Sequential graph convolutional network and DeepRNN based hybrid framework for epileptic seizure detection from EEG signal.

Automated epileptic seizure detection from ectroencephalogram (EEG) signals has attracted significant attention in the recent health informatics field. The serious brain condition known as epilepsy, which is characterized by recurrent seizures, is typically described as a sudden change in behavior caused by a momentary shift in the excessive electrical discharges in a group of brain cells, and EEG signal is primarily used in most cases to identify seizure to revitalize the close loop brain. The development of various deep learning (DL) algorithms for epileptic seizure diagnosis has been driven by the EEG's non-invasiveness and capacity to provide repetitive patterns of seizure-related electrophysiological information. Existing DL models, especially in clinical contexts where irregular and unordered structures of physiological recordings make it difficult to think of them as a matrix; this has been a key disadvantage to producing a consistent and appropriate diagnosis outcome due to EEG's low amplitude and nonstationary nature. Graph neural networks have drawn significant improvement by exploiting implicit information that is present in a brain anatomical system, whereas inter-acting nodes are connected by edges whose weights can be determined by either temporal associations or anatomical connections. Considering all these aspects, a novel hybrid framework is proposed for epileptic seizure detection by combined with a sequential graph convolutional network (SGCN) and deep recurrent neural network (DeepRNN). Here, DepRNN is developed by fusing a gated recurrent unit (GRU) with a traditional RNN; its key benefit is that it solves the vanishing gradient problem and achieve this hybrid framework greater sophistication. The line length feature, auto-covariance, auto-correlation, and periodogram are applied as a feature from the raw EEG signal and then grouped the resulting matrix into time-frequency domain as inputs for the SGCN to use for seizure classification. This model extracts both spatial and temporal information, resulting in improved accuracy, precision, and recall for seizure detection. Extensive experiments conducted on the CHB-MIT and TUH datasets showed that the SGCN-DeepRNN model outperforms other deep learning models for seizure detection, achieving an accuracy of 99.007%, with high sensitivity and specificity.

Optimizing AVR system performance via a novel cascaded RPIDD2-FOPI controller and QWGBO approach.

Maintaining stable voltage levels is essential for power systems' efficiency and reliability. Voltage fluctuations during load changes can lead to equipment damage and costly disruptions. Automatic voltage regulators (AVRs) are traditionally used to address this issue, regulating generator terminal voltage. Despite progress in control methodologies, challenges persist, including robustness and response time limitations. Therefore, this study introduces a novel approach to AVR control, aiming to enhance robustness and efficiency. A custom optimizer, the quadratic wavelet-enhanced gradient-based optimization (QWGBO) algorithm, is developed. QWGBO refines the gradient-based optimization (GBO) by introducing exploration and exploitation improvements. The algorithm integrates quadratic interpolation mutation and wavelet mutation strategy to enhance search efficiency. Extensive tests using benchmark functions demonstrate the QWGBO's effectiveness in optimization. Comparative assessments against existing optimization algorithms and recent techniques confirm QWGBO's superior performance. In AVR control, QWGBO is coupled with a cascaded real proportional-integral-derivative with second order derivative (RPIDD2) and fractional-order proportional-integral (FOPI) controller, aiming for precision, stability, and quick response. The algorithm's performance is verified through rigorous simulations, emphasizing its effectiveness in optimizing complex engineering problems. Comparative analyses highlight QWGBO's superiority over existing algorithms, positioning it as a promising solution for optimizing power system control and contributing to the advancement of robust and efficient power systems.

Sign language recognition using the fusion of image and hand landmarks through multi-headed convolutional neural network.

Sign Language Recognition is a breakthrough for communication among deaf-mute society and has been a critical research topic for years. Although some of the previous studies have successfully recognized sign language, it requires many costly instruments including sensors, devices, and high-end processing power. However, such drawbacks can be easily overcome by employing artificial intelligence-based techniques. Since, in this modern era of advanced mobile technology, using a camera to take video or images is much easier, this study demonstrates a cost-effective technique to detect American Sign Language (ASL) using an image dataset. Here, "Finger Spelling, A" dataset has been used, with 24 letters (except j and z as they contain motion). The main reason for using this dataset is that these images have a complex background with different environments and scene colors. Two layers of image processing have been used: in the first layer, images are processed as a whole for training, and in the second layer, the hand landmarks are extracted. A multi-headed convolutional neural network (CNN) model has been proposed and tested with 30% of the dataset to train these two layers. To avoid the overfitting problem, data augmentation and dynamic learning rate reduction have been used. With the proposed model, 98.981% test accuracy has been achieved. It is expected that this study may help to develop an efficient human-machine communication system for a deaf-mute society.

