Traditional Analysis Research Articles

Semantic transparency modulates the semantic perception of morphemes: Evidence from RSA of BOLD signals

There is no converging evidence on how a word’s semantic transparency affects morphemes’ potential semantic activation. The inconsistent results may be due to the limitation of traditional univariate analyses, in which the semantic transparency was treated as discrete categories. In the current study, Chinese two-character words were used as stimuli and functional magnetic resonance imaging (fMRI) techniques were combined with a priming paradigm. Unlike most previous studies, the multivariate representation similarity analysis (RSA) was used to treat semantic transparency as a continuous variable. The RSA results showed that widespread regions in the frontal-parietal-temporal network represent the semantic perception of characters in all words and transparent words, but no brain areas were identified in opaque words. Unlike RSA results, univariate analyses showed no significant difference between the opaque and transparent words. These results suggest that RSA is more suitable to examine the neural mechanism related to continuous variables such as semantic transparency.

Data Validity Analysis Based on Reinforcement Learning for Mixed Types of Anomalies Coexistence in Intelligent Connected Vehicle (ICV)

Compared with traditional anomaly analysis, intelligent connected vehicle (ICV) data validity analysis is faced with a variety of data anomalies, including sensor anomalies, driving behavior anomalies, malicious tampering, and so on, which eventually leads to anomalies in the data. How to integrate the vehicle moving characteristics, driving style, and traffic flow conditions to provide an effective data detection method has become a new problem in the field of intelligent networked vehicles. Based on ICV data, a particle swarm optimization data validity detection algorithm (TE-PSO-SVM) was proposed by combining driving style and traffic flow theory to realize the effective detection of driving data. In addition, aiming at the problem of mixed types of anomalies in complex scenes, a model pool is constructed, and a model selection algorithm based on reinforcement learning (RLBMS) is proposed. Experiments on the real data set HighD show that RLBMS has a better detection effect in complex scenes of mixed types of anomalies.

Correlation of microstructure and hardness distribution of high-speed train wheels under original and service statuses

High-speed train wheels have complex service environments during wheel–rail contact, and a comprehensive understanding of the microstructural inhomogeneity at the rim is critical for service safety assessment. The local quenching process in the vicinity of the rim will cause a difference in microstructure, directly affecting the service performance of the material. In this study, high-throughput characterization method based on material genome engineering was used, the methods for characterising and identifying the microstructure of wheel steel were developed using high-throughput scanning electron microscopy, and the accuracy and reproducibility of the methods were evaluated. A point-to-point research scheme for microstructure image and hardness data was designed based on the concept of statistical mapping characterization. The area fraction of the proeutectoid ferrite and micro-Vickers hardness distribution in a large size range of the key area of the rim and their internal correlation was obtained, these helped avoid statistical and representativeness limitations of traditional local selection analysis of microstructure and hardness. The results indicates that the area fraction of proeutectoid ferrite and micro-Vickers hardness showed a clear gradient distribution, and opposite distribution trend, with a high negative correlation. In addition, by observing the correlation between microstructure and hardness, and studying the evolution of microstructure, it was found that the microstructure and hardness of the rim near the tread demonstrated a significant synergistic evolution law under the influence of service, this was observed both statistically and microscopically. These findings enhanced the application prospects of the microstructure-performance statistical mapping method, and were beneficial in efficiently evaluating the service life and safety of key components.

Connecting visual metamictization to radiation damage to expand applications of zircon (U-Th)/He thermochronometry

