ד"ר יהודית אפרשטיין

ד"ר יהודית אפרשטיין

ד"ר יהודית אפרשטיין היא מומחית בתחומי מערכות תבוניות ובינה מלאכותית. ב-15 שנים האחרונות הובילה ד"ר אפרשטיין עשרות רבות של מחקרים יישומיים במסגרת אקדמית, תוך שיתופי פעולה עם גופים שונים וכן כיועצת בתעשייה. ד"ר אפרשטיין מתמחה בבניית מערכות מורכבות המשלבות בדרך כלל מספר רב של רכיבים מבוססי AI שצריכים לעבוד ביחד תחת אילוצי המציאות. מחקריה עוסקים בפתרונות עבור יישומים במגוון רחב של תחומים: תחזוקה חזויה, רפואה, ניתוח תמונות אוויריות, ניתוח נתוני חיישנים ואודיו. ד"ר אפרשטיין זכתה במספר מענקי מחקר מגופים שונים.

ד"ר אפרשטיין הינה בעלת תואר שני בתורת המשחקים מהטכניון, דוקטורט בכלכלה מתמטית ממכון ויצמן, עשתה פוסט דוקטורט באוניברסיטת בר-אילן וכן פוסט-דוקטורט באוניברסיטת תל אביב.  ד"ר אפרשטיין הינה בעלת תעודת הוראה ממכון ויצמן ובוגרת תוכנית דו-שנתית בכלכלה ומנהל עסקים במכון ויצמן.

ב-2015 הקימה ד"ר אפרשטיין תכנית תואר שני במערכות תבוניות במכללת אפקה וכיהנה כראש התוכנית עד 2023. ב-2024 הקימה  מרכז מו"פ ליישומים חברתיים של בינה מלאכותית יוצרת (Generative AI). המרכז מאחד חוקרים ומומחים מדיסציפלינות שונות וכן סטודנטים מתואר ראשון ושני. במרכז עובדים על יישומים של GenAI לתחומים חברתיים כמו חינוך, בריאות, תחבורה חכמה, ערים חכמות, בטחון ובטיחות וכדומה.

2024, Ministry of Innovation, Science & Technology, Retrospective Analysis of the Correlation Between Glycated Hemoglobin Levels, GLP-1 Agonist Treatment, and Incidence of Common Brain Disorders , Principal Investigator with Dr. Zeev Nitzan

2024, Mafat, A system for Generative AI-assisted retrieval and prediction of energetic material properties, Principal Investigator

2024, Mafat, LLM-based multiagent systems for analysis of competing hypotheses, Principal Investigator

2023, Mafat, Incremental PTEENet for Inference Cost Optimization, Principal Investigator

2023, Afeka-Ariel Fund, Toward Breakthrough in the Field of Renewable Energy: AI-Based Decision Support System for Harnessing the Potential of Halide Perovskites, Principal Investigator, A joint project with Dr. Lena Yadgarov

2022, Mafat, Robust Deep Learning Model using Curriculum Learning, Principal Investigator

2021-2022, Mafat, Accuracy vs. Computation Cost in Distributed Deep Neural Networks Principal Investigator

2020, Mafat, Detecting structural faults in helicopters using artificial intelligence, Co-Researcher, A joint project with Makienko I., Gildish E. and Dr. Grebstein M.

2014-2017, Mafat, “Consumer brain computer interface devices for continuous authentication” Principal Investigator, A joint project with Prof. Anat Ratnovsky

2012-2013, Ben-Gurion University, Homeland Security Research Institute, “Web Text Mining for Monitoring Social Resilience”, Principal Investigator, A joint project with Prof. Yuval Cohen

2012-2013, Mekorot Water Technologies Entrepreneurship Center,“Outlier detection for water quality monitoring”, Principal Investigator with Dr. Dina Goren-Bar and Dr. Neta Rabin

2010-2011, Israel Chief Scientist ‘NeGeV” project, “Utility theory applied to social recommender systems”, Researcher, A Joint project with Dr. Dina Goren-Bar

“Hybrid Retrieval-and-Prediction Framework for Automatic Design of Energetic Molecules” "Optimal Decentralized Allocation of Heterogeneous Tasks to Heterogeneous Swarms (HT2HS): A novel Collaborative Filtering-based algorithm"

Rokach, L., Aperstein, Y., & Akselrod-Ballin, A. (2024). Deep active learning framework for chest-abdominal CT scans segmentation. Expert Systems with Applications, 125522

Berman, J., Pinhasov, B., Tshuva, M., Aperstein, Y (2024). syN-BEATS for robust pollutant forecasting in data-limited context. Environmental Monitoring and Assessment 196, 1002.

