Search

In accordance with the inability of various hair artefacts subjected to dermoscopic medical images, undergoing illumination challenges that include chest-Xray featuring conditions of imaging acquisi-tion situations built with clinical segmentation. The study proposed a novel deep-convolutional neural network (CNN)-integrated methodology for applying medical image segmentation upon chest-Xray and dermoscopic clinical images. The study develops a novel technique of segmenting medical images merged with CNNs with an architectural comparison that incorporates neural networks of U-net and fully convolutional networks (FCN) schemas with loss functions associated with Jaccard distance and Binary-cross entropy under optimised stochastic gradient descent + Nesterov practices. Digital image over clinical approach significantly built the diagnosis and determination of the best treatment for a patient’s condition. Even though medical digital images are subjected to varied components clarified with the effect of noise, quality, disturbance, and precision depending on the enhanced version of images segmented with the optimised process. Ultimately, the threshold technique has been employed for the output reached under the pre- and post-processing stages to contrast the image technically being developed. The data source applied is well-known in PH2 Database for Melanoma lesion segmentation and chest X-ray images since it has variations in hair artefacts and illumination. Experiment outcomes outperform other U-net and FCN architectures of CNNs. The predictions produced from the model on test images were post-processed using the threshold technique to remove the blurry boundaries around the predicted lesions. Experimental results proved that the present model has better efficiency than the existing one, such as U-net and FCN, based on the image segmented in terms of sensitivity = 0.9913, accuracy = 0.9883, and dice coefficient = 0.0246.

This review article delves into the advancements in the realm of nanogrids and their potential in addressing energy challenges, particularly in regions with limited access to centralized power grids. The paper reviews the work in the areas of nanogrids as solutions for regions like sub-Saharan Africa, where a significant population lacks access to main grid electricity. The integration of multiple nanogrids within a community, coupled with an investor energy bank, is explored as a means to alleviate the economic burden of energy storage and to harness the full potential of solar energy. The article also examines the challenges faced by centralized power grids and the shift towards distributed generation (DG) as a remedy. The concept of nanogrids is further elaborated, discussing their control topologies, techniques, and the potential of interconnecting multiple nanogrids to form a microgrid. Lastly, the co-design of solar generationbased nano-grids and water treatment in remote areas is studied, emphasizing the importance of providing essential drinking water and electricity to underdeveloped regions. The integration of solar-powered electricity with water treatment processes offers a unique solution to address both electricity and water needs in such areas.

This paper offers a comprehensive review of grid-supportive inverter technologies aimed at enhancing power quality. One area of exploration presents a two-stage three-phase three-wire solar photovoltaic (SPV) system. This system utilises a boost converter for optimal power point tracking and a three-leg voltage source converter to channel the harnessed SPV energy. Distinctively, this approach provides harmonics elimination, grid current balancing, and compensation for the nonactive portion of load currents, going beyond traditional solar inverter functionalities. An innovative adjustable step adaptive neuron-based control method is employed to gauge the genuine power reflecting segment of the load current, ensuring swift dynamic adaptability to environmental shifts. Another focal point addresses the complexities introduced by the rising integration of microgrid systems within the AC distribution framework. Highlighting the imperative of maintaining voltage and frequency, the narrative accentuates the pivotal role of energy storage systems (ESS) for the proficient operation of sensitive loads. A grid adaptive power management strategy (GA-PMS) is proposed, orchestrating the current references for renewable energy sources, ESS, and microgridconnected converters. This strategy guarantees uninterrupted microgrid functionality, priority-driven load shedding, and the maintenance of power quality standards at the local bus. Both areas significantly contribute to the evolution of grid-supportive inverter technologies and their potential in power quality betterment.

This review focuses on Distributed Generation Planning within Multi-Energy Microgrids (MES), a transformative approach where various energy forms like electricity, heat, and cooling interact optimally. MES offers significant technical, economic, and environmental benefits, making it crucial to explore intricate modelling and assessment techniques for such systems, including microgrids, virtual power plants (VPPs), and energy hubs. Amid global energy challenges and environmental crises, renewable energy adoption is vital. Distributed Generation (DG) plays a pivotal role, but integrating it at scale poses challenges. Microgrids are a viable solution, and this review introduces their core concepts, emerging trends, and challenges, such as integrating more renewable energy sources, multienergy forms, complex architectures, demand-side management, and advanced storage. Furthermore, the paper delves into Multi-Energy Microgrid planning complexities, particularly in off-grid areas. It presents a stochastic investment model that minimizes costs and carbon emissions while optimizing the distributed energy resource mix, locations, and sizes. This model considers intricate energy flows and uncertainties associated with renewable generation and energy demands. Case studies confirm significant cost and emission reductions, establishing it as a promising multi-energy microgrid planning solution for the future.

