Classification of Fatigue Phases in Healthy and Diabetic Adults Using Wearable Sensor.

Fatigue is defined as "a loss of force-generating capacity" in a muscle that can intensify tremor. Tremor quantification can facilitate early detection of fatigue onset so that preventative or corrective controls can be taken to minimize work-related injuries and improve the performance of tasks that require high-levels of accuracy. We focused on developing a system that recognizes and classifies voluntary effort and detects phases of fatigue. The experiment was designed to extract and evaluate hand-tremor data during the performance of both rest and effort tasks. The data were collected from the wrist and finger of the participant's dominant hand. To investigate tremor, time, frequency domain features were extracted from the accelerometer signal for segments of 45 and 90 samples/window. Analysis using advanced signal processing and machine-learning techniques such as decision tree, k-nearest neighbor, support vector machine, and ensemble classifiers were applied to discover models to classify rest and effort tasks and the phases of fatigue. Evaluation of the classifier's performance was assessed based on various metrics using 5-fold cross-validation. The recognition of rest and effort tasks using an ensemble classifier based on the random subspace and window length of 45 samples was deemed to be the most accurate (96.1%). The highest accuracy (~98%) that distinguished between early and late fatigue phases was achieved using the same classifier and window length.

Secure communication for FSO links in the presence of eavesdropper with generic location and orientation.

When the beam waist at the receiver is significantly larger than the receiver size, free-space optical (FSO) links may be vulnerable to some optical tapping risks at the physical layer. In this paper, we conduct a new framework for the analysis of the secrecy performance in terms of the secrecy outage probability (SOP) of FSO systems affected by gamma-gamma (GG) turbulence-induced fading channels with pointing errors. As a key feature, we evaluate the SOP in the presence of an external eavesdropper with generic location and orientation. For that reason, a new misalignment error model is proposed to consider a non-orthogonal optical beam with respect to the photodetector plane at the eavesdropper's receiver, where the effective area is determined by a rotated ellipse. New approximate and asymptotic solutions at high signal-to-noise-ratio (SNR) for the secrecy performance are obtained in closed-form, which are verified by exact Monte Carlo simulations. By using the developed expressions, we analyze in greater detail some effects such as the SNR of the eavesdropper's channel, the normalized beamwidth at the receiver-side, and the location and orientation of the eavesdropper on the secrecy performance for different turbulence conditions.

Effect of eddy diffusivity ratio on underwater optical scintillation index.

The performance of underwater optical wireless communication systems is severely affected by the turbulence that occurs due to the fluctuations in the index of refraction. Most previous studies assume a simplifying, yet inaccurate, assumption in the turbulence spectrum model that the eddy diffusivity ratio is equal to unity. It is, however, well known that the eddy diffusivities of temperature and salt are different from each other in most underwater environments. In this paper, we obtain a simplified spatial power spectrum model of turbulent fluctuations of the seawater refraction index as an explicit function of eddy diffusivity ratio. Using the derived model, we obtain the scintillation index of optical plane and spherical waves and investigate the effect of the eddy diffusivity ratio.

Planar broad-band and wide-angle hybrid plasmonic IMI filters with induced transmission for visible light applications.

This work presents a technique for the design of visible optical filters using a hybrid plasmonic insulator-metal-insulator (IMI) structure. The proposed IMI visible light filter exhibits high transmission (∼91%) and an insertion loss of ∼0.4 dB with almost an omnidirectional field-of-view (0°-70°), a feature that is important for light collection in miniaturized devices. The proposed design also has a minimal polarization dependent loss of 0.2 dB at an angle of incidence of 60°. The effects of design parameters on the filter's performance are studied. Design rules of the filter are deduced along with physical justifications of the obtained results.

Angle-tolerant hybrid plasmonic filters for visible light communications.

This work presents what we believe is a novel design of a hybrid plasmonic-transmission blue filter for visible light communication systems that employ yellow phosphor-coated blue light-emitting diodes. The proposed filter balances the trade-off between transmission performance and tolerance to variation in angles of incidence (AOIs) while maintaining a low cost with limited complexity design. The designed filter operation is based upon quasi-plasmon mode excitation in a hybrid structure of alternating layers of silver and titanium dioxide over a silica substrate. A primary design approach for a hybrid plasmonic filter of five alternating layers is illustrated in detail. Needle optimization technique is further applied to achieve the required filter performance. The designed filter has an insertion loss of ∼1 dB over a spectral range of 400-485 nm and a minimal close to zero polarization-dependent loss for a wide range of AOI (slightly above 50°). The tolerance of the proposed design against fabrication errors is also tested. The performances of the proposed filters are tested for individual and simultaneous variations from the designed thicknesses, with a ±10% standard deviation from each layer's thickness.

