IoT-based weighing system to improve baby safety

Abstract

An IoT-based weighing system to increase baby safety, consisting of: an intelligent cradle that has been specially designed and configured to meet the needs of an infant; a microcontroller configured to receive and process data from a variety of sensors and components integrated into the smart charging station; a variety of sensors integrated into the smart cradle and operationally connected to the microcontroller, the variety of sensors including: an infrared temperature sensor for non-contact detection of the infant's body temperature, a microphone sensor for detecting sounds from the infant, a moisture sensor for detecting wetness in a diaper, a gas sensor for detecting the presence of gases and smoke in the environment, and a pulse sensor for monitoring the infant's heart rate; a Wi-Fi module integrated into the microcontroller, configured to transmit the processed data to the cloud server via the internet; a servo motor that is operationally connected to the microcontroller and configured to generate a rocking motion in the cradle, the servo motor being activated by the microcontroller when the microphone sensor detects crying sounds from the infant; a buzzer that is functionally connected to the microcontroller and configured to trigger an audible alarm; a camera module with a webcam configured to capture a live video image of the infant and transmit this live video image via the WLAN module, wherein the camera module is further configured to enable facial recognition and facial identification for the purpose of identifying unauthorized persons, wherein the live webcam feed is retrieved by the microcontroller to perform facial recognition and facial identification, and the microcontroller sends a notification via the cloud server when the webcam detects an unknown face; and a cloud server configured to store the processed data and send notifications to a caregiver's mobile device.

Description

AREA OF INVENTION

[0001] The present disclosure relates to an IoT-based baby crib system for increasing baby safety. More precisely, the invention relates to an automated baby monitoring and care system using IoT technology, and in particular to an intelligent baby crib system with multiple sensors, actuators, and communication modules for real-time monitoring of the infant and automated response mechanisms. BACKGROUND OF THE INVENTION

[0002] The increasing participation of women in the workforce presents modern families with significant challenges in infant care. Because both parents often have to work due to high living costs, simultaneously balancing career and childcare is becoming increasingly difficult. Parents therefore frequently resort to external support such as childminders or grandparents, which can raise concerns about the infant's safety and well-being, particularly regarding risks such as sudden infant death syndrome (SIDS).

[0003] Previous automated baby cradles have attempted to solve these problems through various technological approaches. Early systems, such as the spring-loaded motor cradle invented by Marie R. Harper, generated a simple rocking motion to simulate the mother's rocking. Later developments introduced microcontroller-based systems with ATmega16 controllers, equipped with humidity and temperature sensors, as well as cameras to detect sounds and baby movements. Relay circuits control DC motors that rock the cradle and trigger alarms if the baby cries for an extended period or needs a diaper change.

[0004] Newer IoT-based baby monitoring systems use sensor networks to monitor temperature, humidity, pollutants, and heart rate. They also offer video monitoring and mobile app integration. These systems use NodeMCU controller boards to collect sensor data and transmit it to cloud servers via Wi-Fi, enabling remote monitoring through web portals or mobile apps. Some systems use pressure sensor networks with algorithms to adjust the rocking motion of the crib based on the infant's signals, while others integrate GSM modules for connecting to external devices.

[0005] However, existing systems have several limitations. Many systems are expensive and require significant maintenance, lack comprehensive movement and sleep analysis capabilities necessary for the detection of conditions like sudden infant death syndrome (SIDS), and pose safety risks due to potentially dangerous devices such as fans and heaters near infants. Furthermore, conventional systems often lack integrated solutions that combine comprehensive environmental monitoring, real-time health parameter tracking, intruder detection, and automated response measures into a single, cohesive system.

[0006] There remains a need for a cost-effective, comprehensive infant monitoring system that integrates various sensor modalities with intelligent automated responses, real-time remote monitoring capabilities, and enhanced security features including intruder detection, while addressing the limitations of previous systems. SUMMARY OF THE INVENTION

[0007] This disclosure relates to an IoT-based smart baby crib system for increasing infant safety. The system integrates several sensors, including an infrared temperature sensor, a microphone, a humidity sensor, a gas sensor, and a pulse sensor, with a microcontroller for continuous monitoring of the infant's health parameters and environmental conditions. A Wi-Fi-enabled microcontroller module transmits real-time data to a cloud server, enabling remote monitoring via a mobile app. The system automatically responds to detected conditions: when the baby cries, it activates a servo motor that rocks the crib; an audible alarm sounds if dangerous gases are present; and caregivers are notified if thresholds for temperature, pulse, or humidity are exceeded.A webcam with facial recognition enables live streaming and intruder detection, further enhancing the infant's safety. The system meets the needs of working parents through comprehensive real-time monitoring with automated responses and timely alerts to potential safety risks.

