Takato Saito

Takato Saito

Auto-generated profile, based on publicly available information

Takato Saito

NTT DOCOMO, Inc., Tokyo 100-6150, Japan

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 April 2020 in IEEE Access
Verified
Journal Article
Open access
YAYu Abiko
Yu Abiko
TSTakato Saito
Takato Saito
DIDaizo Ikeda
Daizo Ikeda
KOKen Ohta
Ken Ohta
TMTadanori Mizuno
Tadanori Mizuno
HMHiroshi Mineno
Hiroshi Mineno
In the fifth-generation of mobile communications, network slicing is used to provide an optimal network for various services as a slice. In this paper, we propose a radio access network (RAN) slicing method that flexibly allocates RAN resources using deep reinforcement learning (DRL). In RANs, the number of slices controlled by a base station fluctuates in terms of user ingress and egress from the base station coverage area and service switching on the respective sets of user equipment. Therefore, when resource allocation depends on the number of slices, resources cannot be allocated when the number of slices changes. We consider a method that makes optimal-resource allocation independent of the number of slices. Resource allocation is optimized using DRL, which learns the best action for a state through trial and error. To achieve independence from the number of slices, we show a design for a model that manages resources on a one-slice-by-one-agent basis using Ape-X, which is a DRL method. In Ape-X, because agents can be employed in parallel, models that learn various environments can be generated through trial and error of multiple environments. In addition, we design a model that satisfies the slicing requirements without over-allocating resources. Based on this design, it is possible to optimally allocate resources independently of the number of slices by changing the number of agents. In the evaluation, we test multiple scenarios and show that the mean satisfaction of the slice requirements is approximately 97%.

12 May 2021 in Sensors
Verified
Journal Article
Open access
PDF file
ANAkihiro Nakamura
Akihiro Nakamura
TSTakato Saito
Takato Saito
DIDaizo Ikeda
Daizo Ikeda
KOKen Ohta
Ken Ohta
HMHiroshi Mineno
Hiroshi Mineno
MNMasafumi Nishimura
Masafumi Nishimura
A series of eating behaviors, including chewing and swallowing, is considered to be crucial to the maintenance of good health. However, most such behaviors occur within the human body, and highly invasive methods such as X-rays and fiberscopes must be utilized to collect accurate behavioral data. A simpler method of measurement is needed in healthcare and medical fields; hence, the present study concerns the development of a method to automatically recognize a series of eating behaviors from the sounds produced during eating. The automatic detection of left chewing, right chewing, front biting, and swallowing was tested through the deployment of the hybrid CTC/attention model, which uses sound recorded through 2ch microphones under the ear and weak labeled data as training data to detect the balance of chewing and swallowing. N-gram based data augmentation was first performed using weak labeled data to generate many weak labeled eating sounds to augment the training data. The detection performance was improved through the use of the hybrid CTC/attention model, which can learn the context. In addition, the study confirmed a similar detection performance for open and closed foods.

8 April 2019 in Sensors
Verified
Journal Article
Open access
PDF file
DMDaisuke Mochizuki
Daisuke Mochizuki
YAYu Abiko
Yu Abiko
TSTakato Saito
Takato Saito
DIDaizo Ikeda
Daizo Ikeda
HMHiroshi Mineno
Hiroshi Mineno
The demand for mobile data communication has been increasing owing to the diversification of its purposes and the increase in the number of mobile devices accessing mobile networks. Users are experiencing a degradation in communication quality due to mobile network congestion. Therefore, improving the bandwidth utilization efficiency of cellular infrastructure is crucial. We previously proposed a mobile data offloading protocol (MDOP) for improving the bandwidth utilization efficiency. Although this method balances a load of evolved node B by taking into consideration the content delay tolerance, accurately balancing the load is challenging. In this paper, we apply deep reinforcement learning to MDOP to solve the temporal locality of a traffic. Moreover, we examine and evaluate the concrete processing while considering a delay tolerance. A comparison of the proposed method and bandwidth utilization efficiency of MDOP showed that the proposed method reduced the network traffic in excess of the control target value by 35% as compared with the MDOP. Furthermore, the proposed method improved the data transmission ratio by the delay tolerance range. Consequently, the proposed method improved the bandwidth utilization efficiency by learning how to provide the bandwidth to the user equipment when MDOP cannot be used to appropriately balance a load.