HDR-EfficientNet: A Classification of Hypertensive and Diabetic Retinopathy Using Optimize EfficientNet Architecture.

Hypertensive retinopathy (HR) and diabetic retinopathy (DR) are retinal diseases closely associated with high blood pressure. The severity and duration of hypertension directly impact the prevalence of HR. The early identification and assessment of HR are crucial to preventing blindness. Currently, limited computer-aided methods are available for detecting HR and DR. These existing systems rely on traditional machine learning approaches, which require complex image processing techniques and are often limited in their application. To address this challenge, this work introduces a deep learning (DL) method called HDR-EfficientNet, which aims to provide an efficient and accurate approach to identifying various eye-related disorders, including diabetes and hypertensive retinopathy. The proposed method utilizes an EfficientNet-V2 network for end-to-end training focused on disease classification. Additionally, a spatial-channel attention method is incorporated into the approach to enhance its ability to identify specific areas of damage and differentiate between different illnesses. The HDR-EfficientNet model is developed using transfer learning, which helps overcome the challenge of imbalanced sample classes and improves the network's generalization. Dense layers are added to the model structure to enhance the feature selection capacity. The performance of the implemented system is evaluated using a large dataset of over 36,000 augmented retinal fundus images. The results demonstrate promising accuracy, with an average area under the curve (AUC) of 0.98, a specificity (SP) of 96%, an accuracy (ACC) of 98%, and a sensitivity (SE) of 95%. These findings indicate the effectiveness of the suggested HDR-EfficientNet classifier in diagnosing HR and DR. In summary, the HDR-EfficientNet method presents a DL-based approach that offers improved accuracy and efficiency for the detection and classification of HR and DR, providing valuable support in diagnosing and managing these eye-related conditions.

Evaluation of small hydropower turbines installed downstream of Nile River branches (Egypt).

The current study proposes a new strategy for using small hydroelectric turbines in downstream river branches with the least amount of construction and the lowest cost by comparing two different methods of installing the turbines, the first by installing the turbines at the river's bottom and the second by installing the turbines on floating boats. The methodology of this article is based on predicting the distribution of velocities through the watercourse using experimental data collected at various points in the river's depth, and then predicting the resulting electrical power for different sizes of turbines, as well as estimating the number of turbines for each row and the number of rows along the river. Therefore, Investigate the proposed systems. The proposed small hydropower system's economic viability and environmental impact are investigated in this article. According to the nature of the waterway, the best diameter of a turbine that can be used is 1.5 m based on water velocities and river depths. The proposed power plant generated 25.8 kW per single turbine row, with an estimated cost of produced power (0.035 USD/kWh) of approximately 20 turbines installed per row. Compared to other renewable energy sources, the proposed hydropower system is cost-effective and environmentally friendly, as generating electricity with the proposed small hydropower plant could reduce annual carbon dioxide emissions by 368 tones of CO2 per single turbine row.

A Residual-Dense-Based Convolutional Neural Network Architecture for Recognition of Cardiac Health Based on ECG Signals.

Cardiovascular disorders are often diagnosed using an electrocardiogram (ECG). It is a painless method that mimics the cyclical contraction and relaxation of the heart's muscles. By monitoring the heart's electrical activity, an ECG can be used to identify irregular heartbeats, heart attacks, cardiac illnesses, or enlarged hearts. Numerous studies and analyses of ECG signals to identify cardiac problems have been conducted during the past few years. Although ECG heartbeat classification methods have been presented in the literature, especially for unbalanced datasets, they have not proven to be successful in recognizing some heartbeat categories with high performance. This study uses a convolutional neural network (CNN) model to combine the benefits of dense and residual blocks. The objective is to leverage the benefits of residual and dense connections to enhance information flow, gradient propagation, and feature reuse, ultimately improving the model's performance. This proposed model consists of a series of residual-dense blocks interleaved with optional pooling layers for downsampling. A linear support vector machine (LSVM) classified heartbeats into five classes. This makes it easier to learn and represent features from ECG signals. We first denoised the gathered ECG data to correct issues such as baseline drift, power line interference, and motion noise. The impacts of the class imbalance are then offset by resampling techniques that denoise ECG signals. An RD-CNN algorithm is then used to categorize the ECG data for the various cardiac illnesses using the retrieved characteristics. On two benchmarked datasets, we conducted extensive simulations and assessed several performance measures. On average, we have achieved an accuracy of 98.5%, a sensitivity of 97.6%, a specificity of 96.8%, and an area under the receiver operating curve (AUC) of 0.99. The effectiveness of our suggested method for detecting heart disease from ECG data was compared with several recently presented algorithms. The results demonstrate that our method is lightweight and practical, qualifying it for continuous monitoring applications in clinical settings for automated ECG interpretation to support cardiologists.

