O
Ole J. Mengshoel
Researcher at Carnegie Mellon University
Publications - 155
Citations - 3532
Ole J. Mengshoel is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Bayesian network & Activity recognition. The author has an hindex of 28, co-authored 144 publications receiving 3075 citations. Previous affiliations of Ole J. Mengshoel include SINTEF & Ames Research Center.
Papers
More filters
Proceedings ArticleDOI
Convolutional Neural Networks for human activity recognition using mobile sensors
TL;DR: An approach to automatically extract discriminative features for activity recognition based on Convolutional Neural Networks, which can capture local dependency and scale invariance of a signal as it has been shown in speech recognition and image recognition domains is proposed.
Proceedings ArticleDOI
Probabilistic Crowding: Deterministic Crowding with Probabilistic Replacement
TL;DR: Probabilistic crowding as discussed by the authors maintains subpopulations reliably, and analyzes and predicts how this maintenance takes place, and is a member of a family of tournament algorithms called integrated tournament algorithms, which also include deterministic crowding, restricted tournament selection, elitist recombination, parallel recombinative simulated annealing, the Metropolis algorithm, and simulated anealing.
Proceedings ArticleDOI
Understanding and improving recurrent networks for human activity recognition by continuous attention
TL;DR: Wang et al. as mentioned in this paper proposed two attention models for human activity recognition, namely, temporal attention and sensor attention, which adaptively focus on important signals and sensor modalities.
Journal ArticleDOI
FootprintID: Indoor Pedestrian Identification through Ambient Structural Vibration Sensing
Shijia Pan,Tong Yu,Mostafa Mirshekari,Jonathon Fagert,Amelie Bonde,Ole J. Mengshoel,Hae Young Noh,Pei Zhang +7 more
TL;DR: This work utilizes the physical insight on how individual step signal changes with walking speeds and introduces an iterative transductive learning algorithm (ITSVM) to achieve robust classification with limited labeled training data.
Patent
Contact center autopilot algorithms
TL;DR: In this article, a method and apparatus for dynamically reassigning agents among call types in a call distribution system having a plurality of agents assigned to plurality of call types is provided, which includes the steps of detecting a deficiency in agent responsibility assigned to a call type of the plurality ofcall types based upon a measured service parameter and corresponding target service parameter.