five

Smart_Home_Device_Dataset

收藏
DataCite Commons2025-03-11 更新2025-04-16 收录
下载链接:
https://ieee-dataport.org/documents/smarthomedevicedataset
下载链接
链接失效反馈
官方服务:
资源简介:
The Smart Home Device Dataset consists of 5000 samples collected at an hourly interval starting from January 2022, representing consumer electronics and IoT-enabled devices in a home automation environment. Each entry is associated with a unique device ID, ensuring identification of distinct devices. The dataset captures real-time sensor readings, including temperature variations (18°C to 30°C), power consumption levels (10W to 500W), and user activity states (Active, Idle, or Sleep), which provide contextual insights into device operation. Additionally, the dataset logs device modes (Auto, Manual, Standby) to indicate system settings during operation. The anomaly flag denotes potential system failures, with a 5% anomaly rate ensuring a realistic distribution for anomaly detection modeling. The decision label categorizes each sample into Normal, Warning, or Critical states, serving as a ground truth for intelligent decision synthesis in AI models. The dataset is designed for optimal decision-making, and adaptive control optimization, enabling real-time AI-driven automation strategies. The data is diverse, structured, and ethically compliant, ensuring generalizability across different environments.

智能家居设备数据集(Smart Home Device Dataset)包含5000条样本,采集周期自2022年1月起,按小时间隔采集,覆盖家庭自动化场景中的消费电子与物联网(IoT)赋能设备。每条样本均关联唯一设备标识符(device ID),可精准区分不同设备。该数据集采集实时传感器读数,涵盖温度变化区间(18℃至30℃)、功耗水平(10W至500W)以及用户活动状态(活跃、空闲或休眠),可为设备运行状态提供情境化洞察。此外,数据集还记录了设备运行模式(自动、手动、待机),用以表征设备运行时的系统配置。异常标记(anomaly flag)用于标识潜在系统故障,异常样本占比为5%,可保障异常检测建模所需的真实数据分布。决策标签将每条样本划分为正常、警告或严重三类状态,可作为人工智能(AI)模型智能决策合成的基准真值(ground truth)。本数据集旨在支撑最优决策与自适应控制优化,可实现基于人工智能的实时自动化策略构建。该数据集具备多样性、结构化特性且符合伦理规范,可保障在不同应用场景下的泛化能力。
提供机构:
IEEE DataPort
创建时间:
2025-03-11
搜集汇总
数据集介绍
main_image_url
背景与挑战
背景概述
Smart_Home_Device_Dataset是一个包含5000个样本的家庭自动化设备数据集,采集于2022年1月起的小时级间隔,覆盖温度、功耗、用户活动等多维度传感器数据,并标注了异常状态和决策标签。该数据集旨在支持AI驱动的实时自动化策略和自适应控制优化,具有5%的异常率,适用于异常检测和智能决策建模。
以上内容由遇见数据集搜集并总结生成
二维码
社区交流群
二维码
科研交流群
商业服务