Assist-Dermo: A Lightweight Separable Vision Transformer Model for Multiclass Skin Lesion Classification.

A dermatologist-like automatic classification system is developed in this paper to recognize nine different classes of pigmented skin lesions (PSLs), using a separable vision transformer (SVT) technique to assist clinical experts in early skin cancer detection. In the past, researchers have developed a few systems to recognize nine classes of PSLs. However, they often require enormous computations to achieve high performance, which is burdensome to deploy on resource-constrained devices. In this paper, a new approach to designing SVT architecture is developed based on SqueezeNet and depthwise separable CNN models. The primary goal is to find a deep learning architecture with few parameters that has comparable accuracy to state-of-the-art (SOTA) architectures. This paper modifies the SqueezeNet design for improved runtime performance by utilizing depthwise separable convolutions rather than simple conventional units. To develop this Assist-Dermo system, a data augmentation technique is applied to control the PSL imbalance problem. Next, a pre-processing step is integrated to select the most dominant region and then enhance the lesion patterns in a perceptual-oriented color space. Afterwards, the Assist-Dermo system is designed to improve efficacy and performance with several layers and multiple filter sizes but fewer filters and parameters. For the training and evaluation of Assist-Dermo models, a set of PSL images is collected from different online data sources such as Ph2, ISBI-2017, HAM10000, and ISIC to recognize nine classes of PSLs. On the chosen dataset, it achieves an accuracy (ACC) of 95.6%, a sensitivity (SE) of 96.7%, a specificity (SP) of 95%, and an area under the curve (AUC) of 0.95. The experimental results show that the suggested Assist-Dermo technique outperformed SOTA algorithms when recognizing nine classes of PSLs. The Assist-Dermo system performed better than other competitive systems and can support dermatologists in the diagnosis of a wide variety of PSLs through dermoscopy. The Assist-Dermo model code is freely available on GitHub for the scientific community.

Light-Dermo: A Lightweight Pretrained Convolution Neural Network for the Diagnosis of Multiclass Skin Lesions.

Skin cancer develops due to the unusual growth of skin cells. Early detection is critical for the recognition of multiclass pigmented skin lesions (PSLs). At an early stage, the manual work by ophthalmologists takes time to recognize the PSLs. Therefore, several "computer-aided diagnosis (CAD)" systems are developed by using image processing, machine learning (ML), and deep learning (DL) techniques. Deep-CNN models outperformed traditional ML approaches in extracting complex features from PSLs. In this study, a special transfer learning (TL)-based CNN model is suggested for the diagnosis of seven classes of PSLs. A novel approach (Light-Dermo) is developed that is based on a lightweight CNN model and applies the channelwise attention (CA) mechanism with a focus on computational efficiency. The ShuffleNet architecture is chosen as the backbone, and squeeze-and-excitation (SE) blocks are incorporated as the technique to enhance the original ShuffleNet architecture. Initially, an accessible dataset with 14,000 images of PSLs from seven classes is used to validate the Light-Dermo model. To increase the size of the dataset and control its imbalance, we have applied data augmentation techniques to seven classes of PSLs. By applying this technique, we collected 28,000 images from the HAM10000, ISIS-2019, and ISIC-2020 datasets. The outcomes of the experiments show that the suggested approach outperforms compared techniques in many cases. The most accurately trained model has an accuracy of 99.14%, a specificity of 98.20%, a sensitivity of 97.45%, and an F1-score of 98.1%, with fewer parameters compared to state-of-the-art DL models. The experimental results show that Light-Dermo assists the dermatologist in the better diagnosis of PSLs. The Light-Dermo code is available to the public on GitHub so that researchers can use it and improve it.

A Novel PPG-Based Biometric Authentication System Using a Hybrid CVT-ConvMixer Architecture with Dense and Self-Attention Layers.

