The system is built around a Raspberry Pi 4, which acts as the central processing unit. Voice commands are captured through a microphone module and processed locally using TinyML-based deep learning models, allowing efficient and low-latency voice recognition without continuous cloud dependency. Advanced noise filtering techniques are implemented to ensure high accuracy even in noisy environments. Recognized commands are matched with predefined keywords such as “Open Door” and “Close Door”.

Upon successful recognition, the Raspberry Pi drives a servo motor to perform precise door movement operations. The current system status, including command recognition and door position, is displayed on an LCD display for real-time user feedback. An SD card is used for data storage, including trained models and system logs. The entire system operates on a 5V DC power supply, making it suitable for embedded and IoT applications.

This project demonstrates an efficient, low-power, and cost-effective voice-controlled smart door system using TinyML and deep learning, with potential applications in smart homes, assistive technology, and secure access control systems.

The main objectives of this project are:

• To design and develop a voice recognition–based door control system using TinyML and deep learning techniques.
• To implement offline voice command recognition on an IoT device for improved privacy and low latency.
• To efficiently filter background noise and improve voice recognition accuracy using TinyML models.
• To control a servo motor for door opening and closing based on recognized voice commands.
• To display the system status and door operation (Open/Close) on an LCD display.
• To utilize Raspberry Pi 4 as the main controller for processing voice commands and device control.
• To create a low-power, cost-effective, and user-friendly smart door automation system.
• To demonstrate the applicability of TinyML in real-time IoT applications such as smart homes and access control systems.

The major building blocks of this project are:

1. Adapter power supply.
2. Raspberry pi 4.
3. SD card.
4. LCD display.
5. Micro phone.
6. Servo Motor.

Software’s used:

• Raspbian OS.
• TinyML and deep learning techniques.

video:

A battery management system (BMS) is proposed which is used for electronic vehicle that manages a rechargeable battery (cell or battery pack), such as by protecting the battery from operating outside its safe operating area, monitoring its state of charging and state of health using Machine Learning algorithm to improve the performance of the designed project.

Machine learning (ML) is the study of algorithms and mathematical models that computer systems use to progressively improve their performance on a specific task. Machine learning algorithms build a mathematical model of sample data, known as “training data”, in order to make predictions or decisions without being explicitly programmed to perform the task.

The Raspberry Pi4 measure the SOC (State-of-Charge) and (SoH) State-of-Health from voltage sensors and based on that it will switch ON/OFF the relays for battery charging. Here relay works as a switch to ON/OFF the charging connection. And also, it will display the voltage, current, temperature, SOC and SOH values on LCD module. It will activate the buzzer if the sensor data exceed threshold value.

The major building blocks of this project are:

• Adapter power supply.
• Raspberry pi4.
• Temperature sensor.
• Voltage sensor.
• Current sensor.
• Buzzer
• Three battery packs
• Three Relays.
• Charging Circuit.
• LCD display.
• LED Indicators

Software’s used in the project:

1. Embedded Linux OS.
2. Python language.
3. Express SCH for Circuit design.
4. Machine learning (ML).

video:

We can even set up this in our home and get alerts for time-to-time changes in climate which would help us in planning our daily work easily. It would be helpful for a farmer in this agricultural activity by which he can protect his crops according to climatic changes. It would help in transportation giving information of weather conditions.

Internet of things, IoT, as an important part of the new generation of information technology, have developed rapidly both in theory and practice since proposed and derived many applications such as smart home, intelligent environmental monitoring. Things not only liberated a lot of manpower, but also achieved a standardized, automated management.

The main aim of this project is to design a smart way of weather monitoring system using cloud storage technology based on wireless Wi-Fi communication and wireless voice alert based on RF technology. The weather parameters are monitored using sensing devices like rain sensor, temperature and humidity sensors. Then the collected data and analysis results will be available to the user through Wi-Fi to the cloud storage and provides thing speak. When the system detects any abnormal condition, it will give the voice alert wirelessly through speaker. The status of the project will display on LCD. This data will be helpful for future references. The smart way to monitor environment this device is an efficient low-cost embedded system.

