Intelligent IoT Systems: From Research to Real-World Solutions

Smart Water Management Using IoT: An Integrated Approach to Conservation and Automation

Sumit Singha Chowdhury — 2025-09-28

This chapter describes a complete IoT system for domestic and small-scale smart water management that integrates three capabilities: non-contact tank level monitoring; flow-based sealed leak detection with occupancy awareness; and automatic rainwater harvesting. A Wi-Fi-enabled microcontroller integrates sensor inputs and manages local alerts and actuators; a cloud dashboard (Blynk) provides a real-time view, notifications and remote control. This modular, inexpensive system is designed for ease of installation on standard rooftop/storage tanks while allowing user-defined thresholds and operational modes (Home/Away) to reduce noticeable false alarms. The architecture emphasises affordability and practicality, ensuring that it can be adopted even in resource-constrained settings. The design philosophy focuses on simplicity, reliability, and long-term usability. Bench test results in a simulated home environment are illustrative of a reliable system: level estimation remained within ~5% of manual level measurement; leak events prompted action within a remarkable time when Away mode was on; rain-induced lid actuation completed in a matter of seconds. The local buzzer/LED alerts perform as required during a network failure and restore automatically when service is restored. The integration of monitoring, anomaly detection, and harvesting into a single architecture minimises manual engagement, mitigates avoidable loss, and encourages more sustainable use of both stored and harvested water. In addition to benefits for the individual household, this approach is also aligned with larger sustainability objectives. It permits data-driven conservation and creates a retrofit pathway for legacy tanks. This chapter describes the design, implementation, and evaluation of the prototype, practical considerations, future upgrade paths (e.g., predictive analytics, implementation of a backup power source for the actuators, pathway to scaling functionality to multi-tank scenarios, or community-based designs) to facilitate real-world implementation and future research investigations.

IOT-Based Smart Energy Management System for Real-Time Monitoring and Automation

Hanamant R Jakaraddi — 2025-09-28

In present days, energy consumption is becoming a major concern for individuals, businesses, and agriculture. Inefficient energy consumption contributes to environmental degradation by raising electricity bills and increasing reliance on non-renewable resources. This approach gives a design and implements an IoT-based Smart Energy Management System for real-time monitoring, predictive automation, and cloud-based control of electrical appliances in smart homes. The system was created using various sensors to track voltage, current, temperature, occupancy and light. Real-time automation was obtained using relay modules and a servo motor for curtain automation. Firebase Realtime Database was utilised for cloud storage, control, and predictive data retrieval. Energy consumption was calculated in kilowatt-hours based on voltage and current values. Manual, schedule-based, and predictive override were implemented. The system effectively monitored energy consumption and reduced power levels by 18%. It automatically shut down equipment when idle or in accordance with pre-scheduled occupancy estimates. The system responded in real-time to sensor inputs and user-scheduled events. Power telemetry and daily logging were always synchronised with Firebase to enable smooth cloud updates and user interaction. The proposed system offers a safe, scalable, and intelligent home energy management system for the future through the use of IoT sensors and cloud technology to enable automation, predictive control, safety, and future-proof compatibility with new smart grid infrastructure for improved sustainability and operational efficiency.

Design and Implementation of a Voice-Activated IoT-Driven Automatic Pet Feeding System

Sumit Singha Chowdhury — 2025-09-28

This project provides an automated voice-activated pet feeder system using an ESP32 microcontroller, an HC-05 Bluetooth module, an L298N motor driver, and a 16x2 LCD screen. Pet owners can use simple voice commands like "Feeder Open" and "Feeder Close" to feed their pets while receiving real-time information via the LCD screen, giving status updates, such as "Feeder Opening" or "Complete Feed”. Without the user needing to tap a button on an app that can cause randomisation in feeding times, the hands-free system ensures consistent feeding without risking the overfeeding of a pet or underfeeding a pet. The system works in real-life situations with an average voice recognition success rate of 93.7%. It dispenses food consistently with a portion variance of ±2%. It has a response time that is less than 500ms, reliable Bluetooth connectivity of up to 8m, and low hardware costs (estimated at less than $35), making it a much more economical solution than any commercial solution available today. The project highlights the usage of embedded systems as part of daily life, bringing convenience and peace of mind to pet owners. It represents a solid step in developing more expandable and voice-automated pet care systems that remember the trade-offs between cost and home automation. Future enhancements may include Wifi integration, so pet owners can control the feeder remotely via a mobile app and add a Real-Time Clock (RTC) module for scheduling feeding time.