Energy efficient cooperation in underlay RFID cognitive networks for a water smart home.

Shrinking water resources all over the world and increasing costs of water consumption have prompted water users and distribution companies to come up with water conserving strategies. We have proposed an energy-efficient smart water monitoring application in [1], using low power RFIDs. In the home environment, there exist many primary interferences within a room, such as cell-phones, Bluetooth devices, TV signals, cordless phones and WiFi devices. In order to reduce the interference from our proposed RFID network for these primary devices, we have proposed a cooperating underlay RFID cognitive network for our smart application on water. These underlay RFIDs should strictly adhere to the interference thresholds to work in parallel with the primary wireless devices [2]. This work is an extension of our previous ventures proposed in [2,3], and we enhanced the previous efforts by introducing a new system model and RFIDs. Our proposed scheme is mutually energy efficient and maximizes the signal-to-noise ratio (SNR) for the RFID link, while keeping the interference levels for the primary network below a certain threshold. A closed form expression for the probability density function (pdf) of the SNR at the destination reader/writer and outage probability are derived. Analytical results are verified through simulations. It is also shown that in comparison to non-cognitive selective cooperation, this scheme performs better in the low SNR region for cognitive networks. Moreover, the hidden Markov model's (HMM) multi-level variant hierarchical hidden Markov model (HHMM) approach is used for pattern recognition and event detection for the data received for this system [4]. Using this model, a feedback and decision algorithm is also developed. This approach has been applied to simulated water pressure data from RFID motes, which were embedded in metallic water pipes.

ECG-based cardiac arrhythmias detection through ensemble learning and fusion of deep spatial-temporal and long-range dependency features.

Cardiac arrhythmia is one of the prime reasons for death globally. Early diagnosis of heart arrhythmia is crucial to provide timely medical treatment. Heart arrhythmias are diagnosed by analyzing the electrocardiogram (ECG) of patients. Manual analysis of ECG is time-consuming and challenging. Hence, effective automated detection of heart arrhythmias is important to produce reliable results. Different deep-learning techniques to detect heart arrhythmias such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Transformer, and Hybrid CNN-LSTM were proposed. However, these techniques, when used individually, are not sufficient to effectively learn multiple features from the ECG signal. The fusion of CNN and LSTM overcomes the limitations of CNN in the existing studies as CNN-LSTM hybrids can extract spatiotemporal features. However, LSTMs suffer from long-range dependency issues due to which certain features may be ignored. Hence, to compensate for the drawbacks of the existing models, this paper proposes a more comprehensive feature fusion technique by merging CNN, LSTM, and Transformer models. The fusion of these models facilitates learning spatial, temporal, and long-range dependency features, hence, helping to capture different attributes of the ECG signal. These features are subsequently passed to a majority voting classifier equipped with three traditional base learners. The traditional learners are enriched with deep features instead of handcrafted features. Experiments are performed on the MIT-BIH arrhythmias database and the model performance is compared with that of the state-of-art models. Results reveal that the proposed model performs better than the existing models yielding an accuracy of 99.56%.

Enhancing ECG-based heart age: impact of acquisition parameters and generalization strategies for varying signal morphologies and corruptions.

Electrocardiogram (ECG) is a non-invasive approach to capture the overall electrical activity produced by the contraction and relaxation of the cardiac muscles. It has been established in the literature that the difference between ECG-derived age and chronological age represents a general measure of cardiovascular health. Elevated ECG-derived age strongly correlates with cardiovascular conditions (e.g., atherosclerotic cardiovascular disease). However, the neural networks for ECG age estimation are yet to be thoroughly evaluated from the perspective of ECG acquisition parameters. Additionally, deep learning systems for ECG analysis encounter challenges in generalizing across diverse ECG morphologies in various ethnic groups and are susceptible to errors with signals that exhibit random or systematic distortions To address these challenges, we perform a comprehensive empirical study to determine the threshold for the sampling rate and duration of ECG signals while considering their impact on the computational cost of the neural networks. To tackle the concern of ECG waveform variability in different populations, we evaluate the feasibility of utilizing pre-trained and fine-tuned networks to estimate ECG age in different ethnic groups. Additionally, we empirically demonstrate that finetuning is an environmentally sustainable way to train neural networks, and it significantly decreases the ECG instances required (by more than 100 × ) for attaining performance similar to the networks trained from random weight initialization on a complete dataset. Finally, we systematically evaluate augmentation schemes for ECG signals in the context of age estimation and introduce a random cropping scheme that provides best-in-class performance while using shorter-duration ECG signals. The results also show that random cropping enables the networks to perform well with systematic and random ECG signal corruptions.

