Contemporary public road illumination projects commissioned by municipalities and other local authorities install new light-emitting diode (LED)-based luminaires or retrofit existing conventional discharge lamp-based luminaires with LEDs. Such projects require conforming to minimum photometric and energy efficiency standards, and in early-stage planning, it is desirable to estimate illuminance and energy efficiency parameters for ensuring compliance with national and international codes of practice and modification of design parameters, if required. With a view of recent literature proffering linear regression models for the rapid estimation of photometric and energy efficiency parameters of road lighting systems, this study was conducted to perform a comparative assessment of various candidate models in terms of these statistical indices: coefficient of determination (R2), root mean square error (RMSE), mean squared error (MSE) and mean absolute error (MAE). Photometric simulations of road lighting systems with single-sided pole arrangements were conducted in a proprietary software for five randomly chosen LED power ratings between 33 W and 78 W, and the generated extensive simulation data was utilized to develop and train linear and support vector machine (SVM)-based regression models for the prediction of average illuminance, overall uniformity of illuminance, and energy efficiency of lighting installations. Overall, the cubic SVM models demonstrated the most satisfactory performance (R2 = 0.99, RMSE <= 0.51, MSE <= 0.26, and MAE <= 0.44) among all the developed models, and this was also discerned in several experimental cases. This study offers new insights for augmenting extant practices in municipal public road lighting design and commissioning.

Since the introduction of the Street Lighting National Programme (SLNP) in India in 2015, municipalities and local bodies have been upgrading and revamping existing discharge lamp-based street lighting systems with light-emitting diode (LED)-based ones for enhancing energy efficiency. In recent years, artificial neural networks (ANNs) have emerged as a potent machine learning tool for predictive modelling across major engineering disciplines. This study applied feedforward ANNs for street lighting planning for single-sided, opposite, and staggered layouts of LED luminaires of common power ratings (35–116 W). Extensive photometric simulations were performed, and the generated datasets were utilized to train, validate, and test ANN models for the prediction of average illuminance, overall uniformity of illuminance, and installation energy efficiency. All the ANN models demonstrated good performance, and the error margin for the prediction of pertinent photometric and energy efficiency parameters was satisfactory. This machine learning-based approach can assist municipal engineers in street lighting project planning and implementation.

A discernible shift in municipal engineering practices concerning public road lighting in developing countries such as India has made more and more municipalities display a trend of retrofitting conventional discharge lamps such as high-pressure sodium (HPS) vapour and metal halide (MH) lamps with light-emitting diodes (LEDs). This simulation-based study extensively simulated road illumination systems deploying HPS, MH, and LED luminaires and explored 104,976 installation combinations in total. Cataloguing the most appropriate system design configurations and prioritizing energy efficiency (εx) of lighting installations, the LED-based road illumination systems (εx: 26.25 to 31.50 lx*m2/W) were found to be at least 13.63

Energy-efficient road illumination systems are an indispensable part of any modern society to ensure safe nocturnal transportation of freight and passengers, assure better navigation, promote improved visibility of surroundings, and diminish the probability of occurrence of accidents and crimes. Simulative estimation of pertinent photometric parameters and probable energy expenditure before commissioning of projects is very desirable to project managers, transportation engineers, local authorities, and other stakeholders for envisaging a complete picture of the deliverables and ensuring total conformity with applicable lighting and energy codes. This simulation-based work was conducted with luminaire luminous intensity distribution data tables of different light-emitting diode luminaires having type II luminous intensity distribution patterns in the simulation environment of an industry-standard lighting simulation software. Thereafter, the multiple regression analysis technique was utilized upon the simulatively obtained substantial dataset to propound a model of twenty-four bivariate quadratic polynomial equations for estimating the changes in road surface illuminance parameters, and three general equations were derived with the same dataset, two for estimating road surface illuminance parameters and one for estimating energy efficiency. The propounded model and general equations can be readily followed by various stakeholders to rapidly estimate pertinent photometric parameters and installation energy efficiency and the approach expatiated in this work can prove to be useful for exploring inter-variable relationships, providing objective functions in optimization tools, and proffering neoteric, heuristic perspectives to lighting design.

Indoor lighting conditions influence the psychology of pupils in academic institutions and it is expedient to investigate how subjective experiences are modulated by differences in lighting conditions. This study was conducted in a tertiary educational institute in West Bengal, India with twenty-four student participants, divided into three groups of eight each, to assess how the appraisals of task lighting and room aesthetics varied under three ambient lighting conditions. Spread across nine sessions of 1 h each, the groups performed pre-defined tasks and recorded their responses upon copies of a formulated questionnaire at the conclusion of each session. Moreover, blood pressure and heart rate measurements of the participants were made at an interval of 20 min. Statistical analysis with Kruskal-Wallis and Friedman tests implied that there were significant differences among the lighting conditions with respect to several dependent variables of task lighting and room aesthetics appraisal. Artificial lighting was deemed to be uniform, pleasant for task performance, and comfortable for book reading. Daylighting with the concomitant window view was construed as brighter, glaring, dramatic, more contrasting, and less uniform. A combination of natural and artificial lighting was bright, mildly contrasting, dramatic, softer in luminosity, and comfortable. Withal, daylighting with the concomitant window view appeared to regulate participants' blood pressure and heart rate. Thus, this study implies that the balance and holistic synergy between artificial and natural light can create an enlivening and salubrious indoor environment, and building service professionals should conscientiously harness the same for upgrading current practices in indoor lighting.

