Morphometry-based detection of deep learning faults in glomerular segmentation

Background and Purpose:Deep learning promises accurate target contouring for online adaptive MR-guided radiotherapy (MRgRT) in rectal cancer. However, delineating the mesorectal clinical target volume (CTV) remains challenging. Integrating planning-based contours, delineated offline before treatment, can provide anatomical shape and boundary information. This study evaluated deep learning-based segmentation and registration models to determine the optimal approach for incorporating planning contours into online rectal contouring.Materials and Methods:Deep learning-based segmentation and registration models, both U-Nets, were developed using MRI of 104 rectal cancer patients, split into 68, 14, and 22 training, validation, and testing subjects. The segmentation model used the planning CTV and daily fraction MRI, while the registration model used the planning MRI and CTV and the daily fraction MRI. The models were compared in terms of contour accuracy (maximum Hausdorff distance (HD), Dice, and a qualitative score) and robustness against domain shifts.Results:When incorporating the planning contour, the segmentation and registration models achieved comparable median HD values of 9.3 mm (interquartile range, IQR: 7.1-12.1) and 10.2 (8.2-12.4) (p=0.18), respectively. However, segmentation achieved lower HD values in the middle and cranial regions of the target (HDmiddle: 5.3 mm (4.3-6.6) vs. 6.0 mm (4.8-8.0), p0.05; HDcranial: 7.6 mm (6.3-10.7) vs. 9.6 mm (7.5-11.9), p0.05). In addition, segmentation resulted in more clinically acceptable contours (9/10 versus 3/10) and was more robust to rectum volume variations than registration.Conclusion:Deep learning-based segmentation was identified as the optimal approach for incorporating the planning CTV into online rectal delineation in MRgRT.

The article explores the transformative impact of Artificial Intelligence (AI) on
 engineering, focusing on the evolution over the last decade. AI has become a cornerstone in
 reliable engineering, influencing various aspects such as predictive maintenance, fault
 detection, optimization, automation, and decision support. Predictive maintenance, enabled by
 AI algorithms, revolutionizes traditional approaches by analysing extensive datasets to predict
 equipment failures, allowing proactive interventions and minimizing downtime. Fault detection
 and diagnostics benefit from AI's real-time monitoring and early anomaly identification,
 reducing the risk of catastrophic failures and enhancing overall system reliability. Optimization
 of complex systems is facilitated by AI's capacity to process vast amounts of data, leading to
 improved performance and minimized resource consumption. The integration of AI in
 automation and robotics reshapes manufacturing processes, emphasizing precision and
 reliability. Simulation and modelling, data analysis, and supply chain optimization are also
 discussed as vital areas where AI contributes to enhanced reliability. The article highlights the
 importance of ethical considerations and human oversight in deploying AI responsibly,
 emphasizing a collaborative synergy between AI and human expertise for continued
 advancements in engineering solutions.

The increasing complexity of electrical power systems necessitates advanced fault detection and predictive maintenance strategies to enhance operational efficiency and grid reliability. Traditional maintenance approaches, such as reactive and preventive maintenance, have proven insufficient in mitigating unplanned outages and optimizing asset utilization. Recent advancements in artificial intelligence (AI) have introduced data-driven solutions that significantly improve fault classification, failure prediction, and automated recovery processes. This study conducts a systematic review of 180 high-quality peer-reviewed articles, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to ensure a rigorous and transparent research methodology. The findings reveal that AI-driven predictive maintenance methods, including machine learning, deep learning, digital twin technology, IoT-enabled sensor networks, and self-healing grids, have outperformed traditional fault detection techniques in terms of accuracy, adaptability, and cost-effectiveness. AI-based fault detection models achieve an average accuracy of 85% to 95%, reducing false alarms by 50% and minimizing power restoration times by up to 60%. The integration of IoT sensors with real-time analytics has improved anomaly detection rates by 28%, while digital twin technology has enhanced predictive maintenance efficiency, reducing unplanned outages by 35%. Additionally, self-healing grid mechanisms, powered by reinforcement learning algorithms, have demonstrated the ability to autonomously isolate faults and reconfigure energy distribution, preventing nearly 45% of potential service disruptions. Despite these advancements, challenges such as the black-box nature of deep learning models, cybersecurity vulnerabilities, and interoperability with legacy systems continue to pose barriers to large-scale AI adoption. The study highlights the need for explainable AI frameworks, standardized data governance policies, and enhanced cybersecurity measures to ensure the sustainable deployment of AI in power grid management. The findings provide valuable insights for researchers, utility companies, and policymakers seeking to enhance the resilience and efficiency of modern electrical power systems through AI-driven fault detection and predictive maintenance strategies.

