An IoT patient monitoring based on fog computing and data mining: Cardiac arrhythmia usecase

Internet of Things, Journal Year: 2020, Volume and Issue: 11, P. 100251 - 100251

Published: June 20, 2020

Language: Английский

---

Lightweight Cryptographic Protocols for IoT-Constrained Devices: A Survey

IEEE Internet of Things Journal, Journal Year: 2020, Volume and Issue: 8(6), P. 4132 - 4156

Published: Sept. 24, 2020

Internet of Things (IoT) is an emergent and evolving technology, interconnecting the cyber physical worlds. IoT technology finds applications in a broad spectrum areas such as homes, health, water sanitation, transportation, environmental monitoring. However, endless opportunities benefits come with many security challenges due to reduced computation, communication, storage, energy capabilities smart devices. Several computationally lightweight cryptographic protocols exist for these resource-constrained solutions render resource-rich ends systems (e.g., edge, fog, or cloud modes) vulnerable nodes at those have capacity heavier protocols, they operate relatively more malicious environments. This asymmetric computational nature requires that can adapt resource availability node operate. survey describes structure, devices end, platforms, classifies existing protocols. The comparative analysis along their advantages, drawbacks, vulnerabilities highlights need elastic which are capable adapting different systems.

Language: Английский

---

A Review on the State of the Art in Atrial Fibrillation Detection Enabled by Machine Learning

IEEE Reviews in Biomedical Engineering, Journal Year: 2020, Volume and Issue: 14, P. 219 - 239

Published: Feb. 27, 2020

Atrial Fibrillation (AF) the most commonly occurring type of cardiac arrhythmia is one main causes morbidity and mortality worldwide. The timely diagnosis AF an equally important challenging task because its asymptomatic episodic nature. In this paper, state-of-the-art ECG data-based machine learning models signal processing techniques applied for auto are reviewed. Moreover, key biomarkers on common methods equipment used collection data discussed. Besides that, modern wearable implantable sensing technologies gathering presented briefly. end, challenges associated with development solutions also highlighted. This first review paper kind that comprehensively presents a discussion all these aspects related to auto-diagnosis in place. It observed there dire need low energy cost but accurate proactive management AF.

Language: Английский

---

A Joint Deep Learning and Internet of Medical Things Driven Framework for Elderly Patients

IEEE Access, Journal Year: 2020, Volume and Issue: 8, P. 75822 - 75832

Published: Jan. 1, 2020

Deep learning (DL) driven cardiac image processing methods manage and monitor the massive medical data collected by internet of things (IoT) based on wearable devices. A Joint DL IoT platform are known as Deep-IoMT that extracts accurate from noisy conventional devices tools. Besides, smart dynamic technological trends have caught attention every corner such as, healthcare, which is possible through portable lightweight sensor-enabled Tiny size resource-constrained nature restrict them to perform several tasks at a time. Thus, energy drain, limited battery lifetime, high packet loss ratio (PLR) keys challenges be tackled carefully for ubiquitous care. Sustainability (i.e., longer lifetime), efficiency, reliability vital ingredients empower cost-effective pervasive healthcare environment. key contribution this paper sixth fold. First, novel self-adaptive power control-based enhanced efficient-aware approach (EEA) proposed reduce consumption enhance lifetime reliability. The EEA constant TPC evaluated adopting real-time traces static sitting) cycling) activities images. Second, joint DL-IoMT framework remote elderly patients. Third, layered architecture IoMT proposed. Forth, model features wireless channel body postures. Fifth, network performance optimized introducing sustainability, PLR average threshold RSSI indicators. Sixth, Use-case image-enabled patient’s monitoring Finally, it revealed experimental results in MATLAB scheme performs better than enhancing during transmission healthcare.

Language: Английский

---

A Robust Interpretable Deep Learning Classifier for Heart Anomaly Detection Without Segmentation

IEEE Journal of Biomedical and Health Informatics, Journal Year: 2020, Volume and Issue: 25(6), P. 2162 - 2171

Published: Sept. 30, 2020

Traditionally, abnormal heart sound classification is framed as a three-stage process. The first stage involves segmenting the phonocardiogram to detect fundamental sounds; after which features are extracted and performed. Some researchers in field argue segmentation step an unwanted computational burden, whereas others embrace it prior feature extraction. When comparing accuracies achieved by studies that have segmented sounds before analysis with those who overlooked step, question of whether segment extraction still open. In this study, we explicitly examine importance for classification, then seek apply obtained insights propose robust classifier detection. Furthermore, recognizing pressing need explainable Artificial Intelligence (AI) models medical domain, also unveil hidden representations learned using model interpretation techniques. Experimental results demonstrate can be plays essential role classification. Our new shown robust, stable most importantly, explainable, accuracy almost 100% on widely used PhysioNet dataset.

Language: Английский

---

Diagnosis of heart diseases by a secure Internet of Health Things system based on Autoencoder Deep Neural Network

Computer Communications, Journal Year: 2020, Volume and Issue: 162, P. 31 - 50

Published: Aug. 18, 2020

Language: Английский

---

Industrial Internet-of-Things Security Enhanced With Deep Learning Approaches for Smart Cities

IEEE Internet of Things Journal, Journal Year: 2020, Volume and Issue: 8(8), P. 6393 - 6405

Published: Dec. 3, 2020

The significant evolution of the Internet Things (IoT) enabled development numerous devices able to improve many aspects in various fields industry for smart cities where machines have replaced humans. With reduction manual work and adoption automation, are getting more efficient smarter. However, this also made data even sensitive, especially industrial segment. latter has caught attention hackers targeting Industrial IoT (IIoT) or networks, hence number malicious software, i.e., malware, increased as well. In article, we present IIoT concept applications cities, besides presenting security challenges faced by emerging area. We survey currently available deep learning (DL) techniques mainly reinforcement learning, recurrent neural convolutional highlight advantages disadvantages security-related methods. insights, open issues, future trends applying DL enhance security.

Language: Английский

---

Towards development of IoT-ML driven healthcare systems: A survey

Journal of Network and Computer Applications, Journal Year: 2021, Volume and Issue: 196, P. 103244 - 103244

Published: Oct. 20, 2021

Language: Английский

---

A novel transfer learning approach for the classification of histological images of colorectal cancer

The Journal of Supercomputing, Journal Year: 2021, Volume and Issue: 77(9), P. 9494 - 9519

Published: Feb. 10, 2021

Language: Английский

---

Explainable artificial intelligence-based edge fuzzy images for COVID-19 detection and identification

Applied Soft Computing, Journal Year: 2022, Volume and Issue: 123, P. 108966 - 108966

Published: May 13, 2022

Language: Английский

---