Search

Human speech signals may contain specific information regarding a speaker's characteristics, and these signals can be very useful in applications involving interactive voice response (IVR) and automatic speech recognition (ASR). For IVR and ASR applications, speaker classification into different ages and gender groups can be applied in human–machine interaction or computer‐based interaction systems for customised advertisement, translation (text generation), machine dialog systems, or self‐service applications. Hence, an IVR‐based system dictates that ASR should function through users' voices (specific voice‐frequency bands) to identify customers' age and gender and interact with a host system. In the present study, we intended to combine a pitch detection (PD)‐based extractor and a voice classifier for gender identification. The Yet Another Algorithm for Pitch Tracking (YAAPT)‐based PD method was designed to extract the voice fundamental frequency (F0) from non‐stationary speaker's voice signals, allowing us to achieve gender identification, by distinguishing differences in F0 between adult females and males, and classify voices into adult and children groups. Then, in vowel voice signal classification, a one‐dimensional (1D) convolutional neural network (CNN), consisted of a multi‐round 1D kernel convolutional layer, a 1D pooling process, and a vowel classifier that could preliminary divide feature patterns into three level ranges of F0, including adult and children groups. Consequently, a classifier was used in the classification layer to identify the speakers' gender. The proposed PD‐based extractor and voice classifier could reduce complexity and improve classification efficiency. Acoustic datasets were selected from the Hillenbrand database for experimental tests on 12 vowels classifications, and K‐fold cross‐validations were performed. The experimental results demonstrated that our approach is a very promising method to quantify the proposed classifier's performance in terms of recall (%), precision (%), accuracy (%), and F1 score. [ABSTRACT FROM AUTHOR]

A wrist‐based photoplethysmography (PPG) tool offers a simple and non‐invasive approach for applications in vital sign monitoring and healthcare. However, in a telecare network, these physiological signals ensure the authorisation demands for the domain of medical applications. Hence, this study proposes an intelligent method for PPG signal encryption and decryption. This method combines chaotic map and radial basis function network (RBFN) into symmetric cryptography with an adaptive scheme. The sine‐power chaotic map is used as a key generator of 256 non‐ordered numbers (key space) to set the private cipher codes. Two RBFNs are used to train an encryptor and a decryptor with the authorised cipher codes. Its substitution‐based infosecurity scheme can change the numerical values of PPG raw data for each encrypted communication, and the decrypted PPG data are further applied for time‐ and frequency‐domain analyses in clinical applications, such as heart and respiration rate analysis and arterial stiffness and upper extremity vascular disease evaluations. Through experimental results, the security levels are validated using the number of pixel change rate (NPCR), unified averaged changed intensity (UACI), and correlation analysis. The average NPCR, UACI, and correlation coefficient (CC) are 96.57%, 35.43%, and 0.005, respectively, between the plain PPG and the encrypted PPG data against hacker attacks. The larger‐the‐better of NPCR and UACI indexes and the smaller‐the‐better of CC index are obtained to evaluate the efficiency of the proposed cryptography method. The encrypted PPG also guarantees physiological signals of good quality in clinical applications. In addition, the performance of RBFN‐based method is superior in adaptive learning capability than that of the traditional learning method in real‐time applications. The cover image is based on the Original Research Paper Intelligent physiological signal infosecurity: Case study in photoplethysmography (PPG) signal by Chia Hung‐Lin et al., https://doi.org/10.1049/sil2.12089. [ABSTRACT FROM AUTHOR]

Blood leakage and resultant loss during haemodialysis therapy are life‐threatening complications. As the venous needles (at arterial/venous sites) disconnect from blood lines, little reaction time is left to stop the blood loss. The authors integrate the wireless flexible sensor with a virtual internal impedance model to design a warning tool to early detect blood leakage and further lower the mortality rate it causes. This flexible sensor is fabricated via a screen‐printing technique by printing electronic circuits on a soft substrate in an array configuration. The virtual internal impedance model employed is advantageous for both detecting if any short‐circuit branch resistance develops and estimating the virtual internal impedances of the sensor. Once the metering nodal voltage changes, the estimated quantity resistances and near infinite resistances are employed to separate a short circuit from an open circuit. The algorithm developed can be implemented in an embedded system via a wireless fidelity wireless network through cloud computing. The experimental results show feasibility and potential of specifications for commercial design. [ABSTRACT FROM AUTHOR]

