The increasing global demand for renewable energy, coupled with a strong emphasis on environmental protection and sustainable resource management, has made the assessment of sustainable energy systems (SESs) a critical multi-criteria decision-making (MCDM) challenge. Traditional energy production methods are rapidly depleting natural resources and causing long-term environmental damage, necessitating the exploration of green, cost-effective alternatives. This paper develops a novel interval-valued Fermatean fuzzy sets (IVFFSs)-based MCDM model for assessing SESs. First, this paper presents a new generalized Hellinger-type distance measure (GHDM) to quantify the difference between IVFFSs and discusses its properties. A hybrid weighting system is then designed based on the GHDM and the Analytic Hierarchy Process (AHP) to optimally balance objective data-driven weights with subjective expert judgments. Finally, an enhanced Multi-Attributive Ideal-Real Comparative Analysis (MAIRCA) method under an interval-valued Fermatean fuzzy (IVFF) environment is suggested, where the GHDM is employed to quantify the deviation between alternatives and the ideal solutions. The proposed model effectively handles uncertainty and ambiguity in decision-making by incorporating IVFF setting, and it offers a reliable way for assessing and ranking SESs based on various criteria. A case study demonstrates the applicability and robustness of the proposed model in selecting the best energy system, supporting strategic decision-making for sustainable energy planning.

Dempster-Shafer evidence theory, a powerful tool for managing imperfect information, has been extensively used in various fields of multi-source information fusion. However, how to effectively quantify the difference between evidences and the uncertainty within each evidence remains a challenge. In this paper, we introduce two new symmetric belief alpha-divergences based on belief-plausibility transformation to measure the difference between evidences. These divergences exhibit key properties such as nonnegativity, nondegeneracy and symmetry. We also show that they reduce to well-known divergences like chi 2, Jeffreys, Hellinger, Jensen-Shannon and arithmetic-geometric in specific cases. Additionally, we propose a new belief entropy, derived from the belief-plausibility transformation, to quantify the uncertainty inherent in evidence. Leveraging both the divergences and entropy, we develop a new multi-source information fusion method that assesses the credibility and informational volume of each evidence, providing deeper insights into the importance of each evidence. To demonstrate the effectiveness of our method, we apply it to plant disease detection and fault diagnosis, where it outperforms existing techniques.

The integration of photovoltaic systems to utility grids becomes a durable alternative for power generation in many countries. Given the recent advances in artificial intelligence, the performance in output power maximization can be further improved. This paper presents an intelligent control strategy of a grid-connected photovoltaic (GPV) plant based on an efficient artificial bee colony (ABC) metaheuristic. The motivation behind the use of such a design tool is to formulate and systematically solve the GPV output power maximization issue in comparison to empirical and traditional techniques. Such a competing ABC algorithm efficiently contributes to design cascaded proportional–integral (PI) controllers for the DC-link voltage and grid currents dynamics under rapidly changing conditions of irradiance and temperature. The tuning of PI controllers is formulated as a non-analytical optimization problem subject to the operational constraints of output power generation. An offline tuning approach is performed for all PI controllers operating across the entire modeled GPV system. Performance in terms of reproducibility capabilities, algorithmic convergence, and quality of solutions are compared to the most commonly used state-of-the-art algorithms. Analysis of variance (ANOVA) study based on the Friedman ranking and post hoc Bonferroni–Dunn tests is made and discussed. Demonstrative results in terms of output power maximization, harmonics mitigation, and robustness against irradiance and temperature changes are presented. Compared to traditional methods, the ABC-based tuning presents more advantages in system performance with 94.50% of power efficiency and 1.10% of harmonics mitigation, in addition to a benefit in terms of allocated design time and systematization of the control procedure.

This study proposes an ECG classification system using particle swarm optimization (PSO) for automated deep neural network hyperparameter tuning. PSO optimizes five key parameters: neuron counts in two fully connected layers, dropout rate, learning rate, and optimizer selection. ECG signals undergo wavelet decomposition for feature extraction, with classification performed on the MIT-BIH Arrhythmia Database across five heartbeat classes. The PSO-optimized model achieves superior performance with 99.76% accuracy, 99.34% precision, and 99.21% F1 score, demonstrating PSO's effectiveness in improving model reliability while reducing manual effort.

