural Networks and its Applications
3. Tensor Learning
4. Higher Order Tensors
5. Graph Wavelets
6. Spectral Graph Theory
7. Self Organizing Networks
8. Multi-Scale Learning
9. Unsupervised Feature Learning
10. Recommender Systems
11. Automated Response
12. Conversational Recommender Systems
13. Collaborative Deep Learning
14. Trust Aware Collaborative Learning
15. Cold-Start Recommendation Systems
16. Multi-Contextual Behaviours of Users
17. Applications
18. Bioinformatics and Biomedical Informatics
19. Healthcare and Clinical Decision Support
20. Collaborative Filtering
21. Computer Vision
22. Human Activity Recognition
23. Information Retrieval
24. Cybersecurity
25. Natural Language Processing
26. Web Search
27. Evaluation of Learning Systems
28. Computational Learning Theory
29. Experimental Evaluation
30. Knowledge Refinement and Feedback Control
31. Scalability Analysis
32. Statistical Learning Theory
33. Computational Metrics

Track 4: Advances in Data Science

Foundations:

1. Mathematical, Probabilistic and Statistical Models and Theories
2. Machine Learning Theories, Models and Systems
3. Knowledge Discovery Theories, Models and Systems
4. Manifold and Metric Learning
5. Deep Learning and Deep Analytics
6. Scalable Analysis and Learning
7. Heterogeneous Data/Information Integration
8. Data Pre-Processing, Sampling and Reduction
9. Dimensionality Reduction
10. Feature Selection, Transformation and Construction
11. Large Scale Optimization
12. High Performance Computing for Data Analytics
13. Architecture, Management and Process for Data Science
14. Data Analytics, Machine Learning and Knowledge Discovery

Learning for Streaming Data

1. Learning for Structured and Relational Data
2. Latent Semantics and Insight Learning
3. Mining Multi-Source and Mixed-Source Information
4. Mixed-Type and Structure Data Analytics
5. Cross-Media Data Analytics
6. Big Data Visualization, Modeling and Analytics
7. Multimedia/Stream/Text/Visual Analytics
8. Relation, Coupling, Link and Graph Mining
9. Personalization Analytics and Learning
10. Web/Online/Social/Network Mining and Learning
11. Structure/Group/Community/Network Mining
12. Cloud Computing and Service Data Analysis

Management, Storage, Retrieval and Search

1. Cloud Architectures and Cloud Computing
2. Data Warehouses and Large-Scale Databases
3. Memory, Disk and Cloud-based Storage and Analytics
4. Distributed Computing and Parallel Processing
5. High Performance Computing and Processing
6. Information and Knowledge Retrieval, and Semantic Search
7. Web/Social/Databases Query and Search
8. Personalized Search and Recommendation
9. Human-Machine Interaction and Interfaces
10. Crowdsourcing and Collective Intelligence

Social Issues

1. Data Science Meets Social Science
2. Security, Trust and Risk in Big Data
3. Data Integrity, Matching and Sharing
4. Privacy and Protection Standards and Policies
5. Privacy Preserving Big Data Access/Analytics
6. Social Impact and Social Good

Track 5: Advances in Algorithms

Sequential, Parallel and Distributed Algorithms and Data Structures

1. Approximation and Randomized Algorithms
2. Graph Algorithms and Graph Drawing
3. On-Line and Streaming Algorithms
4. Analysis of Algorithms and Computational Complexity
5. Algorithm Engineering
6. Web Algorithms
7. Exact and Parameterized Computation
8. Algorithmic Game Theory
9. Computational Biology
10. Foundations of Communication Networks
11. Computational Geometry
12. Discrete Optimization

Track 6: Advances In Computing

Advances in Communications and Networking

1. Adhoc Networks
2. Network Security
3. Social Media and Networking
4. Wireless communications
5. Sensor Networks
6. Internet of things
7. Smart sensors and MEMS
8. RF and Microwave Communications

Circuits and Systems in Computing

1. Embedded Computing
2. Micro and Nano Electronics
3. Mixed-Signal SoC Applications
4. Distribution System Planning
5. Reliability for System Planning, Operation, Control and protection
6. Electrical System Modeling and Simulation
7. Transients, Propagation, Measurement and Modeling
8. Smart Grid
9. Advanced Control Systems
10. Intelligent Instrumentation
11. Process Control
12. System Analytics
13. Virtual Instrumentation
14. Micro Grid

Signal, Image and Multimedia Processing

1. Statistical Learning and Pattern Recognition
2. Advanced Signal Processing
3. Multimedia Signal Processing
4. Multi-Core Processing
5. Image and Video Processing
6. Audio and Speech Processing
7. Biomedical Signal Processing
8. Signal Processing of Applications of Power Electronics and Drives
9. Power Quality

Databases and Data Management

1. Clustering
2. Databases and Data Mining Applications
3. Database Tuning
4. Distributed Databases
5. Feature Selection and Feature Extraction
6. High Performance Data Mining Algorithms
7. Information Retrieval
8. Knowledge Discovery in Database
9. Knowledge Management
10. Query Optimization
11. Search Engine Optimization
12. Data Mining

Software Engineering

1. Verification and Validation
2. Software Construction
3. Testing Techniques
4. Process Models
5. Software Reuse
6. Software Repositories
7. Software Metrics
8. Software Project Management
9. Component/Aspect Based Software Engineering
10. Knowledge Based Software Engineering
11. Other Advance topics of Software Engineering