The major building blocks of this project are:

1. Adapter power supply.
2. Raspberry pi4.
3. DHT22 sensor
4. Rain sensor.
5. LCD display.
6. SD Card.
7. RF transmitter, receiver.

Software’s used in the project:

1. Raspbian OS.
2. Python language.
3. Express SCH for Circuit Design.
4. THINGSPEAK CLOUD.

Block diagram:

video:

Pi camera is used to monitor the drowsiness of driver using machine learning. Alcohol sensor is used for the detection of alcohol consumption by the driver. Ultrasonic sensor is used to detect the obstacle, if any vehicle comes near to his vehicle. Heartbeat sensor is used to monitor the heartrate of the driver. GPS module is used to track the live location of the vehicle in the form of latitude and longitude values. GSM module is used for sending alert SMS and location link to the predefine mobile number, if the heartbeat value crosses the set limit or if the driver consumes alcohol or if the ultrasonic sensor detects obstacle close the vehicle. In this BLDC motor works as a vehicle which is controlled by the Arduino through VSI (Voltage source inverter). In this vehicle accelerator control automatically based on the heartrate of the driver and stop the vehicle automatically if the driver was alcoholic or if the ultrasonic sensor detects obstacle very close the vehicle.

The main controlling device of the project is raspberry pi4 processor. Pi camera attached to the Raspberry Pi processor, it will monitor the person face whether the driver in drowsy or not using machine learning algorithm. The status of the project will display on LCD screen. To achieve this task raspberry pi loaded program written in python language.

The main objectives of the project are:

1. Automatic Drowsiness detection using machine learning.
2. Automatic alcohol detection and ignition control system.
3. Automatic obstacle detection and ignition control system.
4. Automatic driver heartrate detection and SMS alert.
5. GPS based vehicle location tracking system.
6. GSM based SMS alerting system.
7. Pi camera-based driver drowsiness detection.
8. To achieve this using Raspberry Pi4 Processor.

The major building blocks of the project are:

• Power supply.
• Raspberry pi4.
• SD card.
• Pi Camera.
• Arduino UNO.
• Alcohol sensor.
• Ultrasonic sensor.
• Heartbeat sensor.
• GPS Receiver.
• GSM.
• VSI.
• BLDC motor.

Software’s used:

1. Arduino IDE for dumping the code into the Arduino UNO.
2. Raspbian OS.
3. Python language.
4. Machine learning Algorithm.
5. Express SCH for Circuit design.

Block diagram:

video:

[/iframe

The use of green energy is becoming increasingly more important in today’s world. Therefore, electric vehicles are currently the best choice for the environment in terms of public and personal transportation. Because of its high energy and current density, lithium-ion batteries are widely used in electric vehicles. Unfortunately, lithium-ion batteries can be dangerous if they are not operated within their Safety Operation Area (SOA). Therefore, a battery management system (BMS) must be used in every lithium-ion battery, especially for those used in electric vehicles.

A battery management system (BMS) is proposed which is used for electronic vehicle that manages a rechargeable battery (cell or battery pack), such as by protecting the battery from operating outside its safe operating area, monitoring its state of charging and state of health using Machine Learning algorithm to improve the performance of the designed project.

Machine learning (ML) is the study of algorithms and mathematical models that computer systems use to progressively improve their performance on a specific task. Machine learning algorithms build a mathematical model of sample data, known as “training data”, in order to make predictions or decisions without being explicitly programmed to perform the task.

The Raspberry Pi4 measure the SOC (State-of-Charge) and (SoH) State-of-Health from voltage sensors and based on that it will switch ON/OFF the relays for battery charging. Here relay works as a switch to ON/OFF the charging connection. And also it will display the voltage, current, temperature, SOC and SOH values on LCD module. It will activate the buzzer if the sensor data exceed threshold value.

