Kohei Shiomoto
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Kohei Shiomoto has a total of 180 co-authors. Here are the top co-authors by number of shared publications:
- Masayuki Murata
Osaka University
23 shared publications Takashi Miyamura
NTT Network Service Systems Laboratories, NTT Corporation, Japan
20 shared publicationsN. Yamanaka
19 shared publicationsEiji Oki
Dept. of Information and Communication Engineering, The University of Electro-Communications, Tokyo, Japan
16 shared publicationsIchiro Inoue
NTT Network Service Systems Laboratories, NTT Corporation, 3-9-11 Midori-cho Musashino-shi, Tokyo, 180-8585 Japan
16 shared publicationsE. Oki
Dept. of Information and Communication Engineering, University of Electro-Communications, Tokyo, Japan
12 shared publications
Latest Publications
- Open Access
- 25 May 2024
- Published by Taylor & Francis in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
- Vol. 12 (1)
Evaluation of effectiveness of pre-training method in chest X-ray imaging using vision transformer
- 25 May 2024
- Published by Taylor & Francis in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
- Vol. 12 (1)
Open AccessEvaluation of effectiveness of pre-training method in chest X-ray imaging using vision transformer
- 14 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 25, 1-5
Performance Change with the Ratio of Training Data A Case Study on the Binary Classification of COVID-19 Chest X-Ray by using Convolutional Neural Networks
One of the features of artificial intelligence/machine learning-based medical devices resides in their ability to learn from real-world data. The performance may change after the market introduction. There are many aspects that contribute to the performance change relative to the real-world training data, such as the number and disease ratio. In actual clinical practice, the ratio of obtained training data varies from country to country, from region to region within each country, and from one hospital to another. Therefore, establishing a pre-change control plan at a premarket stage is essential to achieve safety and effectiveness through total product life cycles. In our previous work, we evaluated the performance change on the binary classification of coronavirus disease 2019 (COVID-19) and normal with the number of training data using two publicly large available chest X-ray (CXR) images. However, these results were obtained with the same ratio in the training data. Thus, this study aims to evaluate the performance change with a non-uniform ratio of COVID-19 CXR images based on the results of previous studies. We used the AlexNet and ResNet34 with and without the fine-tuning method as convolutional neural network (CNN) models. A total of 500, 1000, and 2000 CXR images were selected as training and validation datasets. These datasets represent states in which the performance change improves rapidly and those in which an equilibrium state is reached. Each dataset was divided into seven datasets, and the area under the curve was employed to evaluate the performance change for each dataset through independent 1000 test datasets with the same ratio. Our result shows that all performances indicate that there is an upward convex relationship to the ratio of COVID-19 CXR images, and the vertex is where the ratio is the same. This trend was remarkable for the rapidly improving state and the CNNs without a fine-tuning method. Moreover, the visual explanations technique called Grad-CAM for interpreting classification results of CNN models support these results.
- 14 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 25, 1-5
Performance Change with the Ratio of Training Data A Case Study on the Binary Classification of COVID-19 Chest X-Ray by using Convolutional Neural Networks
One of the features of artificial intelligence/machine learning-based medical devices resides in their ability to learn from real-world data. The performance may change after the market introduction. There are many aspects that contribute to the performance change relative to the real-world training data, such as the number and disease ratio. In actual clinical practice, the ratio of obtained training data varies from country to country, from region to region within each country, and from one hospital to another. Therefore, establishing a pre-change control plan at a premarket stage is essential to achieve safety and effectiveness through total product life cycles. In our previous work, we evaluated the performance change on the binary classification of coronavirus disease 2019 (COVID-19) and normal with the number of training data using two publicly large available chest X-ray (CXR) images. However, these results were obtained with the same ratio in the training data. Thus, this study aims to evaluate the performance change with a non-uniform ratio of COVID-19 CXR images based on the results of previous studies. We used the AlexNet and ResNet34 with and without the fine-tuning method as convolutional neural network (CNN) models. A total of 500, 1000, and 2000 CXR images were selected as training and validation datasets. These datasets represent states in which the performance change improves rapidly and those in which an equilibrium state is reached. Each dataset was divided into seven datasets, and the area under the curve was employed to evaluate the performance change for each dataset through independent 1000 test datasets with the same ratio. Our result shows that all performances indicate that there is an upward convex relationship to the ratio of COVID-19 CXR images, and the vertex is where the ratio is the same. This trend was remarkable for the rapidly improving state and the CNNs without a fine-tuning method. Moreover, the visual explanations technique called Grad-CAM for interpreting classification results of CNN models support these results.