Deep learning for ECG Arrhythmia detection and classification: an overview of progress for period 2017-2023.

Cardiovascular diseases are a leading cause of mortality globally. Electrocardiography (ECG) still represents the benchmark approach for identifying cardiac irregularities. Automatic detection of abnormalities from the ECG can aid in the early detection, diagnosis, and prevention of cardiovascular diseases. Deep Learning (DL) architectures have been successfully employed for arrhythmia detection and classification and offered superior performance to traditional shallow Machine Learning (ML) approaches. This survey categorizes and compares the DL architectures used in ECG arrhythmia detection from 2017-2023 that have exhibited superior performance. Different DL models such as Convolutional Neural Networks (CNNs), Multilayer Perceptrons (MLPs), Transformers, and Recurrent Neural Networks (RNNs) are reviewed, and a summary of their effectiveness is provided. This survey provides a comprehensive roadmap to expedite the acclimation process for emerging researchers willing to develop efficient algorithms for detecting ECG anomalies using DL models. Our tailored guidelines bridge the knowledge gap allowing newcomers to align smoothly with the prevailing research trends in ECG arrhythmia detection. We shed light on potential areas for future research and refinement in model development and optimization, intending to stimulate advancement in ECG arrhythmia detection and classification.

Hypoglycemia Detection Using Hand Tremors: Home Study of Patients With Type 1 Diabetes.

BACKGROUND: Diabetes affects millions of people worldwide and is steadily increasing. A serious condition associated with diabetes is low glucose levels (hypoglycemia). Monitoring blood glucose is usually performed by invasive methods or intrusive devices, and these devices are currently not available to all patients with diabetes. Hand tremor is a significant symptom of hypoglycemia, as nerves and muscles are powered by blood sugar. However, to our knowledge, no validated tools or algorithms exist to monitor and detect hypoglycemic events via hand tremors. OBJECTIVE: In this paper, we propose a noninvasive method to detect hypoglycemic events based on hand tremors using accelerometer data. METHODS: We analyzed triaxial accelerometer data from a smart watch recorded from 33 patients with type 1 diabetes for 1 month. Time and frequency domain features were extracted from acceleration signals to explore different machine learning models to classify and differentiate between hypoglycemic and nonhypoglycemic states. RESULTS: The mean duration of the hypoglycemic state was 27.31 (SD 5.15) minutes per day for each patient. On average, patients had 1.06 (SD 0.77) hypoglycemic events per day. The ensemble learning model based on random forest, support vector machines, and k-nearest neighbors had the best performance, with a precision of 81.5% and a recall of 78.6%. The results were validated using continuous glucose monitor readings as ground truth. CONCLUSIONS: Our results indicate that the proposed approach can be a potential tool to detect hypoglycemia and can serve as a proactive, nonintrusive alert mechanism for hypoglycemic events.

Understanding Patient Beliefs in Using Technology to Manage Diabetes: Path Analysis Model From a National Web-Based Sample.

BACKGROUND:  With 425 million individuals globally living with diabetes, it is critical to support the self-management of this life-threatening condition. However, adherence and engagement with existing technologies are inadequate and need further research. OBJECTIVE:  The objective of our study was to develop an integrated belief model that helps identify the significant constructs in predicting intention to use a diabetes self-management device for the detection of hypoglycemia. METHODS:  Adults with type 1 diabetes living in the United States were recruited through Qualtrics to take a web-based questionnaire that assessed their preferences for a device that monitors their tremors and alerts them of the onset of hypoglycemia. As part of this questionnaire, a section focused on eliciting their response to behavioral constructs from the Health Belief Model, Technology Acceptance Model, and others. RESULTS:  A total of 212 eligible participants responded to the Qualtrics survey. Intention to use a device for the self-management of diabetes was well predicted (R2=0.65; F12,199=27.19; P<.001) by 4 main constructs. The most significant constructs were perceived usefulness (ß=.33; P<.001) and perceived health threat (ß=.55; P<.001) followed by cues to action (ß=.17; P<.001) and a negative effect from resistance to change (ß=-.19; P<.001). Older age (ß=.025; P<.001) led to an increase in their perceived health threat. CONCLUSIONS: For individuals to use such a device, they need to perceive it as useful, perceive diabetes as life-threatening, regularly remember to perform actions to manage their condition, and exhibit less resistance to change. The model predicted the intention to use a diabetes self-management device as well, with several constructs found to be significant. This mental modeling approach can be complemented in future work by field-testing with physical prototype devices and assessing their interaction with the device longitudinally.

