A Sustainability-Oriented Platform for Monitoring Electricity Usage and Carbon Footprint in Educational Institutions Using Deep Learning and GIS
深層学習とGISを用いた教育機関における電力使用量とカーボンフットプリント監視のための持続可能性指向プラットフォーム (AI 翻訳)
Warit Attharat, Kritsada Puangsuwan, Supattra Puttinaovarat
🤖 gxceed AI 要約
日本語
本研究は、教室の照明のオン/オフ状態を深層学習（CNN）とGISで検出し、リアルタイムに電力使用量と炭素排出量を可視化するウェブアプリケーションを提案。高い分類精度を確認し、教育機関の持続可能性管理に貢献する。
English
This paper presents a web-based platform that uses deep learning (CNN) and GIS to detect lighting status in rooms, enabling real-time monitoring of electricity usage and carbon emissions. High classification accuracy is achieved, supporting data-driven sustainability management in educational institutions.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本の教育機関でも電力使用の可視化とCO2削減が求められており、本プラットフォームはSSBJやカーボン・ニュートラル達成に向けた実践的なツールとして参考になる。
In the global GX context
This platform aligns with global climate disclosure frameworks (TCFD, ISSB) by enabling granular Scope 2 carbon footprint tracking. It offers a scalable model for institutional energy management worldwide.
👥 読者別の含意
🔬研究者:Demonstrates a practical application of CNN and GIS for real-time carbon monitoring in buildings.
🏢実務担当者:Facility managers can use this tool to monitor room-level energy use and emissions, supporting efficiency improvements.
🏛政策担当者:Illustrates a low-cost approach for institutional carbon footprint tracking, relevant for public sector decarbonization policies.
📄 Abstract（原文）
Amid growing global efforts to mitigate climate change, significant attention has been placed on reducing greenhouse gas emissions, with many organizations striving to achieve Carbon Net Zero in accordance with the Sustainable Development Goals (SDGs). Among the primary contributors to institutional carbon footprints is electricity consumption. However, energy monitoring practices in most institutions remain limited to aggregated monthly readings from electricity meters, offering little insight for short-term or room-level energy management and policy planning. To bridge this gap, this study introduces a web-based application that detects and classifies the on/off status of lighting in individual rooms. The system enables real-time monitoring and verification of electricity usage and the resulting carbon emissions. To address this limitation, this study introduces a web-based application designed to detect and classify the on/off status of lighting in individual rooms, enabling real-time monitoring and verification of electricity usage and the corresponding carbon emissions. The application integrates image processing, machine learning, and geographic information systems (GIS) technologies. Experimental results confirm the high accuracy and robustness of the proposed Convolutional Neural Network (CNN)-based model for image-based classification. Furthermore, the platform offers interactive visualization of carbon footprints through a dynamic dashboard integrated with spatial mapping, supporting data-driven and real-time decision-making for institutional sustainability management.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.18421/tem152-10first seen 2026-06-14 04:29:18 · last seen 2026-06-14 04:38:10
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。