This article reviews the progress in the realm of Hybrid Cloud Surveillance in Smart Grids Optimising Solar Power with Dual-Mode Control, delving into the amalgamation of smart grid systems with modern communication and information technology methodologies. A pronounced focus is given to the employment of hybrid or private clouds for bolstered security, data categorisation, and storage sourced from the power grid. The research accentuates the necessity to establish a robust wireless sensor network for overseeing pivotal parameters within the power system grid, enabling automated decision-making during system disruptions or fault current situations by scrutinising the processed data. This approach enhances the power system design and fortifies its integration with renewable energy sources, improving storage capacity and dependability. Moreover, the paper probes into the workings of a solar hybrid power system, utilising an innovative fuzzy control method. By embedding a supercapacitor hybrid energy storage system (HESS) into the solar hybrid power generation framework, there’s a marked increase in energy consumption, storage space, and power output. The research underscores the challenges presented by the nonlinear behaviour of photovoltaic devices and the necessity for advanced maximum power point tracking (MPPT) techniques, with the integration of a dynamic power factor correction scheme and a conductance-fuzzy dual-mode control strategy emerging as a central solution for optimising the solar hybrid renewable energy system.

This review explores Peer-to-Peer (P2P) Energy Trading Platforms in Local Energy Markets, drawing insights from three key studies. These markets, using P2P trading, efficiently distribute electricity within communities. Research assesses P2P trading’s impact in a Norwegian neighbourhood, comparing it to scenarios without local markets. It also examines integrating PV systems, batteries, and electric vehicles on grid operations. Findings reveal minimal grid impacts with PVs alone, but adding batteries increases voltage fluctuations and losses. However, P2P trading benefits end-users with cost savings and supports Distribution System Operator operations. The paper surveys global P2P energy trading projects, emphasising communication and control networks within local Microgrids. It discusses the transition from passive consumers to prosumers in power networks and introduces the concept of a federated power plant, combining virtual power plants and P2P transactions among prosumers to address challenges and unlock additional value. This review fills research gaps, shedding light on P2P energy trading’s multifaceted aspects in local markets and its transformative potential for the energy sector.

This paper reviews sustainable business models for Photovoltaic (PV) Systems in developing countries. Firstly, it examines the global adoption of energy business models, noting the shift from customer-owned to community-shared initiatives in developing nations and the prominence of the virtual net metering and store-on grid schemes. Secondly, it identifies barriers to distributed energy solutions, exploring the evolution of PV business models and the advantages of community-shared models over other alternatives. Lastly, it investigates the deployment of customersited PV systems in Germany, Japan, and the USA, highlighting distinctive business models that have catalysed PV adoption. The review offers insights for decision-makers and solar firms navigating the PV sector in developing countries.

This paper offers a comprehensive review of the advancements in the domain of solar energy forecasting models, emphasizing their significance for grid integration and power balancing. The increasing inclusion of renewable resources in global energy portfolios underscores the urgency for precise forecasting of variable resources like solar energy. Solar generation technologies have witnessed remarkable growth, leading to heightened grid penetration rates. However, the ground-level solar resource is characterized by high variability, primarily influenced by factors such as cloud cover changes, atmospheric aerosol levels, and certain atmospheric gases. This variability, especially at elevated grid penetration levels, introduces challenges related to reserve costs, dispatchable generation, and overall grid reliability. To address these challenges, there’s a pressing need for forecast systems with high accuracy across multiple time horizons, catering to regulation, dispatching, scheduling, and unit commitment. Furthermore, the variability of renewable energy stands as a significant barrier to its broader adoption. Energy storage emerges as a potential solution to mitigate power imbalances arising from the disparity between available renewable power and load demands. Through an analytical model, this review explores the potential of storage in reducing power imbalances and the requisite storage capacity to achieve this balance. The paper delves into the theory behind these forecasting methodologies and highlights successful applications in solar forecasting for utility-scale solar plants.

In the modern agricultural landscape, the surge in demand for organic farming accentuates the imperative of continuous plant health monitoring. This becomes even more paramount when ensuring both the quality and quantity of produce. Crop devastation by wild and domestic animals, coupled with the challenge of maintaining optimal soil conditions, necessitates innovative solutions, particularly in settings where round-the clock human surveillance is not viable. This review delves into an advanced, automated crop protection system, amalgamating the prowess of the Internet of Things (IoT) and Wireless Sensor Network (WSN) to address these multifaceted issues. The objective of the highlighted research is to craft a remote system capable of ceaseless soil moisture assessment, thereby optimizing plant health and yield. Enhancing the efficiency and longevity of this system, the Exponential Weighted Moving Average (EWMA) event detection algorithm has been incorporated. Furthermore, the system safeguards agricultural territories from intruders and wild animal threats, offering farmers a robust mechanism to prevent substantial financial losses and ensuring they yield healthier, abundant crops.

