著者
長田 拓也 生田目 崇
出版者
一般社団法人 経営情報学会
雑誌
経営情報学会 全国研究発表大会要旨集 2015年秋季全国研究発表大会
巻号頁・発行日
pp.204-207, 2015 (Released:2016-01-29)

購買の意思決定をサポートする仕組みとしてレコメンドシステムがある.しかし,既存のレコメンド手法は意思決定を単純化しており,現代の情報化社会により複雑化した消費者の意思決定を捉えきれていない.そこで,複雑化した消費者の意思決定を考慮したレコメンドを行う必要がある.一方,ここ数年,Deep Learningというアルゴリズムが画像認識や音声認識の分野で成果を挙げている.このDeep Learningを用いることで,複雑化した消費者の意思決定を考慮したレコメンドを行えることが期待できる.本研究では,Deep Learningを用いたレコメンドアルゴリズムを構築し,その性能を評価する.
著者
荒木 大地 長田 拓也 中内 靖 川口 孝泰
出版者
一般社団法人 日本機械学会
雑誌
日本機械学会論文集 (ISSN:21879761)
巻号頁・発行日
vol.83, no.856, pp.17-00210-17-00210, 2017 (Released:2017-12-25)
参考文献数
33

Falling from the bed is a common type of accident and places considerable burdens on patients and nurses. Structural and risk factors for the occurrence of falls have been identified, but fall prevention remains extremely difficult due to the patient’s physical, mental, and social factors and treatment environment. Most fall prevention measures involve ascertaining the risk of falls through the use of risk assessment score sheets and bed sensors, but there are few measures for active fall prediction. To develop a method for fall prediction, we applied area trajectory analysis and spectrum analysis to the characteristics of center-of-gravity variation in certain movements. We used these analysis methods and applied Support Vector Machine (SVM) that is one of the methods of machine learning. Experiments were performed with 5 healthy male and female. Each participant performed 3 movements, Reach out, Bed rail and Active, on a bed for 1 min each, during which time-series data on center-of-gravity variation were recorded. In the micro-average about unknown data, the Precision rate was 90.6%. To evaluate the movements respectively, Active were both higher in Precision rate and Recall rate. However in the Reach out has low Precision rate and that likely cause misinformation, in the Bed rail has low Recall rate and that likely cause overlook. The results of this study suggest the possibility of fall prediction through center-of-gravity analysis. In the next step about this study, need to explore the discriminate about static posture and improvement in accuracy by increasing the learning data.
著者
長田 拓也 鈴木 拓央 中内 靖
出版者
一般社団法人 日本機械学会
雑誌
日本機械学会論文集 (ISSN:21879761)
巻号頁・発行日
vol.83, no.853, pp.17-00118-17-00118, 2017 (Released:2017-09-25)
参考文献数
9

Since medicine treatment is one of the most major and effective cure methods, many patients take medicine every day. On the other hand, patients sometimes have serious accidents because some of them do not follow correct medicine dosing method (i.e. taking medicine without enough quantity of water). Though it may result serious accidents, in general, their doctors cannot notice the above-mentioned facts. In this paper, we propose a sensor-embedded intelligent cup that provides instructions for correct dosing and a medicine instruction support system using it. The proposed cup is the dual structure of a tumbler equipped with water level and acceleration sensors. The cup can detect if enough quantity of water is in it before a user takes medicine by using the water level sensor. We developed a calibration method for the water level sensor and implement it so that the quantity of water can be measured on any temperature. The cup can also detect if a user has taken medicine with the enough quantity of water from the cup by SVM (Support Vector Machine) using data of the acceleration sensor. Furthermore, the cup can also detect the quantity of water left in the cup using the acceleration sensor. The system will also provide the dosing history (i.e. when the dosing has conducted) to a user's caregivers (care giver and family in distant) through web interface. We conducted experiments and confirmed the positive effect of the proposed intelligent medicine cup.