Kavosh Lab

Dr. Hadi Zare Faculty Member, Head of the Lab

PhD, Applied Mathematics, Amirkabir university of technoilogy, 2009

MSc, Amirkabir University of technology

BSc, Shiraz University

Research interests:

  • Machine Learning
  • Mathmatical Learning
  • Network Analysis
  • Statistical pattern Recognition
  • Statistical Graphical Model

About Kavosh Lab

Welcome to the Kavosh Laboratory at the faculty of New Sciences and Technologies located in University of Tehran. Kavosh is a research laboratory created in 2014, and is organized by Dr. Hadi Zare. At Kavosh, we work on:
Statistical and probabilistic approaches, Graphical models, unsupervised techniques, and learning frameworks to analyze and model the high-dimensional, relational, and network based data
Summarize the big dataset based on unsupervised approaches like Community Detection for network dataset and topic models for textual data
Applications of statistical learning to text, image and network
Systems and methods for large scale machine learning

Courses

Machine Learning and Pattern Recognition

M.Sc. Student

Description: Description: This course is about introducing the elements of learning, foundations and algorithms. Classification algorithms such as LDA, Bayes classifier, LogReg, DT and and unsupervised methods such as k-means, Hierarchical clustering methods, PCA and kernel methods are among the content of this course. This course is developed for the students of Networked System Engineering.

Qualitative Research Methods

M.Sc. Student

Description: Description: The aim of this course is to introduce the statistical and mathematical foundation of learning methods. The course starts with statistical learning theory, and then describe the algorithms based on these theoretical framework like Gaussian classifiers, Probabilistic LDA, SVM, and topic models

Mathematical Learning

M.Sc. Student

Description: summry

Probabilistic Graphical Model

M.Sc. Student

Description: Description: This course introduces the fundamentals of graphical models which includes the Representation, Learning, and Inference. The course covers the Bayesian Networks, Markov Networks, data representation based on graphical models, the learning approaches like ML, Bayesian and EM algorithm, and Inference techniques like VE, MP and BP approaches

People

Publications

A novel hybrid method for improving ambulance dispatching response time through a simulation study.

M.Sc. Student

Description: Zarkesh zade, Mahdi, Hadi Zare, Zainabolhoda Heshmati Rafsanjani, and Mehdi Teimouri. ''A novel hybrid method for improving ambulance dispatching response time through a simulation study.'' Simulation Modelling Practice and Theory 60, no. 1 (2015): 170-184.

Memory-enriched big bang–big crunch optimization algorithm for data clustering

M.Sc. Student

Description: Bijari, Kayvan, Hadi Zare, Hadi Veisi, and Hossein Bobarshad. ''Memory-enriched big bang–big crunch optimization algorithm for data clustering.'' Neural Computing & Applications 27, no. 8 (2016): 1-11.

Relevant based structure learning for feature selection

M.Sc. Student

Description: Zare, Hadi, and Mojtaba Niazi. ''Relevant based structure learning for feature selection.'' Engineering Applications of Artificial Intelligence 55, no. -- (2016): 93-102.

IEDC: An Integrated Approach for Overlapping and Non - overlapping Community Detection

M.Sc. Student

Description: Hajiabadi, Mahdi, Hadi Zare, and Hossein Bobarshad. ''IEDC: An Integrated Approach for Overlapping and Non - overlapping Community Detection.'' Knowledge-Based Systems 123, no. 1 (2017): 188-199.

A Data Mining Study on Combustion Dynamicsand NOx Emission of a Swirl Stabilized Combustor with Secondary Fuel Injection.

M.Sc. Student

Description: Riazi, Rouzbeh, Mohammad Asrardel, Maziar Shafaee Roshani, Shidvash Vakilipour, Hadi Zare, and Hadi Veisi. ''A Data Mining Study on Combustion Dynamicsand NOx Emission of a Swirl Stabilized Combustor with Secondary Fuel Injection.'' International Journal of Heavy Vehicle Systems 24, no. 3 (2017): 215-238.

A Random Projection Approach for Estimation of the Betweenness Centrality Measure

M.Sc. Student

Description: H. Zare, A. Mohammadpour, and P. Moradi, “A Random Projection Approach for Estimation of the Betweenness Centrality Measure,” Intell. Data Anal., vol. 17, no. 2, pp. 217–231, Mar.

Improved model-based clustering using evolutionary optimization,

M.Sc. Student

Description: E. Kebriaei, K. Bijari, and H. Zare, “Improved model-based clustering using evolutionary optimization,” in 2017 Artificial Intelligence and Robotics (IRANOPEN), 2017, pp. 182–187.

Overlapping Community Detection in Social Networks Based on Stochastic Simulation

M.Sc. Student

Description: H. Zare and M. Hajiabadi, “Overlapping Community Detection in Social Networks Based on Stochastic Simulation,” Journal of Computer & Robotics, vol. 9, no. 1, pp. 61–68, Jan. 2016.

client
client
client
client
client
client

Projects

Research Areas Goes Here