In the present world, as Internet of Things (IoT) based sensor monitoring and conditional controlling technology has been embedded in our day-to-day lives, there is a need for logging and storing sensor data for big data analysis. Due to free and easy to use features, Google spreadsheet has been chosen as the Cloud-based spreadsheet platform for sensor data logging and storing. This paper has provided a procedure to monitor sensor data, located at different geographical locations onto their corresponding specified worksheet in a well-defined structured manner in a single Google spreadsheet. The sensor readings uploaded in the Google spreadsheet can be accessed online by smartphone or a personal computer. For stable and accurate readings of sensors which work best on 5 V, the hardware communication protocol, Universal Asynchronous Receiver/Transmitter (UART) has been used during the development of the present work and this paper shows a simplistic way for uploading sensor values on the web, where memory constraint for storing sensor data is absent. In this developmental work, Arduino has been used for sensor data monitoring and ESP32 has been used for Internet connection

At this time, the amount of electricity generated around the world is insufficient to meet global demand. Lighting consumes almost a quarter of the total power generated by power utilities. Reducing lighting power consumption will help save a significant amount of energy, which can then be put to better use in other areas. With the introduction of solid-state lights, i.e. Light Emitting Diodes (LED) in recent years, a hopeful future has been gained toward achieving that goal. Adding further functionality to an LED outdoor light by integrating it with an integrated system and a communication module. Not only would it conserve energy, yet it will also give information about the surrounding environment. This extra feature offers a number of benefits, including remote monitoring of luminaire health, cost savings, improved visual performance, reduced maintenance, automatic pedestrian recognition, and intelligent citizen service. A detailed development of an surrounding environment-sensitive intelligent outdoor lighting system is explained in this paper. A few characteristics of the Internet of Things (IoT) have been incorporated and studied in the current work, such as remote monitoring of the luminaire's health utilizing the Zigbee protocol technique of communication with the central computer. A 1 m diameter integrating sphere has been used to do a detailed photometric examination of the luminaire. The luminaire's IsoLux diagram was presented at various Pulse Width Modulation (PWM) duty cycles, which were controlled using a principal computer. It also suggests remedies to existing restrictions as well as some upgrades that could be explored in the near future to improve the system's trustworthiness.

An outdoor luminaire based on light-emitting diodes (LED), including its design, development, and performance study, is discussed in this article. Illuminance on exterior surface, correlated color temperature (CCT), color rendering index (CRI), and spectral power of the light source can be controlled wirelessly. Arrays of cool white (CW) and warm white (WW) LEDs make up light sources. To adjust the light output as well as the correlated color temperature (CCT) and other parameters, algorithm for regulating lighting has been established. The circuitry for controlling the light has been programmed into a microcontroller, and it uses a pulse width modulation (PWM) technique to independently adjust the brightness of the light emitted by the WWLED array and the CWLED array that make up a given light source. The planned system links to the lighting system through Wi-Fi, and it is controlled by a smart phone. The smart phone has been used as a handheld device (HHD). The developed system's performance has been demonstrated by the experimental findings. It offers a wide range of color temperature options, increased spectral power with increased illumination, enhanced color rendering index, and the ability to create a calming nocturnal external lighting ambiance on demand.

Global warming will affect not only the present generation but also future generations. The carbon footprint created by traditional energy sources highlights the need to reduce energy consumption in all possible areas, including the grid. Along with the rapid progress of information and communication technology (ICT), the ability to access the World Wide Web is also on the rise. New networks and servers are introduced regularly, but many of these busy networks are underutilized in terms of time and space. Green grids come to the rescue through more efficient implementation of energy-efficient grid technologies or the use of energy-efficient equipment. The main aim of Green Networking is to provide an energy-optimized model for data centers. There are four lines of research on different interpretations of the causes of energy loss: Interface Proxy, Green Grid from Energy-aware applications, Energy-aware Infrastructure, and Adaptive Link Rate. In this paper, we have summarized the results of some studies on green IT.

In this article, Design and development of a LED based outdoor luminaire is proposed and its performance parameters have been analyzed. Variable Correlated Color Temperature (CCT) of the light source can be controlled wirelessly. This light source consists of two arrays of Warm White (WW) and one array of Cool White (CW) LEDs. Light control logic has been developed to control the light output and Correlated Color Temperature (CCT). The range of CCT variation of the test light source lies within the CCT values of the WW and the CW LEDs. Pulse Width Modulation (PWM) technique has been applied to implement the light control logic and embedded in a microcontroller to control the light outputs of two WWLED arrays and a CWLED array of the light source. The developed system has been connected with the light source and controllable by a Smart Phone as a Hand Held Device (HHD) through WiFi connection. Experimental results establish the satisfactory performance of the developed system. It has wide variation in the CCT range, improved illuminance and can provide a controllable soothing nighttime landscape lighting environment as and when necessary.

