Illuminance imaging based on lux sensor measurements has emerged as an effective alternative to camera-based methods, particularly in environments where optical imaging is impractical or limited. Converting lux data into illumination images provides a lightweight means of visualizing spatial lighting patterns; however, reliably classifying these images remains challenging due to variations in indoor geometry, sensor motion, and non-uniform lighting conditions. These factors often reduce the accuracy of conventional similarity or distance-based classification approaches. This study investigates 2 histogram-driven techniques for classifying real-time illumination images: the histogram intersection method and the histogram Euclidean distance method. A wireless sensing platform was developed by integrating an illuminance sensor with an infrared transceiver and a microcontroller communicating via the I-2 C protocol. As RF-operated mobile unit traversed the indoor test environment, continuous lux measurements were acquired and converted into grayscale illumination images for subsequent analysis. A comparative performance assessment demonstrates that the histogram Euclidean distance method delivers higher classification accuracy and greater consistency than the Histogram Intersection approach. The results highlight the potential of histogram-based lux-to-image classification as an efficient tool for real-time illuminance assessment and support its broader applicability to smart lighting, indoor monitoring, and energy-aware lighting control systems.

We present a cutting-edge illumination monitoring system based on IoT technology. This innovative mobile system allows users to accurately measure sensor values at multiple positions within an indoor space, which are then securely stored in a cloud server network. To achieve this, we developed a sophisticated sensing unit that combines RGB sensor for lux data determination and infrared (IR) transceiver for precise position detection interfaced with embedded microcontroller that features an on-chip WiFi device. This entire setup is mounted on a radio-frequency (RF)-remote-operated car, which serves as mobile platform for data collection. As the car moves throughout the selected indoor space, it collects positional RGB values at specific intervals. These measurements are converted into lux data and then sent to the cloud server via a wireless-transceiver system. By leveraging the power of cloud computing, collected data is securely stored and accessible for further processing. The stored illuminance are utilized to generate a comprehensive light map, providing a visual representation of illumination distribution across the indoor space. This light map serves as a valuable reference for comparison with predefined benchmarks. By analyzing disparities between the measured lighting values and the benchmarks, intelligent insights are derived. These perceptions form the basis for making informed decisions regarding the modification and improvement of existing lighting system. By identifying the areas of inadequate lighting, appropriate adjustments can be implemented to optimize the lighting conditions and enhance the overall user experience and comfort. The novelty of this paper is in its attempt to merge multimodal sensory data with application-specific models, showcasing a perspective to tackle mobility inferencing problems in illumination and CCT monitoring

Correlated Color Temperature (CCT) is an important parameter to determine the quality of lighting in an indoor space. We have presented here the calibration of RGB sensor for estimation of real-time CCT values using Support Vector Machine Regression, General Regression Neural Network, and Gaussian Process Regression techniques. Further, comparative performance assessment have been done on the evaluating parameters: Percentage Absolute Error, R-Squared Error, Mean Absolute Error, Mean Absolute Percentage Error, and Root Mean Squared Error with respect to a calibrated meter. The RGB values have been acquired from a sensor interfaced with a microcontroller and the CCT data are simultaneously observed from a calibrated chroma meter at the client terminal. The machine learning regression techniques have been applied at the server terminal to find out the CCT values and a comparative performance analysis have been done to find the best possible prediction model that can be compared to a standard meter based on the performance indices to decide on their accuracy.

Computer vision methods are conventionally used for identification of object boundaries from an image of interest. Here, it has been performed extensive performance analysis of computer vision techniques for detection of objects present in a room from the acquired real-time lux sensor data. A server-client wireless network is initially set up to capture horizontal lux data of a room using unmanned surface vehicle. The client unit comprises of light intensity sensor and IR transceiver module for capturing the positional lux information of an indoor space. The sensing block is interfaced with a wireless enabled microcontroller and it transmits the sensor values to a sever unit with the help of a wireless router. Now, the obtained values are stored in a computer system working as server module. The acquired real-time positional lux data are converted into image and different computer vision techniques e.g. Canny method, Prewitt method, Sobel method, and Laplacian of Gaussian method have been used to detect the possible position and object shape in the indoor space. Comparative assessment based on performance indices like recall, precision, and  F1 value has been carried out to find out the most acceptable solution.

Illuminance measurement is a salient feature to evaluate the quality of lighting and its precise measurement using appropriate sensor is of utmost importance for any real-time scenario. Here we present, the estimation of lux value on the acquired dataset using different types of machine learning regression models viz. Multiple Linear Regression, Support Vector Machine Regression, General Regression Neural Network, and Gaussian Process Regression. We have carried out extensive comparative performance assessment of the evaluating parameters: Percentage Absolute Error, R-Squared Error, Mean Absolute Error, Mean Absolute Percentage Error, and Root Mean Squared Error to predict the illuminance values with respect to a calibrated meter. The RGB values are obtained from a sensor that is integrated with a microcontroller and the lux data are obtained from a standard chroma meter at the client end. Now, the RGB data are transmitted in a wireless network and four different types of machine learning regression techniques are applied at the server end for proper estimation of the illuminance values. Thus, an accurate RGB sensor model is developed that can predict the lux values and also comparable to a standard lux meter. Gaussian Process Regression has given the best possible response for prediction of illuminance values in comparison with other regression methods on a real-time captured dataset.

