論文

Maintaining indoor condition is an important factor for controlling electric appliances in living space. Generally speaking, a sense of feeling indoor condition is variable between residents. The conventional methods were dealing with this by supposing general residential. This means the conventional methods cannot consider all the residents. This is not realistic when considering installation of the system into the real environment. Thus, in this study, the Bayes' estimation was utilized to analyze the amenity variability. As a result of analysis, the new index, satisfaction rating index, was proposed. To achieve this, the HEMS was constructed in the actual operating residence. As a result, the analysis was acquired from 14 people from 3 different residences. To confirm the availability of the proposed index, the home appliance control system utilizing satisfaction rating index was conducted. The proposed system was evaluated by the experiment in the actual operating residence. From the result, the evaluation showed the availability of the proposed system and satisfaction rating index.

近年，ルータやゲートウエイが取得可能な情報を使って新たなサービスを提供する試みが提案，検討されている．従来，NIDS (Network Intrusion Detection System)構築のため，ゲートウェイ上でレイヤ7での情報検出を可能とするソフトウェア実装は存在したが，アプリケーションプロトコルのHTTP/1.1のgzip encodeやchunk encodeに対応し，情報の検索と抽出を主目的とした実装は公開されていない．そこで本論文ではlibpcapを利用してLinuxゲートウェイのethデバイスやpcapファイルのトラヒックからTCPストリーム再構築と前記HTTPのデコードを行い，文字列抽出を実現するオープンソース・ソフトウエアSLIM (Smart Linux Interface Monitor)を実装，評価した．SLIMにおいて使用メモリ量を削減するため，コンテキストスイッチを利用したパケット単位のTCPストリーム再構築を独自に実装した．評価結果より，SLIMはオンライン解析を行った場合，ゲートウェイ上で21.3Mbpsの処理が可能であり，pcapファイルを直接処理した上でPostgreSQLに保存した場合86.8Mbps, ファイルとして保存した場合1.12Gbpsを達成した．また，オフライン解析を行った場合，1.5TB・最大73万コネクションを含むコアネットワークの仮想トラヒックを解析可能であることを示した．この時，使用メモリ量は5.87GBであった．また，SLIMは研究室ゲートウェイで3ヶ月以上安定して連続動作に成功した．

建築構造物における継続的耐震性評価システムとして運営する際に必要なフォルトトレランシーを維持しつつ，地震発生による倒壊が起きた際においても，その貴重な計測データを極力システムで保持し将来の構造物設計に役立てるシステムについて提案するとともに，実モデルを利用した実験により耐故障性効果を確認している．

The estimation of the number of people is useful for various situations. In this paper, hybrid estimation method of the number of people in a room is proposed. This estimation method is achieved by using CO2 sensor and motion sensor. Adaptive adjusting method of hold time for motion sensor is also proposed for its self-calibration. Proposed method was implemented on an energy management system and evaluated in a classroom environment. This evaluation proves that proposed method can improve the precision from 0.9 in the previous method to 0.4 in the proposed method at the number of people.

Fast growing use of minimally invasive endoscopic surgeries called for development of robots assisting in such procedures. However, existing surgical robots cannot transmit tactile sensation to the operator. To overcome this shortcoming, a bilateral teleoperation method was developed making it possible to accurately convey tactile sensation in single-degree-of-freedom forceps robots. This paper deals with the development of a multi-degree-of-freedom bilateral forceps robot system for surgical procedures which can adapt to actual conditions of the surgery.Bilateral teleoperation of multi-degree-of-freedom robots requires exchange of environmental information between master and slave devices in common coordinates. In this study we adopted mode coordinates which are better related to the motion of the robot. We also proposed a method to decouple the mechanical interference in mode coordinates. An FPGA-based controller introduced in this study makes it possible to reduce data processing time and to use hardware-based real-time control. As a result, multi-degree-of-freedom force feedback is attained.The experimental results show the viability of the proposed method. (C) 2008 Wiley Periodicals, Inc. Electron Comm Jpn, 91(6): 23-33, 2008; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecj.10118

Vehicle-to-grid (V2G) is a key technology that is receiving significant attention as a method for achieving an efficient energy management system (EMS) by connecting electric vehicles (EVs) to an electric power grid. In this study, a fuzzy control method and an optimization control method were proposed as effective control methods for reducing the installation battery capacity and the electric charge in one day by leveling the electric load. As the result, the required battery capacity was 429 kWh for IEVBS model, and 480 kWh for MEVBS model using optimization control method. The control method could save at most $17.98 of an electric bill and achieve power leveling.

