TY - GEN
T1 - On-demand numerosity reduction for object learning
AU - Kalegele, Khamisi
AU - Sveholm, Johan
AU - Takahashi, Hideyuki
AU - Sasai, Kazuto
AU - Kitagata, Gen
AU - Kinoshita, Tetsuo
PY - 2011/12/1
Y1 - 2011/12/1
N2 - In Internet of Things, softwares shall enable their host objects (everyday-objects) to monitor other objects, take actions, and notify humans while using some form of reasoning. The ever changing nature of real life environment necessitates the need for these objects to be able to generalize various inputs inductively in order to play their roles more effectively. These objects shall learn from stored training examples using some generalization algorithm. In this paper, we investigate training sets requirements for object learning and propose a Stratified Ordered Selection (SOS) method as a means to scale down training sets. SOS uses a new instance ranking scheme called LO ranking. Everyday-objects use SOS to select training subsets based on their capacity (e.g. memory, CPU). LO ranking has been designed to broaden class representation, achieve significant reduction while offering same or near same analytical results and to facilitate faster on-demand subset selection and retrieval for resource constrained objects. We show how SOS outperforms other methods using well known machine learning datasets.
AB - In Internet of Things, softwares shall enable their host objects (everyday-objects) to monitor other objects, take actions, and notify humans while using some form of reasoning. The ever changing nature of real life environment necessitates the need for these objects to be able to generalize various inputs inductively in order to play their roles more effectively. These objects shall learn from stored training examples using some generalization algorithm. In this paper, we investigate training sets requirements for object learning and propose a Stratified Ordered Selection (SOS) method as a means to scale down training sets. SOS uses a new instance ranking scheme called LO ranking. Everyday-objects use SOS to select training subsets based on their capacity (e.g. memory, CPU). LO ranking has been designed to broaden class representation, achieve significant reduction while offering same or near same analytical results and to facilitate faster on-demand subset selection and retrieval for resource constrained objects. We show how SOS outperforms other methods using well known machine learning datasets.
KW - data reduction
KW - learning
KW - ranking
KW - sampling
UR - http://www.scopus.com/inward/record.url?scp=84855702549&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84855702549&partnerID=8YFLogxK
U2 - 10.1145/2079353.2079359
DO - 10.1145/2079353.2079359
M3 - Conference contribution
AN - SCOPUS:84855702549
SN - 9781450310437
T3 - Proceedings of the Workshop on Internet of Things and Service Platforms, IoTSP'11
BT - Proceedings of the Workshop on Internet of Things and Service Platforms, IoTSP'11
T2 - Workshop on Internet of Things and Service Platforms, IoTSP'11
Y2 - 6 December 2011 through 9 December 2011
ER -