論文 - 西　宏章

スマートコミュニティで必要となる計算機システムとは?-スマートシティをスマートたらしめる計算機システム

西宏章

研究報告システム・アーキテクチャ (ARC) 2023 (5), 1-1 2023年

Can we say

H Nishi

IEICE Technical Report; IEICE Tech. Rep. 122 (354), 24-24 2023年

Access Control Management System for Edge Computing Environment Using Tag‐Based Matching and Cache Injection

S Shimahara, M Nohara, H Nishi

IEEJ Transactions on Electrical and Electronic Engineering 18 (9), 1472-1481 2023年

Privacy-Preserving Hierarchical Anonymization Framework over Encrypted Data

Jia, J. and Saito, K. and Nishi, H.

arXiv （一般社団法人 電気学会）  abs/2310.12401 （ 10 ） 1011 - 1019 2023年

ISSN  23318422

　概要を見る

Smart cities, which can monitor the real world and provide smart services in a variety of fields, have improved people’s living standards as urbanization has accelerated. However, there are security and privacy concerns because smart city applications collect large amounts of privacy-sensitive information from people and their social circles. Anonymization, which generalizes data and reduces data uniqueness, is an important step in preserving the privacy of sensitive information. However, anonymization methods frequently require large datasets and rely on untrusted third parties to collect and manage data, particularly in a cloud environment. In this case, private data leakage remains a critical issue, discouraging users from sharing their data and impeding the advancement of smart city services. This problem can be solved if the computational entity performs anonymization without obtaining the original plain text. This study proposed a hierarchical k-anonymization framework using homomorphic encryption and secret sharing composed of two types of domains. Different computing methods are selected flexibly, and two domains are connected hierarchically to obtain higher-level anonymization results efficiently. The experimental results show that connecting two domains can accelerate the anonymization process, indicating that the proposed secure hierarchical architecture is practical and efficient.

• Access to Document (DOI)
• CiNii Research

Proposal and implementation of k-anonymization method for data insertion and deletion

Han K., Nishi H.

IEEE International Symposium on Industrial Electronics 2023-June   1 - 6 2023年

　概要を見る

Preserving the privacy of individuals while publishing their relevant data has been an important issue. K-anonymization, which is one of the most useful privacy models, is valid for static data; however, it does not support dynamic data updating. In this paper, we propose a method for inserting and deleting data into and from k-anonymous tabular data while maintaining k-anonymity. This method ensures k-anonymity after multiple publications by retaining the raw data and the latest published data. In the deletion process, the specified record is first deleted from the data table, and the records remaining in the q∗-block to which the specified record belonged are inserted into the data table excluding the remaining records. This insertion of multiple records is performed by repeating the above addition process in sequence.

• Access to Document (DOI)

Layer-7 and 5-Tuple Information Analysis Framework for Providing Positional Flexibility In Location Determination for Service Provision

Sato Y., Namba Y., Nishi H.

IECON Proceedings (Industrial Electronics Conference)    1 - 6 2023年

ISSN  21624704

　概要を見る

In a smart community, which is an initiative to create an efficient regional society by leveraging information and communications technology (ICT), various data exchanges and data processing are performed. Owing to the demand for network transparency in data processing, packet rewriting is required at network edges. In the packet rewriting process, packets need to be analyzed after obtaining the necessary permissions. A conventional method for packet analysis is using a 5-tuple. While this method can analyze packets by a service user, it cannot analyze packets by a service. Moreover, service provision needs to take place at the appropriate locations with respect to the privacy level, and service provision locations need to be flexible enough to change even subsequent to the commencement of services. To address this issue, there is a need to enable positional flexibility in determining the location for service provision between the data source and cloud. In this study, assuming that the permission to analyze packets had been obtained within the smart community, we implemented a framework that could analyze not only 5-tuple but also layer-7 (L7) information and rewrite packet contents based on the analysis results. The process performed at the edge first analyzed the header of the incoming packet to determine whether the packet was subject to L7 information analysis. If the packet was subject to analysis, the L7 information was analyzed to determine whether the packet was subject to rewriting. A packet subject to rewriting were rewritten and forwarded accordingly. For this series of packet process, we used the Data Plane Development Kit (DPDK), a tool that could speed up packet processing. The framework was applied to the anonymization process, and the delay due to the anonymization process was 0.195 ms. With this framework, it is possible to achieve the packet content rewriting process at any point between the IoT device and the cloud by modifying the location of the edge node.