Detecting rare events, such as fights or falls, in surveillance videos is critical for public safety, but is complicated by data imbalance, occlusions, and complex spatiotemporal dynamics. We present a Hybrid TokenShift-Stochastic Transformer that combines a 3D convolutional backbone with a transformer attention mechanism to address these issues. The token shift module effectively captures the temporal context by shifting feature channels across frames, whereas a stochastic Local Winner-Takes-All (LWTA) layer enhances the sparsity for robust feature selection. The model achieved area under the curve-receiver operating characteristic (AUC-ROC) values of 96.8

Multi-view clustering has become increasingly pervasive and prominent as multiple sources often provide different representations of information. However, existing multi-view clustering algorithms still encounter challenges since most multi-view data do not exhibit clear cluster boundaries, meaning cluster boundaries may locally overlap. Consequently, effectively characterizing and unveiling the imprecise and uncertain cluster structures in multi-view clustering remains an unresolved issue. Inspired by the robust capabilities of neutrosophic clustering in modeling imprecise and uncertain information, this paper introduces two novel multi-view neutrosophic c-means clustering algorithms, which can be regarded as derivatives of NCM in multi-view scenarios. The proposed algorithms are designed to represent the imprecision and uncertainty in cluster assignment of multi-view data while also autonomously discerning the importance of each view to boost clustering performance. We craft two objective functions and develop the corresponding optimization strategies to derive the neutrosophic partition matrix, view weight vector, and cluster centers matrix. Through extensive testing on both synthetic and real-world datasets, we demonstrate the practicality and effectiveness of our proposed algorithms.

Formulating and implementing effective transportation policies is of the utmost importance in the context of increasingly imperative urban climate change issues. Utilizing q-rung orthopair fuzzy rough fairly aggregation operators, this paper presents an innovative method for enhancing decision-making in urban transportation policy development. These operators provide a dynamic multi-attribute decision making (MADM) framework particularly for urban climate and transportation problems that are complex, ambiguous, and comprise multiple criteria. By incorporating “q-rung orthopair fuzzy rough sets” (q-ROFRSs) and fairly operations, this methodology provides a comprehensive and systematic method for evaluating and prioritizing sustainable transportation policies while taking into account the inherent ambiguity and imprecision in urban climate change data. This study makes a significant contribution to the field of urban climate change policy development by providing a novel decision-support instrument that improves the transparency, fairness, and efficacy of decision-making process. The findings highlight the significance of incorporating rough set techniques in addressing the complexities of urban climate change transportation policy development, ultimately leading to more resilient and sustainable urban environments.

The heartbeats classification represents a very important tool in cardiology. Deep learning-based techniques for the analysis of ECG signals aid human experts in the appropriate diagnosis of cardiac diseases. This paper presents a two-dimensional deep learning technique for ECG heartbeats classification based on a convolutional neural network (CNN). We have considered five predominant kinds of ECG beats in MIT-BIH database, which are: Normal (N), Left bundle branch block (L), Right bundle branch block (R), Premature Ventricular Contraction (V), and Atrial Premature Contraction (A). The ECG recordings were first denoised and segmented into individual beats. Continuous wavelet transform was then applied to generate scalogram images from these beats, which were after used as inputs of the CNN neural network. The proposed system exhibits excellent performance, achieving a positive predictivity of 99.73

Gas holdup in an Internal Loop Airlift Contactor (ILAC) is one of the primary hydrodynamic features that governs the performance of the contactor. Prediction of gas holdup assumes importance in the design of airlift contactor. The key challenge in prediction of gas holdup is due to the difficulty in obtaining reliable phenomenological models. The improved prediction accuracies can provide better contactor design and equipment performance. The current work focuses on the use of data driven models for prediction of gas holdup, as the existing empirical correlations were found to be inadequate. In this work, 324 data points from the reported works on internal draft airlift contactor are consolidated. The input part of the examples in the data set consists of ten features which are related to geometry, fluid properties and operating conditions. This study improves the predictive accuracy of gas holdup, the output variable, in ILACs using a Random Forest (RF) model optimized via Genetic Algorithms (GA). SHapley Additive exPlanations (SHAP) based interpretability reveals the contribution of key features. The tuned model achieved a Coefficient of Determination (R²) score of 0.9542 and Mean Absolute Error (MAE) 0.0059, surpassing traditional parameter sets and providing insights into hydrodynamic control.

