"BLE-Based Indoor Emergency Recognition Dataset for Medical IoT Environments"
Abstract
"The BLE-Based Indoor Emergency Recognition Dataset is a real-world Medical Internet of Things (IoT) dataset developed to support research in indoor emergency detection, patient safety monitoring, indoor localization, and privacy-preserving artificial intelligence. The dataset was collected using the Medical Indoor BLE Emergency System (MIBES), which consists of wearable ESP32-based BLE Safety Tags, BLE Anchor Nodes, and a Gateway Node deployed within an indoor environment, which was simulated like as it were a hospital patient room.The dataset contains 4,000 labeled records representing both normal and emergency events. Each record captures Bluetooth Low Energy (BLE) communication data and includes seven key attributes: Timestamp, User ID, Zone, Anchor ID, RSSI (Received Signal Strength Indicator), Sequence Number, and Status Label. The Status attribute indicates whether the event corresponds to a normal situation (0) or an emergency condition (1). To improve signal reliability, RSSI values were processed using Exponential Moving Average (EMA) smoothing to reduce noise caused by indoor signal interference and multipath propagation.This dataset is particularly valuable for developing intelligent healthcare monitoring systems capable of recognizing patient emergencies in GPS-denied indoor environments such as hospitals, clinics, nursing homes, and assisted-living facilities. From a patient perspective, it enables faster emergency response and enhanced safety through real-time…
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.