• Access to Document (DOI)

Evaluation of Communication Overhead for Distributed Deep Learning for Local Data Privacy

Okuda Y., Nishikawa A., Nishi H.

IECON Proceedings (Industrial Electronics Conference)    1 - 6 2023年

ISSN  21624704

　概要を見る

In recent years, there has been growing interest in using big data for machine learning applications. However, as data are often distributed across multiple clients, privacy and physical limitations can make it difficult to aggregate and use these data on centralized servers. Federated learning and split neural networks enable machine learning models to be built without requiring the aggregation of distributed data. These methods have received increased attention in the industrial sector as a means of eliminating impediments to privacy preservation in data sharing across various institutions, such as smart factories. One critical aspect of implementing such methods in practice is analyzing the time variation of traffic and estimating the throughput required for operationalizing machine learning. Previous studies have formulated traffic characteristics without considering packet overhead and measured only the total traffic and the throughput per iteration; such an approach is inadequate from a traffic monitoring perspective. To address these issues, this study conducted an empirical investigation of traffic patterns under realistic conditions, with a particular focus on quantifying traffic and latency. The results of this study suggest that due to the dynamic nature of throughput, it is essential to measure traffic using time units that can accommodate the temporal variability of traffic.

• Access to Document (DOI)

Estimation of Indoor Space Temperature Distribution Using Heat Maps

Hayashi E., Sonoda A., Nishikawa A., Nishi H.

IECON Proceedings (Industrial Electronics Conference)    1 - 6 2023年

ISSN  21624704

　概要を見る

In recent years, there has been an increasing demand for accurate measurement of the spatial dispersion of air temperature in air conditioning control for indoor environments. This spatial dispersion of temperature is caused by the unevenness of air conditioning equipment, local temperature gradients due to human activities, and local heat exchange with outdoor air, all of which hinder the provision of a comfortable environment. This issue requires resolution in various fields, including the agricultural sector, where it can negatively impact crop growth. To address this issue, it is necessary to measure air temperature at multiple points, although the number of sensors that can be installed is typically limited, and the temperature at a single point is typically used as a representation of the temperature in the space. Additionally, heat maps using infrared array sensors can acquire temperature distribution in a narrow area; however, they cannot directly determine air temperature as they only measure the surface temperature of an object. Therefore, we propose a deep learning-based method that utilizes both heat maps acquired from infrared array sensors and air temperature data obtained from environmental sensors to estimate air temperature. We evaluate its effectiveness by varying the experimental environment, the model structure, and the resolution and number of heat maps added as input. Furthermore, we assess the usefulness of utilizing a Graphics Processing Unit (GPU), which is a cost-effective solution that can be installed on low-resolution sensors and edge devices. The outcomes indicate that the proposed model can attain an estimation accuracy of under 1 mean squared error (MSE) in approximately 200 seconds, while also exhibiting practical feasibility for deployment on edge devices, including residential abodes and agricultural premises.

• Access to Document (DOI)

Distributed MQTT Brokers Infrastructure with Network Transparent Hardware Broker

Toyohara T., Nishi H.

