An Emotion Recognition Embedded System using a Lightweight Deep Learning Model.

Background: Diagnosing emotional states would improve human-computer interaction (HCI) systems to be more effective in practice. Correlations between Electroencephalography (EEG) signals and emotions have been shown in various research; therefore, EEG signal-based methods are the most accurate and informative. Methods: In this study, three Convolutional Neural Network (CNN) models, EEGNet, ShallowConvNet and DeepConvNet, which are appropriate for processing EEG signals, are applied to diagnose emotions. We use baseline removal preprocessing to improve classification accuracy. Each network is assessed in two setting ways: subject-dependent and subject-independent. We improve the selected CNN model to be lightweight and implementable on a Raspberry Pi processor. The emotional states are recognized for every three-second epoch of received signals on the embedded system, which can be applied in real-time usage in practice. Results: Average classification accuracies of 99.10% in the valence and 99.20% in the arousal for subject-dependent and 90.76% in the valence and 90.94% in the arousal for subject independent were achieved on the well-known DEAP dataset. Conclusion: Comparison of the results with the related works shows that a highly accurate and implementable model has been achieved for practice.

Ocular condition prognosis in Keratoconus patients after corneal ring implantation using artificial neural networks.

The common disorder, Keratoconus (KC), is distinguished by cumulative corneal slimming and steepening. The corneal ring implantation has become a successful surgical procedure to correct the KC patient's vision. The determination of suitable patients for the surgery alternative is among the paramount concerns of ophthalmologists. To reduce the burden on them and enhance the treatment, this research aims to previse the ocular condition of KC patients after the corneal ring implantation. It focuses on predicting post-surgical corneal topographic indices and visual characteristics. This study applied an efficacious artificial neural network approach to foretell the aforementioned ocular features of KC subjects 6 and 12 months after implanting KeraRing and MyoRing based on the accumulated data. The datasets are composed of sufficient numbers of corneal topographic maps and visual characteristics recorded from KC patients before and after implanting the rings. The visual characteristics under study are uncorrected visual acuity (UCVA), sphere (SPH), astigmatism (Ast), astigmatism orientation (Axe), and best corrected visual acuity (BCVA). In addition, the statistical data of multiple KC subjects were registered, including three effective indices of corneal topography (i.e., Ast, K-reading, and pachymetry) pre- and post-ring embedding. The outcomes represent the contribution of practical training of the introduced models to the estimation of ocular features of KC subjects following the implantation. The corneal topographic indices and visual characteristics were estimated with mean errors of 7.29% and 8.60%, respectively. Further, the errors of 6.82% and 7.65% were respectively realized for the visual characteristics and corneal topographic indices while assessing the predictions by the leave-one-out cross-validation (LOOCV) procedure. The results confirm the great potential of neural networks to guide ophthalmologists in choosing appropriate surgical candidates and their specific intracorneal rings by predicting post-implantation ocular features.

Implementation and Validation of a Novel Noninvasive blood Pressure Measurement Algorithm Based on Oscillometric Method with Obtaining International Hypertension Standards.

Background: One of the most prevalent methods in noninvasive blood pressure (BP) measurement with cuff is oscillometric, which has two different types of deflation, including linear and step deflation. With this approach, in addition to designing a novel algorithm by the step deflation method, a sample of its module was constructed and validated during clinical tests in different hospitals. Method: In this study, by controlling the valve, the pressure would be deflated through optimized steps. By real-time processing on the obtained signal from the pressure sensor, pulses in each step would be extracted. After that, in offline mode, mean arterial pressure is estimated based on curve fitting. Result: A BP simulator, various modules, and an auditory method were used to validate the algorithm and its results. During clinical tests, 80 people (men and women), 11 dialysis patients, and 69 non-dialysis (healthy or with other diseases) in the age range of 17-85 years participated. Conclusion: The obtained results compared with the BP simulator are in the standard range according to the international medical standards of the British Hypertension Society (BHS) and the US Association for the Advancement of Medical Instrumentation (AAMI), which are the global standard of comparison in this field.

LDIAED: A lightweight deep learning algorithm implementable on automated external defibrillators.

