DIDaizo Ikeda

Daizo Ikeda

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Daizo Ikeda has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Automatic Detection of Chewing and Swallowing

    by Akihiro Nakamura, Takato Saito, Daizo Ikeda, Ken Ohta, Hiroshi Mineno, 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.


  • Open Access

    Origin-Destination Trips Generated from Operational Data of a Mobile Network for Urban Transportation Planning

    by Ryuichi Imai, Daizo Ikeda, Hiroyasu Shingai, Tomohiro Nagata, Koichi Shigetaka

    Owing to recent advances in information communication technologies, trail data, i.e., movement logs of people on the road or on trains, can be acquired on a 24-h, 365-day basis, some of which have yielded real-world applications. Generating highly granular origin-destination trip data from the operational data of mobile networks would significantly advance the methodology for actualizing and broadening the field of applications in urban transportation planning. This paper proposes a method that estimates origin-destination trips on the basis of mobile network operational data, referred to as mobile spatial dynamics. Statistics are generated using a three-step process comprising anonymization, estimation, and disclosure limitation. Unlike other studies conducted thus far, this study uses large-scale person trip survey data to validate the reliability of estimated origin-destination trips between regions. Analysis of the use cases shows that the proposed method has the potential for mobile spatial dynamics to complement person trip surveys and road traffic censuses.


  • Open Access

    Flexible Resource Block Allocation to Multiple Slices for Radio Access Network Slicing Using Deep Reinforcement Learning

    by Yu Abiko, Takato Saito, Daizo Ikeda, Ken Ohta, Tadanori Mizuno, 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%.


  • Open Access

    Delay-Tolerance-Based Mobile Data Offloading Using Deep Reinforcement Learning

    by Daisuke Mochizuki, Yu Abiko, Takato Saito, Daizo Ikeda, 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.