An ai- based ventilation kpi using embedded iot devices
ABSTARCT : Enhancing Patient Care with Advanced Ventilation System intends to revolutionize mechanical ventilation by creating an automated ventilator that uses an Ambu bag and has complete monitoring features.
The system precisely sets and controls respiratory parameters such as tidal volume, respiratory rate, minute ventilation, peak and plateau pressures, I:E ratio, and FiO2 levels utilizing a DC motor-driven cam lever mechanism for precision Ambu bag compression.
IntelliVent uses modern sensors to monitor important patient characteristics such as blood pressure, glucose levels, oxygen saturation, body temperature, and platelet count, allowing for dynamic modifications to match unique patient demands.
The complex control software offers different ventilation modes and real-time feedback loops, which improves system adaptability and responsiveness. IntelliVent's user-friendly interface, which includes real-time visualization of critical parameters and vital signs, helps clinicians make informed judgments.
This project seeks to provide a cost-effective, dependable, and adjustable ventilation solution that will improve patient care quality and efficiency in critical care settings.
IntelliVent aims to ensure safety, efficacy, and regulatory compliance through thorough calibration, bench testing, and clinical trials, thereby setting a new standard in mechanical ventilation technology.
The KPIv is also based on artificial intelligence algorithms that enrich the information obtained from the current Smart University platform metrics data. Using AI, we can fill in uncertain information or anticipate risky situations where the allowed limits will be exceeded.
The proposed KPIv uses CO2 measurements and the institution’s existing knowledge of its environment: the number of connected Wi-Fi network users, the structure and organisation DB, standard room specifications and classroom volumes, etc.
All this information is available in the university's specific management applications and enables to evaluate the number and characteristics of a room’s occupants and ventilation efficiency.
The KPIv proposal was implemented via a case study performed at the University of Alicante University. It was incorporated into the university’s SmartUA platform architecture.
When the validation phase will be completed, the prototype will be transferred over the current year to ten public universities, which are part of an initial consortium to deploy a common, nationwide Smart University platform.
Cost: Initial setup and ongoing maintenance of IoT devices can be expensive. This includes costs for hardware, software, and integration.
Complexity: The integration of AI and IoT can be complex, requiring specialized knowledge for installation, maintenance, and troubleshooting.
Data Security: IoT devices can be vulnerable to cyberattacks, potentially compromising sensitive data or control systems.
Reliability: Network connectivity issues can affect the performance and reliability of IoT devices, leading to inaccurate data or system failures
This system comprises several interconnected modules that work together seamlessly. At its core, a network of advanced sensors monitors critical parameters such as temperature, humidity, CO2 levels, and particulate matter, continuously collecting data from various locations within the building.
This data is processed at the edge to reduce latency, enabling quick responses to changing conditions.
AI algorithms analyze the aggregated data, identifying patterns and predicting trends to optimize ventilation performance and detect anomalies that may indicate potential issues.
Users interact with a user-friendly dashboard accessible via mobile and web platforms, allowing them to monitor key performance indicators (KPIs) and receive alerts for any irregularities. The system integrates with existing HVAC systems, automatically adjusting ventilation settings based on real-time insights.
Real-Time Monitoring: Continuous data collection allows for real-time monitoring of air quality and ventilation performance, enabling prompt responses to any issues.
Improved Air Quality: By continuously assessing environmental conditions, the system can maintain optimal indoor air quality, enhancing occupant comfort and health.
Predictive Maintenance: AI can predict when maintenance is needed based on usage patterns and performance data, reducing downtime and repair costs.
Data-Driven Insights: The system generates valuable insights into ventilation performance, helping to inform decision-making and policy development.
Scalability: IoT devices can be easily added or adjusted to scale with the needs of a building or facility, allowing for flexible management.
|