Differentiating between shockable and non-shockable Electrocardiogram (ECG) signals would increase the success of resuscitation by the Automated External Defibrillators (AED). In this study, a Deep Neural Network (DNN) algorithm is used to distinguish 1.4-second segment shockable signals from non-shockable signals promptly. The proposed technique is frequency-independent and is trained with signals from diverse patients extracted from MIT-BIH, MIT-BIH Malignant Ventricular Ectopy Database (VFDB), and a database for ventricular tachyarrhythmia signals from Creighton University (CUDB) resulting, in an accuracy of 99.1%. Finally, the raspberry pi minicomputer is used to load the optimized version of the model on it. Testing the implemented model on the processor by unseen ECG signals resulted in an average latency of 0.845 seconds meeting the IEC 60601-2-4 requirements. According to the evaluated results, the proposed technique could be used by AED's.

Chaos-Based Analysis of Heart Rate Variability Time Series in Obstructive Sleep Apnea Subjects.

Obstructive sleep apnea (OSA) is a common disorder which can cause periodic fluctuations in heart rate. To diagnose sleep apnea, some studies analyze electrocardiogram (ECG) signals by adopting chaos-based analysis. This research is going to specifically focus on whether it is possible to use chaos-based analysis of heart rate variability (HRV) signals rather than using chaotic analysis of ECG signals to diagnose OSA. While conventional studies mostly use chaos-based analysis of ECG signals to detect OSA, here, we apply correlation dimension (CD) as a chaotic index to analyze HRV data in OSA patients. For this purpose, 17 patients with OSA and 9 healthy individuals referred to a sleep clinic in Isfahan/Iran are studied, and their HRV time series were extracted from 1-h ECG signals recorded overnight. The preliminary step to calculate CD is phase-space reconstruction of the system based on HRV time series. Corresponding parameters, including embedding dimension and lag time, are estimated optimally using enhanced related methods, and then CD is calculated using Grassberger-Procaccia algorithm. Moreover, to evaluate our results, detrended fluctuation analysis (DFA), one of the well-known nonlinear methods in HRV analysis to detect OSA, is also applied to our data and the result is compared with those obtained from CD analysis of HRV. CD index with P < 0.005 indicates a significant difference in nonlinear dynamics of HRV signals detected from OSA patients and healthy individuals.

Diagnosis of Common Headaches Using Hybrid Expert-Based Systems.

BACKGROUND: Headache is one of the most common forms of medical complaints with numerous underlying causes and many patterns of presentation. The first step for starting the treatment is the recognition stage. In this article, the problem of primary and secondary headache diagnosis is considered, and we evaluate the use of intelligence techniques and soft computing in order to predict the diagnosis of common headaches. METHODS: A fuzzy expert-based system for the diagnosis of common headaches by Learning-From-Examples (LFE) algorithm is presented, in which Mamdani model was used in fuzzy inference engine using Max-Min as Or-And operators, and the Centroid method was used as defuzzification technique. In addition, this article has analyzed common headache using two classification techniques, and headache diagnosis based on a support vector machine (SVM) and multilayer perceptron (MLP)-based method has been proposed. The classifiers were used to recognize the four types of common headache, namely migraine, tension, headaches as a result of infection, and headaches as a result of increased intra cranial presser. RESULTS: By using a dataset obtained from 190 patients, suffering from primary and secondary headaches, who were enrolled from a medical center located in Mashhad, the diagnostic fuzzy system was trained by LFE algorithm, and on an average, 123 pieces of If-Then rules were produced for fuzzy system, and it was observed that the system had the ability of correct recognition by a rate of 85%. Using the headache diagnostic system by MLP- and SVM-based decision support system, the accuracy of classification into four types improved by 88% when using the MLP and by 90% with the SVM classifier. The performance of all methods is evaluated using classification accuracy, precision, sensitivity, and specificity. CONCLUSION: As the linguistic rules may be incomplete when human experts express their knowledge, and according to the proximity of common headache symptoms and importance of early diagnosis, the LFE training algorithm is more effective than human expert system. Favorable results obtained by the implementation and evaluation of the suggested medical decision support system based on the MLP and SVM show that intelligence techniques can be very useful for the recognition of common headaches with similar symptoms.

Effectiveness of CRT-D Versus ICD on Prevention of Electrical Storm: Big Data from the USA.

Patients with implantable cardioverter-defibrillator (ICD) are at the risk of electrical storm (ES) occurrence associated with mortality and poor quality of life. Cardiac resynchronization therapy with defibrillator (CRT-D) minimizes inappropriate ICD shocks. However, limited reports exist on the impact of CRT-D versus traditional ICD on ES occurrences in real-life cohorts. We evaluated the implanted-device characteristics associated with ES events in a large data based on daily stored device-summaries obtained from remote monitoring data in US.Between 2004 and 2016, 19,935 US patients were implanted. Survival analyses with Cox regression for device-shock therapy were performed between patients who experienced at least one ES and those without ES. CRT-D devices (bi-ventricular) were implanted in 5522 (28%) patients during this period, and their ES events over time were compared to ICD recipients implanted with RV lead. Primary endpoint was the first ES event.ES occurred with the rate of 7.26% for all patients during the period. Cox regression analyses revealed significantly an increase risk in ES occurrences (the p-value <; 0.05 and hazard ratio >> 1) with shock therapy. CRT-D implant led to lower ES risk comparing with patients received traditional ICD (RV only).