Zircon (U-Th)/He (ZHe) thermochronometry quantifies the timing and tempo of low-temperature processes and is used to deconvolve tectonic and erosional histories. Accumulation and annealing of radiation damage impacts He diffusion in zircon and resulting ZHe dates. Resolving complex histories requires building relationships between ZHe date, effective U (eU), and radiation damage in grains sharing a common thermal history. Prior work demonstrated that purposefully selecting grains with a spectrum of visual metamictization yields a broad range of intrasample eU values (Ault et al., 2018), but it remained unclear if visual metamictization tracks effective radiation damage. Here we evaluate relationships between visual metamictization, effective damage calculated from Raman spectroscopy, and ZHe dates from a new suite of grains from some of the same Precambrian samples investigated in Ault et al. (2018) and Phanerozoic detrital grains from Armstrong et al. (2022). New ZHe analyses (n = 21) confirm increasing visual metamictization corresponds with increasing eU concentration and dates fall along previously reported ZHe date-eU trends for each sample, despite grain selection by different analysts in different sessions. Raman-based alpha dose calculations from multiple spot analyses from transects across the surface and interior of each grain (n = 480 total analyses) range from 3.19 × 1016 to 1.52 × 1019 α/g across the whole dataset. Alpha dose increases in samples characterized by a clear increase in visual metamictization from different types of ZHe date-eU patterns, supporting that visual metamictization reflects effective radiation damage in these samples. Complexities in visual metamictization-damage trends are due to damage zonation observed in cathodoluminescence, comparative internal and external spot analyses, and 2-D Raman maps, as well as limited spread in intrasample visual metamictization and user grain selection bias. Overall, visual metamictization provides a qualitative estimate of effective damage and should be leveraged when selecting grains for traditional ZHe analyses to build ZHe date-eU-damage patterns.

In Search of Conceptual Clarity About the Structure of Psychopathic Traits in Children: A Network-Based Proposal.

Psychopathic traits in childhood have been revealed as potential identifiers of risk, being predictive of later forms of behavioral maladjustment. Yet, it is still under debate how psychopathic traits in children should be best conceptualized and which are the core dimensions for construct definition and prediction. The present study aims to examine the structure of psychopathic traits in childhood, and its predictive value, by using a combination of traditional factor analysis and more recent network-based methods. Data on psychopathic traits, as measured by the Child Problematic Traits Inventory (CPTI), were collected in a large sample of children (n = 2454; 48.2% girls), aged 3 to 6 at the onset of the study (Mage = 4.26; SD = 0.91), who were followed-up one and two years later using parent- and teacher-reports. Results showed that psychopathic traits measured via CPTI are best conceptualized as five latent factors encompassing grandiosity, deceitfulness, callousness, impulsivity and need of stimulation, a result that converged across informants and time. Callousness and grandiosity emerged as central traits using network analysis of parent-reports, while deceitfulness was most central using teacher-reports. Finally, callousness, impulsivity and deceitfulness emerged as the best predictors of concurrent, prospective and stable conduct problems. These results provide a refined structure of psychopathic traits in children that better accounts for the core elements of the construct. Additional theoretical and practical implications will be discussed in terms of assessment, diagnostic classification and tailored prevention/intervention.

Machine Learning Predictive Modeling of Agricultural Sustainability Indicators

<p>Modern-day researchers are provided with data abundance that has its drawback: increased analysis complexity. Approaching this issue through traditional data analysis techniques provides only partial solutions to the complex situation. This research offers analytical and predictive models based on machine‐learning algorithms (linear regression, random forest, and generalized additive model) that can be used to assess and improve the Common Agricultural Policy (CAP) impact over agricultural sustainability in European Union (EU) countries, providing the identification of proper instruments that can be adopted by EU policymakers and CAP Council in financial management of the policy. The chosen methodology elaborates custom‐developed models based on a dataset containing 22 relevant indicators, considering three main dimensions contributing to the EU sustainable agriculture development goals in the CAP context: social, environment, and economic. The results showed that sustainable agriculture parameters influenced by the relevant indicators could be modeled with both linear and non-linear regression approaches by utilization of real-time data using machine learning. The predictive analytic models provide satisfactory performance and could be adopted by researchers and practitioners as policy impact monitoring and controlling tools, not only the EU but also for other countries that have or plan to adopt similar agricultural policies.</p><p><strong>Keywords: </strong>Agricultural policies, common agricultural policy, machine learning, rural development, sustainable agriculture</p>

Estimation of Geotechnical Parameters for Coal Exploration from Quasi-3D Electrical Resistivity Measurements

Geotechnical parameters are crucial for mine planning and operation at different stages of development. However, estimating these parameters requires a large number of boreholes and subsequent detailed analysis of the samples, making it a cumbersome exercise. Moreover, even after conducting these studies, it is not possible to cover the entire operational area. To address this issue, this study presents an indirect method of estimating geotechnical parameters through mathematical relations using resistivity data. The present study incorporated 2D and 3D subsurface imaging techniques for exploring coal reserves and analyzing geotechnical parameters that define subsurface soil properties. Electrical resistivity tomography (ERT) was utilized for data acquisition, employing a Dipole–dipole array with a multielectrode ABEM Terrameter LS instrument. Six parallel profiles were conducted, each 400 m in length, with an inter-electrode spacing of 10 m and a spacing of 50 m between profiles. These profiles were combined into a 3D dataset referred to as quasi-3D ERT. The inversion process for both 2D and 3D data was performed using the Res2dinv and Res3dinv programs, respectively. This study overcame the challenges of 2D resistivity sections by evaluating horizontal depth slices in the x-z plane from layers 1 to 10, reaching a depth of 81.2 m. The geotechnical parameters, including cohesion, friction angle, moisture content, and plastic index, were derived from the resistivity data. The ERT method proved to be cost-effective and efficient in determining soil properties over a large area compared with traditional laboratory analysis of borehole samples. Additionally, the variation of geotechnical parameters with resistivity values exhibited unique characteristics. The results from both the 2D and quasi-3D ERT were well correlated with the borehole data. Such studies are valuable for resource exploration and mine planning purposes.

Artificial nose of scalable plasmonic array gas sensor for Multi-Dimensional SERS recognition of volatile organic compounds

Gas sensing is one kind of promising analytical technique for high-flux screening and evaluation. Volatile organic compounds (VOCs) analysis by surface-enhanced Raman spectroscopy (SERS) is arising but usually focuses on a single species of VOCs due to the limitations of complexity, stability, and accuracy in practical applications. Canine animals have a sensitive sense of smell due to their large number of olfactory cells. Inspired by this, here we innovatively integrate scalable plasmonic arrays and multi-dimensional chemometrics for simultaneous SERS detection of multiple food-borne VOCs. Both direct and indirect SERS strategies are integrated by coating the array surface with MOFs or different monolayers to provide multi-dimensional recognition and readouts. Four species of VOCs including bacterial metabolites, hydrogen sulfide, aldehyde, and biogenic amine were selectively captured and produced unique SERS spectral profiles. The multi-dimensional outputs greatly increase the dimensionality of VOC fingerprints, thereby significantly improving the sensitivity, reliability, and accuracy for freshness discrimination and forecasting in real food smell evaluation. By virtue of multi-dimensional SERS recognition and machine learning, the array gas sensor shows higher accuracy than traditional SERS analysis and is a promising platform for in situ, real-time, and high-flux gas sensing and inspection.

Histopathology image classification: highlighting the gap between manual analysis and AI automation.

The field of histopathological image analysis has evolved significantly with the advent of digital pathology, leading to the development of automated models capable of classifying tissues and structures within diverse pathological images. Artificial intelligence algorithms, such as convolutional neural networks, have shown remarkable capabilities in pathology image analysis tasks, including tumor identification, metastasis detection, and patient prognosis assessment. However, traditional manual analysis methods have generally shown low accuracy in diagnosing colorectal cancer using histopathological images. This study investigates the use of AI in image classification and image analytics using histopathological images using the histogram of oriented gradients method. The study develops an AI-based architecture for image classification using histopathological images, aiming to achieve high performance with less complexity through specific parameters and layers. In this study, we investigate the complicated state of histopathological image classification, explicitly focusing on categorizing nine distinct tissue types. Our research used open-source multi-centered image datasets that included records of 100.000 non-overlapping images from 86 patients for training and 7180 non-overlapping images from 50 patients for testing. The study compares two distinct approaches, training artificial intelligence-based algorithms and manual machine learning models, to automate tissue classification. This research comprises two primary classification tasks: binary classification, distinguishing between normal and tumor tissues, and multi-classification, encompassing nine tissue types, including adipose, background, debris, stroma, lymphocytes, mucus, smooth muscle, normal colon mucosa, and tumor. Our findings show that artificial intelligence-based systems can achieve 0.91 and 0.97 accuracy in binary and multi-class classifications. In comparison, the histogram of directed gradient features and the Random Forest classifier achieved accuracy rates of 0.75 and 0.44 in binary and multi-class classifications, respectively. Our artificial intelligence-based methods are generalizable, allowing them to be integrated into histopathology diagnostics procedures and improve diagnostic accuracy and efficiency. The CNN model outperforms existing machine learning techniques, demonstrating its potential to improve the precision and effectiveness of histopathology image analysis. This research emphasizes the importance of maintaining data consistency and applying normalization methods during the data preparation stage for analysis. It particularly highlights the potential of artificial intelligence to assess histopathological images.

De-risking superhot EGS development through 3D play fairway analysis: Methodology development and application at Newberry Volcano, Oregon, USA

The DErisking Exploration for multiple geothermal Plays in magmatic ENvironments (DEEPEN) project aims to de-risk exploration of geothermal plays in magmatic systems, with a focus on superhot and supercritical geothermal systems. This article presents advancements in geoscientific assessment of superhot enhanced geothermal system (EGS) resources as part of the DEEPEN project, particularly in exploration and identification of these systems. While there exists a general consensus on key components of conventional hydrothermal systems, there has not been a prior consensus on such components for EGS, let alone superhot EGS. The DEEPEN project identified these key components for superhot EGS plays, and used them to modify the traditional geothermal play fairway analysis (PFA) approach to identify favorable areas in superhot EGS plays in 3D. This was done through modeling both favorability and uncertainty separately for each key component of a superhot EGS play, incorporating diverse 3D geoscientific datasets, including geologic features, models produced from direct observations, single inversions, and joint inversions. The PFA is applied to Newberry Volcano as a form of validation. The results appear to validate the methodology, aligning with expectations derived from conceptual modeling, and highlighting the area targeted for EGS stimulation well NWG 55-29 as favorable, and suggesting potential additional areas worthy of exploration at Newberry.

TransHyDE‐Sys: An Integrated Systemic Approach for Analyzing and Supporting the Transformation of Energy Systems and Hydrogen Infrastructure Development

In addition to the long‐term goal of mitigating climate change, the current geopolitical upheavals heighten the urgency to transform Europe's energy system. This involves expanding renewable energies while managing intermittent electricity generation. Hydrogen is a promising solution to balance generation and demand, simultaneously decarbonizing complex applications. To model the energy system's transformation, the project TransHyDE‐Sys, funded by the German Federal Ministry of Education and Research, takes an integrated approach beyond traditional energy system analysis, incorporating a diverse range of more detailed methods and tools. Herein, TransHyDE‐Sys is situated within the recent policy discussion. It addresses the requirements for energy system modeling to gain insights into transforming the European hydrogen and energy infrastructure. It identifies knowledge gaps in the existing literature on hydrogen infrastructure‐oriented energy system modeling and presents the research approach of TransHyDE‐Sys. TransHyDE‐Sys analyzes the development of hydrogen and energy infrastructures from “the system” and “the stakeholder” perspectives. The integrated modeling landscape captures temporal and spatial interactions among hydrogen, electricity, and natural gas infrastructure, providing comprehensive insights for systemic infrastructure planning. This allows a more accurate representation of the energy system's dynamics and aids in decision‐making for achieving sustainable and efficient hydrogen network development integration.

Intelligenza Artificiale per la cura del diabete mellito: opportunità e prospettive future

Diabetes mellitus is globally prevalent, with the International Diabetes Federation predicting 783 million cases by 2045. Type 2 diabetes (T2DM) is the seventh leading cause of death and poses a significant economic burden on global healthcare, demanding innovative approaches amid resource constraints. Moreover, the increasing volume of data requires advanced computational tools for analysis and therapeutic decision support. Digital technologies, particularly artificial intelligence (AI), offer promising solutions. AI, capable of complex tasks like reasoning and language recognition, leverages digitalization in diabetes care, handling electronic health records, imaging diagnostics, and laboratory data. Machine learning, an advanced form of AI, outperforms traditional data analysis by automatically identifying patterns and generating predictions without specific programming. Emerging technologies utilizing natural language processing and machine learning accelerate the digital transformation, enhancing cognitive capabilities. AI applications in diabetes span screening, classification, and therapy management. Predictive models utilizing machine learning algorithms achieve high accuracy in early diabetes risk identification and aids in understanding T2DM heterogeneity, crucial for precision medicine initiatives. Diagnostic AI tools, particularly for retinopathy, neuropathy, and diabetic foot, enhance accessibility and clinical decision-making. AI’s role extends to predicting and preventing complications, such as ulcers and hypoglycemic events. Challenges include data privacy concerns, algorithmic bias, and the need for transparent decision-making processes. Rigorous optimization of AI data inputs is crucial to avoid misleading outputs. While AI offers tremendous benefits, ethical considerations, regulatory frameworks, and human oversight remain critical for responsible and effective implementation in diabetes care.

