Igor Lashkov

Igor Lashkov

Researcher at SPC RAS
PostDoc at University of Hawaii at Manoa

My research focuses on human-centered applications of machine learning, artificial neural networks, data analysis, recently applicable to the intelligent transportation domain.

Some projects I've worked on.

Drive Safely

Drive Safely Assistant for Android and JVM provides actionable information to a driver how to prevent a road accident. It recognizes driver’s drowsiness, distraction, belt presence, phone usage, eating, smoking, and camera sabotage.

2016–Present Java Kotlin C++ OpenCV TensorFlow

TFProfiler

Profile TensorFlow Lite model and measure its performance using FPS, model initialization time, inference time, and memory consumption on the smartphone. You can tweak model runs with different delegates (CPU, GPU, NNAPI, HEXAGON), XNNPACK option, number of threads.

2020-Present Kotlin Java TensorFlow

Kaggle competitions

Experience in Kaggle-based competitions – Gold medal in Image Matching Challenge 2022, RSNA-MICCAI Brain Tumor Radiogenomic Classification; Silver medal in Google Universal Image Embedding; Bronze medal in Happywhale - Whale and Dolphin Identification.

2021-Present Python Jupyter Notebook TensorFlow PyTorch

HyppoYD – Yawn classification

The trained neural model solves an image classification task that predicts whether the human's mouth is opened or closed.

2021-Present Python Jupyter Notebook TensorFlow