Maternal urinary vascular endothelial growth factor (VEGF) versus N.T. pro brain natriuretic peptide (NT-pro BNP) as novel biomarkers for placental accreta spectrum (PAS): A case-control study.

This study planned to compare the predictive ability of maternal urinary vascular endothelial growth factor (VEGF) versus N-terminal pro B-type natriuretic peptide (NT-pro BNP) for prediction of placenta accreta spectrum (PAS). This was a prospective case-control study carried out in a tertiary university hospital. It included pregnant women between 37-39 weeks. The study included 50 pregnant women classified in two groups. Group (Ι, n=25) were pregnant women with PAS, and group (II, n=25) women with uncomplicated pregnancies, as controls. Urine samples were collected, and quantitative analyses of VEGF and NT-pro BNP were performed by ELISA. VEGF was assessed with a cut point of 215.6 pg/ml and NT-pro BNP with a cut point of 182.2 pg/ml to predict the condition of PAS. Both biomarkers were good predictors of PAS with the area under the ROC curve (AUC) equal to (0.871 and 0.904), respectively. However, maternal urinary VEGF levels could predict PAS better than NT-pro BNP (OR=9.967, 95%CI 2.032-48.879, p=0.005) versus (OR=8.066, 95% CI 1.520 - 42.811, p=0.014) in NT-pro BNP. In conclusion, third trimester urinary levels of both VEGF and NT-pro BNP appear to be s crucially good predictors for PAS. However, VEGF is superior to NT-pro BNP in predicting women with PAS. These biomarkers present promising candidates as they can help to detect patients at high probability of PAS. They can be assessed by non-invasive, simple, and low-cost procedures.

Reduction of Radar Cross Section by Adopting Symmetrical Coding Metamaterial Design for Terahertz Frequency Applications.

This work focused on the novel and compact 1-bit symmetrical coding-based metamaterial for radar cross section reduction in terahertz frequencies. A couple of coding particles were constructed to impersonate the elements '0' and '1', which have phase differences of 180°. All the analytical simulations were performed by adopting Computer Simulation Technology Microwave Studio 2019 software. Moreover, the transmission coefficient of the element '1' was examined as well by adopting similar software and validated by a high-frequency structure simulator. Meanwhile, the frequency range from 0 to 3 THz was set in this work. The phase response properties of each element were examined before constructing various coding metamaterial designs in smaller and bigger lattices. The proposed unit cells exhibit phase responses at 0.84 THz and 1.54 THz, respectively. Meanwhile, the analysis of various coding sequences was carried out and they manifest interesting monostatic and bistatic radar cross section (RCS) reduction performances. The Coding Sequence 2 manifests the best bistatic RCS reduction values in smaller lattices, which reduced from -69.8 dBm2 to -65.5 dBm2 at 1.54 THz. On the other hand, the monostatic RCS values for all lattices have an inclined line until they reach a frequency of 1.0 THz from more than -60 dBm2. However, from the 1.0 THz to 3.0 THz frequency range the RCS values have moderate discrepancies among the horizontal line for each lattice. Furthermore, two parametric studies were performed to examine the RCS reduction behaviour, for instance, multi-layer structures and as well tilt positioning of the proposed coding metamaterial. Overall it indicates that the integration of coding-based metamaterial successfully reduced the RCS values.

Progesterone/Oestradiol ratio can Better Predict Intracytoplasmic Sperm Injection Outcomes than Absolute Progesterone Level.