- 14 January 2023
- Published by Springer Nature in Annals of Telecommunications
- Vol. 78 (1-2) , 53-70
A novel network traffic prediction method based on a Bayesian network model for establishing the relationship between traffic and population
- 14 January 2023
- Published by Springer Nature in Annals of Telecommunications
- Vol. 78 (1-2) , 53-70
A novel network traffic prediction method based on a Bayesian network model for establishing the relationship between traffic and population
- Open Access
- 7 October 2022
- Published by Springer Nature in Journal of Network and Systems Management
- Vol. 31 (1) , 1-22
Network Intrusion Detection System Based on an Adversarial Auto-Encoder with Few Labeled Training Samples
Network intrusion detection systems (NIDS) are critical to defending network systems from cyber attacks. Recently, machine learning has been applied to enhance NIDS capability. To train a supervised machine-learning model, a large number of labeled training samples are required to achieve practical performance. However, labeling data samples is a costly task. Additionally, obtaining anomaly data samples is difficult because trends in network traffic that are subject to NIDS change daily, and new attacks continue to be generated. To address this issue, we propose a semi-supervised machine-learning-based NIDS that reduces the required number of labeled training samples by applying an adversarial auto-encoder (AAE) technique. We evaluated the proposed method through a series of experiments and confirmed that the proposed AAE-based NIDS achieves performance comparable to that of multi-layer perceptron-based NIDS with only 0.1% of the labeled training samples. We also confirmed that the selection of data samples for annotation does not affect the performance of the proposed AAE-based NIDS. We also evaluated the relationship between the performance of the proposed method and the dimension of its latent-variable vector. The best performance as measured by recall and F1 score occurred when the dimensionality of the latent variable vector was 10, which suggests that this structure allows for accurate decomposition of attack and normal. This study presents promising results obtained by the proposed semi-supervised learning method with a reduced number of labeled training samples, which reduces the operational costs of a machine-learning-based NIDS.
- 7 October 2022
- Published by Springer Nature in Journal of Network and Systems Management
- Vol. 31 (1) , 1-22
Open AccessNetwork Intrusion Detection System Based on an Adversarial Auto-Encoder with Few Labeled Training Samples
Network intrusion detection systems (NIDS) are critical to defending network systems from cyber attacks. Recently, machine learning has been applied to enhance NIDS capability. To train a supervised machine-learning model, a large number of labeled training samples are required to achieve practical performance. However, labeling data samples is a costly task. Additionally, obtaining anomaly data samples is difficult because trends in network traffic that are subject to NIDS change daily, and new attacks continue to be generated. To address this issue, we propose a semi-supervised machine-learning-based NIDS that reduces the required number of labeled training samples by applying an adversarial auto-encoder (AAE) technique. We evaluated the proposed method through a series of experiments and confirmed that the proposed AAE-based NIDS achieves performance comparable to that of multi-layer perceptron-based NIDS with only 0.1% of the labeled training samples. We also confirmed that the selection of data samples for annotation does not affect the performance of the proposed AAE-based NIDS. We also evaluated the relationship between the performance of the proposed method and the dimension of its latent-variable vector. The best performance as measured by recall and F1 score occurred when the dimensionality of the latent variable vector was 10, which suggests that this structure allows for accurate decomposition of attack and normal. This study presents promising results obtained by the proposed semi-supervised learning method with a reduced number of labeled training samples, which reduces the operational costs of a machine-learning-based NIDS.
