Innovative Products and Processes for Knowledge Extraction
The PRECIS 305 Laboratory is dedicated to research and educational activities focused on knowledge extraction from data (data mining), structured data storage (data warehousing), and data processing. This laboratory supports research activities for its members and for graduate students under their guidance, especially in research disciplines and related academic courses such as ABD (Advanced Database Design) and MTI (Multimedia Technology and Internet). The lab is also utilized for doctoral research conducted by students under the supervision of Prof. Dr. Eng. Alexandru Boicea and Lect. Dr. Eng. Ciprian Octavian Truică.
Research Services Offered:
- Data Collection Support:
- Assistance in collecting data from multiple data sources.
- Data Preprocessing Support:
- Data cleaning
- Data integration
- Data transformation
- Data reduction
- Data discretization
- Data Mining Services:
- Frequent itemset mining in transaction datasets
- Regression analysis
- Classification (decision trees, rule-based classifiers, Bayesian classifiers, support vector machines, kNN, ensemble methods like Bagging, Boosting, Random Forest)
- Semi-supervised learning (using both labeled and unlabeled data for training)
- Clustering (centroid-based, distribution-based, density-based, hierarchical, fuzzy)
- Web mining applications (content, structure, usage mining)
- Data Storage and Utilization Applications:
- Support in structuring data warehouses and using them effectively.
- Development of applications using Oracle and Microsoft data storage and processing technologies.
- Design and application support for NoSQL systems: MongoDB, Cassandra, RIAK, and platforms like Hadoop, Spark, HBase.
Completed and Ongoing Research Projects:
International Collaborations:
- COST Action CA19102: Language In The Human-Machine Era (LITHME)
- COST Action CA19130: Fintech and Artificial Intelligence in Finance – Towards a Transparent Financial Industry (FinAI)
- COST Action CA18131: Statistical and Machine Learning Techniques in Human Microbiome Studies (ML4Microbiome)
- COST Action CA18209: European Network for Web-centred Linguistic Data Science (NexusLinguarum)
- COST Action CA18231: Multi-task, Multilingual, Multi-modal Language Generation (Multi3Gen)
- COST Action CA17137: A Network for Gravitational Waves, Geophysics, and Machine Learning (G2Net)
- COST Action IC1406: High-Performance Modelling and Simulation for Big Data Applications (cHiPSet)
- NETIO Project: Research, Innovation, and Development Ecosystem for ICT Products and Services in a Society Connected to the Internet of Things, POC Project, Contract No. 53/05.09.2016
- ERRIC Project: Empowering Romanian Research on Intelligent Information Technologies, FP7-REGPOT-2010-1/264207
- Erasmus-Mundus Master Programme: Data Mining & Knowledge Management, Contract No. 159648-EM-1-2009-1-FR-ERA MUNDUS-EMMC, 2009-2014
Hardware and Software Resources:
- Hardware:
- 16 Lenovo All-in-One stations with Windows OS
- 6 HP All-in-One stations with Linux Ubuntu OS
- Video projection system
- Video conferencing system (telepresence)
- Two servers dedicated to the laboratory
- White magnetic board
- Software:
- Databases: Oracle, SQL Server, MySQL
- Apache Hadoop cluster for data processing using MapReduce and Apache Spark
- NoSQL document-oriented database cluster: MongoDB
- NoSQL column-oriented database cluster: Apache Cassandra
- NoSQL key-value database cluster: RIAK
- Data warehouse cluster: HBase
Research Team Members:
- Prof. Dr. Eng. Florin Rădulescu – Co-responsible
- Prof. Dr. Eng. Alexandru Boicea – Co-responsible, PhD supervisor within the Doctoral School of Automatic Control and Computers
- Lect. Dr. Eng. Ciprian Octavian Truică – PhD supervisor within the Doctoral School of Automatic Control and Computers
- Lect. Dr. Eng. Dan Schrager
- Lect. Dr. Eng. Sorin Ciolofan
- Asst. PhD Candidate Eng. Daniel Popeanga
- Asst. PhD Candidate Eng. Izabela Alexandra Oprea