Sleep disorders are a common health condition that can affect numerous aspects of life. Obstructive sleep apnea is one of the most common disorders and is characterized by a reduction or cessation of airflow during sleep. In many countries, this disorder is usually diagnosed in sleep laboratories, by polysomnography, which is an expensive procedure involving much effort for the patient. Multiple systems have been proposed to address this situation, including performing the examination and analysis in the patient's home, using sensors to detect physiological signals that are automatically analyzed by algorithms. However, the precision of these devices is usually not enough to provide clinical diagnosis. Therefore, the objective of this review is to analyze already existing algorithms that have not been implemented on hardware but have had their performance verified by at least one experiment that aims to detect obstructive sleep apnea to predict trends. The performance of different algorithms and methods for apnea detection through the use of different sensors (pulse oximetry, electrocardiogram, respiration, sound, and combined approaches) has been evaluated. 84 original research articles published from 2003 to 2017 with the potential to be promising diagnostic tools have been selected to cover multiple solutions. This paper could provide valuable information for those researchers who want to carry out a hardware implementation of potential signal processing algorithms.

Sleep apnea is a sleep related disorder that significantly affects the population. Polysomnography, the gold standard, is expensive, inaccessible, uncomfortable and an expert technician is needed to score. Numerous researchers have proposed and implemented automatic scoring processes to address these issues, based on fewer sensors and automatic classification algorithms. Deep learning is gaining higher interest due to database availability, newly developed techniques, the possibility of producing machine created features and higher computing power that allows the algorithms to achieve better performance than the shallow classifiers. Therefore, the sleep apnea research has currently gained significant interest in deep learning. The goal of this work is to analyze the published research in the last decade, providing an answer to the research questions such as how to implement the different deep networks, what kind of pre-processing or feature extraction is needed, and the advantages and disadvantages of different kinds of networks. The employed signals, sensors, databases and implementation challenges were also considered. A systematic search was conducted on five indexing services from 2008–2018. A total of 255 papers were found and 21 were selected by considering the inclusion and exclusion criteria, using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) approach.

Sleep quality is directly related to overall wellness and can reveal symptoms of several diseases. However, the term “sleep quality” still lacks a definitional consensus and is commonly assessed in sleep labs with polysomnography, comprising high costs, or through sleep questionnaires, a highly subjective technique. Multiple methods have been proposed to address the estimation of sleep quality, and devices were developed to conduct the examination in the subject's home. The objective of this paper is to analyze the methods and the devices presented in the literature, assessing the development of objective markers that could lead to an improvement of the subjective sleep experience understanding, leading to developments in the treatment of sleep quality deficits. A systematic review was conducted, selecting research articles published from 2000 to 2018, and two research questions were formulated, specifically, “what methods for sleep quality assessment have been developed” and “what kind of measures are employed by the devices that have been developed to estimate sleep quality.” The research trend for the assessment of sleep quality is based on the sleep macrostructure, and it was verified that despite the convenience and considerable popularity among the consumers of home health monitoring of devices, such as actigraphs, the validity of these tools regarding the estimation of sleep quality still needs to be systematically examined. A detailed resume of the key findings and the identified challenges are presented, ascertaining the main gaps in the current state of the art.

In the past few years, Internet of Things (IoT) devices have evolved faster and the use of these devices is exceedingly increasing to make our daily activities easier than ever. However, numerous security flaws persist on IoT devices due to the fact that the majority of them lack the memory and computing resources necessary for adequate security operations. As a result, IoT devices are affected by a variety of attacks. A single attack on network systems or devices can lead to significant damages in data security and privacy. However, machine-learning techniques can be applied to detect IoT attacks. In this paper, a hybrid machine learning scheme called XGB-RF is proposed for detecting intrusion attacks. The proposed hybrid method was applied to the N-BaIoT dataset containing hazardous botnet attacks. Random forest (RF) was used for the feature selection and eXtreme Gradient Boosting (XGB) classifier was used to detect different types of attacks on IoT environments. The performance of the proposed XGB-RF scheme is evaluated based on several evaluation metrics and demonstrates that the model successfully detects 99.94% of the attacks. After comparing it with state-of-the-art algorithms, our proposed model has achieved better performance for every metric. As the proposed scheme is capable of detecting botnet attacks effectively, it can significantly contribute to reducing the security concerns associated with IoT systems.