Pinhasov, B., Lapid, R., Ohayon, R., Sipper, M., & Aperstein, Y. (2024). XAI-Based Detection of Adversarial Attacks on Deepfake Detectors. TMLR.

Berman, J., Aperstein, Y., & Yosipof, A. (2024, September). Elucidation of Molecular Substructures from Nuclear Magnetic Resonance Spectra Using Gradient Boosting. In International Conference on Artificial Neural Networks (pp. 31-42). Cham: Springer Nature Switzerland.

Cohen, Y., & Aperstein, Y. (2024). Generative Shopfloor Layout Design: Challenges and Proposed Modelling Approach. IFAC-PapersOnLine, 58(19), 748-753.

Yalov-Handzel, S, Cohen,I and Aperstein, Y. (2024). Comparative Analysis of CNN Architectures and Loss Functions on Age Estimation of Archaeological Artifacts. Journal of Computer Applications in Archaeology, 7(1): 185-194.

Gildish, E., Grebshtein, M., Aperstein, Y., & Makienko, I. (2023). Vibration Signal Decomposition using Dilated CNN. Annual Conference of the PHM Society, 15(1). 

Halevy, B. Y., Aperstein, Y., & Di Castro, D. (2023). Offline Skill Graph (OSG): A Framework for Learning and Planning using Offline Reinforcement Learning Skills. arXiv preprint arXiv:2306.13630.

Gildish, E., Grebshtein, M., Aperstein, Y., & Makienko, I. (2023). Vibration-Based Estimation of Gearbox Operating Conditions: Machine Learning Approach. In 2023 International Conference on Control, Automation and Diagnosis (ICCAD)(pp. 1-6). IEEE.

Lahiany, A., & Aperstein, Y. (2022). PTEENet: Post-Trained Early-Exit Neural Networks Augmentation for Inference Cost Optimization. IEEE Access, 10, 69680-69687.

Gildish, E., Grebshtein, M., Aperstein, Y., Kushnirski, A., & Makienko, I. (2022, June). Helicopter bolt loosening monitoring using vibrations and machine learning. In PHM Society European Conference (Vol. 7, No. 1, pp. 146-155).

Shavit, D., Davidovits, M., Kushnirsky, A., & Aperstein, Y. (2022). Temporal causality-based feature selection for fault prediction in rotorcraft flight controls. IFAC-PapersOnLine, 55(2), 235-239.

Aperstein, Y., Cohen, L., Bendavid, I., Cohen, J., Grozovsky, E., Rotem, T., & Singer, P. (2019). Improved ICU mortality prediction based on SOFA scores and gastrointestinal parameters. PloS one, 14(9), e0222599.

Bloch, E., Rotem, T., Cohen, J., Singer, P., & Aperstein, Y. (2019). Machine learning models for analysis of vital signs dynamics: a case for sepsis onset prediction. Journal of healthcare engineering, 2019.

Cohen Y., Aperstein Y. (2015) Service Oriented Acquisition Models for Serving Products with Short Expiration Period”, Series: Lecture Notes in Business Information Processing, Vol. 201, Springer. Proceedings, Exploring Services Science, 6th International Conference, IESS.

Aperstein, Y., Maymon, Y., Cohen, Y., & Singer, G. (2013). Nationality and risk attitude: Testing differences and similarities of investors' behavior in selected financial markets. Global Finance Journal, 24(2), 114-118.

Aperstein, Y., & Kannai, Y. (2006). Demand properties of concavifiable preferences. Journal of Mathematical Economics, 43(1), 36-55.

Aperstein, Y., & Holzman, R. (2003). The core and the bargaining set in glove-market games. International journal of game theory, 32, 189-204.

Apartsin, A.Aperstein, Y., & Gurvich, V. (1998). A circular graph—counterexample to the Duchet kernel conjecture. Discrete Mathematics, 178(1-3), 229-231.

