Mohammad Maroof Siddiqui

Sleep disorders, such as insomnia, obstructive sleep apnea (OSA), narcolepsy, REM sleep behavior disorder, and circadian rhythm disturbances, represent a rapidly expanding global health burden that is strongly associated with cardiovascular, metabolic, neurological, and psychiatric diseases. Advancements in wearable sensing technologies and Internet of Medical Things (IoMT) infrastructures have expanded the possibilities for continuous, home-based sleep assessment beyond conventional polysomnography laboratories. These Sleep Health Internet of Things (S-HIoT) systems combine multimodal physiological sensing (EEG, ECG, SpO₂, respiratory effort and actigraphy) with wireless communication and cloud-based analytics for automated sleep-stage classification and disorder detection. Nonetheless, the digitization of sleep medicine brings about significant cybersecurity concerns. The constant transmission of sensitive biomedical information makes S-HIoT networks open to anomalous traffic flows, signal manipulation, replay attacks, spoofing, and data integrity violation. Existing studies mostly focus on analyzing physiological signals and network intrusion detection independently, resulting in a systemic vulnerability of cyber–physical sleep monitoring ecosystems. With the aim of addressing this empirical deficiency, this review integrates emerging advances (2022–2026) in the AI-assisted categorization of sleep phases and IoMT anomaly detector designs on the finer analysis of CNN, LSTM/BiLSTM, Transformer-based systems, and a component part of federated schemes and the lightweight, edge-deployable intruder assessor models available. The aim of this study is to uncover a gap in the literature: integrated architectures to trade off audiences of faithfulness of physiological modeling with communication-layer security. To counter it, we present a single framework to include CNN-based spatial feature extraction, Bidirectional Long Short-Term Memory (BiLSTM)-based temporal models and Random Forest-based ensemble classification using a dual task-learning approach. We propose a multi-objective optimization framework to jointly optimize the performance of sleep-stage prediction and that of network anomaly detection. Performance on publicly available datasets (Sleep-EDF and CICIoMT2024) confirms that hybrid integration can be tailored to achieve high accuracy [99.8% sleep staging; 98.6% anomaly detection] whilst being characterized by low inference latency (<45 ms), which is promising for feasibility in real-time deployment in view of targeting edge devices. This work presents a comprehensive framework for developing secure, intelligent, and clinically robust digital sleep health ecosystems by bridging chronobiological signal modeling with cybersecurity mechanisms. Furthermore, it highlights future research directions, including explainable AI, federated secure learning, adversarial robustness, and energy-aware edge optimization.

The field of sleep medicine depends on accurate sleep staging since it is crucial for the diagnosis of sleep disorders, helps to understand the dynamics of the brain during sleep, and plays an important role in improving basic and advanced research in neuroscience. Electroencephalography (EEG) is a necessary method for recording brain activity given its high temporal resolution and responsiveness to electrophysiological processes. Nevertheless, the manual annotation of sleep stages is time and resource-consuming as well as subject to inter-rater variability, hence needs to be automated. This paper reviews the recent progress of EEG-based sleep stage classification based on traditional ML and DL models. We compare ten most recent studies published between 2020 and 2023 in terms of their performance metrics, datasets used, and methodological differences. Results show that hybrid deep learning models, particularly the Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) architecture, attain the highest accuracy rates (mostly greater than 85%) and provide better generalization performance on relatively heterogeneous data sets. In spite of great success, issues like signal noise, dataset size and generality, and model interpretability are still hurdles. This methodological comparison informs current trends, shortcomings and directs research towards strong, interpretable models suitable for clinical applications.

