Segmentation of skin lesions remains essential in histological diagnosis and skin cancer surveillance. Recent advances in deep learning have paved the way for greater improvements in medical imaging. The Hybrid Residual Networks (ResUNet) model, supplemented with Ant Colony Optimization (ACO), represents the synergy of these improvements aimed at improving the efficiency and effectiveness of skin lesion diagnosis. This paper seeks to evaluate the effectiveness of the Hybrid ResUNet model for skin lesion classification and assess its impact on optimizing ACO performance to bridge the gap between computational efficiency and clinical utility. The study used a deep learning design on a complex dataset that included a variety of skin lesions. The method includes training a Hybrid ResUNet model with standard parameters and fine-tuning using ACO for hyperparameter optimization. Performance was evaluated using traditional metrics such as accuracy, dice coefficient, and Jaccard index compared with existing models such as residual network (ResNet) and U-Net. The proposed hybrid ResUNet model exhibited excellent classification accuracy, reflected in the noticeable improvement in all evaluated metrics. His ability to describe complex lesions was particularly outstanding, improving diagnostic accuracy. Our experimental results demonstrate that the proposed Hybrid ResUNet model outperforms existing state-of-the-art methods, achieving an accuracy of 95.8%, a Dice coefficient of 93.1%, and a Jaccard index of 87.5. The addition of ResUNet to ACO in the proposed Hybrid ResUNet model significantly improves the classification of skin lesions. This integration goes beyond traditional paradigms and demonstrates a viable strategy for deploying AI-powered tools in clinical settings. Future investigations will focus on increasing the version's abilities by using multi-modal imaging information, experimenting with alternative optimization algorithms, and comparing real-world medical applicability. There is also a promising scope for enhancing computational performance and exploring the model's interpretability for more clinical adoption.

Epoxy-based nanocomposites have drawn much interest in high-voltage insulation applications due to their improved dielectric properties. The determination of the optimal nanoparticle (NP) concentration required to achieve a significant enhancement in nanocomposite dielectric properties remains a subject of ongoing research. Previous work has employed iterative experimental methodologies, often characterized by the hit-and-trial method, in attempts to find the optimal nanoparticle concentration. However, these efforts have yielded suboptimal or inconsistent results. Moreover, experimental procedures for optimizing the nanoparticle concentration require significant time and cost. This research study proposed the predictive capabilities of machine learning (ML) for the selection of the nanoparticle concentration in epoxy-based nanocomposite insulators. The authors employed a novel systematic approach in this research work, comprising dataset preparation, ML model implementation, and experimental validation. A real-time dataset with varying concentrations of NPs (TiO₂, SiO₂, Al₂O₃) was developed in the High Voltage Lab, KFUEIT, Pakistan. Several advanced machine learning models are trained on this dataset. Support Vector Regression (SVR) exhibits the highest prediction accuracy, with an R² score of 0.97. SVR predicted a breakdown voltage (BDV) of 46.26 kV, with a (w/w %) concentration of 5% TiO₂, 1.17631% SiO₂, and 3.95755% Al₂O₃. To validate the SVR prediction, a hardware prototype with predicted NP concentration is developed and tested. The experimentally measured BDV of the predicted nanocomposite sample, registering 44.72 kV, authenticates the predictive accuracy of machine learning. This work demonstrates the efficacy of machine learning as a viable and efficient alternative to traditional experimental methods for optimizing nanoparticle concentrations using a predictive approach in epoxy-based nanocomposites for high-voltage insulation applications.

Ensemble learning, which involves combining the opinions of multiple experts to arrive at a better result, has been used for centuries. In this work, a review of the major voting methods in ensemble learning is explored. This work will focus on a new method for combining the results of individual learners. The method depends on the relative accuracy and diversity of teams. Instead of trying to assign weight to each different trainer, the concept of diversity teams is presented. Each team will vote as one player; however, the individual accuracies of each learner still be implemented. The concept of relaxing parameters that deal with each team as one player is presented. Our experiments demonstrate that traditional ensemble voting methods outperform individual learners. There is a limit to the superiority of the ensemble learner that any ensemble learner cannot go beyond. The proposed voting method gives the same results as the traditional ensemble voting methods, however, a different diversity of the proposed method from the traditional voting method or for different values of the relaxing parameter can be achieved.

The development of smart sustainable cities increasingly relies on advanced communication infrastructures to support intelligent transportation systems, energy management, and data-intensive urban services. The rapid expansion of Internet of Everything networks has led to rising energy consumption, posing a critical challenge for sustainable urban development. This research was conducted to address the need for energyefficient, high-performance wireless communication solutions capable of supporting large-scale, innovative city applications. In particular, High Altitude Platform Systems have emerged as promising communication enablers due to their wide coverage and deployment flexibility, however, their effectiveness is constrained by the energy efficiency and performance of antenna systems. This study investigates the application of Machine Learning techniques for the optimisation of 3D antenna structures to enhance communication efficiency. The 3D intelligent Microstrip Patch Multiple Input Multiple Output antenna operating at 28 GHz was designed and optimised using a Machine Learning-driven framework. The antenna design process was carried out using 3D digital Computer Simulation Technology software, enabling precise electromagnetic modelling and performance evaluation. Machine Learning algorithms were employed to systematically adjust antenna parameters, allowing the identification of optimal design configurations beyond conventional trial-and-error methods. The performance of the optimised antenna was evaluated using Quality of Service parameters for power efficiency and lastmile connectivity. Comparative analysis with non-optimised antenna designs demonstrated substantial performance gains. The results reveal an improvement of up to 31 percent in power efficiency, accompanied by enhanced connectivity performance. These findings indicate that Artificial Intelligence-driven antenna design is a practical approach to developing sustainable, energy-efficient communication infrastructure for future, innovative city environments.