Boaz Lerner

Associate Professor

Dept. of Industrial Engineering & Management

Ben-Gurion University

Beer-Sheva 84105

Israel

+972 8 6479 375 (Office)
+972 8 6472 958 (Fax)

boaz@bgu.ac.il

Boaz Lerner is an Associate Professor at the Department of Industrial Engineering & Management (IEM) of Ben-Gurion University (BGU), Israel. He is the head of the M.Sc. program in Data Science at IEM and in the steering committee of the BGU Data Science Research Center. His main areas of research lie in machine learning with applications to 'real-world' problems. Current research focuses on:

Development of machine learning algorithms
Structure learning for Bayesian networks and Bayesian network classifiers
Learning latent variable models
Application of machine learning to data analysis, especially in precision medicine and precision agriculture

Brief Biography

Publications

Software

Professional Activities

Machine Learning and Data Mining Lab

Panacea-ml – Streamlining clinical trials

A short pitch (in Hebrew)

From the media:

· (14 September, 2020) Ben-Gurion University launches Oazis, its academic accelerator

· (15 ספטמבר 2020) מרכז יזמות 360 משיק את המאיץ אואזיס לקידום טכנולוגיות חדשניות שמקורן באוניברסיטה

· The Jerusalem Post; BioWorld; The Times of Israel; CTECH; The Algemeiner; Med-Tech Innovation; mobihealthnews; AI THORITY; Israel Newsstand

Projects

· Artificial Intelligence in Health Care: Engaging ALS Patients (2020-2021)

· Identification of risk factors for Parkinson’s disease using machine-learning analysis of longitudinal multidimensional clinical data (2020-2023)

· Early diagnosis, risk factor identification, and better treatment of inflammatory bowel disease using machine-learning analysis of longitudinal multidimensional clinical data (2020-2021)

· Phenomics – Precision Agriculture, Israel Innovation Authority (2018-2020)

· A System for Computerized Analysis, Stratification, Prediction, and Monitoring of ALS Disease Progression, Israel Innovation Authority (2018-2019)

· Robotics in Rehabilitation, ABC Robotics Initiative (2018-2019)

· Metro 450 – Sampling optimization for X-ray metrology, funded by the Chief Scientist of the Ministry of Economy and Industry

· Learning and mining patterns using stochastic models, funded by the Ministry of Science and Technology

· Identification of factors that account for young drivers’ crash involvement and involvement prediction using machine learning, funded by the National Authority of Road Safety

· Identification of factors that account for young drivers’ crash involvement, involvement prediction, and evaluation of the impact of Or Yarok kit on the involvement using machine learning, funded by Ran Naor Foundation for the Advancement of Road Safety Research

· Others in: medical diagnosis (Parkinson, Alzheimer); genetic abnormality and pre-natal diagnosis (chromosome, FISH); radar target classification; prediction of road accident severity; invoice reading; detonator detection; ferromagnetic target detection; cycle-time predication; reticle inspection; failure early detection; foreign object debris (FOD) detection; electronic warfare

Students of my Machine Learning & Data Mining Lab

· Hila Avisar (Ph.D.) – Risk factor identification for Parkinson’s disease from longitudinal clinical data

· Stas Khoroshevsky (Ph.D.) – Image interpretation using transfer learning by a deep network (with Bar-Hillel)

· Amir Dolev (M.Sc.) – Missing data imputation in healthcare

· Matan Gilboa (M.Sc.) – Machine learning in diabetes

· Moraz Finegold (M.Sc.) – Concept drift in health

· Roy Wolf (M.Sc.) – Risk factor identification and early diagnosis of a disease

· Maya Tzemach (M.Sc.) – Machine learning in inflammatory bowel disease

· Gilad Erez (M.Sc.) – Concept drift detection for disease development analysis

· Chagit Friss (M.Sc.) – Analysis of the utilization of antibiotics in IBD

· Astar Mordechai (M.Sc.) – Early diagnosis and risk factor identification by concept drift detection

· Roy Plaut (M.Sc.), TBD

· Gil Biton (M.Sc.), TBD

· Tom Damari (M.Sc.), TBD

Past students

· Iddo Salton (2004) (M.Sc.)

Classification of imbalanced data using neural networks

· Yaniv Gurwicz (2004) (M.Sc.)

Classification using Bayesian multinets

· Ra'anan Yehezkel (2004) (M.Sc.)

Bayesian network structure learning using recursive autonomy identification

· Roy Malka (2005) (M.Sc.)

Bayesian network classifiers

· Boaz Vigdor (2005) (M.Sc.)

Pattern recognition using a probability-driven fuzzy ARTMAP classifier

· Lior Konis (2006) (M.Sc.)

Radar target classification using dynamic Bayesian networks

· Lev Koushnir (2007) (M.Sc.)

A unified methodology for image analysis and classification of dot and non-dot-like fluorescence in situ hybridization signals

· David Bechor (2007) (M.Sc.)