The major building blocks of this project are:

• Adapter power supply.
• Raspberry pi4.
• Temperature sensor.
• Voltage sensor.
• Current sensor.
• Buzzer.
• Three battery packs.
• Three Relays.
• Charging Circuit.
• LCD display.
• LED Indicators.

Software’s used in the project:

1. Embedded Linux OS.
2. Python language.
3. Express SCH for Circuit design.
4. Machine learning (ML).

Block diagram:

 
video:

[/iframe

Connect the camera module to the raspberry Pi’s camera connector using the ribbon cable provided with the camera. When the camera detects the weapon, then raspberry pi will display the message on LCD and activate the Buzzer for alert. In this project we are using two Servo motors for pan and tilt motion purpose, two DC motors are using for zoom and focus purpose. The 16GB SD card is a key part of the Raspberry Pi; it provides the initial storage for the Operating System and files.

• Develop a Real-Time Weapons Detection System: Utilize machine learning algorithms to accurately identify and classify weapons from video feeds captured by PTZ cameras in real-time, enhancing surveillance capabilities.
• Integrate PTZ Camera Capabilities: Leverage the pan, tilt, and zoom functionalities of PTZ cameras to improve the coverage and detail of video monitoring, ensuring comprehensive detection and tracking of potential threats.
• Optimize Processing on Raspberry Pi: Design and implement a solution that runs efficiently on a Raspberry Pi, providing a cost-effective and compact processing unit capable of handling real-time video analysis and decision-making.
• Enhance Tracking Accuracy: Implement advanced tracking algorithms to follow detected weapons as they move within the camera’s field of view, maintaining continuous and precise monitoring.

Components used:

• Adapter.
• Raspberry pi4.
• SD Card.
• PTZ (Pan-Tilt-Zoom) camera.
• Two Servo motors.
• Two DC motors.
• 16*2 LCD display.
• Buzzer.

Software’s used:

1. Raspbian OS.
2. Python language.
3. Artificial intelligence and Machine learning.
4. Express SCH for Circuit design.

video:

Automatic mode: In this proposed system, an automated boat is used to clean down the floating trash. The system has a Pi camera which is attach to the raspberry pi4 and which detects the trash while moving the boat on water surface by using image processing. The automated boat has conveyor belt setup to collect the floating trash and this will have a bin in the boat where the trash will be stored. Once the trash has been filled the IR sensor will detect it. When IR sensor gives out this information automatically the boat will move to the hub with the help of GPS and DIGITAL COMPASS the trash will be thrown over there.

Manual mode: In this mode boat movement along with conveyor belt can be controlling from web browser while seeing the video by using buttons. This robot consists of ultrasonic sensor to detect and avoid the obstacle while moving on the water surface. Once the trash has been filled the IR sensor will detect it. When IR sensor gives out this information automatically the boat will move to the hub with the help of GPS and DIGITAL COMPASS the trash will be thrown over there.

This system will be more advanced as this would collect down the floating trash with the help of the image processing. The main controlling device of the project is Raspberry pi4 processor. To achieve this task raspberry pi loaded program written in python language. The SD card is a key part of the Raspberry Pi3; it provides the initial storage for the Operating System and files. This proposed system uses AI; the CNN improves the image comprehension by learning more discriminative and richer features.

The objectives of the project include:

1. Design an AI and image processing-based garbage collecting boat.
2. It can work in two modes manual and automatic.
3. Usage of Raspberry Pi4 to achieve the task.
4. Using GPS, Digital compass for location tracking.
5. IR sensor-based trash detecting system.
6. Ultrasonic sensor-based obstacle detection and avoidance system.
7. To collect the trash using Conveyor belt setup.

The major building blocks of this project are:

1. Regulated Power Supply
2. Raspberry Pi4.
3. Pi-camera.
4. DC motors.
5. GPS.
6. Pi camera.
7. Digital compass.
8. IR sensor.
9. Ultrasonic sensor.

Software’s used:

1. Python Programming.
2. Artificial Intelligence.
3. Linux operating system.

Block diagram:

video: