Integral Feature Research Articles

Validation of Inter-Reader Agreement/Consistency for Quantification of Ellipsoid Zone Integrity and Sub-RPE Compartmental Features Across Retinal Diseases

Background: An unmet need exists when clinically assessing retinal and layer-based features of retinal diseases. Therefore, quantification of retinal-layer-thicknesses/fluid volumes using deep-learning-augmented platforms to reproduce human-obtained clinical measurements is needed. Methods: In this analysis, 210 spectral-domain optical coherence tomography (SD-OCT) scans (30 without pathology, 60 dry age-related macular degeneration [AMD], 60 wet AMD, and 60 diabetic macular edema [total 23,625 B-scans]) were included. A fully automated segmentation platform segmented four retinal layers for compartmental assessment (internal limiting membrane, ellipsoid zone [EZ], retinal pigment epithelium [RPE], and Bruch’s membrane). Two certified OCT readers independently completed manual segmentation and B-scan level validation of automated segmentation, with segmentation correction when needed (semi-automated). Certified reader metrics were compared to gold standard metrics using intraclass correlation coefficients (ICCs) to assess overall agreement. Across different diseases, several metrics generated from automated segmentations approached or matched human readers performance. Results: Absolute ICCs for retinal mean thickness measurements showed excellent agreement (range 0.980–0.999) across four cohorts. EZ-RPE thickness values and sub-RPE compartment ICCs demonstrated excellent agreement (ranges of 0.953–0.987 and 0.944–0.997, respectively) for full dataset, dry-AMD, and wet-AMD cohorts. Conclusions: Analyses demonstrated high reliability and consistency of segmentation of outer retinal compartmental features using a completely human/manual approach or a semi-automated approach to segmentation. These results support the critical role that measuring features, such as photoreceptor preservation through EZ integrity, in future clinical trials may optimize clinical care.

Estimation of Interferences in Magnetoencephalography (MEG) Brain Data Using Intelligent Methods for BCI-based Neurorehabilitation Applications

<p>Brain-Computer Interface (BCI) neurorehabilitation offers the potential to improve recovery and quality of life for stroke survivors. It aims to restore lost physical and mental abilities through motor and cognitive therapies. Magnetoencephalography (MEG) signals are a major advancement in BCI technology as they provide accurate and consistent assessments of brain activity for control and interaction applications. MEG is indispensable for recording the magnetic fields produced in the brain during motor imagery tasks due to its capability to evaluate cerebral activity with remarkable temporal resolution. However, one of the major challenges associated with MEG recording is the loss of signal quality due to physiological artifacts and ambient noise. Additionally, the head movement of the individual during the recording process can result in the introduction of artifacts into the recorded data, which can distort the spatial mapping of brain activity. This, in turn, can jeopardize the reliability and accuracy of the results obtained. This study aims to identify the most effective technique for removing artifacts from MEG signals by conducting a comparative performance analysis of prominent denoising algorithms, such as Infomax, FastICA, SOBI, and SWT. The findings conclude that Infomax is the most effective algorithm for removing physiological artifacts from a signal while maintaining the integrity and essential features of the original data. FastICA was found to be the second most effective algorithm. Infomax outperformed FastICA in Power Spectral Density (PSD) and Percentage Root mean square error Difference (PRD) measurements.</p>

ONLINE PRACTICE TEST BANK SOLUTION: A WEB-BASED REVIEW PLATFORM FOR LIBRARY AND INFORMATION SCIENCE PRACTITIONERS

Test construction and test administration in most institutions still adopt the traditional pen-and-paper method of examination, which is very tedious (Kotwal et al., 2016). Its lengthy process can limit the time instructors in devoting to their proactive instruction and assessment. The general purpose of the study is to develop an Online Practice Test bank for Library and Information Science Practitioners. To actualize the Online Practice Test bank, the researcher followed the three phases of the modified rapid application model: Planning or Analyze Phase, Design and Development or Prototyping Phase, and Testing. The result of the study revealed that the developed system was able to execute its different operations. Specifically, by providing an avenue to the contributors/review masters and the reviewees to communicate and interact regarding the different reviewers provided. The reviewees can also track their progress through the learning analytics feature of the system. The contributors/review masters can monitor if the review materials they have provided has efficient test items by accessing the test item analysis. The system also has undergone functionality testing through conducting test cases, which have also gained positive remarks. Based on the results of the developed Online Practice Test bank, it is concluded that the system attained its three objectives in having integrated features that would be a great help, especially to the future licensed professional librarians as they will have a platform where they do their review and assess their knowledge on the six core subjects of library science. It is therefore recommended that mobile or android-based user modules must be developed for it to be more accessible to the users. And also an automated intervention or scaffolding for coping with the results from the performance of the review. And it must have an option or platform for contributors outside the institution who want to share their review materials relevant to the Library and Information Science profession.

Multicenter Integration of MR Radiomics, Deep Learning, and Clinical Indicators for Predicting Hepatocellular Carcinoma Recurrence After Thermal Ablation.

To develop and validate an innovative predictive model that integrates multisequence magnetic resonance (MR) radiomics, deep learning features, and clinical indicators to accurately predict the recurrence of hepatocellular carcinoma (HCC) after thermal ablation. This retrospective multicenter cohort study enrolled patients who were diagnosed with HCC and treated via thermal ablation. We extracted radiomic features from multisequence 3T MR images, analyzed these images using a 3D convolutional neural network (3D CNN), and incorporated clinical data into the model. Model performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. The study included 535 patients from three hospitals, comprising 462 males and 43 females. The RDC model, which stands for the Radiomics-Deep Learning-Clinical data model, demonstrated high predictive accuracy, achieving AUCs of 0.794 in the training set, 0.777 in the validation set, and 0.787 in the test set. Statistical analysis confirmed the model's robustness and the significant contribution of the integrated features to its predictive capabilities. The RDC model effectively predicts HCC recurrence after thermal ablation by synergistically combining advanced imaging analysis and clinical parameters. This study highlights the potential of such integrative approaches to enhance prognostic assessments in HCC patients and offers a promising tool for clinical decision-making.

Integration of seasonal frequency domain electromagnetic surveys and geological data for assessing the integrity of earthen levee systems. The case study of the Panaro River (Northern Italy)

Floods rank among the most widespread and destructive natural hazards worldwide. The progressive degradation, impairment, and breach of earthen riverine levees can occur in both natural and anthropogenic environments, stemming from various scenarios or sequences of events. These may include hydraulic failure due to overtopping because of inadequate height, and structural failure occurring even prior to overtopping, due to insufficient geotechnical and hydraulic characteristics combined with external and internal erosion.Following the catastrophic flood of December 2020, caused by the collapse of a section of the levee system of the Panaro River (a tributary of the Po River, Northern Italy), local Authorities initiated a comprehensive investigation into the causes of the breach. Numerous factors, including geological, geomorphological, and ecological features, were found to have contributed to the progressive decrease of the levee integrity prior to and during the flood. This prompted a broader multidisciplinary study of the Panaro River levee system.The study expanded its focus to include the collapsed section (rebuilt in 2020), as well as an additional 30 km stretch of both the right and left levees north of Modena, totaling 60 km. Detailed geological and geophysical data were integrated into the analysis, with particular emphasis on evaluating the characteristics and integrity features of the levee system.This analysis was carried out using Frequency Domain Electromagnetic Methods (FDEM) on the top of the levees, previously calibrated using Electrical Resistivity Tomography (ERT), geological mapping, core logs, and Cone Penetration Tests (CPTs). The FDEM surveys were repeated in different environmental conditions, specifically in the dry 2021 summer season and in the wet 2023 spring season, during heavy rainfalls that caused disastrous floods in several areas of the Emilia-Romagna Region. Out of the 60 km surveyed in the study area, the comparison of the two datasets highlights an interval of about 4 km where the internal portion of the levees is characterized by relatively coarse-grained materials and higher permeability making it more prone to internal erosion phenomena. This paper describes and integrates the results of these investigations, drawing attention to the strengths and limitations of the FDEM method when applied to extensive surveys on earthen riverine levee systems. The proposed methodology contributes as well to maintenance and retrofitting efforts to reduce flood risk in the context of the present climate change scenarios.

A new variational integrator for constrained mechanical system dynamics

A new variational integrator is proposed to solve constrained mechanical systems. The main distinguishing feature of the present integrator comes from the distinct discretization of Lagrangians based on the Hamilton's principle in its most general form. Specifically, Hermite interpolation is used for discrete positions, which provides at least C1 continuity for generalized coordinates. The velocities and momentums are interpolated using quadratic polynomials for the consistency, such that the kinematic relation between velocities and positions can be exactly satisfied. Meanwhile, the Gauss-Legendre quadrature rule is employed to guarantee the accuracy of discrete Lagrange equations. To tackle constrained mechanical systems, a coordinate partition approach is used to eliminate the constraint equations. The local incremental rotation vector is exploited to get rid of rotation singularities in spatial problems. Moreover, an adaptive stepsize strategy is implemented to improve the efficiency. The strengths of the new integrator lie in the accessible large step sizes in the simulation and its global second-order accuracy for positions as well as velocities. Several examples are performed and analyzed to validate its accuracy and capabilities.

An experimental investigation on surface integrity and wire wear in rough and trim cut modes of WEDM for hybrid composite

PurposeThe purpose of this paper is to investigate the surface integrity features, including surface roughness (SR), recast layer (RL), material migration, topography and wire wear pattern in rough and trim-cut wire electric discharge machine (WEDM) of hybrid composite (Al6061-90%/SiC-2.5%/TiB2-7.5%).Design/methodology/approachEffects of four important factors, namely, rough-cut history (RCH), pulse on time (Ton), peak current (IP) and wire offset (WO) have been assessed on the responses of interest for trim-cut WEDM. Box–Behnken design (RSM) was used to formulate the experimentation plan. Quantitative indices of surface integrity, namely, SR and RL, and selected samples have been investigated for qualitative analysis, namely, surface topography, material migration and wire wear pattern.FindingsTon and IP are found to be most significant, whereas RCH and WO are found insignificant for SR. Ton and WO were found to be the most significant factors affecting RL. After trim cut, an RL of thickness 8.26 µm is observed if the initial rough cut has been accomplished at high discharge energy setting. Whereas the best value of RL thickness, i.e. 5.36 µm, can be realized with low level of RCH. A significant decrease in the presence of foreign materials is recorded, indicating its strong correlation with the discharge energy used during machining.Originality/valueInvestigation on surface integrity features for machining of hybrid composite through rough and trim-cut WEDM has been reported by only a limited number of researchers in the past. This study is attempted at fulfilling few vital gaps by addressing the issues such as evaluation of the efficacy of trim cutting under different discharge energy conditions (using RCH), analysis of wire wear pattern in both rough and trim-cut modes and investigation of the wire breakage phenomenon during machining.

The future of UN peace operations: pragmatism, pluralism or statism?

Abstract Although United Nations peace missions have played an important conflict management role for decades, a backlash against the post-Cold War model of ‘liberal peacebuilding’ and other recent developments have called their future into doubt. Some observers contend that a ‘pragmatic turn’ is now underway—a shift away from ambitious plans to transform war-torn societies into liberal democracies and towards more modest and realistic goals. Whether ‘pragmatism’ offers a viable alternative framework for peacebuilding, however, is less clear. This article challenges key assumptions of the pragmatic approach to peacebuilding, including the notion that UN missions can be ‘agnostic’ about the governance arrangements of societies that host these operations, as some proponents of pragmatism recommend. Historical case-studies show that such assumptions are integral features of collective conflict management systems, including UN peace missions. Moreover, a close examination of the pragmatist approach reveals that it, too, is based on such assumptions—namely, that building peace requires the promotion of pluralist societies and states. Pluralist peacebuilding, the article concludes, could offer a compelling foundation for future UN missions in an era of rising statist–authoritarianism, but developing this approach will first require discarding pragmatism's pretence of ideological agnosticism.

Reversing Sovereignty: Deconstructing State ‘Rights’ and ‘Welfare’ in Jacinta Kerketta’s Poetry

In the prefatory remarks to her translation of Mahashweta Devi’s Draupadi, Gayatri Chakravorty Spivak writes that the self-fulfilling premise of knowledge regarding the objects of critical discourse colours Western observations on the Other, although the text of Draupadi is potent enough in showing its blatant inadequacies and thus rendering the character of Dopdi Mejhen as neither completely understandable nor ‘translatable’. Translation, in critical discourse, therefore transcends the literal definition of the term as change of diction or language and encapsulates the idea of discursive readjustment as well. Jacinta Kerketta’s poems highlight the politics of ‘translation’ adopted by the modern welfare state in postcolonial India vis-à-vis the plight of Adivasis. While constitutional guarantees and safeguards constitute the benevolently sovereign nature of the postcolonial state, the complexities involved in the execution of these guarantees render them fallible in co-opting the demands and rights of the Adivasi in the narrative of national progress and other statist goals and objectives. On the other hand, Kerketta’s poems serve to offer a literary resistance to the complaisant presumptions of politico-legal discourse and create unprecedented fissures in concepts that are held to be self-explanatory and integral features of the modern welfare state.

SUPPLEMENTARY OPEN AND DISTANCE EDUCATION FOR IMPRISONED ADULTS

The adoption and implementation of distance education in the prison school context implies new roles for teachers, formal and non-formal learners and educational materials, while enhancing openness as an integral feature of a distance education environment. This study – through a participatory action research – seeks to explore how teachers have applied e-inclusion to enable inclusive online teaching/learning strategies, emphasizing the interaction of digital tool learners and teachers. Needs emerged that helped to clearly show the necessity of face-to-face teaching but also the existence of complementary distance education to prevent the digital divide from increasing the difficulties of students with special educational needs, in relation to the possibilities of distance education in prison schools. The investigation of the educational needs of institutionalised adults from their own perspective was defined as the basis for the creation of appropriate and effective educational material. The novelty of the material lies in the fact that it presents information in a way of active involvement of the trainees in the learning process. In the design of the multimodal educational material, the purpose and expected results were used, so that the trainee could evaluate their progress on their own. Our aim was for learners to be able to improve their knowledge across the whole range of teaching contents by developing cognitive and social skills.<p> </p><p><strong> Article visualizations:</strong></p><p><img src="/-counters-/soc/0717/a.php" alt="Hit counter" /></p>

Deep neural networks integrating genomics and histopathological images for predicting stages and survival time-to-event in colon cancer.

There exists an unexplained diverse variation within the predefined colon cancer stages using only features from either genomics or histopathological whole slide images as prognostic factors. Unraveling this variation will bring about improved staging and treatment outcomes. Hence, motivated by the advancement of Deep Neural Network (DNN) libraries and complementary factors within some genomics datasets, we aggregate atypia patterns in histopathological images with diverse carcinogenic expression from mRNA, miRNA and DNA methylation as an integrative input source into a deep neural network for colon cancer stages classification, and samples stratification into low or high-risk survival groups. The genomics-only and integrated input features return Area Under Curve-Receiver Operating Characteristic curve (AUC-ROC) of 0.97 compared with AUC-ROC of 0.78 obtained when only image features are used for the stage's classification. A further analysis of prediction accuracy using the confusion matrix shows that the integrated features have a weakly improved accuracy of 0.08% more than the accuracy obtained with genomics features. Also, the extracted features were used to split the patients into low or high-risk survival groups. Among the 2,700 fused features, 1,836 (68%) features showed statistically significant survival probability differences in aggregating samples into either low or high between the two risk survival groups. Availability and Implementation: https://github.com/Ogundipe-L/EDCNN.

Stochastic Dynamic Buckling Analysis of Cylindrical Shell Structures Based on Isogeometric Analysis

In this paper, we extend our previous work on the dynamic buckling analysis of isogeometric shell structures to the stochastic situation where an isogeometric deterministic dynamic buckling analysis method is combined with spectral-based stochastic modeling of geometric imperfections. To be specific, a modified Generalized-α time integration scheme combined with a nonlinear isogeometric Kirchhoff–Love shell element is used to simulate the buckling and post-buckling problems of cylindrical shell structures. Additionally, geometric imperfections are constructed based on NURBS surface fitting, which can be naturally incorporated into the isogeometric analysis framework due to its seamless CAD/CAE integration feature. For stochastic analysis, the method of separation is adopted to model the stochastic geometric imperfections of cylindrical shells based on a set of measurements. We tested the accuracy and convergence properties of the proposed method with a cylindrical shell example, where measured geometric imperfections were incorporated. The ABAQUS reference solutions are also presented to demonstrate the superiority of the inherited smooth and high-order continuous properties of the isogeometric approach. For stochastic dynamic buckling analysis, we evaluated the buckling load variability and reliability functions of the cylindrical shell with 500 samples generated based on seven nominally identical shells reported in the geometric imperfection data bank. It is noted that the buckling load variability in the cylindrical shell obtained with static nonlinear analysis is also presented to show the differences between dynamic and static buckling analysis.

Threat in the context of identifying the victim

It is indicated that an important feature of the injured person, which allows to distinguish him from other persons, is related to the infliction of damage. The etymological and semantic analysis of the term «victim» shows that damage is an integral feature of a victim. The article examines the possibility and expediency of recognizing a person as a victim in the criminal law field in the event of a threat to cause harm to him. Provisions of the current Criminal Code of Ukraine, the project of the new Criminal Code of Ukraine, national judicial practice are taken into account. It is argued that in context of the injured person, term damage is understood in two meanings: 1) narrowly (includes only real damage); 2) in a broad sense (includes both damage and the danger/threat of causing it, as well as the threat). At the same time, attributing the threat as an independent action to a type of harm, as suggested by authors of the draft Criminal Code of Ukraine, seems debatable, because in such a case the term «threat» will denote both an action and a consequence. It is also worth paying attention to whether there is a need to use both the term «threat» and the term «danger» in the draft Criminal Code of Ukraine. It has been established that the term «threat» in the context of the definition of the victim means both actual moral or other types of harm to him, as well as the threat/danger of his task. It has been proven that victim in a certain composition of a criminal offense can be characterized not only by harm in its narrow sense, but also by threat or danger of its occurrence, that is, harm in the broad sense, as well as the threat of harm. The threat in the context of the criminal-legal understanding of victim is important, first of all, if there is no implementation. In case of the implementation of a threat, which is provided as an independent crime and is a stage of a single criminal activity, united by a single intention and aimed at causing damage to the same object, qualification under the article providing for responsibility for the threat is not required, and therefore and there is no need to establish the victim of the threat. If a threat is a way of committing an act, then the victim is determined in the context of act in general, taking into account the threat as a way of committing it.

An Enhanced Credit Risk Evaluation by Incorporating Related Party Transaction in Blockchain Firms of China

Related party transactions (RPTs) can serve as channels for the spread of credit risk events among blockchain firms. However, current credit risk-assessment models typically only consider a firm’s individual characteristics, overlooking the impact of related parties in the blockchain. We suggest incorporating RPT network analysis to improve credit risk evaluation. Our approach begins by representing an RPT network using a weighted adjacency matrix. We then apply DANE, a deep network embedding algorithm, to generate condensed vector representations of the firms within the network. These representations are subsequently used as inputs for credit risk-evaluation models to predict the default distance. Following this, we employ SHAP (Shapley Additive Explanations) to analyze how the network information contributes to the prediction. Lastly, this study demonstrates the enhancing effect of using DANE-based integrated features in credit risk assessment.

The Toll of Exclusion on Immigrants’ Health across the Life Course: Research Advances and Future Directions

Health is an integral feature of immigration, providing not only insight into population health but also a critical lens into immigrant integration and the power structure in receiving countries. The goal of this article is to chart the trajectory of scholarship on immigrants’ health, focusing on the formative shift away from dominant individualistic perspectives focused on cultural and behavioral explanations toward a profoundly structural understanding of immigrants’ health. Focusing primarily on the US context, we synthesize theoretical and empirical advances in structural perspectives of immigrants’ health. We anchor these advances in the concept of exclusion, detailing how it undergirds structuralist perspectives of immigrants’ health. We review common ways in which exclusion has been measured in the empirical literature on immigrants’ health and highlight recent evidence linking exposure to exclusion to immigrants’ health outcomes across the life course. We conclude by discussing key directions and challenges for future research.

Enhanced 3D object detection for autonomous driving: A spatial-temporal alignment approach in Bird's Eye View scenarios

This paper presents a novel 3D object detection algorithm designed for Bird's Eye View (BEV) scenarios, which significantly improves detection capabilities by integrating spatial and temporal features. The core of our approach is the spatial-temporal alignment module that efficiently processes information across different time steps and spatial locations, enhancing the precision and robustness of object detection. We employ a temporal self-attention mechanism to capture the motion information of objects over time, allowing the model to correlate features across various time steps for identifying and tracking moving objects. Additionally, a spatial cross-attention mechanism is utilized to focus on spatial features within regions of interest, promoting interactions between features extracted from camera views and BEV queries. Our method also implements temporal feature integration and multi-scale feature fusion to enhance detection stability and accuracy for fast-moving objects and to capture multi-scale context information, respectively. The model employs an enriched feature set post alignment for 3D bounding box prediction, ascertaining the position, dimensions, and orientation of objects. We conducted experiments on two public datasets for autonomous driving nuScenes and Waymo Open Dataset, demonstrating that our method outperforms previous BEVFormer and other state-of-the-art methods in terms of detection accuracy and robustness. The paper concludes with potential future directions for optimizing the BEVFormer model's performance and exploring its application in broader scenarios and tasks.

Diabetes and its Silent Partner: A Critical Review of Hyperinsulinemia and its Complications.

In this complex realm of diabetes, hyperinsulinemia is no longer regarded as just a compensatory response to insulin resistance but rather has evolved into an integral feature. This comprehensive review provides a synthesis of the current literature, including various aspects associated with hyperinsulinemia in diabetic complications. Hyperinsulinemia has been shown to be more than just a compensatory mechanism, and the key findings demonstrate how hyperinsulinism affects the development of cardiovascular events as well as microvascular complications. Additionally, recognizing hyperinsulinemia as a modifiable factor, the diabetes management paradigm shifts towards cognitive ones that consider the use of lifestyle modifications in combination with newer pharmacotherapies and precision medicine approaches. These findings have crucial implications for the clinical work, requiring a careful appreciation of hyperinsulinemia's changing aspects as well as incorporation in personalized treatment protocol. In addition, the review focuses on bigger issues related to public health, showing that prevention and early diagnosis will help reduce the burden of complications. Research implications favor longitudinal studies, biomarker discovery, and the study of emerging treatment modalities; clinical practice should adopt global evaluations, patient education, and precision medicine adaptation. Finally, this critical review provides an overview of the underlying processes of hyperinsulinemia in diabetes and its overall health effects.

Collaborative Learning Platform for Academicians in Libya

Higher education academicians face a variety of difficulties, such as the need for improved collaboration, streamlined communication, and effective resource management. In order to tackle these concerns, this study investigates the unique challenges that academicians in higher education face. The study emphasizes the need for integrated features and user interfaces that are simple to understand and customized for a particular requirement of higher education. Moreover, by exploring the recognition and understanding of these barriers, the study not only clarifies the complex terrain of difficulties but also establishes the foundation for the creation of a platform for collaborative learning. With a focus on the problems faced by academicians, this platform will include features like a forum that is easy to use, the ability to share resources, a powerful search engine, a section devoted to frequently asked questions, and a chatbot that can engage users. Together, these elements seek to offer a thorough resolution to the problems noted, promoting enhanced dialogue, information sharing, and instructional effectiveness among academicians.

Administrative and legal regime of martial law

Currently, Ukraine is under martial law. Historically, it is known that military conflicts of various nature and scale have become an integral feature of the evolution of mankind since ancient times. And therefore, in ancient times, war was a normal, natural state of nations, while peace was an accidental state. Humanity has become more aware of the value of life. However, in the 21st century, Ukraine faced events that, in our time, seemed to be unacceptable, and many citizens have the question of what the martial law regime is, what are its main aspects, taking into account their significant consequences for the normal life of the population. Martial law is a special legal regime introduced on the territory of Ukraine or in some of its localities, which gives the military command, state authorities, military administrations and local self-government bodies certain powers necessary to avert a potential threat, repel armed aggression and ensure national security within countries. The introduction of martial law is associated with the implementation of certain legal procedures provided for by national legislation. The introduction of martial law is carried out by the highest authorities of the state. Law of Ukraine No. 389-VIII «On the Legal Regime of Martial Law» establishes the procedure for introducing martial law in Ukraine. The National Security and Defense Council of Ukraine submits proposals for the introduction of martial law in Ukraine or in some of its localities for consideration by the President of Ukraine. In connection with the introduction of martial law in Ukraine, the constitutional rights and freedoms of a person and a citizen, provided for in Articles 30-34, 38, 39, 41-44, 53 of the Constitution of Ukraine, may be temporarily limited for the period of the legal regime of martial law, as well as to introduce temporary restrictions on the rights and legal interests of legal entities within the limits and to the extent necessary to ensure the possibility of introducing and carrying out measures of the legal regime of martial law, which are provided for by the first part of Article 8 of the Law of Ukraine «On the Legal Regime of Martial Law». Thus, in the event of the introduction of a legal regime of martial law, significant restrictions on the rights of both individuals and legal entities may be applied. However, such restrictions may occur except within the limits of temporary restrictions on the constitutional rights and freedoms of a person and a citizen, as well as the rights and legal interests of legal entities, provided for by the decree of the President of Ukraine on the introduction of martial law. Therefore, in the case of the initiation of the procedure for the introduction of the legal regime of martial law, as it happened in Ukraine, information on the features and main aspects of this regime is relevant and important.

Forecasting ground-level ozone and fine particulate matter concentrations at Craiova city using a meta-hybrid deep learning model

Air quality forecasting is vital for managing and mitigating the adverse effects of air pollution on human health, crops, and the environment. This study aims to forecast daily time series of ozone and fine particulate matter (PM) concentrations using a meta-hybrid deep NARMAX (Nonlinear Auto-Regressive Moving Average with eXogenous inputs) model. Two datasets were utilised: (a) data on meteorological parameters (temperature, air pressure, relative humidity) and air pollutant concentrations (particulate matter, ozone, dioxide of carbon, volatile organic compounds, formaldehyde) provided by a sensor model A3 situated in the centre of Craiova city, and (b) data on wind direction, wind speed, and sunshine duration provided by the National Meteorological Administration. The data sets covered a time interval from December 10, 2020, to January 05, 2024. Initially, a statistical analysis was conducted to assess the correlation between variables. Results revealed that ozone concentration is primarily influenced by meteorological variables such as temperature (r = 0.79), sunshine duration (r = 0.55), and relative humidity (r = −0.48), and secondarily by air pollution indicators including VOC (r = −0.34), PM concentrations (r = −0.34), and CO2 (r = −0.3). In the subsequent stage, thirteen Machine Learning (ML) models were employed in conjunction with an integral feature selection (IFS) method to identify the best combinations of predictor variables for predicting ozone and PMs. Finally, a deep NARMAX model was developed to forecast the next periods of ozone and PMs based on the optimal combinations identified earlier. Results indicated the selection of sixty best models for ozone forecasting and four best models for PMs. The R2 values surpassed 0.97 for ozone and exceeded 0.8 for PMs, demonstrating the efficacy of the forecasting approach.