It has become essential to protect vital infrastructures from cyber threats in an age where technology permeates every aspect of our lives. This article examines how machine learning and cybersecurity interact, providing a thorough overview of how this dynamic synergy might strengthen the defence of critical systems and services. The hazards to public safety and national security from cyberattacks on vital infrastructures including electricity grids, transportation networks, and healthcare systems are significant. Traditional security methods have failed to keep up with the increasingly sophisticated cyber threats. Machine learning offers a game-changing answer because of its ability to analyse big datasets and spot anomalies in real time. The goal of this study is to strengthen the defences of key infrastructures by applying machine learning algorithms, such as CNN, LSTM, and deep reinforcement learning for anomaly algorithm. These algorithms can anticipate weaknesses and reduce possible breaches by using historical data and continuously adapting to new threats. The research also looks at issues with data privacy, algorithm transparency, and adversarial threats that arise when applying machine learning to cybersecurity. For machine learning technologies to be deployed successfully, these obstacles must be removed. Protecting vital infrastructures is essential as we approach a day where connectivity is pervasive. This study provides a road map for utilising machine learning to safeguard the foundation of our contemporary society and make sure that our vital infrastructures are robust in the face of changing cyberthreats. The secret to a safer and more secure future is the marriage of cutting-edge technology with cybersecurity knowledge.

In today's data-driven environment, protecting machine learning ecosystems has taken on critical importance. Organisations are relying more and more on AI and ML models to guide important decisions and operations, which have led to an increase in system vulnerabilities. The critical need for techniques to create resilient machine learning (ML) systems that can withstand changing threats is discussed in this study.Data protection is an important component of securing ML environments. Every part of the process, from data preprocessing through model deployment, needs to be secured. In order to reduce potential vulnerabilities, this incorporates code review procedures, safe DevOps practises, and container security.System resilience is vitally dependent on on-going monitoring and anomaly detection. Organisations can respond quickly to security problems by detecting deviations from normal behaviour early on and adjusting their defences as necessary.A strong incident response plan is essential. To protecting machine learning ecosystems necessitates a comprehensive strategy that includes monitoring, incident response, model security, pipeline security, and data protection. By implementing these tactics, businesses may create robust machine learning (ML) systems that can endure the changing threat landscape, protect their data, and guarantee the validity of their AI-driven decision-making processes.

Data privacy has grown to be of utmost importance in today's digitally driven world. Protecting sensitive information has never been more important due to the explosion of data across many areas. This abstract explores cutting-edge machine learning techniques for improving data privacy in the digital age.Artificial intelligence's subset of machine learning presents a viable way to overcome issues with data privacy. This study investigates how machine learning algorithms can be used to strengthen confidentiality protections in a range of applications. Machine learning models may uncover vulnerabilities and potential breaches in real time by analysing large information, offering proactive defence against cyber threats.We explore a number of data privacy topics, such as access control, encryption, and data anonymization, while emphasising how machine learning approaches might improve these procedures. We also cover how federated learning protects privacy during collaborative data analysis, enabling different parties to gain knowledge without jeopardising the integrity of the data.The importance of ethics and compliance in the creation and application of machine learning solutions for data confidentiality is also emphasised in this abstract. It highlights the necessity for ethical AI practises and highlights the difficulties in finding a balance between the preservation of privacy and the usefulness of data.This study investigates how machine learning could strengthen data confidentiality, paving the path for a more safe and considerate digital future. It highlights the value of interdisciplinary cooperation between data scientists, ethicists, and policymakers to fully utilise machine learning's promise in protecting our sensitive information in the digital world.

Machine learning algorithms have quickly risen to the top of several fields' decision-making processes in recent years. However, it is simple for these algorithms to confirm already present prejudices in data, leading to biassed and unfair choices. In this work, we examine bias in machine learning in great detail and offer strategies for promoting fair and moral algorithm design. The paper then emphasises the value of fairnessaware machine learning algorithms, which aim to lessen bias by including fairness constraints into the training and evaluation procedures. Reweighting, adversarial training, and resampling are a few strategies that could be used to overcome prejudice. Machine learning systems that better serve society and respect ethical ideals can be developed by promoting justice, transparency, and inclusivity. This paper lays the groundwork for researchers, practitioners, and policymakers to forward the cause of ethical and fair machine learning through concerted effort.