[0008] The present disclosure aims to provide an IoT-based smart baby crib system to enhance infant safety. The system comprises: a smart baby crib designed and configured to hold an infant; a microcontroller that receives and processes data from several sensors and components integrated into the smart baby crib; several sensors integrated into the smart baby crib and connected to the microcontroller, including: an infrared temperature sensor for non-contact measurement of the infant's body temperature, a microphone sensor for detecting sounds from the infant, a moisture sensor for detecting wetness in the diaper, a gas sensor for detecting gases and smoke in the environment, and a pulse sensor for monitoring the infant's heart rate.A Wi-Fi module integrated into the microcontroller for transmitting the processed data to a cloud server via the internet; a servo motor connected to the microcontroller that creates a rocking motion in the baby cradle and is activated by the microcontroller as soon as the microphone sensor detects the infant crying; a buzzer connected to the microcontroller that triggers an audible alarm; a camera module with a webcam that captures live video footage of the infant and transmits it via the Wi-Fi module; the webcam is also equipped for facial recognition and identification to identify unauthorized persons; the microcontroller accesses the live webcam feed to perform facial recognition and identification; the microcontroller sends a notification to the cloud server when the webcam detects an unknown face;and a cloud server that stores the processed data and sends notifications to a caregiver's mobile device.

[0009] The purpose of this disclosure is to provide an IoT-based intelligent weighing system to improve the safety of babies.

[0010] Another objective of this disclosure is to create a safe environment for infants. Using IoT, the device ensures that the baby's environment is continuously monitored, thereby reducing potential hazards. This includes monitoring various factors such as temperature, humidity, heart rate, gases, and noise, with the aim of promoting an environment conducive to the safety and well-being of infants.

[0011] Another goal of this disclosure is to give parents and caregivers the ability to monitor their baby remotely. The system offers convenience and security through immediate access to important baby data. This feature is particularly beneficial for working parents.

[0012] Another objective of the present disclosure is the integration of the system with alarm and notification functions, whereby the parents are notified via the app in case of emergency and the system sends a notification to the parents via the app whenever the sensors or the video camera detect changes that are unfavorable for the baby.

[0013] Another objective of this disclosure is to provide a comfortable, personalized experience. By monitoring sensor data such as temperature, humidity, heart rate, etc., this model optimizes sleeping conditions and promotes sleep quality. These features contribute to increasing the overall performance of the system.

[0014] Another objective of the present disclosure is the detection of intruders using facial recognition. The system utilizes facial recognition technology to detect and identify potential intruders. This function primarily aims to ensure the infant's safety by preventing unauthorized access near the crib.

[0015] To further clarify the advantages and features of the present disclosure, the invention is described in more detail with reference to specific embodiments illustrated in the accompanying drawings. It is understood that these drawings merely show typical embodiments of the invention and are therefore not to be understood as limiting its scope of protection. The invention is described and explained in more detail and with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE IMAGES

[0016] These and other features, aspects and advantages of the present disclosure will be better understood when the following detailed description is read with reference to the accompanying drawings, in which identical symbols represent identical parts, wherein: Fig. Figure 1 shows a block diagram of an IoT-based intelligent weighing system for improving baby safety according to an embodiment of the present disclosure; Fig. Figure 2 shows a block diagram of the proposed intelligent Cardle system according to an embodiment of the present disclosure; and Fig. Figure 3 shows a table with the system components according to one embodiment of the present disclosure.

[0017] Furthermore, those skilled in the art will recognize that the elements in the drawings are simplified and not necessarily drawn to scale. For example, the flowcharts illustrate the process by highlighting the main steps to facilitate understanding of this disclosure. With regard to the construction of the device, one or more components may be represented in the drawings by conventional symbols. The drawings may show only those specific details relevant to understanding the embodiments of this disclosure, so as not to clutter the drawings with details that are already apparent to those skilled in the art from the description contained herein. DETAILED DESCRIPTION:

[0018] To facilitate understanding of the principles of the invention, reference is made below to the embodiment illustrated in the drawings, which is described using specific terms. It is understood, however, that this does not limit the scope of protection of the invention. Rather, modifications and further developments of the illustrated system, as well as further applications of the inventive principles depicted therein, are conceivable, insofar as they would typically occur to a person skilled in the art in the field of the invention.