Plant identification based on leaf images is a widely concerned application field in artificial intelligence and botany. The key problem is extracting robust discriminative features from leaf images and assigning a measure of similarity. This study proposes an effective, robust shape descriptor to identify plant species from images of their leaves, which we call the high-level triangle shape descriptor (HTSD). First, we extract a leaf image's external contour and internal salient point information. We then use triangle features to describe the leaf contour, which we call the contour point based on triangle features (CPTFs). The internal information of the leaf image is based on salient point triangle features (SPTFs). The third step is to apply the Fisher vector to encode the two kinds of point-based local triangle features into the HTSD. Finally, we employ the simple euclidean distance to calculate the dissimilarities between the HTSD characteristics of leaf images. We have extensively evaluated the proposed approach on several public leaf datasets successfully. Experimental results show that our method has superior recognition accuracy, outperforming current state-of-the-art shape-based and deep-learning plant identification approaches.

In this paper, we propose a novel method for extracting the optimal structure element for MST-based shape description. Specifically, we use tabu search to solve the optimal structure element extraction problem for morphological signature transform (MST)-based shape description. To the best of our knowledge, this is the first attempt in which tabu search has been used in computer vision. Our tabu search (TS) has a number of advantages: (1) TS avoids entrapment in local minima and continues the search to give a near-optimal final solution; (2) TS is very general and conceptually much simpler than either simulated annealing or genetic algorithms; (3) TS is very easy to implement and the entire procedure only occupies a few lines of code; (4) TS is a flexible framework of a variety of strategies originating from artificial intelligence and is therefore open to further improvement.

CT patterns of viral pneumonia are usually only qualitatively described in radiology reports. Artificial intelligence enables automated and reliable segmentation of lungs with chest CT. Based on this, the purpose of this study was to derive meaningful imaging biomarkers reflecting CT patterns of viral pneumonia and assess their potential to discriminate between healthy lungs and lungs with viral pneumonia. This study used non-enhanced and CT pulmonary angiograms (CTPAs) of healthy lungs and viral pneumonia (SARS-CoV-2, influenza A/B) identified by radiology reports and RT-PCR results. After deep learning segmentation of the lungs, histogram-based and threshold-based analyses of lung attenuation were performed and compared. The derived imaging biomarkers were correlated with parameters of clinical and biochemical severity (modified WHO severity scale; c-reactive protein). For non-enhanced CTs (n = 526), all imaging biomarkers significantly differed between healthy lungs and lungs with viral pneumonia (all p < 0.001), a finding that was not reproduced for CTPAs (n = 504). Standard deviation (histogram-derived) and relative high attenuation area [600–0 HU] (HU-thresholding) differed most. The strongest correlation with disease severity was found for absolute high attenuation area [600–0 HU] (r = 0.56, 95% CI = 0.46–0.64). Deep-learning segmentation-based histogram and HU threshold analysis could be deployed in chest CT evaluation for the differentiating of healthy lungs from AP lungs.

In this paper, the application of Artificial intelligence (AI) methods in power system protection and inspection has been discussed. In this paper particularly AI application of line scout Robot is used. Line scout robot is an inspection based Artificial intelligence Robot. Line Scout robot is able to work on the power lines while they are operating (at very high tension). The robot can patrol in a substation and inspect equipment with a visible-light camera and thermograph. It has possess a vast array of cameras and tools that allow the remote operators to inspect and conduct (albeit minor) repairs on the power lines without needing to put the off-service or risking their lives. It is preventive arrangement for detection of fault (very high temperature). Keywords: Artificial intelligence (AI), artificial general intelligence (AGI), corona pulse, Line Scout Robot, power system

Driven by the high penetration of renewable energy sources and power electronic devices, modern power systems have become increasingly complex, intensifying the demand for accurate and intelligent fault detection. This paper analyzes a total of 81 references to explore the integrated application of artificial intelligence (AI) technologies across all stages of fault data processing, modeling, and optimization. The application potential of AI in fault data processing is firstly analyzed in terms of its performance in mitigating class imbalance, extracting feature information, handling data noise and classification. Then, the modeling of fault detection is classified into rule-driven, data-driven and hybrid-driven methods to evaluate their applicability in scenarios such as transmission lines and distribution networks. The accuracy of fault detection models is also investigated by studying the hyperparameter optimization (HPO) methods. The results indicate that the utilization of AI-driven imbalance handling enhances model accuracy by a range of 16.2% to 26.2%, while deep learning-based feature extraction techniques sustain accuracy levels exceeding 98.5% under a signal-to-noise ratio (SNR) of 10 dB. With a 99.96% detection accuracy, hybrid-driven models applied in fault detection perform the best. For the optimization of fault detection models, heuristic algorithms provide 6.92–19.375% improvement over the baseline models. The findings suggest that AI-driven methodologies in data processing demonstrate notable noise resilience and other benefits. For modeling fault detection, data-driven and hybrid-driven models are presently extensively employed for detecting short-circuit faults, predicting transformer gas trends, and identifying faults in complex and uncertain scenarios. Conversely, rule-driven models are better suited for scenarios possessing a comprehensive experience library and are utilized with less frequency. In the optimization of fault detection models, heuristic algorithms occupy a pivotal position, whereas hyperparameter optimization incorporating reinforcement learning (RL) is better suited for real-time fault detection. The discoveries presented in this paper facilitate the seamless integration of AI with fault detection in modern power systems, thereby advancing their intelligent evolution.