Studying and comparing initial starting points of the K-means clustering algorithm

· Yair Meidan (2008) (M.Sc.)

Identifying and quantifying factors affecting waiting time and its prediction in manufacturing fabs using machine learning (with G. Rabinowitz)

· Tal Alumot (2009) (M.Sc.)

On sensitivity to parameters of methods of Bayesian network structure learning, parameter estimation and combination of learning methods

· Roy Kelner (2010) (M.Sc.)

Learning Bayesian network classifiers by risk minimization

· Tali Alterman (2011) (M.Sc.)

Machine learning for explanation and prediction of accident severity: Learning strategies in imbalanced problems

· Noam Cohen (2011) (M.Sc.)

On the impact of missing data on machine learning algorithms and sensitivity reduction to missing data by dynamic allocation of neighbors (with A. Even)

· Naama Simchon (2011) (M.Sc.)

Selective constraint-based structure learning for Bayesian networks

· Elad Ben Akoune (2011) (M.Sc.)

A robust value difference metric for feature-oriented imputation (with A. Even)

· Rafi Bojmel (2011) (M.Sc.)

Automatic threshold selection for Bayesian network structure learning algorithms

· Maydan Wienreb (2011) (M.Sc.)

Analysis and Prediction of FAB's Work in Process Using Machine Learning: Trading Between Accuracy and Information in Classification Problem (with G. Rabinwitz)

· Michal Caspi (2011) (M.Sc)

Adaptive thresholding in learning the structure of a Bayesian network

· Hanna Belyavin (2012) (M.Sc.)

Learning the structure of a Bayesian network using multiple test corrections

· Idit Bernstein (2012) (M.Sc.)

Improving NBC using structure extension by ensemble selection and instance cloning

· Dan Halbersberg (2013) (M.Sc.)

Scoring a structure in learning a Bayesian network classifier

· Asaf Cohen (2013) (M.Sc.)

Exploiting interactions in learning a Bayesian network

· Noam Nelke (2014) (M.Sc.)

Trend-based accuracy estimation for machine learning

· Nuaman Asbeh (2014) (Ph.D.)

Learning latent variable models by pairwise cluster comparison

· Alon Amedi (2015) (M.Sc.)

A greedy branching approach for Bayesian network structure learning

· Liran Nahum (2015) (M.Sc.)

Concept-drift detection in Bayesian networks by parameter sequential monitoring

· Faina Khoroshevsky (2016) (M.SC.)

Mobility-pattern discovery and next-place prediction

· Jonathan Gordon (2016) (M.Sc.)

A machine-learning analysis of ALS

· Noa Ben-David (2017) (M.Sc.)

Bayesian network structure learning using edge probabilities and integer linear programming

· Eyal Ben-Zion (2017) (Ph.D.)

Analysis and prediction of human mobility patterns by learning dynamic models

· Oded Zinman (2018) (M.Sc.)

Identification of social function land use in urban areas

· Aviv Nahon (2018) (M.Sc.)

Algorithms for learning temporal models for understanding ALS

· Alon Shpigler (2018) (M.Sc.)

A generative model for regularization and analysis of deep neural networks activity (with Bar Hillel)

· Hila Avisar (2019) (M.Sc.)

Identifying relations between lipidome and the diagnosis of Parkinson’s disease and its severity using machine learning

· Shir Kashi (2019) (M.Sc.)

A machine-learning model for automatic detection of movement compensations in stroke patients (with Levy-Tzedek and Rokach)

· Yael Konforti (2020) (M.Sc.)

Probabilistic interpretation and visualization of deep neural network (with Bar Hillel)

· Dan Halbersberg (2021) (Ph.D.)

Learning temporal latent variable models

· Ben Hadad (2021) (M.Sc.)

Data-driven analysis of neurodegenerative diseases using machine-learning algorithms

· Shon Mendelson (2021) (M.Sc.)

Concept drift in machine learning – Detection and relearning

· Yaniv Malowany (2021) (M.Sc.)

Algorithm for learning latent variable models

· Dor Simoni (M.Sc.) (2022)

Risk factor and biomarker identification for ALS using statistical methods and machine learning

· Hanan Mann (M.Sc.) (2022)

Deep learning in digital healthcare

· Yoav Reisner (M.Sc.) (2022)

Early diagnosis and risk factor identification by concept drift detection with application to inflammatory bowel disease and amyotrophic lateral sclerosis

· Ofir Kedem (M.Sc.) (2022)

Amyotrophic lateral sclerosis prediction and risk factor identification using machine learning and a questionnaire

· Shoam Shabat (M.Sc.) (2022)

Algorithms for learning latent variable models

· Ori Ben-Yehuda (M.Sc.) (2022)

Early diagnosis of pulmonary embolism using machine learning

· Yotam Baron (M.Sc.) (2022)

Ensemble-based concept drift detection using Bayesian networks