[0019] It will be clear to those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not to be understood as a limitation of it.

[0020] References to “an aspect”, “another aspect”, or similar phrases in this description mean that a particular feature, structure, or property described in connection with the embodiment is included in at least one embodiment of the present disclosure. Therefore, phrases such as “in one embodiment”, “in another embodiment”, and similar expressions in this description may, but do not necessarily, all refer to the same embodiment.

[0021] The terms "includes," "comprehensive," or similar expressions denote non-exclusive inclusion. Thus, a procedure or method containing a list of steps does not only include those steps but may also include further steps not explicitly listed or inherent in the procedure or method. Likewise, the statement "includes..." for one or more devices, subsystems, elements, structures, or components, without further limitations, does not preclude the existence of other devices, subsystems, elements, structures, or components.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meanings generally known to those skilled in the art in the field to which this invention belongs. The systems, methods, and examples described herein serve only for illustration and are not to be understood as limiting.

[0023] Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0024] The system (100) according to Fig. 1 comprises: a smart baby cradle (102) designed and configured to hold an infant; a microcontroller (104) that receives and processes data from several sensors and components integrated into the smart baby cradle; several sensors (106) integrated into the smart baby cradle (102) and connected to the microcontroller (104), the sensors (106) comprising: an infrared temperature sensor (106a) for non-contact measurement of the infant's body temperature, a microphone sensor (106b) for detecting sounds from the infant, a moisture sensor (106c) for measuring wetness in the diaper, a gas sensor (106d) for detecting gases and smoke in the environment, and a pulse sensor (106e) for monitoring the infant's heart rate; a WLAN module (108) integrated into the microcontroller (104) for transmitting the processed data to the cloud server via the Internet.A servo motor (110), connected to the microcontroller (104), which generates a rocking motion in the cradle, is activated by the microcontroller (104) as soon as the microphone sensor (106b) detects the infant crying. A buzzer (112), also connected to the microcontroller (104), generates an audible alarm. A camera module (114) with a webcam captures a live video of the infant and transmits it via Wi-Fi. The camera module (114) also serves for facial recognition and identification to identify unauthorized persons. The microcontroller (104) accesses the live webcam image to perform facial recognition and identification and sends a notification to the cloud server as soon as the webcam detects an unknown face. A cloud server (116) stores the processed data and sends notifications to a caregiver's mobile device.

[0025] In one embodiment, the microcontroller (104) is configured as a central processing unit for controlling and coordinating the operations of the various sensors (106), the servo motor (110), the buzzer (112), and the WLAN module (108). The microcontroller (104) activates the servo motor to rock the cradle as soon as the microphone sensor detects the infant crying. Furthermore, the microcontroller sends a notification to the cloud server when the humidity sensor detects wetness.

[0026] It also activates the buzzer and sends a notification to the cloud server as soon as the gas sensor detects gases or smoke. Similarly, if the infrared temperature sensor measures a body temperature above a predefined threshold, the microcontroller sends a notification to the cloud server. Finally, it sends a notification to the cloud server when the pulse rate sensor measures a heart rate above a predefined upper or below a predefined lower threshold.

[0027] In one embodiment, the Wi-Fi module (108) is configured to establish serial communication with the microcontroller (104) and to transmit sensor data and a video stream to the cloud server via a wireless internet connection.

[0028] In one embodiment, the predetermined temperature threshold is one hundred degrees Fahrenheit, the upper predetermined pulse rate threshold is one hundred sixty beats per minute, and the lower predetermined pulse rate threshold is eighty beats per minute.

[0029] In one embodiment, the microphone sensor (106b) is configured to convert sound into electrical signals. The microcontroller (104) is configured to analyze the electrical signals to detect the presence of crying sounds. Once crying sounds are detected, the microcontroller (104) sends a control signal to the servo motor (110) to generate rhythmic rocking movements in the cradle.

[0030] In one embodiment, the pulse rate sensor (106e) is configured to detect the pulse rate by emitting infrared wavelengths; the pulse rate sensor (106e) is configured to detect changes in the infant's blood flow; and the pulse rate sensor (106e) is configured to continuously transmit pulse rate data to the microcontroller (104) for monitoring and analysis.