Purpose: This paper is a pioneering study that investigates the integration of Artificial Intelligence (AI) to enhance energy efficiency in 5G Radio Access Networks (RANs). This paper aims to identify AI-driven strategies that can significantly optimize energy consumption in the rapidly evolving 5G network infrastructure, which is essential for meeting the increasing demand for high-speed connectivity.&#x0D; Methodology: The methodology used for this research is a detailed review and analysis of the 5G RAN architecture and its energy dynamics, alongside the exploration of AI applications in optimizing network operations. The study focuses on AI techniques such as resource allocation, traffic prediction, adaptive sleep modes, and fault detection, proposing a holistic approach to energy management in 5G networks. A key contribution of this research is its in-depth examination of AI's role in 5G energy efficiency, highlighting its practical implications and potential for future applications. The paper offers novel insights into the implementation of AI in real-world 5G scenarios and addresses the challenges in transitioning from theoretical models to practical solutions.&#x0D; Findings: The findings reveal that AI integration is a vital step towards reducing the environmental footprint of 5G networks, with AI-based solutions showing promise in enhancing efficiency beyond the inherent capabilities of current 5G technologies. Despite many AI applications being in nascent stages, their potential impact on energy efficiency is significant.&#x0D; Unique contributor to theory, policy and practice: This paper is a valuable guide for researchers, industry professionals, and policymakers in telecommunications and environmental sustainability. It provides a clear roadmap for leveraging AI in 5G networks, emphasizing the synergy between technological innovation and ecological responsibility.

Artificial intelligence (AI) and deep learning (DL) have shown tremendous potential in driving sustainability across various sectors. This paper reviews recent advancements in AI and DL and explores their applications in achieving sustainable development goals (SDGs), renewable energy, environmental health, and smart building energy management. AI has the potential to contribute to 134 of the 169 targets across all SDGs, but the rapid development of these technologies necessitates comprehensive regulatory oversight to ensure transparency, safety, and ethical standards. In the renewable energy sector, AI and DL have been effectively utilized in optimizing energy management, fault detection, and power grid stability. They have also demonstrated promise in enhancing waste management and predictive analysis in photovoltaic power plants. In the field of environmental health, the integration of AI and DL has facilitated the analysis of complex spatial data, improving exposure modeling and disease prediction. However, challenges such as the explainability and transparency of AI and DL models, the scalability and high dimensionality of data, the integration with next-generation wireless networks, and ethics and privacy concerns need to be addressed. Future research should focus on enhancing the explainability and transparency of AI and DL models, developing scalable algorithms for processing large datasets, exploring the integration of AI with next-generation wireless networks, and addressing ethical and privacy considerations. Additionally, improving the energy efficiency of AI and DL models is crucial to ensure the sustainable use of these technologies. By addressing these challenges and fostering responsible and innovative use, AI and DL can significantly contribute to a more sustainable future.

The rapid advancement of Artificial Intelligence (AI) is opening up exciting new ways to improve hybrid renewable energy systems (HRES). These advancements promise greater efficiency, reliability, and sustainability in how we generate and use energy. In this review, we examine the current application of AI in HRES, focusing on techniques such as machine learning, deep learning, and reinforcement learning that facilitate energy use forecasting, resource management, and fault detection. However, integrating AI into these energy systems is not without its challenges. Issues such as data quality, the need for transparent algorithms, cybersecurity risks, and compatibility with older technologies can complicate things. Additionally, there are significant regulatory and ethical concerns to address, like algorithmic bias and ensuring inclusivity in AI applications, which can slow down widespread adoption. To tackle these obstacles, future research should focus on developing AI models that are easy to understand and explain. We also need systems that can adapt to changing market conditions and security frameworks that safeguard our cyber-physical infrastructures. Collaboration across disciplines, bringing together experts in data science, energy engineering, and environmental policy, will be crucial in building systems that are not only resilient but also tailored to specific contexts. Looking ahead, it is vital to include local communities and policymakers in the conversation to ensure that energy distribution is fair and that people trust AI-driven solutions. This review emphasizes that when used responsibly, AI can help drive a global shift toward more innovative, cleaner, and more inclusive energy systems.