Trends and Extremes in Time Series Based on Fuzzy Logic

The authors develop the theory of discrete differentiation and, on its basis, solve the problem of detecting trends in records, using the idea of the connection between trends and derivatives in classical analysis but implementing it using fuzzy logic methods. The solution to this problem is carried out by constructing fuzzy measures of the trend and extremum for a recording. The theoretical justification of the regression approach to classical differentiation in the continuous case given in this work provides an answer to the question of what discrete differentiation is, which is used in constructing fuzzy measures of the trend and extremum. The detection of trends using trend and extremum measures is more stable and of higher quality than using traditional data analysis methods, which consist in studying the intervals of constant sign of the derivative for a piecewise smooth approximation of the original record. The approach proposed by the authors, due to its implementation within the framework of fuzzy logic, is largely focused on the researcher analyzing the record and at the same time uses the idea of multiscale. The latter circumstance provides a more complete and in-depth understanding of the process behind the recording.

Fault diagnosis using signal processing and deep learning-based image pattern recognition

Abstract The vibration signal is a typical non-stationary signal, making it challenging to use traditional time-frequency analysis techniques for fault diagnosis. Therefore, this work investigates the processing of vibration signals and proposes a deep learning method based on processed signals for the fault diagnosis of ball bearings. In this work, the fault diagnosis is formulated as an image classification problem and solved with deep learning networks. The intrinsic mode functions (IMFs), converted from the vibration signals in the time domain, are then transformed into symmetrized dot pattern (SDP) images. In order to increase classification accuracy, the SDP parameters in this study are chosen by optimizing image similarity. The feasibility and accuracy of the proposed approach are examined experimentally.

A human factor reliability analysis method for maritime transport based on an improved CREAM model and group decision-making

Maritime transportation has a crucial position in world trade, and maritime transportation accidents can cause large casualties, environmental pollution and economic losses. In order to evaluate human-caused and non-human-caused errors more comprehensively, so as to improve the reliability of maritime transportation, a reliability analysis model for maritime transporters is proposed, which combines quantitative and qualitative analysis, and can be used to analyze maritime transportation accidents retrospectively and predictively. Different from the traditional reliability analysis model, on the one hand, human-caused and non-human-caused events are analyzed by the optimized CREAM and GDM classifications respectively in the quantitative analysis part; on the other hand, the evolutionary process of the events and the logical hierarchical interactions of the sub-events can be analyzed in more detail by constructing the ETA-FTA analysis framework in the qualitative analysis part. In addition, in the optimization of the specific method, more attention is paid to the occurrence scenario and process of the event, so that the analysis results obtained through the model have a higher correlation with the actual data.

Multimodal Sentiment Analysis Method Based on Hierarchical Adaptive Feature Fusion Network

The traditional multi-modal sentiment analysis (MSA) method usually considers the multi-modal characteristics to be equally important and ignores the contribution of different modes to the final MSA result. Therefore, an MSA method based on hierarchical adaptive feature fusion network is proposed. Firstly, RoBERTa, ResViT, and LibROSA are used to extract different modal features and construct a layered adaptive multi-modal fusion network. Then, the multi-modal feature extraction module and cross-modal feature interaction module are combined to realize the interactive fusion of information between modes. Finally, an adaptive gating mechanism is introduced to design a global multi-modal feature interaction module to learn the unique features of different modes. The experimental results on three public data sets show that the proposed method can make full use of multi-modal information, outperform other advanced comparison methods, improve the accuracy and robustness of sentiment analysis, and is expected to achieve better results in the field of sentiment analysis.

