3 papers
cs.LG2019
Guided Layer-wise Learning for Deep Models using Side Information
Pavel Sulimov, Elena Sukmanova, Roman Chereshnev +1
Training of deep models for classification tasks is hindered by local minima problems and vanishing gradients, while unsupervised layer-wise pretraining does not exploit informatio…
cs.CY2018
RapidHARe: A computationally inexpensive method for real-time human activity recognition from wearable sensors
Roman Chereshnev, Attila Kertesz-Farkas
Recent human activity recognition (HAR) methods, based on on-body inertial sensors, have achieved increasing performance; however, this is at the expense of longer CPU calculations…
cs.CY2017
HuGaDB: Human Gait Database for Activity Recognition from Wearable Inertial Sensor Networks
Roman Chereshnev, Attila Kertesz-Farkas
This paper presents a human gait data collection for analysis and activity recognition consisting of continues recordings of combined activities, such as walking, running, taking s…