Fault detection and circuit testing consider as an important stage in production process. Fault detection is generally the last part of production process and after that the system is ready to use. Nowadays, controlling circuits and systems are widely used in control, communications, medical instruments and etc. the complexity of circuits are increased by growth of technology. Therefore, research and investigation on circuit fault detection is a challenging and non-ignorable issue. Many method has been presented in order to solve this problem. In this work methods based on signal processing and artificial intelligence will be used. Many of this methods such as wavelet transform, artificial neural networks, support vector machines, genetic algorithm and etc. were used in fault detection field. In this paper, a new method for the empirical mode decomposition of signals into independent IMF is presented, which results in extraction of discriminative features and better fault detection accuracy. The proposed method has been investigated and compared using two analog benchmark circuit. The results show a better performance of the proposed method.

This important book fills the gap between smart photovoltaic technology and artificial intelligence technologies and is a major contribution to a growing field. Artificial Intelligence for Smart Photovoltaic Technologies provides a comprehensive introduction to these two areas and includes a description of key artificial intelligence algorithms and their applications in PV systems.Key topics include: • A focus on cutting-edge applications of the AI technologies for smart photovoltaic technologies• Presenting future applications of AI in PV power generation process, including power forecasting, predictive control, fault detection and diagnosis, and smart PV management• The role of artificial intelligence for highly efficient and stable PV power generation systemsThis book is the ideal introduction for researchers in industry and academia working in both photovoltaics and applied artificial intelligence. It will also appeal more broadly to technicians, consultants, and policy experts involved in photovoltaic deployment. Graduate and advanced undergraduate students and those interested in renewable energy or artificial intelligence will also find it a useful reference.

The pursuit of energy sustainability has become paramount in addressing the global challenges of climate change, depleting fossil fuel resources, and increasing energy demand. This study explores the convergence of artificial intelligence (AI), energy sustainability, and wireless electricity generation as a transformative pathway toward a resilient and eco-friendly energy future. Energy sustainability involves developing systems that ensure long-term energy availability while minimizing environmental impacts. Traditional energy infrastructures face limitations in efficiency, accessibility, and scalability. Emerging technologies, particularly AI and wireless power transfer (WPT), offer innovative solutions to these constraints. AI plays a pivotal role in optimizing energy systems by enabling real-time data analysis, predictive maintenance, smart grid management, and demand forecasting. Its application enhances decision-making processes and improves system reliability and efficiency. Simultaneously, wireless electricity generation and transmission technologies—such as resonant inductive coupling, microwave power transmission, and laser-based energy transfer—are redefining how energy is transmitted and accessed. These technologies eliminate the need for physical connections, reduce energy losses, and offer scalable deployment in remote and urban settings. The integration of AI with wireless electricity generation facilitates adaptive control systems, fault detection, and dynamic load balancing, significantly improving system performance and sustainability. Furthermore, these systems can be embedded into renewable energy infrastructures, such as solar and wind farms, allowing for seamless and efficient energy delivery to distributed networks and off-grid communities. This synergy not only reduces carbon emissions but also supports the equitable distribution of clean energy resources. The study also evaluates potential challenges including energy loss during transmission, safety concerns, technological standardization, and regulatory frameworks. However, through interdisciplinary innovation and collaboration, these challenges can be mitigated to realize the full potential of AI-enhanced wireless energy systems. This paper contributes to the growing body of research advocating for sustainable energy transitions, emphasizing the critical role of intelligent, contactless power systems.

In the rapidly evolving landscape of software engineering, the integration of AI into the Software Development Lifecycle (SDLC) heralds a transformative era for developers. Recently, we have assisted to a pivotal shift toward AI-assisted programming, exemplified by tools like GitHub Copilot and OpenAI’s ChatGPT, which have become a crucial element for coding, debugging, and software design. In this article, we provide a comparative analysis between the current state of AI-assisted programming in 2024 and our projections for 2030, by exploring how AI advancements are set to enhance the implementation phase, fundamentally altering developers’ roles from manual coders to orchestrators of AI-driven development ecosystems. We envision HyperAssistant , an augmented AI tool that offers comprehensive support to 2030 developers, addressing current limitations in mental health support, fault detection, code optimization, team interaction, and skill development. We emphasize AI as a complementary force, augmenting developers’ capabilities rather than replacing them, leading to the creation of sophisticated, reliable, and secure software solutions. Our vision seeks to anticipate the evolution of programming practices, challenges, and future directions, shaping a new paradigm where developers and AI collaborate more closely, promising a significant leap in SE efficiency, security, and creativity.