BACKGROUND:Surgical Robotic Platforms (SRPs) have transformed the way surgeons perform Robot-Assisted Minimally Invasive Surgeries (RMIS). SRPs utilize Computer-Assisted Surgery (CAS) systems to guide surgeons. METHODS:This review paper systematically examines 31 SRPs, analysing their benefits and limitations to provide a comprehensive understanding of their role in RMIS execution. In addition, it proposes the logical classification of SRPs. Furthermore, it presents and validates the hypothesis that the use of SRPs and AI-based CAS enhances clinical outcomes by providing an accurate RMIS execution. Moreover, it proposes a logically structured classification of CAS systems. RESULTS:Classification of evaluation parameters identified for the comparison of SRPs is introduced. An overview of 27 video-guided CAS systems and their comparison is presented. CONCLUSION:In a single place, this paper combines in-depth discussions of three contemporary areas: SRPs, RMIS, and CAS systems. It discusses the identified challenges and extensive future scope of research in three areas.

The identification of abnormal cardiac beats represents the most significant indicators of heart ailments. This paper aimed to find a powerful classification system of ECG arrhythmias based on the conjoint use of the multilayer feed-forward neural network and the particle swarm optimization algorithm. In this work, five predominant categories of of heartbeats from MIT-BIH database are taken as desired output classes and divers kinds of features were computed and employed as inputs of the MLF neural network. First, we have proposed a new particle swarm optimization algorithm (MPSO) to update the weights and bias vectors for optimizing the classification performances. Then, we have added a new stage of features vector reduction based on the PSO algorithm to choose the most relevant features to considered categories of ECG beats for improving classification performances. We have computed a specificity of a 99.76

Multiple Sclerosis (MS) is a chronic neurological disease of the central nervous system, marked by inflammation, demyelination and scarring (sclerosis) in the brain and spinal cord, resulting in a variety of motor, sensory and cognitive symptoms. This article examines recent advances and future prospects in the in-depth exploration of Deep Learning (DL) techniques for segmenting MS lesions. Highlighting recent developments, it explores innovative methods for lesion identification and segmentation, while addressing persistent challenges. This review offers a critical analysis of the current research landscape and suggests promising avenues for the future evolution of these techniques.

The integration of technology and healthcare, particularly through artificial intelligence and deep learning, is revolutionizing precision medicine. Advances in medical imaging using deep learning have proven effective in diagnosing and managing neurodegenerative diseases like Alzheimer's, Parkinson's, and Multiple Sclerosis [1,2,3,4,5]. Deep learning excels in detecting subtle changes in brain structure and function, providing early detection, and significantly influencing patient prognosis and treatment efficacy [6,7,8]. This transformative synergy enhances our understanding of disease progression and marks a crucial advancement in neurodegenerative disease diagnosis and management [9,[10][11][12][13]. This editorial aims to illuminate the remarkable strides made in the field of medical imaging, specifically the contributions of deep learning, in unravelling the complexities of neurodegenerative diseases.

The COVID-19 pandemic profoundly affects elective surgery and healthcare resources. Efficient management of resources, like ward capacity and operating theaters, is crucial. The operations research community explores solutions, notably leveraging artificial intelligence, to address scheduling challenges amid COVID-19 restrictions. In this situation, applying AI becomes essential to getting the best results. In this paper, we address the problem of daily scheduling elective surgeries while accounting for hospital ward capacity. It is possible to reduce this issue to a scheduling puzzle that, given a variety of restrictions, resembles a four-stage hybrid flow shop. These limitations include the availability of resources, patient flow control, wait time avoidance, patient prioritizing, and resource coordination. With the crucial aid of artificial intelligence, our main goal is to assign patients to different surgical resources to minimize the length of time they spend on average in the hospital ward. We suggest putting into practice effective optimization strategies that make use of AI-based algorithms, particularly the variable neighborhood search (VNS) and variable neighborhood descent (VND) algorithms, which are inextricably linked with artificial intelligence concepts. Our studies demonstrate the effectiveness and efficiency of the general VNS in addressing the daily elective surgical scheduling issue (SSP) with the priceless assistance of artificial intelligence. The experiments are based on novel data instances that were inspired by current literature guidelines. The test results conclusively demonstrate the ability of our algorithms to find virtually perfect solutions. Moreover, our results highlight that the use of these methods, strengthened by AI, can significantly increase the size of the solved issue by a remarkable factor of 19.54. In light of the current COVID-19 pandemic, AI thus becomes a key factor in optimizing the scheduling of elective surgeries and the allocation of resources.

