The results of this study demonstrate that the combination of IoT sensors with LSTM Autoencoder analysis of water consumption allows for the monitoring of water consumption patterns and early detection of anomalies, thus providing a means to achieve a reduction in average monthly household water consumption from approximately 21 m3 to 18 m3.
Abstract
Due to an increase in the demand for water and the limited availability of real time monitoring technologies, efficient management of residential water resources poses a unique problem. This study describes the development of an inexpensive Internet of Things (IoT)-based electronic system capable of providing real time monitoring and artificial intelligence (AI)-driven analysis of residential water consumption. The electronic system consists of the use of a YF-DN50 flow sensor connected to an ESP32 microcontroller allowing for continuous data acquisition. The data collected is stored in a cloud-based spreadsheet on Google Colab for processing and analysis, where an unsupervised Long Short-Term Memory (LSTM) Autoencoder model was developed for anomaly detection. The developed model produced a final training loss value of 0.038 and a validation loss value of 0.045, with the threshold for anomaly detection determined to be mean + 3 standard deviations above the reconstruction error. During the observation period, the system detected a total of 7 anomalous events as well as detecting an overall 85.7% of the detected known events and having a 33% reduction in false negative detections compared to a simple fixed threshold baseline. The results of this study demonstrate that the combination of IoT sensors with LSTM Autoencoder analysis of water consumption allows for the monitoring of water consumption patterns and early detection of anomalies, thus providing a means to achieve a reduction in average monthly household water consumption from approximately 21 m3 to 18 m3.
Findings indicate that the proposed framework serves as an innovative prototype for Smart Health management within higher education institutions, aligned with the global Smart Campus paradigm.
S. Janpla, Thanakorn Uiphanit· International Journal of Int...· 0 citations
Traditional energy management at universities is characterised by manual monitoring, static control systems, and lack of real-time data, resulting in excessive energy consumption and high operational costs. This study presents the design, implementation, and evaluation of a Smart Energy Management System (SEMS) at the University of Calabar, Cross River State, Nigeria, with the objective of reducing energy consumption and operational costs. The SEMS integrates Internet of Things (IoT) sensors, real-time data analytics, and automated control mechanisms to monitor and manage energy consumption dynamically. Key hardware components include motion sensors, smart meters, and environmental monitors, all connected to a centralised dashboard that provides actionable insights for energy optimisation. A six-month pilot deployment using a three-tier IoT architecture demonstrated energy savings of 30–40%, improved operational efficiency, with automated response times of 2–4 seconds and system uptime exceeding 95%. Comparative analysis confirmed that the SEMS outperforms traditional energy management in responsiveness (automated response time of 2.5–3.5 seconds versus delayed manual response), cost-effectiveness (30–40% reduction in energy expenditure with low long-term operational costs), and data visibility (real-time, room-level consumption data versus monthly, incomplete utility bills). The study provides a scalable framework for implementing smart energy solutions in university settings.
Ofem Ajah Ofem, Iniobong Ime, Osowomuabe Njama-Abang et al.· Global Journal of Pure and A...· 0 citations
This paper presents the design, development and evaluation of an Internet of Things (IoT)-based smart waste management system aimed at addressing the inefficiencies and public health concerns associated with traditional waste collection methods. The proposed system integrates ultrasonic sensors for real-time bin fill-level detection, a rain sensor for environmental compensation, an ESP32 microcontroller for data processing and transmission, and a dual-mode feedback mechanism via a local LCD display and a remote web dashboard. Experimental results demonstrate a 99% accuracy in fill-level and rain detection, with data updates to the cloud platform (ThingSpeak) occurring within 2 seconds of a 15-second reporting interval. The system's robustness, low cost, and energy efficiency highlight its potential for scalable deployment in urban environments, contributing to cleaner, smarter communities.
O. Saeed, Ayesha Noroz, Maimoona Waqar et al.· Natural and Applied Sciences...· 0 citations
The findings indicate that integrating IoT technology with cloud communication and MATLAB analytics provides a practical, low-cost, and scalable solution for intelligent energy monitoring.
I. M. Danjuma, M. Asih, S. S. Garba et al.· International Journal of App...· 0 citations
Accurate water consumption measurement and equitable billing are vital for sustainable water resource management, especially in regions facing scarcity and uneven distribution. Conventional systems, which often rely on shared mechanical meters, fail to provide individual usage data, leading to disputes, waste, and inefficiencies. This paper presents the design and experimental validation of a low-cost, IoT-enabled Smart Water Billing System (SWBS) that delivers real-time consumption monitoring, adaptive calibration, and automated proportional billing. The proposed system integrates an ESP8266 NodeMCU, YF-B1 Hall-effect flow sensors, and anomaly detection algorithms to ensure precise measurement and early leak detection, where the IoT functionality of the prototype is realized through the Wi-Fi-enabled NodeMCU, which transmits processed consumption and status data to a remote backend using HTTP-based communication for cloud-connected logging and monitoring. A multi-stage calibration method was developed to maintain accuracy across diverse flow rates, reducing measurement error to below 3%. Experimental results confirm that the system reliably tracks individual unit consumption, supports scalable deployment in multi-unit buildings, and provides transparent billing through wireless data transmission. By combining affordability, accuracy, and real-time analytics, the SWBS offers a sustainable solution for modern urban water management, promoting conservation and fair resource distribution.
M. M. Zayed, Mohamed A. El-morsy, M. Shaker et al.· Scientific Reports· 0 citations
Introduction: A significant portion of the population still lacks access to drinking water and relies on non-conventional sources such as wells and springs. In these cases, information on water quality and availability is difficult and expensive to obtain. The solutions available in the local market do not offer equitable access to tools that effectively address these needs.Objective: This work describes the development of an autonomous system composed of hardware and software, designed to monitor in real time the physical-chemical parameters of water, as well as to visualize and interpret the data in a way that is accessible and understandable for the community.Methodology: An IoT-WQMS-based device is presented, which uses five sensors to measure in real time key water parameters, such as pH, conductivity, turbidity, flow rate, temperature and humidity. The data is transmitted via GSM signal using the MQTT protocol, and is processed and visualized through easy-to-use software, designed to be accessible to the community.Results: The results include the graphical interface and visualization of water quality data in a laboratory prototype, both instantaneously and averaged over defined time intervals.Conclusions: The IoT-WQMS system presents advantages in terms of cost and accessibility for obtaining and interpreting water quality data in low-flow sources, in a laboratory environment. Future challenges include the transition to renewable energy and the integration of additional communication protocols, such as LoRaWAN.
Unknown authors· Inge-Cuc· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
