Paper Info
Title
Toward Flexible and Efficient Home Context Sensing: Capability Evaluation and Verification of Image-Based Cognitive APIs.
Abstract
Cognitive Application Program Interface (API) is an API of emerging artificial intelligence (AI)-based cloud services, which extracts various contextual information from non-numerical multimedia data including image and audio. Our interest is to apply image-based cognitive APIs to implement flexible and efficient context sensing services in a smart home. In the existing approach with machine learning by us, with the complexity of recognition object and the number of the defined contexts increases by users, it still requires directly manually labeling a moderate scale of data for training and continually try to calling multiple cognitive APIs for feature extraction. In this paper, we propose a novel method that uses a small scale of labeled data to evaluate the capability of cognitive APIs in advance, before training features of the APIs with machine learning, for the flexible and efficient home context sensing. In the proposed method, we exploit document similarity measures and the concepts (i.e., internal cohesion and external isolation) integrate into clustering results, to see how the capability of different cognitive APIs for recognizing each context. By selecting the cognitive APIs that relatively adapt to the defined contexts and data based on the evaluation results, we have achieved the flexible integration and efficient process of cognitive APIs for home context sensing.
Year
DOI
Venue
2020
10.3390/s20051442
SENSORS
Keywords
DocType
Volume
smart home,contexts,cognitive API,image,document similarity,internal cohesion,external isolation,clustering
Journal
20
Issue
ISSN
Citations 
5
1424-8220
0
PageRank 
References 
Authors
0.34
0
3
Name
Order
Citations
PageRank
Sinan Chen113.14
Sachio Saiki25524.46
Masahide Nakamura352672.51