Traditional Statistical Analysis Research Articles

Effects of neighbourhood characteristics on the distribution of vacant houses in Toda city, a satellite city of Tokyo metropolis of japan

As Japan faces a growing crisis of vacant housing, this study investigates the underexplored relationship between vacant house distribution and neighbourhood characteristics in Toda City, a satellite city of the Tokyo metropolis located in Saitama Prefecture. We selected 10 community features, including living convenience, housing supply, and policy support, to explore their influence on vacancy rates. Using a comprehensive dataset primarily derived from the PLATEAU data, we employed a two-step method combining global and local Moran’s I analyses to assess the spatial distribution normality of vacant houses. We then compared traditional statistical data analysis with spatial data analysis through multiscale geographically weighted regression to evaluate their effectiveness and identify the factors most closely associated with vacancy rates. Our findings reveal that spatial data analysis provides superior insights compared to traditional statistical methods. Both approaches consistently indicate a significant positive correlation between the supermarket area ratio and vacancy rates, and a significant negative correlation between road adjacency and vacancy rates. This study demonstrates the feasibility of using spatial data to analyse neighbourhood characteristics in the context of declining vacancy rates in satellite cities. The insights gained offer theoretical support for selecting data and methodologies in future research and policymaking that are aimed at mitigating the growth of vacant houses.

The Mechanism of Tendentious Information Dissemination in Cyberspace

Cyberspace has evolved into a hub for the dissemination of large amounts of tendentious information, posing significant challenges to the role of mainstream value information. As netizens’ are the main recipients of tendentious information, their personal cognition, attitude, and behavioral ability affect their willingness to re-disseminate information, making them an inalienable force in the promotion of information dissemination. Exploring the dissemination mechanism of tendentious information in cyberspace can help to understand the law of information dissemination and predict the trend of information diffusion, which is of great significance to maintaining information security and social stability. However, the existing research has overlooked the potential influence of the attribute characteristics of information in terms of content, and has failed to overcome the methodological constraints of traditional statistical analysis to accurately describe the variables and mechanisms influencing the dissemination of tendentious information at the cognitive level. Therefore, using structural equation modeling, we propose a research index system based on the Theory of Planned Behavior and the characteristics of tendentious information. To this end, confirmatory factor and model fitting analyses were conducted to develop a tendentious information dissemination mechanism model, which we validated through testing and comparative experiments. Path analysis revealed that Attitude Toward Dissemination, Information Dissemination Intention, and Information Dissemination Behavior are the main links in the information dissemination process. Moreover, Information Sentiment Orientation was found to strongly promote the dissemination of tendentious information, while Subject Norm of Dissemination had a minor inhibiting effect.

Application of multiparametric methods of data science for the classification of Russian subjects on the basis of subsidisation

The relevance of the study is justified by the importance of monitoring and forecasting the subsidisation of the Russian regions in order to identify the main criteria for classifying subjects on the basis of subsidisation. In a brief review of the literature, mathematical models used to model the subsidisation of the Russian regions are considered. They have mainly fixed socio-economic indicators that need to be given attention while applying, and also regression models are used, but mathematically sound recommendations for the withdrawal of regions from clusters of subsidisation are not provided. The paper analyses the socio-economic and demographic indicators of the Russian regions applying methods that identify patterns in a multiparametric dataset. The methods of traditional statistical analysis and machine learning, including the author’s ones, are used. Statistically significant patterns have been identified, reflecting the relationship of subsidisation with such indicators as investments in fixed capital, fixed assets, average per capita income and average size of assigned pensions, unemployment rate, etc. The performed logical and statistical analysis strongly supports the use of machine learning (Data Science) methods in identifying statistically significant relationships between various indicators characterising the development of the regions of the Russian Federation.

