Healthcare and the Internet of Medical Things: Applications, Trends, Key Challenges, and Proposed Resolutions

Informatics, Journal Year: 2024, Volume and Issue: 11(3), P. 47 - 47

Published: July 16, 2024

In recent years, the Internet of medical things (IoMT) has become a significant technological advancement in healthcare sector. This systematic review aims to identify and summarize various applications, key challenges, proposed technical solutions within this domain, based on comprehensive analysis existing literature. highlights diverse applications IoMT, including mobile health (mHealth) remote biomarker detection, hybrid RFID-IoT for scrub distribution operating rooms, IoT-based disease prediction using machine learning, efficient sharing personal records through searchable symmetric encryption, blockchain, IPFS. Other notable include management systems, non-invasive real-time blood glucose measurement devices, distributed ledger technology (DLT) platforms, ultra-wideband (UWB) radar pulse oximeters, accident emergency informatics (A&EI), integrated wearable smart patches. The challenges identified privacy protection, sustainable power sources, sensor intelligence, human adaptation sensors, data speed, device reliability, storage efficiency. mitigations encompass network control, cryptography, edge-fog computing, alongside rigorous risk planning. also identifies trends advancements IoMT architecture, monitoring innovations, integration learning AI, enhanced security measures. makes several novel contributions compared literature, (1) categorization extending beyond traditional use cases emerging technologies such as UWB systems DLT platforms; (2) an in-depth AI highlighting innovative approaches monitoring; (3) detailed examination measures, proposing advanced cryptographic blockchain implementations enhance protection; (4) identification future research directions, providing roadmap addressing current limitations advancing scientific understanding healthcare. By suggesting work advance

Language: Английский

---

Energy Efficient Priority-Based Hybrid MAC Protocol for IoT-Enabled WBAN Systems

IEEE Sensors Journal, Journal Year: 2023, Volume and Issue: 23(12), P. 13524 - 13538

Published: May 15, 2023

Among the wireless body area network (WBAN) scarce resources, energy resource is an essential on which most of WBAN biomedical devices activities depend upon. The are usually battery-powered and if they fail to operate as required because battery power drain, system would become unreliable, this could lead life-threatening situations. Consequently, it be advantage logical minimize consumption wastage issues achieve energy-efficient system. Following this, we proposed a coordinated superframe duty cycle hybrid MAC (SDC-HYMAC) protocol enhance efficiency prolong devices' lifetime. To improve system, introduced different management strategies including design priority-based slot-allocation scheme timeslot wastage. Also, (SDC) accurately select appropriate order (SO) based traffic information priority level save We compared SDC-HYMAC with other related protocols like MG-HYMAC, HyMAC, CPMAC for sake validation, simulated in MATLAB. outcome simulation results revealed that performed better than existing using performance metrics convergence speed, efficiency, delay, packet drop ratio,

Language: Английский

---

Water Quality Assessment Tool for On-Site Water Quality Monitoring

IEEE Sensors Journal, Journal Year: 2024, Volume and Issue: 24(10), P. 16450 - 16466

Published: April 12, 2024

Reliable water quality monitoring requires on-site processing and assessment of data in near real-time. This helps to promptly detect changes quality, prevent biodiversity loss, safeguard the health well-being communities, mitigate agricultural problems. To this end, we proposed a Highway-Bidirectional Long Short-term Memory (Highway-BiLSTM)-based classification tool for potential integration into an edge-enabled system facilitate classification. The performance classifier was validated by comparing it with several baseline classifiers. outperformed terms accuracy, precision, sensitivity, F1-score, confusion matrix. Specifically, surpassed random forest (RF) 2% F1-score. Moreover, achieved increase 4% F1-score classifying compared Gradient Boosting classifier. Additionally, method has 3% precision support vector machine (SVM) artificial neural network (ANN) 1% Finally, demonstrated rare errors accurately complex samples. These findings suggest that our could be used effectively classify aid accurate decision making environmental management.

Language: Английский

---

Autoencoder-Based Neural Network Model for Anomaly Detection in Wireless Body Area Networks

IoT, Journal Year: 2024, Volume and Issue: 5(4), P. 852 - 870

Published: Nov. 25, 2024

In medical healthcare services, Wireless Body Area Networks (WBANs) are enabler tools for tracking conditions by monitoring some critical vital signs of the human body. Healthcare providers and consultants use such collected data to assess status patients in intensive care units (ICU) at hospitals or elderly facilities. However, subject anomalies caused faulty sensor readings, malicious attacks, severe health degradation situations that professionals should investigate further. As a result, anomaly detection plays crucial role maintaining quality across various real-world applications, including healthcare, where it is early abnormal conditions. Numerous techniques have been proposed literature, employing methods like statistical analysis machine learning identify WBANs. lack normal datasets makes training supervised models difficult, highlighting need unsupervised approaches. this paper, novel, efficient, effective model WBANs developed using autoencoder convolutional neural network (CNN) technique. Due their ability reconstruct completely manner reconstruction error, autoencoders hold great potential. Real-world physiological from PhysioNet dataset evaluated suggested model’s performance. The experimental findings demonstrate efficacy, which provides high accuracy, as reported F1-Score 0.96 with batch size 256 along mean squared logarithmic error (MSLE) below 0.002. Compared existing models, outperforms them effectiveness efficiency.