BACKGROUND: Several parameters were proposed to predict the impact of premature luteinization on intracytoplasmic sperm injection (ICSI) outcomes such as isolated progesterone (P) level, progesterone to oocyte ratio, and progesterone/estradiol ratio (P/E2). AIM: The aim of this study is to compare the predictive value of P/E2 ratio and isolated P level on the ovulation triggering day for pregnancy outcomes in fresh GnRH antagonist ICSI cycles. SETTINGS AND DESIGN: A retrospective cohort study conducted in a university-affiliated in vitro fertilization center between January 2017 and April 2019. METHODS: The study included women who underwent their first- or second-ranked GnRH antagonist ICSI cycles with day-3 embryo transfer. P/E2 ratio was calculated as (P [ng/mL] × 1000)/E2 (pg/mL). Cutoff values of ≥1.5 ng/ml for high P (HP) and ≥0.55 for HP/E2 ratio were chosen based on the literature. STATISTICAL ANALYSIS: A receiver operating curve was performed to detect the predictability of serum P/E2 and P for the ongoing pregnancy rate. First, patients were divided according to either P level (low P < 1.5 ng/mL and HP ≥1.5 ng/mL) or P/E2 ratio (low P/E2 <0.55 and HP/E2 ≥ 0.55). Patients were further divided into four subgroups: (Group A: HP and HP/E2 ratio, Group B: low P and low P/E2 ratio, Group C: HP only, and Group D: HP/E2 only). A multivariate regression analysis models were used to account for the effect of the cycle confounders on the likelihood of pregnancy. RESULTS: A total of 402 ICSI cycles were analyzed. The area under the curve was 0.67 and 0.59 for P/E2 and P, respectively. P/E2 showed a significant association with ongoing pregnancy (adjusted odds ratios [aOR]: 0.409, 95% confidence interval [CI] 0.222-0.753, P = 0.004) while HP revealed no significant predictive value (aOR: 0.542, 95% CI 0.284-1.036, P = 0.064) after the multivariate analysis. CONCLUSIONS: P elevation may not present as an independent predictor for cycle outcomes. P/E2 ratio has a better prognostic value than P alone in predicting pregnancy of GnRH antagonist cycles.

Effect of Metformin on Premature Luteinization and Pregnancy Outcomes in Intracytoplasmic Sperm Injection-Fresh Embryo Transfer Cycles: A Randomized Double-Blind Controlled Trial.

BACKGROUND: Premature luteinization (PL) is not unusual in in vitro fertilization (IVF) and could not be wholly avoided by using either gonadotropin-releasing hormone (GnRH) agonists or GnRH antagonist regimens. The study aims to evaluate metformin's efficacy in preventing PL in fresh GnRH antagonist intracytoplasmic sperm injection (ICSI) cycles with cleavage-stage embryo transfer. MATERIALS AND METHODS: This randomized, double-blind, placebo-controlled trial was conducted in a tertiary university IVF center. We recruited infertile women who were scheduled to perform their first or second ICSI trial. Eligible women were recruited and randomized in a 1:1 ratio into two groups. Metformin was administered in a dose of 1500 mg per day since the start of contraceptive pills in the cycle antecedent to stimulation cycle until the day of ovulation triggering, while women in the placebo group received a placebo for the same regimen and duration. The primary outcome was the incidence of PL, defined as serum progesterone (P) on the triggering day ≥1.5 ng/mL. Secondary outcomes comprised the live birth, ongoing pregnancy, implantation, and good-quality embryos rates. RESULTS: The trial involved 320 eligible participants (n=160 in each group). Both groups had comparable stimulation days, endometrial thickness, peak estradiol levels, number of oocytes retrieved, and number of mature oocytes. Metformin group experienced lower level of serum P (P<0.001) and incidence of PL (10 vs. 23.6%, P=0.001). Moreover, lower progesterone/estradiol (P/E) ratio and progesterone to mature oocyte index (PMOI) (P=0.002 and P=0.002, respectively) were demonstrated in women receiving metformin. Metformin group generated a better rate of goodquality embryos (P=0.005) and ongoing pregnancy (43.8 vs. 31.8%, P=0.026). A similar trend, though of borderline significance, was observed in the live birth rate in favor of metformin administration (38.15 vs. 27.5%, P=0.04). CONCLUSION: Metformin could be used in patients with potential PL to improve fresh cycle outcomes by preventing PL (Registration number: NCT03088631).

