CIMA: A Novel Classification‐Integrated Moving Average Model for Smart Lighting Intelligent Control Based on Human Presence

Abstract

Smart lighting systems utilize advanced data, control, and communication technologies and allow users to control lights in new ways. However, achieving user comfort, which should be the focus of smart lighting research, is challenging. One cause is the passive infrared (PIR) sensor that inaccurately detects human presence to control artificial lighting. We propose a novel classification-integrated moving average (CIMA) model method to solve the problem. The moving average (MA) increases the Pearson correlation (PC) coefficient of motion sensor features to human presence. The classification model is for a smart lighting intelligent control based on these features. Several classification models are proposed and compared, namely, k-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), näive Bayes (NB), and ensemble voting (EV). We build an Internet of things (IoT) system to collect movement data. It consists of a PIR sensor, a NodeMCU microcontroller, a Raspberry Pi-based platform, a relay, and LED lighting. With a sampling rate of 10 seconds and a collection period of 7 days, the system achieved 56852 data records. In the PC test, movement data from the PIR sensor has a correlation coefficient of 0.36 to attendance, while the MA correlation to attendance can reach 0.56. In an exhaustive search of an optimum classification model, KNN has the best and the most robust performance, with an accuracy of 99.8%. It is more accurate than direct light control decisions based on motion sensors, which are 67.6%. Our proposed method can increase the correlation value of movement features on attendance. At the same time, an accurate and robust KNN classification model is applicable for human presence-based smart lighting control.

Human Activity Recognition Improvement on Smartphone Accelerometers Using Cima

“…This research shows that CNN has better accuracy than SVM in detecting these four activities. On the other hand, in a previous study, we found an effective CIMA method for intelligent lighting sequential classification [5]. This method predicts the presence of movement data generated by the PIR sensor.…”

“…CIMA is a classification of time series data case studies that utilize moving averages to increase the correlation of time series data with predicted labels [5]. The process involves several simultaneous moving average windows and Pearson correlation coefficient (PCC) analysis.…”

“…Activity detection using the accelerometer on a smartphone is sequential classification. In previous research, we discovered a method called classification integrated moving average (CIMA), which is effective for the intelligent lighting sequential category [5]. This method predicts the presence of movement data produced by the passive infrared (PIR) sensor.…”

NS-SVM: Bolstering Chicken Egg Harvesting Prediction with Normalization and Standardization

“…3 shows the K-fold cross-validation algorithm. K-fold cross-validation tests as many as K iterations [25]. In each iteration, the algorithm divides the data into K equal parts.…”

Optimization of peak path of industrial carbon emissions in Shanghai based on integrated intelligent algorithm

“…Other scholars established a carbon dioxide absorption desorption process optimization system based on the product life cycle theory by using the life cycle cost method [4]. Some scholars applied the principles of supply chain environmental management and resource allocation to build a multi-stage linear solution based on single objective integer programming, solved the problem of mismatch between carbon emission peak and emission reduction benefit indicators, and achieved comprehensive energy conservation and cost reduction effect [5][6]. Therefore, based on integrated intelligence, this paper studies and discusses the optimization of the peak path of industrial carbon emissions in Shanghai.…”