In this paper, it has been proposed a method to detect similarity level of lux images from a real-time captured dataset using a wireless server–client network arrangement. An illuminance sensor is interfaced with an embedded wireless microcontroller, which is considered to be the client terminal. This entire system is kept at the top of a remote car; while traversing through the selected floor space, it acquires lux values of that place, transmit and save them in a computer system, which is considered as the server terminal. The process is repeated to capture multiple training data, and at the server end, each data is converted into a grayscale illuminance image, possessing spatial pixel intensity for each instance in pre-processing phase. Now, when a test image arrives, it is compared for resemblance with a training image using eigenface method by calculating their pixel proximities. This computation generates a feature value, which can be used as a comparison metric. For an unknown or test image, if this feature value is very small, then it is understood to be in close proximity with the concerned training image, but if the feature value is comparatively high, then it is considered to have the least proximity with the respective training image.

In any electrical or electronic systems, unwanted signals known as noise signals are encountered which interact with the true signal and thus affecting signal quality. Noise may enter into a device or system in many forms and have a different order of impacts. Prevention and elimination of noise had attained paramount importance to ensure signal fidelity. This chapter presents a comprehensive analysis on elimination of noise by electronic grounding of instrumentation and automation systems as well as various engineering considerations for the same.

The device handling complexity increases by integration of more functionality into Human–Machine Interface. The use of different sensory channels of human simplifies the interaction with in-car devices. Robots are playing a big role in our daily lives. The existing techniques to control these robots are by using a keyboard, joystick, or pre-programmed commands. This paper introduces a new way to control a robot by using the gestures of a human being. A robot-car is developed which is controlled by the gesture commands provided to the Raspberry Pi controller. The model has two components a car and a control station. The control station is computer that has gesture recognition hardware so that it can detect the commands and send them to the car. The control station is the microcomputer Raspberry Pi model 3B. The data from the hand movements acquired from the accelerometer sensor are fed to the motor driver L293D through the Raspberry Pi, which converts electrical energy to mechanical energy to drive the robot-car.

The novel coronavirus (COVID-19) infection had spread throughout the globe since the beginning of 2020 giving rise to a pandemic situation. In this paper, attempts have been made to model the COVID-19 infection in India using exponential, logistic and Gompertz-based mathematical machine learning regression models. These predictive methods show an excellent fit with the daily count of confirmed cases for the period between January 30, 2020, and February 3, 2021. The mean squared logarithmic error (MSLE) of the Gompertz model being lowest among the three machine learning regression methods considered in this paper making it ideal at least as a case study for future predictions in Indian scenario. Nevertheless, the epidemiologists, healthcare personnel, or other Government authorities may use this study as a reference for future planning in prevention of such pandemic situation in similar developing nations.

This paper deals with biological and health impact on public caused by artificial light.The primary aim of a lighting layout is to provide efficient light for visual phenomenon.On the other hand, non-visual functions integrate and control our organic activities like circadian rhythm, myosis, melatonin secretion, intellectual ability, memory, temper and locomotion, to name a few.The use of light emitting diodes has significant impact on our biological processes and photodynamic therapy instead of metal-halide luminaries or compact fluorescent bulbs.The considerations for sports lighting, hospital lighting and photonics for affordable health-care along with the health hazards of artificial lighting have been discussed to strive for a healthy human life.

The present work proposes an experimental technique to classify the illuminance images after acquisition from a lux sensor interfaced with Wi-Fi-enabled microcontroller and placed over the roof of a remote operated car in a client–server wireless network configuration. The illuminance images thus generated experimentally are analyzed using image processing technique for evaluation of its illumination level in comparison with standard lux images. In the preprocessing stage, the captured illuminance images are converted into gray-scale form having spatial pixel intensity. Then, they are normalized and the Eigenface is detected for both training as well as testing image. The feature value of the Eigenface is used to find the composite distance. PCA based Eigenface method projects the large-dimensional image space into lesser dimensional image space by finding their principal components. Eigenface can calculate the proximity of neighboring pixels between training and testing images. The difference in composite distance is found out to check the similarity between the known Eigenface and test Eigenface obtained from the image formed by the captured illuminance data.