Anomaly detection in time series data is a critical challenge across various domains. Traditional methods typically focus on identifying anomalies in immediate subsequent steps, often underestimating the significance of temporal dynamics such as delay time and horizons of anomalies, which generally require extensive post-analysis. This paper introduces a novel approach for time series anomaly prediction, incorporating temporal in-formation directly into the prediction results. We propose a new dataset specifically designed to evaluate this approach and conduct comprehensive experiments using several state-of-the-art methods. Our results demonstrate the efficacy of our approach in providing timely and accurate anomaly predictions, setting a new benchmark for future research in this field.

Training deep models for time series forecasting is a critical task with an inherent challenge of time complexity. While current methods generally ensure linear time complexity, our observations on temporal redundancy show that high-level features are learned 98.44% slower than low-level features. To address this issue, we introduce a new exponentially weighted stochastic gradient descent algorithm designed to achieve constant time complexity in deep learning models. We prove that the theoretical complexity of this learning method is constant. Evaluation of this method on Kernel U-Net (K-U-Net) on synthetic datasets shows a significant reduction in complexity while improving the accuracy of the test set.

Purpose: Multiple Sclerosis (MS) is a chronic disease of the Central Nervous System (CNS), characterized by the presence of disseminated lesions in the brain and Spinal Cord (SC). Magnetic Resonance Imaging (MRI) has become an essential tool for studying the anatomy and functions of the CNS in vivo, enabling not only the identification of brain structures but also the detection of damaged tissue in various neurodegenerative diseases, including MS. The segmentation of lesions on MR images is a crucial step in the diagnosis and monitoring of the disease. However, manual segmentation of MS lesions is a complex and time-consuming task requiring considerable expertise. Methods: This paper proposes a fully automated method for MS lesion segmentation based on a Convolutional Neural Network (CNN) architecture. The model was trained on datasets from the MICCAI 2016 and ISBI 2015 international challenges. FLAIR images from these databases were used as input to the CNN. Results: The results show a significant improvement in the accuracy and robustness of the model, resulting in high-quality segmentation of MS lesions. The model achieved remarkable performance, with a Dice Similarity Coefficient (DSC) of over 89%, outperforming recent methods. Conclusion: These promising results underline the considerable potential for future advances in the automated segmentation of MS lesions.

The logistics market stands to benefit from the accessibility and increased use of new technologies. As technology continues to advance, drones have emerged as a notable innovation. Within the logistics field, there is growing interest in leveraging drones, particularly for handling small and medium-sized orders such as mobile phones. The appeal of drones lies in their economic and environmental advantages, attributed to their reduced energy consumption. These unmanned aerial vehicles are considered a valuable component of the ongoing technological revolution in transportation, with the potential to enhance the efficiency of last-mile deliveries. To explore their applicability, mixed vehicle-drone distribution models have surfaced as a promising alternative to traditional delivery methods. These models enable companies to minimize transportation costs by leveraging the strengths of both vehicles and drones. In this study, we present a solution to the vehicle routing model with multiple drones (VRPm-D). Our objective is to efficiently transport a specified quantity of products from a central depot to customers by devising optimal routes for both trucks and drones. The study focuses on employing a VRPm-D model to facilitate the transportation process, involving a predetermined fleet of vehicles and drones. The vehicles start and end their routes at a central depot. The primary goal is to minimize the time taken by trucks utilizing drones to cater to the needs of every customer effectively while considering the payload capacity and energy endurance constraints of the drones. To address these objectives, we propose a hybrid vehicle-drone routing problem formulated using the genetic clustering algorithm (HVDRP-GCA). This approach aims to optimize the routes and schedules for both vehicles and drones, taking into account the aforementioned constraints. Our results demonstrate that the processing time exponentially increases as the number of customers grows, particularly noticeable in routes with five or more customers. Importantly, the HVDRP-GCA model outperforms existing methods in the literature, providing favorable outcomes. The results highlight the dominance of our proposed model compared to previous approaches found in the literature.