Industrial automation has been transformed by the Internet of Things (IoT) through real time monitoring, predictive maintenance and increased operating efficiency. An IoT-based monitoring system is introduced in this paper for three-phase induction motor serving industrial sector. Conventional motor maintenance includes a regular hand-checking inspection, which is laborious, and sometimes causes random failure. Real time data collection and analysis are possible by introducing IoT technology so that motor reliability can increase and downtime can decrease drastically. The developed system uses a variety of sensors to monitor the most important parameters (temperature, vibration, voltage and current). Data is processed with a microcontroller and is sent to a cloud-based platform using Wi Fi or cellular network. “This enables remote monitoring and predictive maintenance and early detection of faults, and thus improved effectiveness of industrial operations. The system is also equipped with an alarm system to which users may be alerted when the normal operation state is breached, mitigating catastrophic failure of the same. The system was tested in a field industrial environment and proved to be successful in real-time fault detection and industrial operation performance. A notable reduction in maintenance cost and unexpected breakdowns is evidence in practice compared to traditional monitoring systems that were demonstrated. The paper also analyses the possibility of using AI and ML algorithms to enhance predictive maintenance opportunities.

Sleep disorders are medical conditions affecting the sleep patterns of individuals or living beings, with some being severe enough to disrupt normal physical, mental, and emotional functioning. This research article discusses the analysis of the attributes and waveforms of electroencephalogram (EEG) signals in humans. The major objective is to present the findings through signal spectrum analysis, highlighting changes through various sleep stages. The objective of this research is to assess the potential effectiveness of EEG patterns in diagnosing sleep disorders, particularly those associated with rapid eye movement behavior disorder. These conditions frequently lead to detectable alterations in the electrical and chemical processes within the brain, which can be analyzed by examining brain signals and images. This research paper utilizes the short time-frequency analysis of power spectrum density (STFAPSD) method on EEG signals to diagnose various types of sleep disorders. Calculated values are normalized and the average power of the spectral signal spectra, relating to EEG wave components (delta: 1-4 Hz; theta: 4-8 Hz; alpha: 8-13 Hz; beta 13--25~30 Hz). These indices are used as diagnoses to discriminate among different types of sleep disturbances. The results comparison performs accurate power spectral density (PSD) estimations for several sleep disorders, which makes this technique highly efficient to analyze a large database in a short time. Importantly, we achieve significantly results when analyzing the normalized beta power of both C4-A1 and EMG1-EMG2 channels during the rapid eye movement (REM) stage in the EEG signal. This observation demonstrates a strong difference in PSD values (beta normalized) between normals and REM sleep behavior disorders (RBDs).

Intensive Care Units (ICUs) are high priority care units for patients with life threatening conditions, where many time-series data from monitoring devices, laboratory readings and vital signs are collected. These physiologic measurements should be closely monitored to detect early signs of decline, including CO2 retention, sepsis and cardiac events. Artificial Intelligence (AI) models, particularly deep learning-based architectures have the potential for superior handling of complex multi-layered and multi-dimensional datasets to aid real-time prediction and early warning. In this paper, focus on the development and application of AI-driven Early Warning Systems (EWS) for ICU patients based on time-series data. Investigate the use of RNNs, LSTM models and transformer-based sequential architectures to predict key events such as sepsis, respiratory failure and cardiac instability. The paper also discusses problems of data heterogeneity, missing values and model interpretability. Experimental studies indicate that our transformer-based models achieve superior prediction performance and earlier warning time point than the traditional LSTM models. Finally, the paper also addresses the potential inclusion of explainable AI (XAI), multimodal data fusion and real-time CDSS in ICU patient care.