Proceedings - 2023 11th International Symposium on Computing and Networking, CANDAR 2023    182 - 188 2023年

　概要を見る

In recent years, the number of IoT devices has been rapidly increasing. Therefore, MQ Telemetry Transport (MQTT) has attracted attention as a lightweight protocol for IoT devices. MQTT employs a publish/subscribe model of communication via a broker, and since the performance of the MQTT broker directly affects the quality of service, various studies have been conducted to improve its performance. Among them, the hardware implementation of MQTT broker has higher performance than software implementations in terms of publish throughput and processing delay. However, there are some problems such as inflexibility and resource limitations. Therefore, we propose a distributed MQTT brokers infrastructure using the hardware broker. In this architecture, the software broker on the cloud and the hardware broker at the edge region work in cooperation to achieve low latency processing at the edge region and software flexibility. The hardware broker operates network transparently, so that end devices communicate with the software broker in the cloud and do not need to be aware of the presence of the hardware broker at the edge region. This enables resource and processing load distribution without affecting end devices. We implemented the network transparent hardware broker in a field-programmable gate array (FPGA) and evaluated it.

• Access to Document (DOI)

Differential Privacy Framework using Secure Computing on Untrusted Servers

Jia J., Nishi H.

Proceedings - 2023 IEEE 6th International Conference on Industrial Cyber-Physical Systems, ICPS 2023 （IEEE）     1 - 6 2023年

ISSN  2769-3902

　概要を見る

Smart cities use cutting-edge technologies to monitor the real world and improve various aspects of human life, such as traffic, agriculture, electric power grid, and medical care. However, protecting users' privacy is crucial in smart-city applications for service coordination. Any leakage of users' sensitive information may prevent users from sharing their data, and thereby hinder the progress of smart cities. Differential privacy (DP) is one of the approaches that protects sensitive information in a dataset, and strongly resists background knowledge attacks. This study proposes a central differential privacy scheme using secure computing methods. After receiving the ciphertext of the data, the central data curator in this system generates a perturbed dataset in the encrypted domain. The unmodified data of each user is not exposed to the data curator, therefore the data users do not need a trusted data curator. Moreover, compared with the existing models in which significant amount of noise is locally added before sending the data to the data curator, the proposed scheme adds considerably less noise while maintaining the same privacy requirement, resulting in enhanced data utility. Model evaluation demonstrates that our system effectively protects the privacy of individuals and provides accurate data for statistical analysis.

• Access to Document (DOI)

Black Soldier Fly Bioconversion System: A Digital Twin Approach

Yu G., Nishi H., Pang C., Gu Q., Lin Y., Liang J., Dai W., Vyatkin V.

IEEE International Symposium on Industrial Electronics 2023-June   1 - 4 2023年

　概要を見る

Insect-based bioconversion is an emerging and economically viable approach that could simultaneously solve the global issues on food waste treatment and protein shortage. An essence of insect-based bioconversion is to feed insects on food wastes and then harvest and refine the developed insects into value-added commodities. This is a circular bioeconomic approach that can efficiently upcycle the nutrients and energy in food waste streams back into agricultural supply chains, but the difficulty is how to realize mass production of insects. This paper reports a commercial-scale insect-based bioconversion system using black soldier flies, whose design and development follow a digital twin paradigm. In particular, an industrialized rearing environment has been established, where the larvae growth can be systematically monitored, controlled, and managed to evaluate the overall bioconversion process efficacy. The system has been deployed in a pilot plant, whose Phase I is capable of handling 20 tons of food waste feedstocks per day and has been consecutively operating to date.

• Access to Document (DOI)

Attention-PVS for Domestic Hot Water Consumption Forecasting in Individual Household

Sonoda A., Compagnon P., Reyboz M., Nishi H.