Hot spots drive uptake and short‐term processing of organic and inorganic carbon and nitrogen in intertidal sediments

AbstractThis study uses dual‐labeled (13C and 15N) stable isotope applications to examine microbial uptake and short‐term processing of carbon (C) and nitrogen (N) from organic and inorganic compounds in subtropical intertidal sediment. Four treatment applications were applied: (1) algal dissolved organic matter (DOM), (2) amino acid mixture, (3) glucose and , and (4) NaHCO3 and to assess bioavailability effects on processing (1 vs. 2) and short‐term processing for OM fixed via microphytobenthos only (pennate diatom dominated) (4) vs. material taken up by the entire microbial community (3) across 24 h. 13C from algal‐DOM was preferentially used by the microbial community vs. 15N. At 24 h more 13C from algal‐DOM remained in microbial biomass indicating use of labeled precursor molecules to form biomass. Conversely, 13C from the amino acid treatment was not incorporated into biomass and was either rapidly respired to DIC or discarded as the in situ microbial community preferentially used and retained 15N from amino acids. Short‐term export of 13C as CO2 from glucose was lower than from microphytobenthos‐C, while retention of 15N from was similar between treatments (3 and 4) despite doubling the application N concentration, suggesting potentially higher glucose‐stimulated 15N export via nitrification–denitrification that was not confirmed via flux measurements in this study. Despite careful site selection for similar tidal exposure and sediment types among the three estuaries, the uptake and processing of labeled substrate varied substantially between replicates and sites which challenged traditional statistical analysis. Disproportionate processing of substrates occurring in sediment hotspots of microbial activity can cause variability spanning orders of magnitude which was found to be widespread through comparison of our results against 19 previous studies in intertidal settings. Development of robust analytical techniques to handle variability from abiotic and biotic factors will allow greater clarity surrounding in situ biogeochemical processing in intertidal environments.

Analysis of Kinematics Graph Interpretation Skills Using RapidMiner

This study explores the application of data mining techniques in physics education research, focusing on the analysis of kinematics graph interpretation skills. The research had two main objectives: to demonstrate the utility of RapidMiner, a data mining tool, in analyzing educational data, and to compare its effectiveness with traditional item analysis methods. Fifty-nine Grade-10 students at Chiang Mai University Demonstration School completed the Test of Understanding Graphs in Kinematics (TUG-K) before and after participating in a problem-based learning module integrating high-speed video analysis. Traditional statistical analysis revealed significant improvement in student performance (p<0.001, effect size 0.76). Association rule mining, conducted using RapidMiner, uncovered key relationships between test items that were not apparent through traditional analysis. These relationships provided insights into common student misconceptions and areas requiring targeted instruction. The study demonstrates the potential of advanced data mining techniques to reveal deeper patterns in educational data compared to conventional item analysis methods. This novel application of RapidMiner in physics education research offers a promising approach for more detailed analysis of student understanding, potentially informing more effective teaching strategies and curriculum design in physics education.

ANALYSIS OF THE RUSSIAN ACCOUNTING LABOR MARKET FROM THE PERSPECTIVE OF THE THEORY OF ENVIRONMENTAL DETERMINISM

The aim of the paper is to show the failure of the institutional environment of the accounting system in Russia. For this purpose, we analyze the accounting labor market, where the existing disproportions are a symptom of the problem. The research is based on the theory of environmental determinism, which requires to consider the accounting system in the context of factors (institutions) that form it. This approach allowed us to identify a number of problems, among which the key ones are the following: the obsolescence of the profession due to the fact that young specialists no longer enter the labor market; entry barriers work inadequately; low wages are one of the reasons for the development of shadow economy in the country, etc. The study is based on the theory of ecological determinism. With the help of traditional statistical analysis and standard techniques of econometric analysis, two samples (on the example of Moscow) characterizing the «supply» (applicants) of accounting workforce and «demand» (vacancies) for it were studied. The analysis showed: 1) for job seekers: key factors (work experience, age, education, availability of certificates) do not explain the amount of wages they claim; 2) for vacancies: the «minimum» amount of wages (the left boundary of the price interval) is primarily influenced by the applicant's education and competencies, while the «maximum» amount of wages (the right boundary of the price interval) is explained to a greater extent by the applicant's competencies, and work experience may not matter. Work experience may indeed be irrelevant, as the labor market is 90% female accountants with more than six years of work experience, thus employers emphasize the competencies of job seekers. The paper confirms that the remuneration of accountants is extremely underpaid across the country, including in relation to the 'business and administration' group. A gender pay gap is also found, but due to the fact that the profession is predominantly represented by women, a conclusion is made about the industry specificity of the analyzed sphere of activity. It is argued that Russia in the foreseeable future will face a similar problem to that of the US in terms of the shortage of accountants. Future research should continue to analyze the institutional environment of the accounting system in Russia from the perspective of other factors (education, attestation, government regulation, etc.), and only as this is done will it be possible to develop a plan to address the existing imbalances.

