Recently, indoor positioning systems have attracted a great deal of research attention, as they have a variety of applications in the fields of science and industry. In this study, we propose an innovative and easily implemented solution for indoor positioning. The solution is based on an indoor visible light positioning system and dual-function machine learning (ML) algorithms. Our solution increases positioning accuracy under the negative effect of multipath reflections and decreases the computational time for ML algorithms. Initially, we perform a noise reduction process to eliminate low-intensity reflective signals and minimize noise. Then, we divide the floor of the room into two separate areas using the ML classification function. This significantly reduces the computational time and partially improves the positioning accuracy of our system. Finally, the regression function of those ML algorithms is applied to predict the location of the optical receiver. By using extensive computer simulations, we have demonstrated that the execution time required by certain dual-function algorithms to determine indoor positioning is decreased after area division and noise reduction have been applied. In the best case, the proposed solution took 78.26% less time and provided a 52.55% improvement in positioning accuracy.

A highly accurate indoor positioning under the effect of multipath reflections has been a prominent challenge for recent research. This paper proposes a novel indoor visible light communication (VLC) positioning model by connecting k-nearest neighbors (kNN) and random forest (RF) algorithms for reflective environments, namely, kNN-RF. In this fingerprint-based model, we first adopt kNN as a powerful solution to expand the number of input features for RF. Next, the importance rate of these features is ranked and the least effective one(s) may be removed to reduce the computation effort. Next, the training process using the RF algorithm is conducted. Finally, the estimation process is utilized to discover the final estimated position. Our simulation results show that this new approach improved the positioning accuracy, making it nearly five times better than other popular kNN algorithms.

Enhancing the accuracy of indoor visible light positioning systems with simple, real-time, and stable methods is one of the interesting challenges in recent research. In this paper, a relatively minor mean positioning error of 8 mm and a 42-52% improvement in computational time could be achieved within a real space of 1.2 m × 1.2 m × 1.2 m by transcending the serious limitations of the traditional knearest neighbors (KNN) algorithm. These disadvantages (slow execution time, high error formation) are a result of finding the nearest neighbors from all the fingerprints, averaging the Euclidean distances, and the excessive passivity of the K value. To overcome the above limitations of KNN, we proposed a maximum received signal strength recognition (MRR) technique and weighted optimum KNN (WOKNN) algorithm, which is a combination of optimum KNN (OKNN) and weighted KNN (WKNN). While MRR was used to reduce the computational time, WOKNN was used to solve the remaining problems. Specifically, OKNN was used to automatically determine the best number of nearest neighbors for each position in the area under consideration, and WKNN helped improve the errors that come from the Euclidean distance averaging process. Based on positive experimental results and a meaningful comparison with various versions of KNN, we demonstrated that the improved conventional KNN algorithm can achieve very high positioning accuracy and is totally suitable for several specific 2-D indoor positioning applications.

During continuous operation, transformer problems can occur due to various reasons. In reality, the operating parameters of the transformer have been collected and monitored through the supervisory control and data acquisition (SCADA) systems. However, these systems face many challenges when applied to no‐human substations. Currently, noise signals have been used to detect transformer errors. Abnormal noise recognition and vibration monitoring can recognize the transformer's potential defects and errors. In this study, the authors built an internet of things (IoT) system that allows remote control centres to monitor the condition of transformers through noise and vibration at non‐human substations. The proposed model was equipped with a wireless sensor network node consisting of vibration sensors, audio collectors, Arduino modules, and Lora modules. The authors set up two schemes for the IoT network: one sensor node for a 220‐kV transformer and three sensor nodes for all three phases of the 500‐kV transformer. The data obtained from the sensor node were sent to LoRa Gateway and displayed on the computer through LabVIEW. The study also enabled monitoring of parameters through IoT devices such as Desktops, Laptops, Smartphones from LabVIEW NXG Web VI platform, ThingSpeak, and Amazon S3 storage cloud. In addition, a Model Predictive Control (MPC) algorithm was applied to predict the deterioration of transformer health to maintain the system stability and, hence, prolong the transformer life and operability.