[0031] In one embodiment, the camera module (114) is configured to continuously transmit a live video stream, the webcam being positioned to capture visual data of an area around the charging cradle, the microcontroller (104) further being configured to execute a face detection and identification algorithm to detect facial areas in the captured images, the face detection and identification algorithm being configured to compare detected faces with stored authorized faces by pixel matching through grayscale, and the system being configured to send a notification if the detected face does not match any stored authorized face.

[0032] In one embodiment, the system (100) further comprises a user interface (118) configured for execution on the caregiver's mobile device; wherein the user interface (118) is configured to receive and display real-time sensor data from the cloud server (116), wherein the user interface (118) is configured to receive and display the live video stream from the webcam, wherein the user interface (118) is configured to receive and display notifications from the cloud server, and wherein the caregiver is enabled to remotely monitor the infant's environmental conditions and health parameters via the mobile application.

[0033] In one embodiment, notifications are additionally sent to the caregiver via email, and the system is configured to provide real-time remote monitoring functions that allow the caregiver to view sensor data and environmental conditions at any time via a network connection.

[0034] The present invention relates to an automated baby monitoring and care system using Internet of Things (IoT) technology, in particular an intelligent cradle system with multiple sensors, actuators, and communication modules for real-time monitoring of the infant and automated response mechanisms. The cradle care system consists of a baby cradle with an Arduino Mega microcontroller as the central control unit, which is connected to several sensors for comprehensive monitoring of the infant. An infrared temperature sensor (MLX90614) measures body temperature without contact, while a microphone sensor (LM393) detects crying. A rain sensor (FC37) measures diaper wetness, a gas sensor detects harmful gases and smoke, and a pulse sensor monitors the heart rate. A servo motor (SG90) generates soothing rocking motions when the infant cries, while a buzzer triggers audible alarms.A NodeMCU module (ESP8266) enables the Wi-Fi connection for data transmission to a Blynk cloud server. A webcam continuously streams live video and uses facial recognition algorithms (Python) to identify unauthorized individuals. The system notifies parents via app and email as soon as measurements exceed predefined thresholds or safety concerns arise. This provides working parents with comprehensive remote monitoring capabilities and the peace of mind that their infant is doing well.

[0035] The intelligent baby crib system was developed to ensure the baby's well-being and create a safe environment. It consists of sensors, actuators, and communication modules integrated into the crib. The system aims to provide the baby with security and comfort, relieving working parents of worry about their child. The system utilizes various sensors and actuators that ensure seamless communication with the server. These include temperature, gas, pulse, microphone, and humidity sensors. The sensors continuously detect and monitor the baby's condition. In the event of abnormalities such as elevated temperature, gas or smoke exposure, crying, increased pulse, or a wet diaper, a notification is immediately sent to the parents or caregivers via the app and email. Additionally, the system offers real-time monitoring of all sensor data, allowing parents to view it at any time in the app.In addition, the system features live streaming and facial recognition, which detects whether an intruder is near the baby car seat and sends a notification via app and email if an unknown face is detected. This feature increases the system's security.

[0036] In relation to Fig. 2. The most important components and features of the system are described as follows: 1. Sensors: The following sensors are used: MLX 90614 (infrared temperature sensor), microphone sensor (LM393), rain sensor (FC37) and others. They serve to monitor the baby's environment based on noise levels, temperature and other data to ensure its comfort and well-being. 2. Remote monitoring: Remote monitoring helps parents or caregivers to check their baby's condition from a distance; it is easy to read the baby's temperature, the humidity in the crib, and other environmental factors. 3. Warning system: An alarm system also intervenes in emergencies such as gas leaks or drastic changes in the health of infants. Using notifications, it can send alarms via voice output to a mobile device – this way, caregivers near the child are quickly informed and can react accordingly. 4. A personalized and comfortable experience: The goal of a personalized and comfortable experience is to improve the overall health of infants in the crib by observing environmental factors. 5. Central Processing Unit: The Arduino Mega acts as the central processing unit and is responsible for managing and coordinating sensors, actuators and communication modules, processing the collected data and controlling the system's response. 6. Wi-Fi and video functions: The system communicates with the cloud server via the Internet using NodeMCU (ESP8266). 7. Actuators: The system has a servo motor (SG90) for mechanical movements such as rocking the cradle when the baby cries, as well as a buzzer that triggers an alarm in case of defects.