IoT-Enabled Smart Aquarium System for Automated Feeding and Real-time Monitoring

Hanamant R Jakaraddi — 2025-09-28

There are significant requirements for environmental monitoring and fish feeding logs when managing an aquarium, which can also be tedious and error-prone for the caregiver/technician. The rapid adoption of Internet of Things (IoT) technologies opens up exciting new opportunities for aquarium management by automating tasks that will allow the environment to remain stable for the aquatic life. This chapter discusses the design and evaluation of a Smart Aquarium System that can automate fish feeding and monitor temperature, pH, turbidity, and water level, as well as real-time connectivity via the cloud. An ESP32-CAM module was also integrated into the system, which transmits live video and images, so fish and how the system is functioning can be observed remotely. The Smart Aquarium system was tested under various operating conditions to evaluate accuracy, responsiveness, and reliability. The results showed it had a feeding accuracy of 96.4%, temperature maintained to a range of ±0.5 °C, pH was reliably detected in the 6.0–8.0 range, turbidity results were reported in NTU units, and the water level stabilised within a range of ±1 cm, respectively. Cloud-based data transfer was accomplished with an average latency of less than 200 ms, which supported effective real-time cloud and local visualisation and control. Safety procedures, such as dry-run prevention for a pump and fault-detection for sensors, were established to enhance reliability. Overall, the results suggest that IoT-based smart aquariums indicate a reduction in manual workload, improve user management of aquatic health and potentially be a low-cost tool for users, including aquaculture operators and hobbyists.

IoT Based Power Consumption Monitoring for Home Appliances

Rajendra M Jotawar — 2025-09-28

This study seeks to create a smart system that has the potential to monitor and manage electricity use in homes by the Internet of Things (IoT) technology. Energy usage within homes is increasing due to the use of more appliances daily. This system attempts to reduce wasted power consumption and save users money by monitoring the power consumption of all home appliances in real time. The system makes use of smart meters and sensors located in real homes, and captures the data for the energy consumption of households and sends the information from the home to a central computer or to a Cloud server. The dataset that we used for this work was a combination of real-time IoT sensor readings measured within homes and previously publicly available smart energy datasets so as to be able to train and test the forecasting model. This study used machine learning forecasting generative models' long short-term memory' (LSTM) and Extreme Gradient Boost (XGBoost) to forecast power usage, where the results achieved a mean absolute error (MAE) of 2.8% and root mean square error (RMSE) of 3.5%. As stated in these results highlighted the proposed approach were effective in forecasting near-term and long-term consumption trends compared to the ground-truth. The great value of the platform includes a friendly user dashboard showing the energy consumption trends, peak usage hours, and alerts, should anything alarming happen to the household electric supply. Furthermore, the platform can provide useful information, such as optimal times to use heavy appliances to avoid unexpectedly high bills. The platform provides full support for renewable energy sources such as solar and wind energy, and can operate irrespective of the homeowners' internet speeds.

Agrosense: IOT-Based Smart Vegetable Gardening System

Hanamant R Jakaraddi — 2025-09-28

Greenhouse farming needs precise monitoring to guarantee healthy plant growth, while conventional methods are cumbersome, inexact, and not amenable to steady-state operation. This study outlines an Internet of Things (IoT)-based vegetable garden monitoring system that automatically controls irrigation, climate, and plant disease in a greenhouse. The system incorporates an LDR light sensor, ESP32-CAM, soil moisture sensor, and DHT11 temperature-humidity sensor controlled by an ESP8266. A motor pump is activated when the soil moisture is less than the threshold value; temperature and humidity are controlled by a fan, while light is provided through an LED when light intensity is low. At specified time epochs, the ESP32-CAM shoots plant pictures that are analysed through a Python-based deep learning algorithm to determine five plant health classes: yellow leaves, curled leaves, leaf spot, white fly infestation, and healthy. A web page presents sensor readout in real time as well as disease classification outcome. Experimental validation indicates classification accuracy of 94.6 %, ±2°C accuracy in temperature regulation, ±5% in humidity control, and 92% accuracy in irrigation. Against previous works that employed IoT to automate greenhouse farming, this solution is not only superior in control accuracy but also incorporates automatic disease diagnosis. Despite limitations due to internet reliability as well as dataset size, the solution provides insights into how IoT, as well as AI, can minimize manual intervention, facilitate early detection, as well as, promote sustainable farming.

Smart Gardening System Using Microcontroller and Smart Application

Sumit Singha Chowdhury — 2025-09-28

The Smart Gardening System represents an IoT-driven initiative designed to make plant maintenance easier and more effective by handling watering automatically. It relies on a soil moisture sensor to track moisture levels in the soil continuously. If the soil gets too dry—say, below 30% moisture—the sensor alerts the Arduino Uno microcontroller, which then switches on a water pump using a relay module. The pump stops once the soil hits an optimal level, like 60%, to avoid wasting water or drowning the roots. Core parts include the Arduino Uno, soil moisture sensor, relay module, water pump, and a separate power source. To make things user-friendly, we have added a basic web page built with Flask that shows live updates on soil moisture and whether the pump is running or not, so people can check in from anywhere online. During tests, the setup responded in less than a second, with the sensor hitting 95% accuracy across different soils, and it cut water use by about 40% compared to doing it by hand. This approach cuts down on manual work, stops plants from getting too much or too little water, and helps them grow stronger. It's especially handy for folks with packed schedules or who travel a lot. In the end, it makes gardening more sustainable by saving resources and effort.