Many studies dealing with energy saving have been conducted from the viewpoint of mitigating global warming. However, most of them only consider energy saving and ignore total environmental impact toward human life. It is necessary to provide a comfortable workspace using efficient and optimized energy control, because excessive demand control may have a negative impact on a living environment. Excessive demand control also brings impact on efficiency of working and learning. In order to provide a comfortable indoor environment, some environmental indexes are necessary, including not only temperature, humidity, luminance, wind speed, but also CO2 concentration. In this paper, we propose a novel method to allocate power optimally by using learning efficiency, which contains both PMV and CO2 concentration as its index. We constructed experiments at real place with developed BEMS that enables both monitoring environmental indexes and controlling HVAC systems.

At present, massive amounts of data are utilized for artificial intelligence technologies such as machine learning and deep learning. However, these data must be utilized carefully while preserving data privacy. Data anonymization is a technique enabling both data mining and privacy protection, preventing the identification of individuals by generalizing the data to include multiple records with the same values. In this study, we consider a data-publishing infrastructure for personal data sharing. The infrastructure anonymizes data prior to publishing it to users for privacy protection; however, the problem of unauthorized republishing by malicious users must be considered. To address this issue, we studied digital watermarking methods that correlate data users with anonymized data. Our previous method embedded information indicating the original user to detect illegally republished data. However, this method did not focus on information loss. This study proposes another digital watermarking method for anonymized data that achieves low information loss. The proposed method replaces values in tuples to embed information. To reduce the information loss caused by the embedding, the proposed method selects replacement values from the candidates whose meanings are similar to the original. We propose the use of vector-conversion tables to select replacement values. The proposed method also extends the maximum length of the embedded bit string by embedding multiple bits into a single tuple. Moreover, we measured the tolerance to distortion attacks to evaluate the efficacy of the proposed method. The proposed method is non-blind, i.e., data prior to digital watermarking is required to perform extraction.

Recently, cashless payment services have been rapidly introduced, increasing the demand for recommender systems for real stores. Recommender systems have been well-studied and successful in many Internet services. While factors such as the diversity and coverage of products should be considered, the prediction accuracy of user purchasing behaviors is the most crucial factor in a recommender system. This research proposes a purchasing behavior prediction model for real stores by using purchase history data collected from a supermarket in Saitama City, Japan, as a part of a smart city project. Time-series patterns in purchasing behavior indicate the sales characteristics of supermarkets, where daily products are predominately purchased. For example, some users repeatedly purchase specific products in a certain period or purchase different products from their previous visit. Many previous studies have only considered the compatibility between the features of users and items; however, this work also models the time-series patterns of purchasing behavior. The proposed prediction model adopts ensemble learning, in which weak learners learn the two factors (the compatibility between users and items) and time-series patterns of purchasing behavior separately. Moreover, product names in supermarkets often contain meta-information of the product alongside the item name. For instance, the product name “three tomatoes from Gunma Prefecture” includes information about the quantity and manufacturer as well as the item name “tomato”. However, products that are the same item but have different product names are likely to be purchased together in the context of purchasing activity, thus deteriorating the prediction accuracy. Therefore, a product classification method is proposed to categorize the products for each item. The experimental results show 3.2% and 10.6% improvements in the precision-recall area under the curve (PR-AUC) for the proposed method compared to models that consider only the compatibility between users and items and the time-series patterns of purchasing behavior, respectively.

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.

In the DSM (Demand Side Management) system, a control method for controlling electric appliances in living space should take account of environmental amenity. This paper focuses on a trade-off relationship between power consumption and environmental amenity. We proposed a new method to evaluate this relationship, and it enables to optimize the environmental amenity by air conditioning under the restriction of total power consumption. The proposed method was evaluated by using real environment. This evaluation shows the proposed could improve up to 27.4% in temporary summation of comfort index compared with an existing method.