Atherosclerosis and resultant peripheral arterial disease (PAD) are common complications in patients with type 2 diabetes mellitus or end‐stage renal disease and in elderly patients. The prevalence of PAD is higher in patients receiving haemodialysis therapy. For early assessment of arterial occlusion using bilateral photoplethysmography (PPG), such as changes in pulse transit time and pulse shape, bilateral timing differences could be used to identify the risk level of PAD. Hence, the authors propose a discrete fractional‐order integrator to calculate the bilateral area under the systolic peak (AUSP). These indices indicated the differences in both rise‐timing and amplitudes of PPG signals. The dexter and sinister AUSP ratios were preliminarily used to separate the normal condition from low/high risk of PAD. Then, transition probability‐based decision‐making model was employed to evaluate the risk levels. The joint probability could be specified as a critical threshold, < 0.81, to identify the true positive for screening low or high risk level of PAD, referring to the patients' health records. In contrast to the bilateral timing differences and traditional methods, the proposed model showed better efficiency in PAD assessments and provided a promising strategy to be implemented in an embedded system. [ABSTRACT FROM AUTHOR]

Although exertional dyspnea and worsening hypoxia are hallmark clinical features of idiopathic pulmonary fibrosis ( IPF), no drug currently available could treat them. GBT1118 is a novel orally bioavailable small molecule that binds to hemoglobin and produces a concentration-dependent left shift of the oxygen-hemoglobin dissociation curve with subsequent increase in hemoglobin-oxygen affinity and arterial oxygen loading. To assess whether pharmacological modification of hemoglobin-oxygen affinity could ameliorate hypoxemia associated with lung fibrosis, we evaluated GBT1118 in a bleomycin-induced mouse model of hypoxemia and fibrosis. After pulmonary fibrosis and hypoxemia were induced, GBT1118 was administered for eight consecutive days. Hypoxemia was determined by monitoring arterial oxygen saturation, while the severity of pulmonary fibrosis was assessed by histopathological evaluation and determination of collagen and leukocyte levels in bronchoalveolar lavage fluid. We found that hemoglobin modification by GBT1118 had strong antihypoxemic therapeutic effects with improved arterial oxygen saturation to near normal level. Moreover, GBT1118 treatment significantly attenuated bleomycin-induced lung fibrosis, collagen accumulation, body weight loss, and leukocyte infiltration. This study is the first to suggest the beneficial effects of hemoglobin modification in fibrotic lungs and offers a promising and novel therapeutic strategy for the treatment of hypoxemia associated with chronic fibrotic lung disorders in human, including IPF. [ABSTRACT FROM AUTHOR]

We investigated the in vitro metabolism and estrogenic and antiestrogenic activity of toremifene (TOR), tamoxifen (TAM) and their metabolites to better understand the potential effects of cytochrome P-450 2D6 (CYP2D6) status on the activity of these drugs in women with breast cancer. The plasma concentrations of TOR and its N-desmethyl (NDM) and 4-hydroxy (4-OH) metabolites during steady-state dosing with TOR were also determined. Unlike TOR, TAM and its NDM metabolite were extensively oxidized to 4-OH TAM and 4-OH-NDM TAM by CYP2D6, and the rate of metabolism was affected by CYP2D6 status. 4-OH-NDM TOR concentrations were not measurable at steady state in plasma of subjects taking 80 mg of TOR. Molecular modeling provided insight into the lack of 4-hydroxylation of TOR by CYP2D6. The 4-OH and 4-OH-NDM metabolites of TOR and TAM bound to estrogen receptor (ER) subtypes with fourfold to 30-fold greater affinity were 35- to 187-fold more efficient at antagonizing ER transactivation and had antiestrogenic potency that was up to 360-fold greater than their parent drugs. Our findings suggest that variations in CYP2D6 metabolic capacity may cause significant differences in plasma concentrations of active TAM metabolites ( i.e., 4-OH TAM and 4-OH-NDM TAM) and contribute to variable pharmacologic activity. Unlike TAM, the clinical benefits in subjects taking TOR to treat metastatic breast cancer would not likely be subject to allelic variation in CYP2D6 status or affected by coadministration of CYP2D6-inhibiting medications. [ABSTRACT FROM AUTHOR]