[0037] As in Fig. 2 and Fig.As shown in Figure 3, the system consists of several key components that work together in a coordinated manner to ensure comprehensive monitoring and care of the infant. A microphone sensor detects sounds such as a baby crying and triggers specific actions upon detection. A gas sensor detects the presence of certain gases, such as liquefied petroleum gas (LPG) or other potentially harmful gases, as well as smoke in the environment. A moisture sensor detects moisture, typically caused by a diaper. An infrared temperature sensor measures the baby's body temperature without contact. A pulse sensor monitors the baby's heart rate and provides valuable health information via the app. Servo motors enable reliable and programmable movement of the smart baby cradle, thus contributing to the baby's comfort and restful sleep. A webcam is used for facial recognition to detect intruders.The system captures images or video sequences, analyzes them to detect unauthorized individuals, and triggers appropriate actions, such as notifying parents via the app if an intruder is present. A webcam with live streaming allows caregivers and parents to monitor the baby in real time via video transmission. A Wi-Fi-enabled microcontroller in the smart baby cradle enables wireless communication (serial interface) and connectivity. This allows the cradle to interact with other devices, services, or platforms via a local network or the internet. The microcontroller is the central processing unit of the smart baby cradle and controls various components and desired functions. It acts as the brain of the system, receiving input from sensors, processing data, making decisions, and controlling outputs.

[0038] The implementation begins with initializing the Arduino Mega. The microphone sensor detects the baby's sounds or cries and converts them into electrical signals. The servo motor receives feedback from these electrical signals and generates rhythmic movements in the crib, simulating the soothing movements of a caregiver. The wetness sensor detects moisture in the diaper and sends signals. The data is collected and sent to the Blynk server via Wi-Fi (ESP8266 NodeMCU). The gas sensor detects gases, and the speaker receives the signals and emits an alarm. Simultaneously, the data is collected, stored, and sent to the server, which notifies the parents via their device / app. If the temperature at the infrared temperature sensor rises above 100°F (37.8°C), the microcontroller sends a notification to the parents.The pulse sensor measures the pulse rate using the infrared radiation it emits and detects changes in blood flow. The data is collected and only transmitted to the parents if the measured pulse rate is above 160 or below 80 beats per minute. The webcam, which records the live feed, allows parents to monitor their baby via Wi-Fi (ESP8266 NodeMCU) using a live stream. It detects the baby's face and compares it to the faces stored in the system using a facial recognition algorithm and grayscale pixel matching. If there is no match, a notification is sent to the parents' device. All data collected by the sensors is stored on the Blynk server and can be viewed by parents on their devices via the Blynk app.

[0039] In a preferred embodiment, the system uses an Arduino Mega microcontroller based on the ATmega2560. This provides 54 digital inputs / outputs, 14 of which can be used as PWM outputs, 16 analog inputs, 4 UARTs (hardware interfaces), and a 16 MHz crystal oscillator. The infrared temperature sensor is factory calibrated for a temperature range of -40 to +125 °C (sensor temperature) and -70 to +380 °C (object temperature). It operates in a temperature range of 0 to 70 °C, offers high accuracy of 0.5 °C over a wide temperature range (±50 °C for both), and has high medical-grade accuracy. The supply voltage is +5 V DC, the typical current consumption is 20 mA, and 5 mA in sleep mode. The LM393 microphone sensor operates with a supply voltage of 3.3-5 V DC and a supply current of 4-5 mA. Its microphone sensitivity (1 kHz) is between 52 and 48 dB.It features a digital output, a single-channel signal output, and emits a low-level signal with an LED indicator when noise is detected. The MQ-135 gas sensor operates at +5 V and measures and detects ammonia (NH3), alcohol, nitrogen oxides (NOx), benzene, carbon monoxide (CO2), and smoke. It offers an analog output voltage range of 0-5 V, a digital output voltage range of 0-5 V (TTL logic), a heating voltage of 5 V ± 0.1 V, a measurement range of 10-1000 ppm (ammonia, toluene, hydrogen, smoke), a heating power consumption of less than 800 mW, and an operating temperature range of -10 °C to -45 °C. The FC37 rain sensor operates at a voltage of 3.3 V to 5 V and an output current of 15 mA. Sensitivity is adjustable via a potentiometer. It has two output modes: analog and digital. A red LED serves as an operating indicator, a green LED indicates the digital switching status.The pulse sensor is a heartbeat and biometric pulse sensor with an operating voltage range of +5 V or +3.3 V. It can be used as a plug-and-play sensor with a current consumption of 4 mA. The SG90 servo motor offers a torque of 2.0 kg / cm at 4.8 V and 2.2 kg / cm at 6 V, a speed of 0.09 s / 60° at 4.8 V and 0.08 s / 60° at 6 V, a rotation angle of 180°, an operating voltage of 4.8 to 6 V, a dead time of 7 µs, and a weight of 10.5 g. The NodeMcu ESP8266 features a Tensilica 32-bit RISC CPU Xtensa LX106 microcontroller, an operating voltage of 3.3 V, an input voltage of 7-12 V, 16 digital I / O pins, 1 analog input pin, 1 UART, 1 SPI, 1 I2C, 4 MB flash memory, 64 KB SRAM, a clock frequency of 80 MHz and includes USB-TTL based on CP2102 on the board, enabling plug-and-play.