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.

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.

Commissioning, maintenance and revamping of energy-efficient, economical and controllable road lighting systems that satisfactorily cater to the visual requirements of pedestrians and motorists are preferable in the wake of the current global energy crisis. Installation of new road lighting systems or retrofitting of the existing ones would require careful consideration of the design configurations that would maintain road surface average illuminance, uniformity of illuminance, and diversity of illuminance levels in accordance with applicable regional, national, or international standards and guidelines. To facilitate rapid approximation of pertinent road surface illuminance parameters with a view of the prevailing road lighting practices involving common heuristic configurations, photometric simulations of road lighting were conducted in a created software model with photometric data tables of high-pressure sodium (HPS) and light-emitting diode (LED) luminaires possessing different power ratings for a specified set of luminaire mounting height, road width, pole spacing, overhang and tilt values, and a mathematical model consisting of six equations derived by multiple linear regression was propounded (coefficient of determination > 0.90) with relevant predictor variables. Moreover, a framework for LED luminaire power rating selection for retrofitting operations was proposed to assist manufacturers, electrical contractors and utility operators entrusted with such work.

Normal life can be ensured for schizophrenic patients if diagnosed early. Electroencephalogram (EEG) carries information about the brain network connectivity which can be used to detect brain anomalies that are indicative of schizophrenia. Since deep learning is capable of automatically extracting the significant features and make classifications, the authors proposed a deep learning based model using RNN-LSTM to analyze the EEG signal data to diagnose schizophrenia. The proposed model used three dense layers on top of a 100 dimensional LSTM. EEG signal data of 45 schizophrenic patients and 39 healthy subjects were used in the study. Dimensionality reduction algorithm was used to obtain an optimal feature set and the classifier was run with both sets of data. An accuracy of 98% and 93.67% were obtained with the complete feature set and the reduced feature set respectively. The robustness of the model was evaluated using model performance measure and combined performance measure. Outcomes were compared with the outcome obtained with traditional machine learning classifiers such as Random Forest, SVM, FURIA, and AdaBoost, and the proposed model was found to perform better with the complete dataset. When compared with the result of the researchers who worked with the same set of data using either CNN or RNN, the proposed model's accuracy was either better or comparable to theirs.

Purpose Good illumination creates an aesthetic environment that may positively influence patients’ well-being and provide comfort to the hospital staff. This study aims to focus on exploring the energy efficiency of lighting and subjective perception of the lit environment in a hospital ward to assess quality indicators of ambient lighting conditions. Design/methodology/approach The existing conventional tubular fluorescent lamp–based lighting system in the surveyed patients’ ward was retrofitted with light-emitting diode (LED) luminaires to explore illumination and energy parameters. Thereafter, a software lighting model was created, simulated and analyzed. A Web-based survey with five bipolar adjective pairs in a semantic differential scale was conducted with 48 participants to record and analyze their subjective responses pertaining to the variations in lamp types and surface reflectance combinations. Findings The findings imply that the LED tubular lamp–based illumination was deemed more adequate compared to other lamp types and the effects of variations in room surface reflectance combinations on the participants’ responses were statistically significant at α = 0.05 level. The simulated horizontal work plane average illuminance level varied from 131 to 171 lx, mean room surface exitance (MRSE) levels remained between 30 and 90 lm/m2 and overall uniformity of illuminance remained between 0.5 and 0.7. Originality/value In a hospital ward illuminated by LED tubular lamps, variations in room surface reflectance combinations for a constant luminous flux package output from the lamps may affect the subjective perception of users and the correlation between horizontal work plane average illuminance and MRSE is found to be highly linear (coefficient of determination > 0.97).

The present work deals with performance study and stability analysis of an LED driver system. An LED driver based on buck-boost topology is designed and simulated in MATLAB Simulink environment. The driver satisfactorily operates LED modules having power rating in the range of 6 W to 24 W. The power factor and Total Harmonic Distortion comply with standard recommended values. The mathematical model of the LED driver is formulated and the stability analysis of the designed driver is carried out during its operation.

This paper describes a microcontroller based emergency lighting system, which can early detect fire and send the alarm message through a mobile network. This is achieved via smoke and gas detector technology added with integrated microcontroller, mobile communication and a LED emergency light. First five Minutes of fire is more important than last five hours [1]. Hence, it is important to have early detection of fire and start fire fighting in its inception. In many hazardous areas where flammable materials are handled, any leak or spillage may give rise to an explosive atmosphere. In this situation, early detection of leaking gas or smoke plays an important role in reducing fire deaths and injuries. In fact, immediately after detection of fire, fire fighting should be started by means of portable fire extinguishers or by informing the fire brigade. This developed system can initiate these functions by detecting the fire hazard, establishing the communication to dwellers and turning on the emergency light to show the exit route.