Melanoma is a fatal type of skin cancer; the fury spread results in a high fatality rate when the malignancy is not treated at an initial stage. The patients’ lives can be saved by accurately detecting skin cancer at an initial stage. A quick and precise diagnosis might help increase the patient’s survival rate. It necessitates the development of a computer-assisted diagnostic support system. This research proposes a novel deep transfer learning model for melanoma classification using MobileNetV2. The MobileNetV2 is a deep convolutional neural network that classifies the sample skin lesions as malignant or benign. The performance of the proposed deep learning model is evaluated using the ISIC 2020 dataset. The dataset contains less than 2% malignant samples, raising the class imbalance. Various data augmentation techniques were applied to tackle the class imbalance issue and add diversity to the dataset. The experimental results demonstrate that the proposed deep learning technique outperforms state-of-the-art deep learning techniques in terms of accuracy and computational cost.

The interconnection of renewable energy systems, which are complex nonlinear systems, often results in power fluctuations in the interconnection line and high system frequency due to insufficient damping in extreme and dynamic loading situations. To solve this problem, load frequency control ensures nominal operating frequency and orderly fluctuation of grid interconnection power by delivering high-quality electric power to energy consumers through efficient and intelligent control systems. To introduce the frequency control of power systems, this paper presents a novel control technique of Fractional Order Integral-Tilt Derivative with Filter (FOI-TDN) controller optimized by the current soft computing technique of hybrid Sine-Cosine algorithm with Fitness Dependent Optimizer (hSC-FDO). For more realistic analysis, practical constraints with nonlinear features, such as controller dead band, communication time delay, boiler dynamics, and generation rate constraint are embedded in the given system model. The proposed approach outperforms some recently developed heuristic approaches such as fitness dependent optimizer, firefly algorithm, and particle swarm optimization for the interconnected power system of two areas with multiple generating units in terms of minimum undershoot, overshoot, and settling time. To improve the system performance, capacitive energy storage devices are used in each area and thyristor control phase shifter is used in the interconnection line of the power system. The potential of the hSC-FDO-based FOI-TDN is demonstrated by comparing it with conventional FOTID/FOPID/PID controllers for two areas with multiple power generators IPS. Finally, a robustness analysis is performed to determine the robustness of the presented control system by varying the system loads and system parameters.

The guava plant has achieved viable significance in subtropics and tropics owing to its flexibility to climatic environments, soil conditions and higher human consumption. It is cultivated in vast areas of Asian and Non-Asian countries, including Pakistan. The guava plant is vulnerable to diseases, specifically the leaves and fruit, which result in massive crop and profitability losses. The existing plant leaf disease detection techniques can detect only one disease from a leaf. However, a single leaf may contain symptoms of multiple diseases. This study has proposed a hybrid deep learning-based framework for the real-time detection of multiple diseases from a single guava leaf in several steps. Firstly, Guava Infected Patches Modified MobileNetV2 and U-Net (GIP-MU-NET) has been proposed to segment the infected guava patches. The proposed model consists of modified MobileNetv2 as an encoder, and the U-Net model’s up-sampling layers are used as a decoder part. Secondly, the Guava Leaf Segmentation Model (GLSM) is proposed to segment the healthy and infected leaves. In the final step, the Guava Multiple Leaf Diseases Detection (GMLDD) model based on the YOLOv5 model detects various diseases from a guava leaf. Two self-collected datasets (the Guava Patches Dataset and the Guava Leaf Diseases Dataset) are used for training and validation. The proposed method detected the various defects, including five distinct classes, i.e., anthracnose, insect attack, nutrition deficiency, wilt, and healthy. On average, the GIP-MU-Net model achieved 92.41% accuracy, the GLSM gained 83.40% accuracy, whereas the proposed GMLDD technique achieved 73.3% precision, 73.1% recall, 71.0% mAP@0.5 and 50.3 mAP@0.5:0.95 scores for all the aforesaid classes.

Sentiment analysis was nominated as a hot research topic a decade ago for its increasing importance in analyzing the people’s opinions extracted from social media platforms. Although the Arabic language has a significant share of the content shared across social media platforms, its content’s sentiment analysis is still limited due to its complex morphological structures and the varieties of dialects. Traditional machine learning and deep neural algorithms have been used in a variety of studies to predict sentiment analysis. Therefore, a need of changing current mechanisms is required to increase the accuracy of sentiment analysis prediction. This paper proposed an optimized heterogeneous stacking ensemble model for enhancing the performance of Arabic sentiment analysis. The proposed model combines three different of pre-trained Deep Learning (DL) models: Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) in conjunction with three meta-learners Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM) in order to enhance model’s performance for predicting Arabic sentiment analysis. The performance of the proposed model with RNN, LSTM, GRU, and the five regular ML techniques: Decision Tree (DT), LR, K-Nearest Neighbor (KNN), RF, and Naive Bayes (NB) are compared using three benchmarks Arabic dataset. Parameters of Machine Learning (ML) and DL are optimized using Grid search and KerasTuner, respectively. Accuracy, precision, recall, and f1-score were applied to evaluate the performance of the models and validate the results. The results show that the proposed ensemble model has achieved the best performance for each dataset compared with other models.

Frequency, voltage, and power flow between different control zones in an interconnected power system are used to determine the standard quality of power. Therefore, the voltage and frequency control in an IPS is of vital importance to maintaining real and reactive power balance under varying load conditions. In this paper, a dandelion optimizer (DO)-based proportional-integral-proportional-derivative (PI-PD) controller is investigated for a realistic multi-area, multi-source, realistic IPS with nonlinearities. The output responses of the DO-based PI-PD were compared with the hybrid approach using artificial electric field-based fuzzy PID algorithm (HAEFA), Archimedes optimization algorithm (AOA)-based PI-PD, learning performance-based behavior optimization (LPBO)-based PI-PD and modified particle swarm optimization (MPSO)-based PI-PD control schemes in a two-area network with 10% step load perturbation (SLP). The proposed strategy was also investigated in a two- and three-area IPS in the presence of different nonlinearities and SLPs. The simulation results and the comprehensive comparison between the different control schemes clearly confirm that the proposed DO-based PI-PD is very effective for realistic, multi-area multi-source IPS with nonlinearities.

Digitalization in healthcare through advanced methods, tools, and the Internet are prominent social development factors. However, hackers and malpractices through cybercrimes made this digitalization worrisome for policymakers. In this study, the role of E-Government Development as a proxy for digitalization and corruption prevalence has been analyzed in Healthcare sustainability in developing and underdeveloped countries of Asia from 2015 to 2021. Moreover, a moderator role of Cybersecurity measures has also been estimated on EGDI, CRP, and HS through the two-step system GMM estimation. The results show that EGDI and CRP control measures significantly improved HS in Asia. Furthermore, by deploying strong and effective Cybersecurity measures, Asia’s digitalization and institutional practices are considerably enhanced, which also has an incremental impact on HS and ethical values. This present study added a novel contribution to existing digitalization and public health services literature and empirical analysis by comprehensively applying advanced econometric estimation. The study concludes that cybersecurity measures significantly improved healthcare digitalization and controlled the institutional malfunctioning in Asia. This study gives insight into how cybersecurity measures enhance the service quality and promote institutional quality of the health sector in Asia, which will help draft sustainable policy decisions and ethical values in the coming years.