Unveiling the future of breast cancer assessment: a critical review on generative adversarial networks in elastography ultrasound.

Elastography Ultrasound provides elasticity information of the tissues, which is crucial for understanding the density and texture, allowing for the diagnosis of different medical conditions such as fibrosis and cancer. In the current medical imaging scenario, elastograms for B-mode Ultrasound are restricted to well-equipped hospitals, making the modality unavailable for pocket ultrasound. To highlight the recent progress in elastogram synthesis, this article performs a critical review of generative adversarial network (GAN) methodology for elastogram generation from B-mode Ultrasound images. Along with a brief overview of cutting-edge medical image synthesis, the article highlights the contribution of the GAN framework in light of its impact and thoroughly analyzes the results to validate whether the existing challenges have been effectively addressed. Specifically, This article highlights that GANs can successfully generate accurate elastograms for deep-seated breast tumors (without having artifacts) and improve diagnostic effectiveness for pocket US. Furthermore, the results of the GAN framework are thoroughly analyzed by considering the quantitative metrics, visual evaluations, and cancer diagnostic accuracy. Finally, essential unaddressed challenges that lie at the intersection of elastography and GANs are presented, and a few future directions are shared for the elastogram synthesis research.

Estimating age and gender from electrocardiogram signals: A comprehensive review of the past decade.

Twelve lead electrocardiogram signals capture unique fingerprints about the body's biological processes and electrical activity of heart muscles. Machine learning and deep learning-based models can learn the embedded patterns in the electrocardiogram to estimate complex metrics such as age and gender that depend on multiple aspects of human physiology. ECG estimated age with respect to the chronological age reflects the overall well-being of the cardiovascular system, with significant positive deviations indicating an aged cardiovascular system and a higher likelihood of cardiovascular mortality. Several conventional, machine learning, and deep learning-based methods have been proposed to estimate age from electronic health records, health surveys, and ECG data. This manuscript comprehensively reviews the methodologies proposed for ECG-based age and gender estimation over the last decade. Specifically, the review highlights that elevated ECG age is associated with atherosclerotic cardiovascular disease, abnormal peripheral endothelial dysfunction, and high mortality, among many other cardiovascular disorders. Furthermore, the survey presents overarching observations and insights across methods for age and gender estimation. This paper also presents several essential methodological improvements and clinical applications of ECG-estimated age and gender to encourage further improvements of the state-of-the-art methodologies.

Diabetes Management Experience and the State of Hypoglycemia: National Online Survey Study.

BACKGROUND: Hypoglycemia, or low blood sugar levels, in people with diabetes can be a serious life-threatening condition, and serious outcomes can be avoided if low levels of blood sugar are proactively detected. Although technologies exist to detect the onset of hypoglycemia, they are invasive or costly or exhibit a high incidence of false alarms. Tremors are commonly reported symptoms of hypoglycemia and may be used to detect hypoglycemic events, yet their onset is not well researched or understood. OBJECTIVE: This study aimed to understand diabetic patients' perceptions of hypoglycemic tremors, as well as their user experiences with technology to manage diabetes, and expectations from a self-management tool to ultimately inform the design of a noninvasive and cost-effective technology that detects tremors associated with hypoglycemia. METHODS: A cross-sectional internet panel survey was administered to adult patients with type 1 diabetes using the Qualtrics platform in May 2019. The questions focused on 3 main constructs: (1) perceived experiences of hypoglycemia, (2) experiences and expectations about a diabetes management device and mobile app, and (3) beliefs and attitudes regarding intention to use a diabetes management device. The analysis in this paper focuses on the first two constructs. Nonparametric tests were used to analyze the Likert scale data, with a Mann-Whitney U test, Kruskal-Wallis test, and Games-Howell post hoc test as applicable, for subgroup comparisons to highlight differences in perceived frequency, severity, and noticeability of hypoglycemic tremors across age, gender, years living with diabetes, and physical activity. RESULTS: Data from 212 respondents (129 [60.8%] females) revealed statistically significant differences in perceived noticeability of tremors by gender, whereby males noticed their tremors more (P<.001), and age, with the older population reporting lower noticeability than the young and middle age groups (P<.001). Individuals living longer with diabetes noticed their tremors significantly less than those with diabetes for ≤1 year but not in terms of frequency or severity. Additionally, the majority of our participants (150/212, 70.7%) reported experience with diabetes-monitoring devices. CONCLUSIONS: Our findings support the need for cost-efficient and noninvasive continuous monitoring technologies. Although hypoglycemic tremors were perceived to occur frequently, such tremors were not found to be severe compared with other symptoms such as sweating, which was the highest rated symptom in our study. Using a combination of tremor and galvanic skin response sensors may show promise in detecting the onset of hypoglycemic events.