IECON Proceedings (Industrial Electronics Conference)    1 - 6 2023年

ISSN  21624704

　概要を見る

Short-term hot water consumption forecasting in an individual household is important to realize energy-efficient hot water management while meeting users' comfort. However, consumption traits in an individual household contain much irregularity, and that gives additional challenges to accurate forecasting. This paper proposes an Attention-PVS model to tackle this issue, which focuses on consumption values with similar past consumption trends. In this study, verification experiments were conducted on a real-household hot water consumption dataset collected by Electricity of France. The model was evaluated with its consumption forecasting error with MAE, MSE, and RMSE metrics and computational costs. As for the computational cost, experiments were conducted on NVIDIA Jetson Nano (Jetson) to validate the applicability to embedded systems. The results revealed that the proposed model performs consumption forecasting with comparable accuracy to other state-of-the-art models. Additionally, while LSTM scored lower error than the proposed model, Attention-PVS performed training and inference on Jetson in shorter times than LSTM.

• Access to Document (DOI)

Temperature Monitoring and Airflow Control System for Balancing the Greenhouse Environment Using IEEE 1451 Standards

Nishi H., Takayama Y., Wijekoon J.L., Song E.Y., Lee K.B.

IECON Proceedings (Industrial Electronics Conference)    1 - 6 2023年

ISSN  21624704

　概要を見る

It is vital to establish a suitable thermal environment for greenhouses to improve production quality for crop cultivation. However, in greenhouse environments, uneven temperature, caused by the influence of outside temperature, leads to unevenness in air conditioning and results in sub-optimized crop quality and yield. This paper introduces a real-time temperature monitoring and airflow controlling system using IEEE P1451.0 and P1451.1.6 standards to balance and improve greenhouse environments. The controlling system consists of three components: an infrared array of smart temperature sensors (STS) placed inside and outside the greenhouse, a smart airflow controller (SAC), and a temperature monitoring and airflow control application (TMACA). The network communications among STS, TMACA, and SAC are based on IEEE P1451.0 and P1451.1.6 standard network services using the message queuing telemetry transport (MQTT) protocol. In the system, the TMACA can monitor the temperatures inside and outside the greenhouse using two STS, process and estimate the temperature differences inside the greenhouse, and then control and equalize the temperature of the greenhouse using the SAC based on the temperature differences to balance and improve the greenhouse environment.

• Access to Document (DOI)

動きベクトル検出用 3D 画像フィルタの FPGA への実装

陳宇晨， ウェイカイジ， 西宏章， 天野英晴

電子情報通信学会技術研究報告; 信学技報 122 (174), 13-14 2022年

スマートコミュニティ・スマートシティでのエッジコンピューティングの本当の役割 エッジコンピューティングの位置自在性・透明性が社会を変える

西 宏章

JBPress - 2022年

• CiNii Research

Hierarchical Multiobjective Distributed Deep Learning for Residential Short-Term Electric Load Forecasting

Sakuma Y., Nishi H.

IEEE Access （IEEE Access）  10   69950 - 69962 2022年

ISSN  2169-3536

　概要を見る

Short-term load forecasting plays an essential role in appliance control in households and demand response at the neighborhood or community level. When load forecasting is simultaneously performed at different levels in a smart community, a central method that directly aggregates raw household data may incur a security issue. However, an individual method that builds separate models for each level requires additional data collection. We propose a distributed load forecasting framework that is secure, data efficient, and resource efficient. Our proposed method shares the latent variables, the reduced expression of the input data, of the household models without revealing the raw data. The latent variables are aggregated and fed to the neighborhood model, and during inference, input data collection can be abbreviated in the neighborhood. Because household models provide informative latent variables, the number of model parameters for the neighborhood model can be reduced. Our proposed method is evaluated using real electricity consumption data for six different models under 24 h and 1 h ahead forecasting. Our proposed method with the long short-term memory, multi-layer perceptron, and convolution neural network-based models presents the degradation in average mean absolute percentage error 3.68% and 5.16% at most for household and neighborhood forecasting, respectively, compared to the individual method. At the same time, it reduces the neighborhood's model size by approximately 53%.

• Access to Document (DOI)

Survey of Protocols for V2G Communications

Shom S., Guha A., Tsang K.F., Nishi H., Wu C.K., Shuaib K., Sharif H., Alahmad M.

