Data-Driven Demand Quantification and AI-Assisted Design of Community Low-Carbon Recycling Terminals
データ駆動型需要定量化とAI支援設計によるコミュニティ低炭素リサイクル端末 (AI 翻訳)
Chenyan Wang, Yingying Jiang
🤖 gxceed AI 要約
日本語
本研究は、コミュニティの低炭素リサイクル端末の設計における需要定量化とAI統合の課題に対し、K-meansクラスタリングとKano-AHPモデルを組み合わせたデータ駆動型設計フレームワークを提案。ユーザー需要を分類・優先順位付けし、視覚認識、圧縮、太陽光発電、満杯アラート、収集スケジューリング、炭素フットプリント可視化などの機能を備えた端末とプラットフォームを開発。設計プロセスを標準化し、主観性を排除する方法論を提供。
English
This study proposes a data-driven, AI-assisted design framework for community low-carbon recycling terminals, combining K-means clustering and Kano-AHP to quantify user needs and prioritize design features. The developed terminal and platform integrate visual recognition, compaction, PV power, fill-level alerts, scheduling, and carbon-footprint visualization, forming a closed loop from disposal to carbon accounting. The methodology offers a standardized, replicable workflow for user-centric public facility design, reducing subjectivity.
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
日本では、循環型社会形成推進基本計画やプラスチック資源循環促進法などでリサイクル高度化が求められており、本フレームワークは自治体や企業のリサイクル施設設計に応用可能。AIと需要定量化の統合は、SSBJ開示における廃棄物関連Scope 3排出量の算定基盤としても有用。
In the global GX context
Globally, this work aligns with circular economy and low-carbon infrastructure trends, offering a replicable AI-driven design method for recycling terminals. It contributes to carbon accounting and disclosure by integrating carbon-footprint visualization, relevant for ISSB and CSRD reporting on waste and Scope 3 emissions.
👥 読者別の含意
🔬研究者:Provides a novel integration of K-means and Kano-AHP for user-centric design, applicable to broader AI-ESG research.
🏢実務担当者:Offers a practical framework for designing recycling terminals with intelligent features, useful for waste management and facility design teams.
🏛政策担当者:Demonstrates a data-driven approach to enhance recycling infrastructure, informing policy on circular economy and low-carbon transitions.
📄 Abstract（原文）
Insufficient user demand quantification and weak integration of intelligent functions remain common problems in the design of community recycling terminals. To address these issues, this paper presents a data-driven and AI-assisted design framework for community low-carbon recycling terminals. Field surveys and questionnaires were used to collect user demand data, and a coupled K-means and Kano-AHP model was adopted to support user segmentation, requirement classification, and design priority ranking. On this basis, a low-carbon recycling terminal and a multi-terminal service platform were developed, including edge-side visual recognition, servo-driven compaction, photovoltaic-assisted power supply, fill-level alerts, intelligent collection scheduling, and carbon-footprint visualization. The proposed framework forms a closed service loop covering disposal, recognition, collection, operation management, and carbon accounting. Methodologically, the integrated K-means clustering and Kano-AHP analysis process provides a standardized, replicable quantitative workflow for user-centric public facility design, eliminating the subjectivity of traditional experience-based design decision-making. This study also provides an application-oriented design case for intelligent public facilities and offers a practical reference for the low-carbon transformation of community recycling services.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.1051/e3sconf/202672802015/pdffirst seen 2026-08-05 04:52:38
🔔 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。