[0040] In one implementation, the algorithm for the Arduino code begins with initialization. This includes including the necessary libraries, declaring global variables and constants, initializing sensor objects and assigning pins, as well as setting thresholds for rain detection, water detection, and LPG concentration. During setup, the system initiates serial communication at the specified baud rate, initializes the sensors and configures their settings, sets the pin modes for sensor inputs and actuator outputs, and allows a short delay for sensor stabilization. The main loop runs continuously, reading the ambient and object temperatures from the temperature sensor and outputting the object temperature in Fahrenheit. It reads the value from the rain sensor and triggers appropriate actions when it falls below the rain threshold.It reads the value from the sound sensor and moves the servo motor to simulate crying when the sound exceeds the threshold. It reads the value from the LPG sensor to calculate the LPG concentration in ppm and output the result. Simultaneously, a buzzer is activated to indicate a gas leak if the threshold is exceeded. It reads the value from the pulse sensor to assign it to the heart rate range and output the heart rate value. Appropriate delays are inserted between sensor measurements and actions, ensuring the system operates continuously, monitoring environmental conditions and responding to events. The algorithm for communication with the Blynk server and data transfer to the app begins with initialization by defining the Blynk settings and sensor thresholds. During setup, serial and Blynk communication are initiated.The main loop continuously checks incoming sensor data via SoftwareSerial, processes it based on the sensor identifier ("b" for pulse, "w" for water, "g" for gas, "s" for sound, "t" for temperature), and sends the sensor data to Blynk's virtual pins. When a threshold is exceeded, an event with the corresponding label is logged. The system operates continuously, monitoring the sensors and reacting to events. The facial recognition algorithm consists of three main phases. During initialization and data acquisition, the camera is initialized for video recording, the video image dimensions are set, the Haar cascade classifier is loaded for facial recognition, the user is prompted to enter a unique numeric user ID, and the number of detected faces is reset to zero.The system runs in a loop, capturing a video image, flipping it vertically, converting it to grayscale, detecting faces within the grayscale image, and incrementing the face count for each detected face. The captured face image is then saved in the "dataset / " directory with a unique filename based on the user ID and the count. The loop continues until the user terminates the program or a certain number of faces have been captured. Afterward, the camera is released, and all OpenCV windows are closed. During face training, face images and labels (user IDs) are retrieved from the "dataset / " directory. The system processes each face image, converts it to grayscale, detects faces within the grayscale image, and extracts the facial area for each detected face. This area, along with the corresponding label, is added to the training data.The LBPH face recognizer is trained using the training data, and the trained model is saved as "trainer.yml" in the "trainer / " directory. For real-time face and intruder detection, the LBPH face recognizer is initialized, and the trained model is loaded from the "trainer / " directory. The Haar Cascade classifier is loaded for face recognition, the minimum window size for face recognition is defined, the font for text display is initialized, known usernames and the labeling of unknown faces (intruders) are specified, and video recording is initialized. The system then runs a loop in which it records video frames, converts them to grayscale images, detects faces in the grayscale images, and identifies each detected face using the trained model.If the confidence level is within a certain range, the detected user ID is displayed; if it is below that range, the face is flagged as an intruder. The video stream is displayed with the detected faces and the intruder markings. This loop continues until the user terminates the system. Afterward, the camera is unlocked and all OpenCV windows are closed.

[0041] In one embodiment, the system comprises two microcontrollers, namely an Arduino Mega and a NodeMCU (ESP8266), which are connected in series to run the overall system. The present invention aims to improve the care of infants whose parents are employed and who are cared for by a caregiver. The system is helpful for monitoring the baby's care and observing it remotely. The Arduino Mega receives data from the sensors and controls the actuators accordingly. The sensor values ​​are transmitted to the Blynk app via a cloud server using NodeMCU. If anomalies or abrupt changes in the sensor values ​​above a certain threshold are detected, the system triggers an action and sends a notification via the Blynk app as well as an email to the parents' smartphone. This occurs according to code written in the Arduino and NodeMCU development environments.Upon receiving the notifications, parents or caregivers can take the necessary measures.

