T
Teemu Pulkkinen
Researcher at Helsinki Institute for Information Technology
Publications - 11
Citations - 179
Teemu Pulkkinen is an academic researcher from Helsinki Institute for Information Technology. The author has contributed to research in topics: Interference (wave propagation) & Semi-supervised learning. The author has an hindex of 7, co-authored 11 publications receiving 162 citations. Previous affiliations of Teemu Pulkkinen include University of Helsinki.
Papers
More filters
Book ChapterDOI
Semi-supervised learning for WLAN positioning
TL;DR: A semi-supervised manifold learning technique for building accurate radio maps from partially labeled data, where only a small portion of the signal strength measurements need to be tagged with the corresponding coordinates, thereby dramatically reducing the need of location-tagged data.
Proceedings ArticleDOI
Influence of landmark-based navigation instructions on user attention in indoor smart spaces
TL;DR: A user study with $20$ participants in a large national supermarket investigated how the attention the user pays on her surroundings varies across two types of landmark-based instructions that vary in terms of their visual demand, indicating that an increase in the visual demand does not necessarily improve the participant's recall of their surrounding environment and that this increase can cause a decrease in navigation efficiency.
Book ChapterDOI
AWESOM: automatic discrete partitioning of indoor spaces for wifi fingerprinting
Teemu Pulkkinen,Petteri Nurmi +1 more
TL;DR: AWESOM (Activations Weighted by the Euclidean-distance using Self-Organizing Maps), a novel measure for automatically creating a discrete partitioning of the space where the WiFi positioning is being deployed, is proposed.
Proceedings ArticleDOI
Ma$$iv -- An Intelligent Mobile Grocery Assistant
Sourav Bhattacharya,Patrik Floréen,Andreas Forsblom,Samuli Hemminki,Petri Myllymäki,Petteri Nurmi,Teemu Pulkkinen,Antti Salovaara +7 more
TL;DR: A user study was conducted that explored customer preferences regarding features in a mobile grocery aid to guide the design of Ma$$iv€, an intelligent mobile grocery assistant that provides support for the customer during the entire shopping process.
Semi-supervised Convolutional Neural Networks for Identifying Wi-Fi Interference Sources
TL;DR: A novel structured extension of the pseudo-label technique is proposed to take advantage of temporal continuity in the data and show that already a few seconds of training data for each device is sufficient for highly accurate recognition.