In response to the growing demand for sustainable agriculture, this study proposes a cost-effective system for greenhouse microclimate estimation combining multi-point, low-resolution thermal imaging with humidity and illuminance sensors. The system is designed to reduce sensor installation and energy cost while maintaining high accuracy in predicting spatial environmental conditions. Based on lightweight deep learning models, the proposed method estimates four environmental parameters, air temperature, relative humidity, soil temperature, and soil volumetric water content, one hour in advance across a greenhouse area with 384 m2 equipped with four infrared array sensors, 80 air temperature sensors, 12 humidity and illuminance sensors, and 8 soil sensors. A fully connected neural network using down-sampled 12 × 16 thermal images combined with humidity and illuminance data trained on data collected over 12 days achieved a mean absolute error (MAE) of 1.46°C (air temperature), 5.04% RH (relative humidity), 0.89°C (soil temperature), and 1.04% VWC (soil moisture) over a 12-day dataset. These results meet the agronomic benchmarks of ± 2.5°C, ± 10% RH, and ± 5% VWC required for practical control of tomato cultivation. The system was implemented on a Jetson Orin Nano device, completing training of 100 epochs in about 20 minutes, which is within the 30-minute interval of electricity metering in Japan. The findings confirm that multi-view low-resolution thermal imaging combined with minimal environmental sensors and efficient neural networks provides a practical solution for energy-efficient greenhouse management. Compared with conventional approaches such as LSTM-based forecasting, the proposed lightweight FCNN and CNN models achieve lower computational cost and better suitability for parallel processing on edge hardware.

In edge computing environments, challenges in utilizing FPGAs as computational resources in edge nodes include the separation of expertise among FPGA designers, network engineers, and IoT engineers, as well as issues of logic reusability and flexible configuration. A GUI-based framework using Node-RED is proposed, leveraging the reconfigurability of FPGAs and dynamic network configuration to enable collaboration among engineers from different fields.The proposed framework utilizes the Processing System (PS) and Programmable Logic (PL) of SoC FPGAs, allowing visual operation of FPGA nodes on Node-RED. When FPGA nodes are connected consecutively, direct data transfer between FPGAs is possible without passing through Node-RED, minimizing communication latency and overhead. Furthermore, by dynamically configuring network settings instead of hard-coding them into the logic, the same logic design can be reused in different network environments, reducing development costs and enabling rapid service deployment.In evaluation experiments, communication latency between Node-RED and FPGAs was measured in both two-point and three-point communication scenarios. The results confirmed that the additional latency introduced by the proposed framework is minimal and does not compromise the processing speed advantage of hardware accelerators. Additionally, resource evaluation showed that sufficient resources can be secured, indicating the possibility of implementing additional applications.With this framework, FPGA designers can focus on logic design without considering network or communication partners, while IoT engineers can use FPGAs as applications without knowledge of FPGA or coding. This improves the practicality and reusability of FPGAs in edge computing environments and demonstrates the potential for more engineers to participate in FPGA-based application development.

発電施設の導入面積が拡大し，大規模な事例もみられる。営農型太陽光発電システムは圃場上部に太陽光発電パネルを展開するが，間隔をあけて設置するため光や気温などの栽培環境にムラが生じることが考えられる。そこで，本研究では約10 000m2の営農型太陽光発電施設を設置している圃場の14地点で気温，相対湿度，日射強度を計測した。気温については，特に風の弱い晴天日に周辺よりも平均で0.65℃低かった。これは，太陽光発電パネルによる直達日射の遮蔽の影響によると考えられる。比較的風の強い日には周辺より平均で0.3℃低く，圃場の気温分布に対する太陽光発電パネルによる直達日射遮蔽の影響は風の弱い日に強く現れる傾向がみられた。以上より，気温分布への影響は日射と風速が主な要因であると考えられる。一方，相対湿度への太陽光発電パネル設置の影響は確認できなかった。太陽光発電パネルの設置が耕地の日照環境に与える影響を評価したところ，パネル下に透過する日射強度は1 日を通して時間帯により全ての計測点で極端に小さい値を示すなど大きく変動していた。営農型太陽光発電圃場の耕地環境を考慮するうえで，地域の太陽高度や風など気象条件を考慮した施設構造の設計が重要である。