With the development of advanced technologies in the field of robotics and computer vision, real time image processing has become a very popular tool. The paper aims at using the RaspberryPi camera along with suitable machine learning algorithms to perform face detection and face recognition for security purpose. This paper portrays machine-learning approach for face recognition with high identification rates using Intel’s open source framework called OpenCV (Open Source Computer Vision) library in python programming language. RaspberryPi-cam is used to capture picture of the faces that are to be stored in the database in the form of grayscale and colored image. This is a three-stage process namely, face detection, data gathering, and face recognition, which will match the live faces with facial pictures stored in the database and give us identification details of the person under consideration. If the matching index is 45% or more then only the face will be recognized properly. Here, Haar-Cascade algorithm is used and this whole setup is successfully demonstrated using a RaspberryPi model 3B hardware setup. Based on successful face recognition, a miniature door will open and the security of the system will be ensured. Whereas, if the face matching index is below the threshold, then the face is not to be identified and the door will remain closed. This is a real-time implementation of smart security application using RaspberryPi.

In this study, an IoT based system is developed to monitor obstacles at the indoor surface using mobile sensors in a client-server wireless network. An IR transceiver system gives the positional information and light intensity sensor measures the lux values. An embedded wifi enabled microcontroller is interfaced with the sensors and performs as the client system. The client module is placed over the roof of a car and when it moves through a particular indoor space, it collects the positional illumination data and transmit them to the server unit. The captured sensor values are stored in server laptop as MS-Excel file under the influence of a wifi router. By using offline processing, the real-time sensor data is converted into an image and filtering methods are applied for linear and nonlinear noise removal. Then, edge detection techniques like Canny, Prewitt, Sobel, and Roberts methods are applied to detect the presence of obstacles. The study is repeated for another room to find out the best possible obstacle identification method. Finally, it was concluded that the Canny’s algorithm provides the most accurate identification of static obstacles for both the rooms.

This study presents an IoT-based illumination monitoring system, which enables the users to measure lux values at multipositional indoor space using mobile sensors and store them in a cloud server network. The sensing unit is designed by the integration of an illumination sensor and IR transceiver for position detection with embedded microcontroller having on-chip Wi-Fi device placed over RF-operated car. The car when moves through a selected indoor space gathers positional lux values at certain time interval and stores them on the cloud server through a wireless transceiver system. The stored values are used to generate a lux map, which is compared with the benchmark, and the result of comparison is considered to be intelligent information for modification of the existing illumination system.

In the present work, a novel experimental method has been explored for monitoring of illuminance values at different parts in indoor space using mobile sensor system connected to wi-fi enabled microcontroller in server-client network configuration. The mobile sensor system is built by integrating gyro-accelerometer and lux sensors connected to an embedded controller having on chip wi-fi unit. The sensor system is mounted on remote controlled vehicle/car, the movement of which is guided and controlled by RF operated remote key pad. The car can manoeuvre through various positions of any selected indoor space and continuously monitor the illuminance values at each location from where it is passing through. The lux data along with its coordinate position are received by server computer configured in local network, and thereby stores these data into a file. These data are further processed for generating lux map i.e. variation of lux values with respect to different spatial location on the floor of concerned indoor space. The generated lux map can be compared with the reference lux map designed by lighting expert. The result of comparison i.e. the error in lux values at different coordinate locations can be considered as intelligent information towards modification of lighting design.

Technical upgradation in the field of surveillance as well as in remote package delivering systems have led us to the development of a quadcopter. The quadcopter’s flight controller is developed using Arduino Uno R3 based microcontroller board and its flight movements can be controlled using a transmitter-receiver setup. A gyro cum accelerometer module is attached to give the exact coordinate location of the place where the quadcopter is positioned whereas the magnetometer module indicates the direction of travel. The microcontroller is supplied with a LIPO battery. The microcontrollers are programmed to turn on the quad rotors using electronic speed controllers (ESCs).

This paper represents a unique home appliance control system based on voice commands over the internet. Through this proposed system, any appliance can be controlled efficiently from any location irrespective of their distance from the appliance through the help of Artificial Intelligent (AI) voice assistant over internet using cloud server technology. Primarily, voice is captured by the AI assistant and is sent to IFTTT (If This Then That) open cloud server which then connects to another open cloud server named Webhooks. It then sends information to the Blynk application (app) which in turn transmits to ESP8266 based microcontroller unit and finally passes on the information to the relay connection module to switch on the appliances. Almost 100% accuracy has been obtained by the proposed system with a delay time of 0.99 seconds, considering the fact that internet connection strength remains healthy. The proposed system has already been successfully tested from a distance of 10 metres.

This study is an attempt for an automated irrigation system which enable the users to regularly supervise relative humidity of the soil at different sites through the entire agricultural field for more accurate setting up of irrigation cycles. The sensing unit is modeled on a feedback mechanism with centralized control system which measures relative humidity (RH) of the soil and controls supply of water to the field in a real time process. A wireless communication is established between the sensor as well as controlling unit and the sprinkler. In practice, the pump on which control action is to be taken is at a distance from the land. A data acquisition system with a PC interface using UART-USB is also built up to record instantaneous values of soil temperature.