Background/Objectives: REM Sleep Behavior Disorder (RBD) is a parasomnia that manifests as the occurrence of abnormal motor movement in the REM sleep and is becoming known as a prominent early indicator of neurodegenerative diseases. Over the last couple of years, due to the increasing need and desire to find efficient and objective means of diagnostics, there has been much research within the area of automated RBD detection. This paper will attempt to give a deep introduction to the contemporary methodologies and technological developments in the automated detection of RBD with the help of physiological signals. Methods: Current literature was also reviewed in a systematic manner, and the emphasis was laid on studies that employ polysomnography data such as electroencephalography (EEG) and electromyography (EMG) to detect RBD. The focus was made on signal processing, feature extraction algorithms, especially spectral and time-frequency features, as well as machine learning and deep learning models application. Unimodal and multimodal approaches were also compared to each other. Results: Available studies reveal that spectral characteristics, particularly the ones obtained using the higher frequencies bands, are significant in discriminating between RBD victims and healthy participants. EMG-based features have high discrimen-native ability because of their capability to obtain an abnormal muscle activity whereas the EEG-based features offer the supplementary information in neural dynamics. Multimodal frameworks that combine EEG and EMG signals have also been shown to enhance accuracy of detection. The use of new models of computation, such as convolutional neural networks and hybrid classifiers, has made additional improvements to the per-performance, yet issues of data variability and generalization persist. Conclusions: Signal processing and smart algorithms have also led to significant development in automated RBD detection. The results of this work are promising but more efforts are needed to work on standardized, reliable and clinically relevant systems. Future studies need to work on increasing the model interpretability, whereas feature selection should be optimized, and need validation on a wide range of datasets to facilitate the implementation in the real world.Overall, automated RBD detection is one of the rapidly developing areas that can help diagnose the disorder earlier, conduct mass screening, and gain a deeper insight into sleep-related disorders.

Background: Sleep disorders like insomnia, obstructive sleep apnea (OSA), REM behavior disorder etc. are nowadays diagnosed through the Internet of Things (IoT)-enabled sys-tems that monitor and analyze the subject's sleep data. Health IoT networks are rife with communications of sensitive physiological data from wearable EEG, ECG, SpO₂ and res-piratory sensors. However, these networks face threats from anomalous traffic flows, sig-nal sabotage and data integrity violation. In this paper, an AI-based hybrid detection and classification framework is proposed for secure Sleep Health IoT (S-HIoT) networks. The integrated CNN, BiLSTM and RF model provides a proposed framework for joint sleep-stage classification and network anomaly detection. To this end, a multi-objective loss function is proposed for jointly optimizing the physiological state prediction and se-cure traffic monitoring. Experimental validation using the Sleep-EDF and CICIoMT2024 datasets demonstrate a classification accuracy of 97.8% for sleep staging, and 98.6% for network detection with low inference latency (

Neurological disorders are different type of health disease associated with Central and Peripheral Nervous system that include Brain, spinal cord & they includes various networks within the body or just a disorder spectrum. The burden of these diseases, including neurodegenerative conditions such as Alzheimer’s and Parkinson’s disease, other disorders of neural development, and autoimmune neurological diseases is great for individuals, families, and healthcare systems worldwide. The array of symptoms ranging from cognitive and motor deficits to sensory and emotional dysfunctions with which the clinical features manifest in each disease make it particularly complicated to diagnose and treat these disorders. This research article has been devoted primarily to the etiology, diagnostic developments and treatment options in neurological diseases. This approach fosters an understanding of the genetic, environmental and physiological factors contributing to these conditions. The advancements in diagnostic methods, utilizing imaging modalities, biomarkers and neurophysiology to improve the early detection of HCM (with further monitoring). This article also examines current and emerging therapies including pharmacological, gene therapy, stem cell and neurorehabilitation strategies. Review the most up-to-date clinical and experimental research, providing a classification of neurological diseases with incidence. Through a perspective on current therapeutic modalities, reveal the potential hurdles associated with treating neurological diseases together with some of the recent successes that may be heralding higher patient quality of life and outcomes. The nature of these technical advancements can be crucial to their success and the wearability, usability, and efficacy need to be evaluated by professionals from multiple disciplines such as neurology psychiatry genetics and biomedical engineering rather than a single field as neurological disorders are highly heterogeneous. The study highlights the benefits of such an interprofessional approach for better tools that will open doors for integration of solution in clinical practice