Language: Английский

---

ClinClip: a Multimodal Language Pre-training model integrating EEG data for enhanced English medical listening assessment

Frontiers in Neuroscience, Journal Year: 2025, Volume and Issue: 18

Published: Jan. 7, 2025

In the field of medical listening assessments,accurate transcription and effective cognitive load management are critical for enhancing healthcare delivery. Traditional speech recognition systems, while successful in general applications often struggle contexts where state listener plays a significant role. These conventional methods typically rely on audio-only inputs lack ability to account listener's load, leading reduced accuracy effectiveness complex environments. To address these limitations, this study introduces ClinClip, novel multimodal model that integrates EEG signals with audio data through transformer-based architecture. ClinClip is designed dynamically adjust listener, thereby improving robustness settings. The leverages cognitive-enhanced strategies, including EEG-based modulation hierarchical fusion data, overcome challenges faced by traditional methods. Experiments conducted four datasets-EEGEyeNet, DEAP, PhyAAt, eSports Sensors-demonstrate significantly outperforms six state-of-the-art models both Word Error Rate (WER) Cognitive Modulation Efficiency (CME). results underscore model's handling scenarios highlight its potential improve assessments. By addressing aspects process. contributes more reliable delivery, offering substantial advancement over approaches.

Language: Английский

---

A Review of Deep Learning Applications in Intrusion Detection Systems: Overcoming Challenges in Spatiotemporal Feature Extraction and Data Imbalance

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(3), P. 1552 - 1552

Published: Feb. 3, 2025

In the rapid development of Internet Things (IoT) and large-scale distributed networks, Intrusion Detection Systems (IDS) face significant challenges in handling complex spatiotemporal features addressing data imbalance issues. This article systematically reviews recent advancements applying deep learning techniques IDS, focusing on core feature extraction imbalance. First, this analyzes dependencies Convolutional Neural Networks (CNN) Recurrent (RNN) network traffic examines main methods these models use to solve problem. Next, impact IDS performance is explored, effectiveness various augmentation techniques, including Generative Adversarial (GANs) resampling methods, improving detection minority class attacks assessed. Finally, paper highlights current research gaps proposes future directions optimize further enhance capabilities robustness environments. review provides researchers with a comprehensive perspective, helping them identify field laying foundation for efforts.

Language: Английский

---

Mental Disorder Assessment in IoT-Enabled WBAN Systems with Dimensionality Reduction and Deep Learning

Journal of Sensor and Actuator Networks, Journal Year: 2025, Volume and Issue: 14(3), P. 49 - 49

Published: May 7, 2025

Mental health is an important aspect of individual’s overall well-being. Positive mental correlated with enhanced cognitive function, emotional regulation, and motivation, which, in turn, foster increased productivity personal growth. Accurate interpretable predictions disorders are crucial for effective intervention. This study develops a hybrid deep learning model, integrating CNN BiLSTM applied to EEG data, address this need. To conduct comprehensive analysis disorders, we propose two-tiered classification strategy. The first tier classifies the main disorder categories, while second specific within each category provide detailed insights into classifying disorder. methodology incorporates techniques handle missing data (kNN imputation), class imbalance (SMOTE), high dimensionality (PCA). enhance clinical trust understanding, model’s explained using local model-agnostic explanations (LIME). Baseline methods proposed CNN–BiLSTM model were implemented evaluated at both tiers PSD FC features. On unseen test our demonstrated 3–9% improvement prediction accuracy 4–6% compared existing methods. approach offers potential more reliable explainable diagnostic tools prediction.

Language: Английский

---

Advancing Speech Emotion Recognition for Urdu: Methodological Developments in Low-Resource Contexts

Lecture notes in electrical engineering, Journal Year: 2025, Volume and Issue: unknown, P. 220 - 244

Published: Jan. 1, 2025

Language: Английский

---

Energy-Efficient Multichannel Hybrid MAC Protocol for IoT-Enabled WBAN Systems

IEEE Sensors Journal, Journal Year: 2023, Volume and Issue: 23(22), P. 27967 - 27983

Published: Oct. 12, 2023

Internet-of-Things (IoT)-enabled wireless body area networks (WBANs) are resource-constrained in nature (energy, bandwidth, and time-slot resources); hence, their performance healthcare monitoring often deteriorates as the number of active IoT devices sharing network increases. Consequently, improving efficiency IoT-enabled WBAN systems is essential for monitoring. Hence, we propose an energy-efficient multichannel hybrid medium access control (MAC) (MC-HYMAC) protocol that combines benefits carrier sense multiple with collision avoidance (CSMA/CA) time division (TDMA) protocols to improve overall systems. We also proposed adaptive power scheme, management channel utilization mechanism, dynamic back-off policy efficiency. In addition, applied a finite-state discrete-time Markov model determine traffic arrival pattern analyze transition states biomedical facilitate optimal decision-making enhanced network. Standard metrics, such energy efficiency, throughput, delay, packet drop ratio, lifetime, were used evaluate compare existing MAC protocols.

Language: Английский

---

Internet of Things for Emotion Care: Advances, Applications, and Challenges

Cognitive Computation, Journal Year: 2024, Volume and Issue: 16(6), P. 2812 - 2832

Published: Aug. 7, 2024

Language: Английский

---