- 16 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 355-360
An Annotating Method of GPS Trajectory Data for Human Mobility Analysis in Urban Area
The widespread use of GPS-enabled devices enables us to accumulate unprecedented amounts of individuals' trajec-tories with high accuracy, providing an abundant data resource for human mobility research. We propose a grid-based distance measure between trajectories and an annotation-aware clustering method. We annotate the trajectory by considering the moving mode of humans (walk, trip, or stay) inferred from the moving speed calculated from the trajectory data. We model a one-day human trajectory as a path that consists of a sequence of multiple segments connecting Point-of-Interests (PoIs) associated with episodes. We apply our method to a real-world dataset of human trajectories in the Tokyo area. We confirmed that discriminating the moving mode (walk and trip) of segments yielded meaningful clusters. We found that the smaller grid size of 50 m square produced finer resolution clusters than the larger grid size of 100 m square.
- 16 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 355-360
An Annotating Method of GPS Trajectory Data for Human Mobility Analysis in Urban Area
The widespread use of GPS-enabled devices enables us to accumulate unprecedented amounts of individuals' trajec-tories with high accuracy, providing an abundant data resource for human mobility research. We propose a grid-based distance measure between trajectories and an annotation-aware clustering method. We annotate the trajectory by considering the moving mode of humans (walk, trip, or stay) inferred from the moving speed calculated from the trajectory data. We model a one-day human trajectory as a path that consists of a sequence of multiple segments connecting Point-of-Interests (PoIs) associated with episodes. We apply our method to a real-world dataset of human trajectories in the Tokyo area. We confirmed that discriminating the moving mode (walk and trip) of segments yielded meaningful clusters. We found that the smaller grid size of 50 m square produced finer resolution clusters than the larger grid size of 100 m square.
- Open Access
- 20 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 17 (4) , 2077-2089
Few-Shot Learning and Self-Training for eNodeB Log Analysis for Service-Level Assurance in LTE Networks
With the increasing network topology complexity and continuous evolution of the new wireless technology, it is challenging to address the network service outage with traditional methods. In the long-term evolution (LTE) networks, a large number of base stations called eNodeBs are deployed to cover the entire service areas spanning various kinds of geographical regions. Each eNodeB generates a large number of key performance indicators (KPIs). Hundreds of thousands of eNodeBs are typically deployed to cover a nation-wide service area. Operators need to handle hundreds of millions of KPIs to cover the areas. It is impractical to handle manually such a huge amount of KPI data, and automation of data processing is therefore desired. To improve network operation efficiency, a suitable machine learning technique is used to learn and classify individual eNodeBs into different states based on multiple performance metrics during a specific time window. However, an issue with supervised learning requires a large amount of labeled dataset, which takes costly human-labor and time to annotate data. To mitigate the cost and time issues, we propose a method based on few-shot learning that uses Prototypical Networks algorithm to complement the eNodeB states analysis. Using a dataset from a live LTE network consists of thousand of eNodeB, our experiment results show that the proposed technique provides high performance while using a low number of labeled data.
- 20 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 17 (4) , 2077-2089
Open AccessFew-Shot Learning and Self-Training for eNodeB Log Analysis for Service-Level Assurance in LTE Networks
With the increasing network topology complexity and continuous evolution of the new wireless technology, it is challenging to address the network service outage with traditional methods. In the long-term evolution (LTE) networks, a large number of base stations called eNodeBs are deployed to cover the entire service areas spanning various kinds of geographical regions. Each eNodeB generates a large number of key performance indicators (KPIs). Hundreds of thousands of eNodeBs are typically deployed to cover a nation-wide service area. Operators need to handle hundreds of millions of KPIs to cover the areas. It is impractical to handle manually such a huge amount of KPI data, and automation of data processing is therefore desired. To improve network operation efficiency, a suitable machine learning technique is used to learn and classify individual eNodeBs into different states based on multiple performance metrics during a specific time window. However, an issue with supervised learning requires a large amount of labeled dataset, which takes costly human-labor and time to annotate data. To mitigate the cost and time issues, we propose a method based on few-shot learning that uses Prototypical Networks algorithm to complement the eNodeB states analysis. Using a dataset from a live LTE network consists of thousand of eNodeB, our experiment results show that the proposed technique provides high performance while using a low number of labeled data.