Koren, M., Yellin, D., & Aperstein, Y. (2026). Point Cloud Outlier Removal with Corruption-Stable Tokenization. Electronics, 15(22), 5272.

 

ביבליוגרפיה: 

1.      Apartsin A, Aperstein Y. Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Industrial-IoT Cyber-Physical Systems. IoT. 2026; 7(4):94.

2.      Sasson O, Apartsin A, Aperstein Y. Toward Controllable Learner Simulation for Teacher Education: Benchmarking Skill-Profile Control in LLM Answer Behavior. Education Sciences. 2026; 16(10):1752.

3.      Carter, D., Shagan Damti, R., Aperstein, Y., Ram, E., Hoffer, O. (2026) Artificial Intelligence–Assisted Transrectal Ultrasound for Rectal Cancer Invasion Depth Classification, Techniques in Coloproctology.

4.      Aperstein, Y. & Apartsin, A. (2026). A Controlled Synthetic Benchmark for Educational Aspect-Based Sentiment Analysis. Transactions on Machine Learning Research. Certifications: Reproducibility

5.      Aperstein, Y., Halifa, L., Bar, S., & Apartsin, A. (2026). LLM-guided headline rewriting for clickability enhancement without clickbait. Scientific Reports.

6.      Aperstein, Y., Tzahar, A., Gottlib, A., Verber, T., Damti, R. S., & Apartsin, A. (2026). Selective multipathology chest X-ray classification via rejection mechanisms. Scientific Reports.

7.      Atia T., Aperstein Y. and Apartsin A. (2026). SeaAlert: Robust Severity Classification and LLM-Based Information Extraction for Noisy Maritime Distress Communications, IEEE Access, doi: 10.1109/ACCESS.2026.3709004

8.      Aperstein, Y., Moran, E., & Apartsin, A. (2026). IRC-Bench: Recognizing Entities from Contextual Cues in First-Person Reminiscences. Machine Learning and Knowledge Extraction, 8(7), 186.

9.      Adamenko, I., Ben Aharon, O., Aperstein, Y., & Apartsin, A. (2026). Mapping License Plate Recoverability Under Extreme Viewing Angles for opportunistic urban sensing. AI, 7(7), 237.

10.   Aperstein, Y., & Apartsin, A. (2026). CalexNet: Soft Cascade-Aligned Training and Calibration for Lightweight Early-Exit Branches. Electronics, 15(10), 2149.

11.   Werthaim, M., Kimhi, M., Apartsin, A., Aperstein Y. (2026). A benchmark for evaluating diagnostic questioning efficiency of LLMs in patient conversations. Scientific Reports.

12.   Darhi, L., Dvorjetski, A., & Aperstein, Y. (2025). Data-Driven Estimation of Helicopter Engine Power Using Regular Flight Data: A Machine Learning Approach. Electronics, 15(1), 141.

13.   Aperstein, Y., Gottlib, A., Benita, G., & Apartsin, A. (2025). Explainable Semantic Text Relations: A Question-Answering Framework for Comparing Document Content. Information, 16(12), 1090.

14.   Milman, O., Yellin, D., & Aperstein, Y. (2025). Adapting SAM for Visible-Light Pupil Segmentation Baseline. Electronics, 14(9), 1850.

15.   Aperstein, Y., Cohen, Y., & Apartsin, A. (2025). Generative AI-Based Platform for Deliberate Teaching Practice: A Review and a Suggested Framework. Education Sciences, 15(4), 405.

 

 

ספרים:

1.     Apartsin, A., & Aperstein, Y. (2026). Building Conversational AI with LLMs and Agents: From the Mathematics of Attention to Production Agent Systems. https://llmbook.icsgen-ai.org/

2.     Apartsin, A., & Aperstein, Y. (2026). Building Vision AI: From Pixels to Generative Models. https://visionbook.icsgen-ai.org/

3.     Apartsin, A., & Aperstein, Y. (2026). Building Temporal AI: From Forecasting to Sequential Decision Making.  https://temporalbook.icsgen-ai.org/

4.     Apartsin, A., & Aperstein, Y. (2026). Building Scalable AI: From Big Data Algorithms to Distributed Intelligence. https://scalablebook.icsgen-ai.org/

5.     Apartsin, A., & Aperstein, Y. (2026). Building Discovery AI: From Vibe Coding to Autonomous Science. https://discoverybook.icsgen-ai.org/