Pupil localization extracts pupil center coordinates from images and videos of the human eye along with the pupillary boundary. Pupil localization essentially plays a major role in identity verification, disease recognition, visual focus of attention (VFOA) tracking, dementia cognitive assessment, and human fatigue detection. However, the process of pupil localization still remains challenging due to various factors, such as poor-quality images, eye makeup, contact lenses, eyelashes, hair strips, eyebrows, closed eyes, and eye saccades. The pupil localization strategies are essentially divided into learning-based and non-learning-based approaches and discussed in detail with the relevant techniques used. This article aims to deliver the essence of current trends in pupil localization and critically discusses the advantages and disadvantages of each method. Hence, this article can be useful to a broad spectrum of readers as a guide to analyze the latest trends in pupil localization.

Non-intrusive load monitoring (NILM) systems have gained immense popularity in the last two decades. Although many solutions were developed using the NILM approach, the majority of solutions failed to identify low-power-consuming appliances. However, a NILM system deployed in a domestic installation should be capable of identifying low-power-consuming appliances precisely. Therefore, we propose two real-time NILM solutions that can identify low-power residential appliances. These two solutions rely on active power and harmonic information extracted from the measured current waveform. We analyzed the performances of the two solutions using simulations and real-world experiments. Results indicate that both solutions can correctly identify appliances with an average accuracy above 90 percent.

Due to the increase in electricity demand and the rapid depletion of fossil fuels, energy management has become a critical issue over the last two decades. Thus, researchers, utility suppliers, governments, and policymakers are working in tandem to develop novel solutions. In recent years, solutions based on Intrusive Load Monitoring (ILM) and Non-intrusive Load Monitoring (NILM) have garnered the interest of many researchers. However, NILM systems are less difficult to implement and more cost-effective than ILM systems. Even though available NILM-based solutions can identify single-state devices with acceptable accuracy, identifying the various operating states of multi-state devices remains a problem. This research work proposes a novel supervised learning algorithm to correctly identify the operating states of multi-state residential devices. Results obtained through extensive simulations indicate that the proposed algorithm can achieve device and state identification accuracy of 93 percent and 91 percent, respectively.

Real-time non-intrusive load monitoring (NILM) systems have gained significant importance in various applications, including demand-side management, appliance anomaly detection, and ambient assisted living. While numerous research-based solutions have been developed over the past two decades, still it remains a need for an affordable application-level NILM solution. In this paper, we present a novel rule-based self-supervised approach that operates within a low-price range. Our proposed methodology offers automatic identification of unknown appliances within the system, achieving real-time appliance identification with a satisfactory level of accuracy. We contribute to the development of a cost-effective and efficient solution for non-intrusive load monitoring, enabling applications across diverse domains.

Non-intrusive load monitoring (NILM) has recently become a promising and trending topic in energy management. Although several NILM-based solutions were proposed, a commercial-grade universal solution is yet to be developed due to inherent limitations in the event detection and appliance identification algorithms. This work proposes a novel real-time event detection algorithm specifically designed to be effective in NILM-based solutions developed for residential loads. Real-world experimental results indicate that the proposed algorithm can detect a change in the operating state of a device with a 98 percent accuracy within 1.35 milliseconds, on average.

Iris extraction has gained prominence due to its application versatility across many domains. However, achieving real-time iris extraction poses challenges due to several factors. While non-learning-based iris extraction methods are cost-effective and resource-efficient, they are outperformed by learning-based algorithms, which deliver superior accuracy and performance. In response, this article proposes a Convolutional Neural Networks (CNN)-based accurate direct iris extraction mechanism for a broad spectrum of eye images. The innovation of our approach lies in its proficiency with varied image types, including those where the iris is partially obscured by the eyelid. We enhance the method’s reliability by introducing a modified Circular Hough Transform (CHT). Extensive testing demonstrates our method’s excellent real-time performance across diverse image types, even under challenging conditions. These findings underscore the proposed method’s potential as a cost-effective and computationally efficient solution for real-time iris extraction in varied application domains.