- 7 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Magazine
- Vol. 58 (7) , 42-43
Telecom Software, Network Virtualization, and Software Defined Networks
The articles in this special section focus on telecommunications software, network virtualization, and software defined networks. (SDN) Network softwarization is changing how we build and operate communication networks. It is expected to enable the fifth-generation (5G) networks to provide logically-independent and fully programmable network slices by flexibly, efficiently and securely partitioning the network infrastructure. End-to-end network services are then dynamically provisioned on those slices to meet the diverse requirements of vertical industries. Extensive research and development effort is currently being conducted to explore several aspects of network softwarization including network architecture, management frameworks, and open-source software. The fourth issue of the “Telecom Software, Network Virtualization, and Software Defined Networks” Series features five papers that deal with critical challenges related to 5G networks, such as network slicing, security and trust, access and usage control, service development and opensource tools deployment.
- 7 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Magazine
- Vol. 58 (7) , 42-43
Telecom Software, Network Virtualization, and Software Defined Networks
The articles in this special section focus on telecommunications software, network virtualization, and software defined networks. (SDN) Network softwarization is changing how we build and operate communication networks. It is expected to enable the fifth-generation (5G) networks to provide logically-independent and fully programmable network slices by flexibly, efficiently and securely partitioning the network infrastructure. End-to-end network services are then dynamically provisioned on those slices to meet the diverse requirements of vertical industries. Extensive research and development effort is currently being conducted to explore several aspects of network softwarization including network architecture, management frameworks, and open-source software. The fourth issue of the “Telecom Software, Network Virtualization, and Software Defined Networks” Series features five papers that deal with critical challenges related to 5G networks, such as network slicing, security and trust, access and usage control, service development and opensource tools deployment.
- 1 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Magazine
- Vol. 58 (4) , 16-17
Telecom Software, Network Virtualization, and Software Defined Networks
By introducing rapid and innovative network functions, software-based networking and virtualization are fundamentally revamping how the communication infrastructures are designed, programmed and operated. Network slicing, mobile edge computing, new radio access networks, and programmable cloud-native services represent some of the key technical components of future network infrastructures, including 5G networks that started being commercialized in 2019. The third issue of the "Telecom Software, Network Virtualization, and Software Defined Networks" series features five papers that deal with critical aspects of future networks, such as the adoption of edge computing technologies for mobile networks; the use of network slicing for 5G access and mission-critical services; advanced techniques for virtualized network programmability; and automation of virtualized network security services.
- 1 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Magazine
- Vol. 58 (4) , 16-17
Telecom Software, Network Virtualization, and Software Defined Networks
By introducing rapid and innovative network functions, software-based networking and virtualization are fundamentally revamping how the communication infrastructures are designed, programmed and operated. Network slicing, mobile edge computing, new radio access networks, and programmable cloud-native services represent some of the key technical components of future network infrastructures, including 5G networks that started being commercialized in 2019. The third issue of the "Telecom Software, Network Virtualization, and Software Defined Networks" series features five papers that deal with critical aspects of future networks, such as the adoption of edge computing technologies for mobile networks; the use of network slicing for 5G access and mission-critical services; advanced techniques for virtualized network programmability; and automation of virtualized network security services.
- 1 January 2020
- Published by Optica Publishing Group
- p. M3Z.4
Automatic Resource Mapping Using Functional Block Based Disaggregation Model for ROADM Networks
Automated mapping of real hardware composition onto a ROADM-based model is demonstrated. The functional-block-based model precisely describing the physical layer structures can act as a hardware abstraction layer for more abstracted models like OpenROADM.
- 1 January 2020
- Published by Optica Publishing Group
- p. M3Z.4
Automatic Resource Mapping Using Functional Block Based Disaggregation Model for ROADM Networks
Automated mapping of real hardware composition onto a ROADM-based model is demonstrated. The functional-block-based model precisely describing the physical layer structures can act as a hardware abstraction layer for more abstracted models like OpenROADM.