Toward Egocentric Compositional Action Anticipation with Adaptive Semantic Debiasing

Predicting the unknown from the first-person perspective is expected as a necessary step toward machine intelligence, which is essential for practical applications including autonomous driving and robotics. As a human-level task, egocentric action anticipation aims at predicting an unknown action seconds before it is performed from the first-person viewpoint. Egocentric actions are usually provided as verb-noun pairs; however, predicting the unknown action may be trapped in insufficient training data for all possible combinations. Therefore, it is crucial for intelligent systems to use limited known verb-noun pairs to predict new combinations of actions that have never appeared, which is known as compositional generalization. In this article, we are the first to explore the egocentric compositional action anticipation problem, which is more in line with real-world settings but neglected by existing studies. Whereas prediction results are prone to suffer from semantic bias considering the distinct difference between training and test distributions, we further introduce a general and flexible adaptive semantic debiasing framework that is compatible with different deep neural networks. To capture and mitigate semantic bias, we can imagine one counterfactual situation where no visual representations have been observed and only semantic patterns of observation are used to predict the next action. Instead of the traditional counterfactual analysis scheme that reduces semantic bias in a mindless way, we devise a novel counterfactual analysis scheme to adaptively amplify or penalize the effect of semantic experience by considering the discrepancy both among categories and among examples. We also demonstrate that the traditional counterfactual analysis scheme is a special case of the devised adaptive counterfactual analysis scheme. We conduct experiments on three large-scale egocentric video datasets. Experimental results verify the superiority and effectiveness of our proposed solution.

Optimal Recovery of Rayleigh‐Wave Overtones by Multi‐Directional Acquisition

AbstractRayleigh waves are ubiquitously used for subsurface characterization through dispersion curve inversion, whose quality depends on the number of useable overtones. Traditional analysis is based on vertical receivers and, for active surveys, sources. However, for layered media, eigenfunction theory shows that optimal recovery of any given dispersion mode and frequency can be achieved by either vertical source‐vertical receiver or radial source‐radial receiver configurations, with source directivity being more dominant. Multi‐directional near‐surface wave‐equation modeling and field examples, including distributed acoustic sensing data, validate these predictions. Statistical analysis of compaction‐type near‐surface models shows that overtones are better recovered for radial‐radial surveys in large portions of the useable spectrum, extending beyond 60% for the second and above modes. We conclude that incorporating radial‐radial data acquisition is beneficial and should become standard procedure in active surveying, as well as analyzing the radial component in ambient noise and earthquake‐induced Rayleigh waves.

Multidimensional subgroup discovery on event logs

Subgroup discovery (SD) aims at finding significant subgroups of a given population of individuals characterized by statistically unusual properties of interest. SD on event logs provides insight into particular behaviors of processes, which may be a valuable complement to the traditional process analysis techniques, especially for low-structured processes. This paper proposes a scalable and efficient method to search significant SD rules on frequent sequences of events, exploiting their multidimensional nature. With this method, it is intended to identify significant subsequences of events where the distribution of values of some target aspect is significantly different than the same distribution for the entire event log. A publicly available real-life event log of a Dutch hospital is used as a running example to demonstrate the applicability of our method. The proposed approach was applied on a real-life case study based on the public transport of a medium size European city (Porto, Portugal), for which the event data consists of 133 million smartcard travel validations from buses, trams and trains. The results include a characterization of mobility flows over multiple aspects, as well as the identification of unexpected behaviors in the flow of commuters (public transport). The generated knowledge provided a useful insight into the behavior of travelers, which can be applied at operational, tactical and strategic business levels, enhancing the current view of the transport services to transport authorities and operators.

Multi-feature fusion sonar image target detection evaluation based on particle swarm optimization algorithm

Traditional sonar image target detection analysis has problems such as long detection time, low detection accuracy and slow detection speed. To solve these problems, this paper will use the multi-feature fusion sonar image target detection algorithm based on the particle swarm optimization algorithm to analyze the sonar image. This algorithm uses the particle swarm algorithm to optimize the combination of multiple feature vectors and realizes the adaptive selection and combination of features, thus improving the accuracy and efficiency of sonar image target detection. The results show that: when other conditions are the same, under the particle group optimization algorithm, the sonar image multiple feature detection algorithm for three sonar image detection time between 4s-9.9s, and the sonar image single feature detection algorithm of three sonar image detection time between 12s-20.9s, shows that the PSO in multiple feature fusion sonar image target detection with better performance and practicability, can be effectively applied to the sonar image target detection field.