Predicting Electrical Storm Using Episodes' Parameters from ICD Recorded Data.

Electrical storm (ES) is a life-threatening heart condition for patients with implantable cardioverter defibrillators (ICDs). ICD patients experienced episodes are at higher risk for ES. However, predicting ES using previous episodes' parameters recorded by ICDs have never been developed. This study aims to predict ES using machine learning models based on ICD remote monitoring-summaries during episodes in the anonymized large number of patients. Episode ICD-summaries from 16,022 patients were used to construct and evaluate two models, logistic regression and random forest, for predicting the short-term risk of ES. Episode parameters in this study included the total number of sustained episodes, shocks delivered and the cycle length parameters. The models evaluated on the data sections not used for model development. Random forest performed significantly better than logistic regression (P <; 0.01), achieving a test accuracy of 0.99 and an Area Under an ROC Curve (AUC) of 0.93 (vs. an accuracy of 0.98 and an AUC of 0.90). The total number of previous sustained episodes was the most relevant variables in the both models.

Estimating occupant satisfaction of HVAC system noise using quality assessment index.

Noise may be defined as any unwanted sound. Sound becomes noise when it is too loud, unexpected, uncontrolled, happens at the wrong time, contains unwanted pure tones or unpleasant. In addition to being annoying, loud noise can cause hearing loss, and, depending on other factors, can affect stress level, sleep patterns and heart rate. The primary object for determining subjective estimations of loudness is to present sounds to a sample of listeners under controlled conditions. In heating, ventilation and air conditioning (HVAC) systems only the ventilation fan industry (e.g., bathroom exhaust and sidewall propeller fans) uses loudness ratings. In order to find satisfaction, percent of exposure to noise is the valuable issue for the personnel who are working in these areas. The room criterion (RC) method has been defined by ANSI standard S12.2, which is based on measured levels of in HVAC systems noise in spaces and is used primarily as a diagnostic tool. The RC method consists of a family of criteria curves and a rating procedure. RC measures background noise in the building over the frequency range of 16-4000 Hz. This rating system requires determination of the mid-frequency average level and determining the perceived balance between high-frequency (HF) sound and low-frequency (LF) sound. The arithmetic average of the sound levels in the 500, 1000 and 2000 Hz octave bands is 44.6 dB; therefore, the RC 45 curve is selected as the reference for spectrum quality evaluation. The spectral deviation factors in the LF, medium-frequency sound and HF regions are 2.9, 7.5 and -2.3, respectively, giving a Quality Assessment Index (QAI) of 9.8. This concludes the QAI is useful in estimating an occupant's probable reaction when the system design does not produce optimum sound quality. Thus, a QAI between 5 and 10 dB represents a marginal situation in which acceptance by an occupant is questionable. However, when sound pressure levels in the 16 or 31.5 Hz octave bands exceed 65 dB, vibration in lightweight office construction is possible.

Effects of electric and magnetic loadings on bone surface remodeling: a model modification and simulation.

This paper presents a new modification to the previous model of bone surface remodeling under electric and magnetic loadings. For this study, the thermo-electro-magneto-elastic model of bone surface remodeling is used. This model is modified by considering an important phenomenon occurring in living bone through its adaptation to external loadings called desensitization. In fact, bone cells lose their responsiveness and sensitivity to long-term external loadings, i.e., they become desensitized. Therefore, bone cells need a recovery period, during which they become resensitized. In this work, this phenomenon is considered in the original model. The effects of various electric and magnetic loading conditions, including various frequencies, waveforms and pulse duty cycles, are explored on the modified model and compared to the original model. The modified model is also searched for the optimal frequency and duty cycle, to obtain the best bone growth response under electromagnetic fields. The results of this paper show that the modified model is consistent with experimental observations. In addition, it is indicated that this modified model in contrast to the original model, is sensitive to frequency. It is shown that the optimal frequency of loading for the modified model is 1 Hertz (Hz), and the pulse duty cycles up to 50% are sufficient for bone remodeling to reach its maximum value.