ABSTRACT
In recent years, malicious visit sales are increasing in Japan, targeting elderly people living alone and dementia patients. Since it is difficult for them to deal with problems with their own power, it is necessary for surrounding people to support damage deterrence. So, we aim to realize a watching system that anyone can use if there is only a smart speaker. In this study, we propose a method to detect door-to-door sales from conversation information of elderly people and visitors with the aim of realizing a system to prevent elderly consumers' troubles. In the evaluation experiment, we evaluate how accurately door-to-door sales can be detected out of the conversation dataset. In addition, we try to determine the risk degree by learning the door-to-door sales sample data given the risk label.
- Naoshi Matsuo, Hayakawa Shoji, Shouji Harada, Kazuya Takeda, and Kiwao Furihata, (2014). Development of the System for Stress Situation Detection based on the Voice Information. DICOMO2014, 131--137.Google Scholar
- Quoc Le, Tomas Mikolov, (2014). Distributed Representations of Sentences and Documents. Proceedings of The 31st International Conference on Machine Larning, 1188--1196.Google Scholar
- Aurelien Geron, (2017). Hands-On Machine Learning with Scikit-Learn & TensorFlow, O' Reilly, 978-1-491-96229-9, p 145--165Google Scholar
- Fujimura Itsuko, Shoju Chiba, Mieko Ohso, 2012, Lexical and Grammatical Features of Spoken and Written Japanese in Contrast: Exploring a lexical profiling approach to comparing spoken and Written corpora, Proceedings of the VII th GSCP International Conference. Speech and Corpora, 393--398.Google Scholar
- Tomas Mikolov et al., (2013). Distributed Representations of Words and Phrases and their Compositionality, Advances in neural information processing systems, pp 3111--3119.Google Scholar
- Nitesh V. Chawla, Kevin W. Bowyer, Lawrence O. Hall, and W. P. Kegelmeyer. (2002). SMOTE: Synthetic minority over-sampling technique, Journal of Artificial Intelligence Research, Vol.16, pp. 321--357Google ScholarCross Ref
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova, (2018). Bert: Pre-training of deep bidirectional transformers for language understanding, arXiv:1412.6980.Google Scholar
Index Terms
- Study on Watching System for Door-to-door Sales Detection and Risk Determination
Recommendations
Research on Hybrid Information Evaluation Type Watching Technology for the Improvement of QOL of the Elderly
AbstractThe increase in living alone and old households due to aging of the society has led to a decline in the quality of life (QOL) of elderly people. How to maintain and improve the quality of life for elderly people is a pressing issue of society. We ...
Knocking on elders' door: investigating the functional and emotional geography of their domestic space
CHI '09: Proceedings of the SIGCHI Conference on Human Factors in Computing SystemsThe domestic environment is more than a place where to live. It is a territory of meaning, a place where pleasure, affect and aesthetics are deeply interwoven with the functional and utilitarian dimensions. With the aging process, the home is ...
Low-cost and Device-free Activity Recognition System with Energy Harvesting PIR and Door Sensors
MOBIQUITOUS 2016: Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing Networking and ServicesProgress of IoT and ubiquitous computing technologies has strong anticipation to realize smart services in households such as efficient energy-saving appliance control and elderly monitoring. In order to put those applications into practice, high-...
Comments