Institution profile

Reichman University

Academic institutioneurope · il
Official website
Research library105linked papers
Opportunities0open roles
Selected work

Representative Papers

CarSpeedNet: A Deep Neural Network-based Car Speed Estimation from Smartphone Accelerometer

Jan 15, 2024arXiv.org

Accurate vehicle speed estimation for mobile robots and autonomous ground vehicles using only low-cost triaxial accelerometers—such as those embedded in smartphones—remains challenging, especially without gyroscopes, wheel odometry, vehicle bus data, or external positioning signals. Method: This paper proposes an end-to-end deep neural network that operates exclusively on sliding-windowed temporal accelerometer measurements. It incorporates long-range temporal modeling to enhance robustness in dynamic driving scenarios and directly learns the nonlinear mapping from acceleration sequences to instantaneous speed. Contribution/Results: To our knowledge, this is the first work achieving sub-meter-per-second speed estimation (mean absolute error of 0.72 m/s) using smartphone-grade accelerometers alone, validated over 13 hours of real-world road testing across diverse conditions. The method delivers high-output frequency (10–100 Hz), significantly surpassing GPS (1 Hz), and runs entirely offline—requiring no vehicle interfaces or real-time external assistance.

2 citationsRead paper

Stochastic Discount Factors with Cross-Asset Spillovers

Feb 24, 2026

This study proposes a unified framework that explicitly models the intrinsic relationships among firm-level predictive signals, cross-asset information spillovers, and the stochastic discount factor (SDF). By jointly estimating predictive signals and spillover effects through Sharpe ratio maximization, the approach yields an economically interpretable SDF that not only identifies feature importance but also reveals the directional nature of predictive influences across assets. Innovatively integrating cross-asset information spillovers with firm characteristics into SDF estimation, the analysis uncovers that large-cap, low-turnover stocks act as net information transmitters, thereby enabling the construction of a well-structured information network. Out-of-sample tests demonstrate that the resulting SDF significantly outperforms both autoregressive and expected-return benchmark models across diverse portfolios and market regimes.

1 citationsRead paper

Learning to Score

Apr 19, 2025

This work addresses the problem of unsupervised continuous severity scoring under label scarcity or ambiguous label definitions—e.g., ill-defined clinical disease progression criteria. We propose a novel unsupervised scoring framework integrating representation learning, side-information modeling, and metric learning. For the first time, we formalize clinical symptoms and domain-specific constraints as semantic constraints or auxiliary signals, and design an end-to-end trainable semantic triplet architecture that eliminates reliance on explicit labels. Our method introduces a constraint-aware loss function that jointly optimizes structured side-information encoding and pairwise/triplet metric learning. Evaluated on standard benchmarks and real-world biomedical electronic health records, the approach significantly outperforms baselines: the learned severity scores achieve high concordance with clinical assessments (Pearson *r* > 0.82), while demonstrating strong interpretability and cross-institutional generalizability.

1 citationsRead paper
Recent publications

Latest Papers