Proceedings of the IEEE International Conference on Industrial Technology （IEEE）  2022-August   1 - 8 2022年

　概要を見る

The bi-directionality of electric vehicle (EV) charging has proved to be important for load leveling purposes, amongst others. Thus, Vehicle-to-Grid (V2G) communication protocols are a necessity which ensures that the information exchange that takes place during this process, is efficient, secure, and reliable. Several research articles regarding different V2G communication protocols have been published over the years. This paper summarizes current relevant research in this area in order to provide a reference guide for researchers interested in this subject.

• Access to Document (DOI)

Personal Data Access and Distribution Management Extension to FIWARE

Namba Y., Nishi H.

IECON Proceedings (Industrial Electronics Conference) （IEEE）  2022-October   1 - 6 2022年

ISSN  21624704

　概要を見る

In smart communities which refers to communities that leverage the use of technologies to benefit their citizens, it is necessary to ensure data interoperability among services and secure data operations. Particularly, it is necessary to manage the data path of services based on edge computing to consider the level of privacy between regions and at different network layers. FIWARE, a smart city operating system(OS) that has been recently deployed in several cities, provides an application programming interface (API) based on common rules to ensure interoperability and to enable coordination and distribution of services and data. However, the data distribution control component is assumed to be placed in the cloud, and it does not have a distribution management mechanism. In this study, within the architecture of FIWARE, we have built a mechanism that manages data paths on an edge by using tags of dataflows which is associated with the personal information in the packets. Additionally, we implemented a benchmark and measured a processing delay for gathering personal information. In the simulation environment, the processing time delay was 0.05 seconds by using proposed system when the control component is placed in the egde area.

• Access to Document (DOI)

Optimum Configuration of Edge Computing Protocols for Industrial Internet-of-Thing Applications

Bakhtiari M., Wei Y., Nishi H., Fung Tsang K., Aljuhaishi N., Alahmad M.

IECON Proceedings (Industrial Electronics Conference) （IEEE）  2022-October   1 - 6 2022年

ISSN  21624704

　概要を見る

Industrial Internet-of-Things (IIoT) technology has been rigorously developed in recent years, moving towards the ambitious goal of industry 4.0, Network Automation. However, there are a few critical challenges regarding the implementation of a reliable IIoT ecosystem for different applications; security, battery life, and bandwidth are controversial challenges. All the challenges regarding IIoT are mainly struggling within the edge computing smaller box of the big picture in which a cloud is an upstream object while sensors and actuators act as downstream devices. Therefore, having a reliable IIoT ecosystem necessitates focusing on the whole IIoT's challenges in the edge computing smaller box; first realizing the vital, practical demands of a specific IIoT application, and then defining the compatible protocols to form the effective edge computing configuration. This paper reviews four IIoT case study applications with their specific requirements and their counterpart sensor/actuator properties to find the appropriate edge computing protocols satisfying their demands.

• Access to Document (DOI)

Implementation of IEEE P1451.0 and P1451.1.6 Sensor Networks

Nishi H., Lee K.B.

IECON Proceedings (Industrial Electronics Conference) （IEEE）  2022-October   1 - 6 2022年

ISSN  21624704

　概要を見る

This paper introduces an implementation of a standard-based sensor network for the Internet of Things (IoT) applications adhering to the Institute of Electrical and Electronics Engineers (IEEE) P1451.0 and P1451.1.6 draft standards. The architecture of standards-based sensor networks consists of P1451.0 and P1451.1.6-based wide-area networks (WAN), P1451.0, and P1451.5.X-based wireless local area networks (WLANs), and P1451.0 and P1451.2-based wired local-area networks (LANs). A few case studies P1451.0 and P1451.1.6 WAN are provided with preliminary results to verify some network service specifications of the sensor network based on P1451.0 network services and P1451.1.6 MQTT interfaces in order to verify and improve draft specifications helping to achieve interoperability.

• Access to Document (DOI)