[0042] The system consists of a complete model with integrated sensors, actuators, and facial recognition. Program output can be monitored in the Arduino's serial monitor. The mobile app displays sensor readings and includes a notification panel for alerts. If gas or smoke is detected near the baby's crib, or if the baby cries, the system notifies the parents via a pop-up in the app. The same notification mechanism is used for elevated temperature, increased heart rate, or a wet diaper. Since a microphone sensor is used, an alert is issued via email and notification if a certain ambient noise level is exceeded. If the alert persists, it indicates the baby is crying; otherwise, it's just ambient noise. This limitation can be overcome with speech recognition, making the project more efficient. Intruder detection via facial recognition is implemented in Python.The system offers a continuous live stream of the baby on a website. If a face is detected that does not match the existing database of faces, the system displays a message "Unknown Face", captures the face, and sends the image via a Telegram cradle bot.

[0043] Prices for available automatic baby cradles range from approximately 9,000 to 16,000 rupees, while the IoT-based weighing system with advanced features costs around 8,500 rupees. In an age of advanced technologies in infant care, this system offers premium features such as facial recognition and IoT. The implementation of cutting-edge technology, including the integration of a webcam with facial recognition, an Arduino Mega, and a NodeMCU ESP8266 for system control, requires a careful cost-benefit analysis. The hardware and component costs total 8,500 rupees, whereas conventional baby cradles with only basic or no features cost between 9,000 and 16,000 rupees. While conventional cradles offer only basic functionality, this solution not only ensures the safety of infants but also represents a cost-effective alternative in the long run.

[0044] The system can advance the healthcare sector, as parents can remotely monitor their baby's health from anywhere via the internet. Should an anomaly or unfavorable situation occur, the system's integrated alarm mechanism will alert the parents, who can then inform their caregiver of their concerns.

[0045] In one implementation, various improvements can be made to the system and the app to make them more user-friendly and efficient. A lullaby player can be integrated to soothe the crying baby and promote better sleep, as music significantly influences the infant's mood and well-being. A speaker can be used for this purpose. Speech recognition technology can enhance the system by recognizing only the baby's cries and not any noises near the crib. This way, parents are only notified when the baby is actually crying. The app can be optimized using platforms like Android Studio to provide a more user-friendly interface and easy access to monitoring the baby and its health data.Facial recognition and identification can be improved through technological advancements and algorithm optimization to ensure security. Future technological developments can make this project even more user-friendly, accurate, and efficient.

[0046] The drawings and the preceding description illustrate embodiments. Those skilled in the art will recognize that one or more of the described elements can be combined to form a single functional element. Alternatively, certain elements can be divided into several functional elements. Elements of one embodiment can be added to another. For example, the process flows described here can be modified and are not limited to the manner described herein.

[0047] Furthermore, the actions in a flowchart do not have to be performed in the sequence shown; nor do all actions necessarily have to be carried out. Actions that are independent of other actions can be performed in parallel. The scope of protection for the embodiments is in no way limited by these specific examples. Numerous variations, whether explicitly stated in the description or not, such as differences in structure, dimensions, and materials, are possible. The scope of protection for the embodiments is at least as comprehensive as described by the following claims.

[0048] The advantages, other benefits, and problem solutions have been described above with reference to specific embodiments. However, the advantages, benefits, problem solutions, and any components that can effect or enhance an advantage, benefit, or solution are not to be construed as critical, necessary, or essential features or components of the claims. REFERENCES 100 Block Diagram of an IoT-Based Intelligent Cradle System to Improve the Safety of Babies. 102 Intelligent Cradle 104 microcontrollers 106 Variety of Sensors 106a Infrared temperature sensor 106b microphone sensor 106c humidity sensor 106d gas sensor 106e Pulse Rate Sensor 108 Wi-Fi module 110 servo motor 112 Summer 114 Camera module 116 cloud servers 118 User interface 202 Sensor module 204 microphone sensor 206 Gas sensor 208 Humidity sensor 210 Temperature sensor 212 Heart rate sensor 214 microcontrollers 216 WLAN module 218 Webcam for Face Recognition and Live Streaming 220 cloud servers 222 Mobile device 222a Intelligent application 224 servo motor