Accelerometer-Based Wheel Odometer for Kinematics Determination.

Various high budget industries that utilize wheel-based vehicles rely on wheel odometry as an integral aspect of their navigation process. This research introduces a low-cost alternative for typical wheel encoders that are typically used to determine the on-track speed of vehicles. The proposed system is referred to as an Accelerometer-based Wheel Odometer for Kinematics determination (AWOK). The AWOK system comprises just a single axis accelerometer mounted radially at the center of any given wheel. The AWOK system can provide direct distances instead of just velocities, which are provided by typical wheel speedometers. Hence, the AWOK system is advantageous in comparison to typical wheel odometers. Besides, the AWOK system comprises a simple assembly with a highly efficient data processing algorithm. Additionally, the AWOK system provides a high capacity to handle high dynamics in comparison to similar approaches found in previous related work. Furthermore, the AWOK system is not affected by the inherited stochastic errors in micro-machined electro-mechanical systems (MEMS) inertial sensors, whether short-term or long-term errors. Above all, the AWOK system reported a relative accuracy of 0.15% in determining the distance covered by a car.

Comparison of dienogest versus combined oral contraceptive pills in the treatment of women with adenomyosis: A randomized clinical trial.

OBJECTIVE: To compare the efficacy and safety of dienogest with combined oral contraceptives (COCs) for treating adenomyosis-associated symptoms. METHODS: This was a randomized clinical trial including women with symptomatic adenomyosis conducted from March 1, 2019 to August 1, 2020 at Assiut Woman's Health Hospital, Egypt. Participants were randomly assigned to the dienogest group or COCs group. The primary outcome was the level of adenomyosis-associated pain from before to 6 months after treatment measured by a visual analog scale (VAS). Changes in the uterine bleeding pattern, uterine volume, and uterine artery blood flow were also reported. RESULTS: The VAS score of pain was significantly decreased in both groups; however, the decreased rate was more pronounced in the dienogest group (3.21 ± 1.18) in comparison with the COCs group (4.92 ± 1.22). Bleeding pattern was improved greatly; uterine volume and uterine artery blood flow decreased significantly in the dienogest group. However, women in the dienogest group reported a higher rate of side effects. CONCLUSION: Dienogest and COCs are effective in treating adenomyosis-associated symptoms after 6 months of use but dienogest is more effective. The decrease in uterine volume and uterine artery blood flow may be the cause of the treatment effect. Dienogest carries a higher risk of side effects. CLINICAL TRIAL: gov: NCT03890042.

Dual trigger using recombinant HCG and gonadotropin-releasing hormone agonist improve oocyte maturity and embryo grading for normal responders in GnRH antagonist cycles: Randomized controlled trial.

OBJECTIVES: To evaluate the effectiveness of dual trigger using gonadotropin-releasing hormone (GnRH) agonist and recombinant human chorionic gonadotropin (rHCG) versus rHCG alone for normal responders in GnRH antagonist intracytoplasmic sperm injection (ICSI) cycles. PATIENTS AND METHODS: The current study was a registered open-labeled randomized controlled trial (clinical trial.gov: NCT02916173) conducted in the ART Unit of a tertiary University hospital between October 2016 and October 2018. The study participants were randomized to either group I (HCG group) or group II (dual trigger group). The primary outcome was the number of mature (MII) oocytes in both groups. RESULTS: Both groups were similar regarding the baseline demographic and clinical characteristics. Women in the dual trigger group had a statistically significant higher number of retrieved oocytes (p = 0.001), MII oocytes (p = 0.01) and the number of grade one embryos (p = 0.04). Both groups were similar regarding the fertilization, implantation, clinical pregnancy and live birth rates in a fresh cycle. Dual trigger group was significantly higher in the clinical pregnancy rate and live birth rate after frozen embryo transfer (p = 0.04, 0.03, respectively). CONCLUSION: Dual trigger by GnRH agonist and rHCG improve the oocyte maturity and embryo grading for normal responders in GnRH antagonist ICSI cycles.

How far can one-stage laparoscopic Fowler-Stephens orchiopexy be implemented in intra-abdominal testes with short spermatic vessels?