Neural Signatures of Handgrip Fatigue in Type 1 Diabetic Men and Women.

Type 1 diabetes (T1D) is associated with reduced muscular strength and greater muscle fatigability. Along with changes in muscular mechanisms, T1D is also linked to structural changes in the brain. How the neurophysiological mechanisms underlying muscle fatigue is altered with T1D and sex related differences of these mechanisms are still not well investigated. The aim of this study was to determine the impact of T1D on the neural correlates of handgrip fatigue and examine sex and T1D related differences in neuromuscular performance parameters, neural activation and functional connectivity patterns between the motor regions of the brain. Forty-two adults, balanced by condition (healthy vs T1D) and sex (male vs female), and performed submaximal isometric handgrip contractions until voluntary exhaustion. Initial strength, endurance time, strength loss, force variability, and complexity measures were collected. Additionally, hemodynamic responses from motor-function related cortical regions, using functional near-infrared spectroscopy (fNIRS), were obtained. Overall, females exhibited lower initial strength (p < 0.0001), and greater strength loss (p = 0.023) than males. While initial strength was significantly lower in the T1D group (p = 0.012) compared to the healthy group, endurance times and strength loss were comparable between the two groups. Force complexity, measured as approximate entropy, was found to be lower throughout the experiment for the T1D group (p = 0.0378), indicating lower online motor adaptability. Although, T1D and healthy groups fatigued similarly, only the T1D group exhibited increased neural activation in the left (p = 0.095) and right (p = 0.072) supplementary motor areas (SMA) over time. A sex × condition × fatigue interaction effect (p = 0.044) showed that while increased activation was observed in both T1D females and healthy males from the Early to Middle phase, this was not observed in healthy females or T1D males. These findings demonstrate that T1D adults had lower adaptability to fatigue which they compensated for by increasing neural effort. This study highlights the importance of examining both neural and motor performance signatures when investigating the impact of chronic conditions on neuromuscular fatigue. Additionally, the findings have implications for developing intervention strategies for training, rehabilitation, and ergonomics considerations for individuals with chronic conditions.

Anatomical Region-Specific In Vivo Wireless Communication Channel Characterization.

In vivo wireless body area networks and their associated technologies are shaping the future of healthcare by providing continuous health monitoring and noninvasive surgical capabilities, in addition to remote diagnostic and treatment of diseases. To fully exploit the potential of such devices, it is necessary to characterize the communication channel, which will help to build reliable and high-performance communication systems. This paper presents an in vivo wireless communication channel characterization for male torso both numerically and experimentally (on a human cadaver) considering various organs at 915 MHz and 2.4 GHz. A statistical path loss (PL) model is introduced, and the anatomical region-specific parameters are provided. It is found that the mean PL in decibel scale exhibits a linear decaying characteristic rather than an exponential decaying profile inside the body, and the power decay rate is approximately twice at 2.4 GHz as compared to 915 MHz. Moreover, the variance of shadowing increases significantly as the in vivo antenna is placed deeper inside the body since the main scatterers are present in the vicinity of the antenna. Multipath propagation characteristics are also investigated to facilitate proper waveform designs in the future wireless healthcare systems, and a root-mean-square delay spread of 2.76 ns is observed at 5 cm depth. Results show that the in vivo channel exhibit different characteristics than the classical communication channels, and location dependence is very critical for accurate, reliable, and energy-efficient link budget calculations.