Claims

[1] An IoT-based weighing system to increase baby safety, consisting of: an intelligent cradle that has been specially designed and configured to meet the needs of an infant; a microcontroller configured to receive and process data from a variety of sensors and components integrated into the smart charging station; a variety of sensors integrated into the smart cradle and operationally connected to the microcontroller, the variety of sensors including: an infrared temperature sensor for non-contact detection of the infant's body temperature, a microphone sensor for detecting sounds from the infant, a moisture sensor for detecting wetness in a diaper, a gas sensor for detecting the presence of gases and smoke in the environment, and a pulse sensor for monitoring the infant's heart rate; a Wi-Fi module integrated into the microcontroller, configured to transmit the processed data to the cloud server via the internet; a servo motor that is operationally connected to the microcontroller and configured to generate a rocking motion in the cradle, with the servo motor being activated by the microcontroller when the microphone sensor detects crying sounds from the infant; a buzzer that is functionally connected to the microcontroller and configured to trigger an audible alarm; a camera module with a webcam configured to capture a live video image of the infant and transmit this live video image via the WLAN module, wherein the camera module is further configured to enable facial recognition and facial identification for the purpose of identifying unauthorized persons, wherein the live webcam feed is retrieved by the microcontroller to perform facial recognition and facial identification, and the microcontroller sends a notification via the cloud server when the webcam detects an unknown face; and a cloud server configured to store the processed data and send notifications to a caregiver's mobile device. [2] System according to claim 1, wherein the microcontroller is configured as a central processing unit for controlling and coordinating the operations of the multiple sensors, the servo motor, the buzzer, and the Wi-Fi module, wherein the microcontroller is configured to activate the servo motor to rock the cradle when the microphone sensor detects the infant crying, wherein the microcontroller is further configured to send a notification via the cloud server when the humidity sensor detects wetness, wherein the microcontroller is further configured to activate the buzzer and send a notification via the cloud server when the gas sensor detects the presence of gases or smoke, wherein the microcontroller is further configured to send a notification via the cloud server when the infrared temperature sensor detects a body temperature above a predetermined temperature threshold.the microcontroller is further configured to send a notification via the cloud server when the pulse rate sensor detects a heart rate above a predefined upper pulse rate threshold or below a predefined lower pulse rate threshold. [3] System according to claims 1 and 2, wherein the Wi-Fi module is configured to establish serial communication with the microcontroller and to transmit sensor data and a video stream to the cloud server via a wireless internet connection. [4] System according to claim 2, wherein the predetermined temperature threshold is one hundred degrees Fahrenheit; the upper predetermined pulse rate threshold is one hundred sixty beats per minute; and the lower predetermined pulse rate threshold is eighty beats per minute. [5] System according to claims 1 and 2, wherein the microphone sensor is configured to convert sound into electrical signals; the microcontroller is configured to analyze the electrical signals to detect the presence of wine sounds; and after detecting wine sounds, is configured to send a control signal to the servo motor to generate rhythmic rocking movements in the cradle. [6] System according to claims 1 and 2, wherein the pulse sensor is configured to detect the pulse rate by emitting infrared wavelengths; the pulse sensor is configured to detect changes in the infant's blood flow; and the pulse sensor is configured to continuously transmit pulse rate data to the microcontroller for monitoring and analysis. [7] System according to claim 1, wherein the webcam is configured to continuously transmit a live video stream, wherein the webcam is positioned to capture visual data of an area around the charging cradle, wherein the microcontroller is further configured to execute a face detection and identification algorithm to detect facial areas in the captured images, wherein the face detection and identification algorithm is configured to compare detected faces with stored authorized faces by pixel matching through grayscale, and wherein the system is configured to send a notification when the detected face does not match any stored authorized face. [8] The system according to claim 1 further comprises: a user interface configured for execution on the caregiver's mobile device; wherein the user interface is configured to receive and display real-time sensor data from the cloud server; the user interface is configured to receive and display the live video stream from the webcam; the user interface is configured to receive and display notifications from the cloud server; and enables the caregiver to remotely monitor the environmental conditions and health parameters of the infant via the mobile application. [9] System according to claim 1, wherein the notifications are additionally transmitted to the caregiver via e-mail; and the system is configured to provide real-time remote monitoring functions that allow the caregiver to view sensor data and environmental conditions at any time via a network connection.

Images