建物と設備の振動制御により、機能維持だけでなく復旧時間の短縮までを考慮することで、総合的なレジリエンス性能を向上できるか明らかにする。具体的には以下の４項目を解明する。 ①復旧時間を短縮する振動制御のためのセンサー・アクチュエーターの設置位置 ②制御系設計に適した損傷‐復旧モデル ③復旧時間を短縮する制御系設計法とその有効性 ④機能維持性と早期修復性の双方を考慮した建物・設備の協調制御手法とその有効性 医療施設を対象にレジリエンス性能を向上する制御系設計法を開発した。設備機器の地震被害と復旧情報から、フラジリティ曲線と復旧時間の確率モデルを構築した。想定地震動に対する復旧確率の時間推移を表す復旧曲線を用いてレジリエンス性能を最大化するLQR制御パラメータを探索する制御系設計法を提案し、有効性を検証した。 また、データセンターを対象に、サーバの地震応答を予測し、閾値超過確率に基づき仮想マシン等を待機系に移行し機能維持を図るウォームスタンバイ法の開発を行った。 加えて、機能維持や早期復旧のボトルネックとなる高置水槽をスロッシングダンパーとして活用し、レジリエンス性能を高める制震システムを開発した。 これまで、土木・建築・機械構造物の地震対策技術としてアクティブ・セミアクティブ制御の研究は広く行われているが、地震後の復旧のフェーズまで視野に入れて制御系の設計を行っているものは存在しなかった。 そのような背景のもと、本研究は建築・機械の構造振動制御分野と情報・通信技術分野の研究者が連携して、機能維持から復旧まで総合的なレジリエンス性能の向上を目指し構造制御を行う制御手法や情報システム、制震装置の開発に取り組んだ。 新規性・独創性が高く、新たな地震防災技術を切り拓いたと考えられる。

This study aims to realize a mechanism for packet processing in the edge domain while maintaining network transparency, in order to accommodate diverse service requirements in smart communities. Since conventional flow control, which operates on a per-packet basis, lacks flexibility, we propose a content-based fine-grained flow management method that enables control at the level of individual content segments within packets. In addition, we introduce an out-of-path transparent add-on architecture to address the limitations of conventional transparent add-ons, which assume the presence of processing resources on the main path. The proposed system implements one approach for selective content masking and two approaches for out-of-path anonymization. Furthermore, we develop a mechanism for dynamically rewriting Ack and Seq numbers to preserve TCP session integrity. The proposed approaches were implemented and evaluated on Mininet, and the results demonstrate that effective flow management can be achieved with minimal impact on network delay while maintaining network transparency.

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.

This study proposes a pioneering approach for anomaly detection in smart factories through the analysis of equipment acoustic data, leveraging the StyleGAN2-ADA deep generative model, originally developed for facial image generation, to analyze acoustic data. This method shows the potential to accurately estimate the severity and type of unusual sounds, allowing for early identification of equipment faults or wear and tear, and subsequently estimating their operational lifespan. Specifically, acoustic data from small motors are converted into Mel spectrograms, which are treated as images. By training the StyleGAN2-ADA model with these spectrograms and analyzing the resulting latent vectors, the technique classifies the nature and extent of anomalies in previously unseen acoustic data. Using unsupervised learning to analyze anomalous sounds holds significant potential for improving industrial monitoring and maintenance planning.

Accurate, memory-efficient forecasting of greenhouse energy loads and indoor environmental conditions is essential for demand management in modern horticultural facilities. This study introduces μRWKV, a lightweight variant of the Receptance-Weighted Key-Value (RWKV) network tailored to multivariate time-series inference. μRWKV replaces the token embedding and softmax layers of natural language models with linear projections and regression heads. At the same time, it retains RWKV-v2's inherent recurrent Time-Mixing and Channel-Mixing blocks, enabling sequential prediction during inference. These modifications produce an effectively constant inference memory footprint that remained below 11 MB across all tested sequence lengths, and training time scaled smoothly with model dimension. We trained and evaluated μRWKV on winter measurements from a Venlo-type greenhouse, using outdoor temperature, accumulated solar radiation, and temporal encodings to predict indoor temperature, electricity demand, and gas consumption. Compared with tuned LSTM and GRU baselines, μRWKV matched mean absolute error (MAE) and achieved the lowest difference in mean absolute rate of change (DMARC), indicating superior fidelity to short-term fluctuations. These fine-grained forecasts can support real-time load shifting and peak shaving, underscoring μRWKV's practical value for energy-aware greenhouse control.

The global positioning system (GPS) data are commonly used for location-based services such as traffic flow prediction. However, such data contain considerable sensitive information and thus, they must be anonymized before being published. In this study, we investigate trajectory anonymization. Previous methods have limitations in that they cannot be applied for different load network sparseness and cannot preserve the trajectory information. Thus, we propose a DNN-based method that can anonymize trajectories with different load network sparseness and also preserve the trajectory information. Specifically, the trajectories are projected to the latent space using the pre-trained encoder-decoder model, and the latent variables are generalized. Furthermore, to reduce the information loss, we propose a segment-aware trajectory modeling and study the effectiveness of assuming the normal distribution to the latent space. The experimental results using real GPS data show the effectiveness of the proposed method, presenting the improvement in the data reservation rate by approximately 3% and reducing the reconstruction error by approximately 31%. © 2024 The Author(s). IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.