Biometric authentication is a widely used method for verifying individuals' identities using photoplethysmography (PPG) cardiac signals. The PPG signal is a non-invasive optical technique that measures the heart rate, which can vary from person to person. However, these signals can also be changed due to factors like stress, physical activity, illness, or medication. Ensuring the system can accurately identify and authenticate the user despite these variations is a significant challenge. To address these issues, the PPG signals were preprocessed and transformed into a 2-D image that visually represents the time-varying frequency content of multiple PPG signals from the same human using the scalogram technique. Afterward, the features fusion approach is developed by combining features from the hybrid convolution vision transformer (CVT) and convolutional mixer (ConvMixer), known as the CVT-ConvMixer classifier, and employing attention mechanisms for the classification of human identity. This hybrid model has the potential to provide more accurate and reliable authentication results in real-world scenarios. The sensitivity (SE), specificity (SP), F1-score, and area under the receiver operating curve (AUC) metrics are utilized to assess the model's performance in accurately distinguishing genuine individuals. The results of extensive experiments on the three PPG datasets were calculated, and the proposed method achieved ACCs of 95%, SEs of 97%, SPs of 95%, and an AUC of 0.96, which indicate the effectiveness of the CVT-ConvMixer system. These results suggest that the proposed method performs well in accurately classifying or identifying patterns within the PPG signals to perform continuous human authentication.

Parametric optimisation for the design of gravity energy storage system using Taguchi method.

Gravitational energy storage systems are among the proper methods that can be used with renewable energy. However, these systems are highly affected by their design parameters. This paper presents a novel investigation of different design features of gravity energy storage systems. A theoretical model was developed using MATLAB SIMULINK to simulate the performance of the gravitational energy storage system while changing its design parameters. A parametric optimization study was also conducted using Taguchi and analysis of variance (ANOVA) techniques for optimizing the energy storage rate. Six parameters were studied; three are related to the piston design (diameter, height, and material density). The other parameters are the return pipe diameter, length, and charging/discharging time. Results revealed that the piston diameter and height are the two most significant parameters for the system performance compared to the other parameters, as they contributed by 35.11% and 30.28%, respectively. The optimization results indicated that the optimal piston diameter, height, and return pipe diameter were 0.25, 0.5, and 0.01 of the container height. The outcomes of this paper can significantly improve energy storage and power generation from renewable energy systems as it provides a reliable, economical, sustainable, and durable energy storage system.

An Automatic Detection and Classification System of Five Stages for Hypertensive Retinopathy Using Semantic and Instance Segmentation in DenseNet Architecture.

The stage and duration of hypertension are connected to the occurrence of Hypertensive Retinopathy (HR) of eye disease. Currently, a few computerized systems have been developed to recognize HR by using only two stages. It is difficult to define specialized features to recognize five grades of HR. In addition, deep features have been used in the past, but the classification accuracy is not up-to-the-mark. In this research, a new hypertensive retinopathy (HYPER-RETINO) framework is developed to grade the HR based on five grades. The HYPER-RETINO system is implemented based on pre-trained HR-related lesions. To develop this HYPER-RETINO system, several steps are implemented such as a preprocessing, the detection of HR-related lesions by semantic and instance-based segmentation and a DenseNet architecture to classify the stages of HR. Overall, the HYPER-RETINO system determined the local regions within input retinal fundus images to recognize five grades of HR. On average, a 10-fold cross-validation test obtained sensitivity (SE) of 90.5%, specificity (SP) of 91.5%, accuracy (ACC) of 92.6%, precision (PR) of 91.7%, Matthews correlation coefficient (MCC) of 61%, F1-score of 92% and area-under-the-curve (AUC) of 0.915 on 1400 HR images. Thus, the applicability of the HYPER-RETINO method to reliably diagnose stages of HR is verified by experimental findings.

Synthesis, Structural Characterization, and Preclinical Efficacy of a Novel Paclitaxel-Loaded Alginate Nanoparticle for Breast Cancer Treatment.

Purpose. The antitumor activity of a novel alginate (ALG) polymer-based particle that contained paclitaxel (PTX) was evaluated using human primary breast cancer cells. Materials and Methods. PTX was combined with ALG in a nanoparticle as a drug delivery system designed to improve breast cancer tumor cell killing. PTX-ALG nanoparticles were first synthesized by nanoemulsification polymer cross-linking methods that improved the aqueous solubility. Structural and biophysical properties of the PTX-ALG nanoparticles were then determined by transmission electron microscopy (TEM) and high performance liquid chromatography (HPLC) fluorescence. The effect on cell cycle progression and apoptosis was determined using flow cytometry. Results. PTX-ALG nanoparticles were prepared and characterized by ultraviolet (UV)/visible (VIS), HPLC fluorescence, and TEM. PTX-ALG nanoparticles demonstrated increased hydrophobicity and solubility over PTX alone. Synthetically engineered PTX-ALG nanoparticles promoted cell-cycle arrest, reduced viability, and induced apoptosis in human primary patient breast cancer cells superior to those of PTX alone. Conclusion. Taken together, our results demonstrate that PTX-ALG nanoparticles represent an innovative, nanoscale delivery system for the administration of anticancer agents that may avoid the adverse toxicities with enhanced antitumor effects to improve the treatment of breast cancer patients.