OBJECTIVE: The aim of the study was to compare the outcome of the prospective cohort who had one-stage laparoscopic Fowler-Stephens orchiopexy (LFSO) with an earlier, similar cohort who had a two-stage LFSO. Both cohorts included only intra-abdominal testes (IATs) with short spermatic vessels. STUDY DESIGN: The present study initially included all patients between the age of six months and preschool age, presenting with an IAT to the authors' tertiary clinic from January 2012 to December 2014. Only intra-abdominal testes with short testicular vessels, correlating to type 3A, 3B and 4A as per the updated Ain Shams classification, were included in this study. One-stage LFSO was performed on all patients. Patients with bilateral intra-abdominal testes had the procedure performed on the contralateral side 6-8 weeks later. Follow-up was performed at 6, 12 and 36 months postoperatively by means of Doppler ultrasound in the first two visits. A similar subgroup of the historical cohort from years 2002 to 2010 had a two-stage LFSO, with the second stage being performed 12-16 weeks later. In bilateral cases, a three-interval surgery based on two-stage LFSO was performed, with a follow-up at 6 months postoperatively. RESULTS: The recent cohort included 16 IATs (10 unilateral and 3 bilateral). The median age of the patients was 1.41 years. At 6-month follow-up, 4 testes were found atrophic (25%), whereas the remaining 12 testes (75%) were viable. In those viable, only half of them had a low scrotal position. No difference was found at 12- or 36-month follow-up. Doppler ultrasound confirmed adequate intratesticular blood flow at 6 and 12 months postoperatively. In the similar subgroup of the historical cohort, 3 of 25 (12%) testes were found atrophied at six months postoperatively, with only one testis (4%) having a high scrotal position. In a comparison of both cohorts, the two-stage LFSO was found to be associated with a halving of the testicular atrophy rate (p value = 0.401) and a higher incidence of low scrotal position (p value = 0.004). A comparison of both cohorts is shown in the summary table. CONCLUSION: Although one-stage LFSO may seem tempting, it still holds a higher rate of testicular atrophy, which is not justified. LEVEL OF EVIDENCE: Level III (Case-control study).

Particle Imaging Velocimetry Gyroscope.

Inertial measurement units (IMUs) are typically classified as per the performance of the gyroscopes within each system. Consequently, it is critical for a system to have a low bias instability to have better performance. Nonetheless, there is no IMU available commercially that does not actually suffer from bias-instability, even for the navigation grade IMUs. This paper introduces the proposition of a novel fluid-based gyroscope, which is referred to hereafter as a particle imaging velocimetry gyroscope (PIVG). The main advantages of the PIVG include being nearly drift-free, a high signal-to-noise ratio (SNR) in comparison to commercially available high-end gyroscopes, and its low cost.

Improving the Accuracy of Direct Geo-referencing of Smartphone-Based Mobile Mapping Systems Using Relative Orientation and Scene Geometric Constraints.

This paper introduces a new method which facilitate the use of smartphones as a handheld low-cost mobile mapping system (MMS). Smartphones are becoming more sophisticated and smarter and are quickly closing the gap between computers and portable tablet devices. The current generation of smartphones are equipped with low-cost GPS receivers, high-resolution digital cameras, and micro-electro mechanical systems (MEMS)-based navigation sensors (e.g., accelerometers, gyroscopes, magnetic compasses, and barometers). These sensors are in fact the essential components for a MMS. However, smartphone navigation sensors suffer from the poor accuracy of global navigation satellite System (GNSS), accumulated drift, and high signal noise. These issues affect the accuracy of the initial Exterior Orientation Parameters (EOPs) that are inputted into the bundle adjustment algorithm, which then produces inaccurate 3D mapping solutions. This paper proposes new methodologies for increasing the accuracy of direct geo-referencing of smartphones using relative orientation and smartphone motion sensor measurements as well as integrating geometric scene constraints into free network bundle adjustment. The new methodologies incorporate fusing the relative orientations of the captured images and their corresponding motion sensor measurements to improve the initial EOPs. Then, the geometric features (e.g., horizontal and vertical linear lines) visible in each image are extracted and used as constraints in the bundle adjustment procedure which correct the relative position and orientation of the 3D mapping solution.