Effect of Schistosoma mansoni infection on offsprings born from infected mothers.

Offsprings C57BL/6 mice (4 weeks old) coming from either moderately infected (40 S. mansoni cercariae) or heavily infected (100 S. mansoni cerariae) mothers, were exposed to 40 S. mansoni cercariae each. Seven weeks post infection (P.I.), Offsprings were sacrificed. In both groups there was significant reduction in the worm load, both hepatic and intestinal tissue egg count. The oogram profile was not altered. Humoral immune response as regards the level of anti S. mansoni SEA Ab was elevated in both groups in comparison to their parallel controls at 2 weeks post delivery and 7 weeks P.I. The level of antibodies was significantly higher in heavily infected Offsprings than that present in offsprings coming from moderately infected mothers. Delayed footpad swelling and hepatic granuloma size were significantly reduced in both groups comparing with their corresponding controls.

Mutual effect of Schistosoma mansoni infection and pregnancy in experimental C57 BL/6 black mice.

Sixty female C57BL/6 mice were infected with 40 Schistosoma mansoni cercariae each. Seven weeks later, they were mated with normal syngeneic males. Uninfected mice (30) were bred in parallel, and both groups were bred several more times with daily records of pregnancy, delivery and number of offsprings. The number of pregnancy was 146, with 50 survived infants (34.2%) in contrast to 121 pregnancy with 93 survived infants (76.8%) in controls. The outcome of pregnancy was 13% abortion, 10.9% maternal death and 41.7% infanticide. The weight of offspring at 2 and 4 weeks of age was significantly less than in controls (P < 0.01). Again, C57BL/6 (40) female mice were mated, then infected with 100 S. mansoni cercariae each. The results showed that, pregnancy had no effect on bilharzial infection as the total worm burden and distribution, hepatic and intestinal tissue egg count and the oogram profile, were not significantly differ from that in the control group (20). Besides, the immediate footpad swelling was significantly higher but the delayed footpad swelling and the level of antibodies against S. mansoni soluble egg antigen were insignificantly differ from that present in the parallel control (infected but not pregnant). As regards histopathological parameters, although there was insignificant difference in the size of hepatic granuloma, yet there was more collagenous fibrous tissue deposition distributed in-between inflammatory cells specially at the periphery of the granuloma.

A new derivative of glucose and 2-C-methyl-D-erythritol from Ferula sinaica.

A new glucose derivative (1) and 2-C-methyl-D-erythritol (2) were isolated from the leaves of Ferula sinaica. The two structures were elucidated by highfield NMR spectroscopy, and that of 1 was confirmed by X-ray diffraction analysis.

Transseptal approach for mitral valve surgery. A safe alternative when the need calls.

Within a 40-month period ending in June 1992, we used the transseptal approach in performing mitral valve surgery on 18 patients. The patients selected had 1 or more of the following indications: small left atrium; adhesions from previous cardiac surgery or rheumatic activity; large, organized left atrial thrombus: the need for concomitant tricuspid valve surgery; or any combination of these factors. We made the septal incision in the long axis of the fossa ovalis and extended it anteriorly and posteriorly, taking care not to injure either the aortic root or the coronary sinus. In 15 patients, we easily obtained good mitral exposure; in 3, exposure was still difficult. One patient died, but the cause of death was not related to the surgical approach. Although none of our patients had early postoperative cardiac arrhythmias, the small number in our series and the short follow-up time prevent us from predicting the effect of this incision on late postoperative cardiac arrhythmias. Therefore, we recommend limiting the transseptal approach to complex reoperations and to operations necessitating right atriotomy for concomitant procedures. It is also very useful in patients with a large, organized left atrial thrombus. Under these conditions, we conclude that using the transseptal approach for mitral valve surgery is a simple, safe, and time-saving technique.