Discriminating the origin of fish from closely related water bodies by combining NMR spectroscopy with statistical analysis and machine learning

Pikeperch, perch and bream are among the most traded and valued fish species in North-Eastern Europe. Therefore, it is necessary to be able to distinguish fish from different lakes and coastal sea regions to ensure a good traceability of products in the fish market and to protect both consumers and fish stocks. Untargeted metabolomics using nuclear magnetic resonance (NMR) spectroscopy is a suitable tool for this purpose. It is an established method for determining various properties of biological and living systems, such as health, origin, type, etc. Statistical methods including principal component analysis (PCA) and linear discriminant analysis (LDA) are typically applied to NMR data to correlate spectra with a particular research question.Herein we examine fish from three closely related water bodies and demonstrate that reliable determination of the water body that a particular fish originates from by traditional statistical analysis (PCA and LDA) of fish NMR spectra is not possible. In contrast, determining the fish species is possible. We proceed to show that machine learning methods perform better and that a combination of statistical analysis (LDA) and random forest (RF), a supervised machine learning technique, allows reliable determination of the originating water body, while being also tolerant to seasonal variations. This is an improvement over prior work, which has dealt with more clearly distinguished origins of fish. Exceptional accuracy was achieved in correctly assigning fish to their origin even in a scenario where two of the water bodies are connected by a river through which the fish are known to migrate. Since determining the origin of fish is important in environmental protection, we recommend following up this approach and using it as the basis of a robust tool for environmental protection and other monitoring purposes.

Next-generation statistical methodology: Advances health science research

Accurately modeling health science data is crucial for advancing medical research and improving patient outcomes. Traditional statistical analysis methods face significant challenges due to the complexity and diversity of health sciences data. This article introduces a groundbreaking statistical framework designed to overcome these challenges by developing a next-generation family of distributions, with a special focus on the versatility of the Weibull distribution. The data used in this study has been thoroughly authenticated to ensure reliability and validity. Comprehensive Monte Carlo simulations revealed that the Maximum Product of Spacing Estimator is the most effective among seven-point estimation methods, according to standard metrics. Additionally, the study identifies optimal methods for analyzing various types of lifetime data, including the Maximum Product of Spacing Estimator for pharmaceutical efficacy (ED50), the Least Squares Estimator for psychiatric treatment durations, the Cramer-von Mises Estimator for data on 43 leukemia patients and for survival periods of 20 leukemia patients, and the Right Tail Anderson-Darling Estimator for remission times of 128 bladder cancer patients. The adaptability and flexibility of the next-generation Weibull distribution set it apart as the best match among its contemporaries.

Mixing lint grades in relation to fiber and yarn quality of Egyptian cotton

This study was undertaken to investigate the effect of different mixing percentages of lint grades of Egyptian cotton varieties on fiber properties and yarn strength. Two lint grades within each variety of four Egyptian cottons from 2022 and 2023 crop seasons were used; Good to Fully Good (G/FG) and Fully Good Fair (FGF) for Giza 86, Good to Fully Good (G/FG) and Fully Good Fair to Good (FGF/G) for Giza 92, Good to Fully Good (G/FG) and Good Fair (GF) for Giza 94 and, Fully Good (FG) and Fully Good Fair (FGF) for Giza 95 with mixing percentage (30%-40%-50%) of the highest grades for each variety. Mixed lots of lint cotton grades were tested on Fiber Classifying System (FCS) instrument to measure fiber properties. Yarn strength was tested on Good Brand Lea tester at 60s and 3.6 twist factor. This experiment was conducted at Egyptian & International Cotton Classification Center (EICCC) in Cotton Research Institute (CRI), Agricultural Research Center (ARC), Giza, Egypt. Using traditional statistical analysis (normal probability distribution) with untraditional method (assumed probability distribution) illustrated that; It was remarkably increased upper half mean length,mean length, uniformity index, fiber strength, micronaire reading, maturity and linear density with increase of the percentage of the highest grade in the mixing for each studied variety. Meanwhile short fiber content showed the opposite trend, whereas, elongation had no obvious trend. Prominent improvement in yarn strength was observed when the highest lint cotton grade percentage increased from 30% through 40% and 50% in the mixing lots. Yarn strength increased from 2690 to 3170, from 2475 to 2850, from 2440 to 2845 and from 2135 to 2360 for Giza 92, Giza 86, Giza 94 and Giza 95, respectively. Generally, mixing method based on lint grades exhibited significant improvement in fiber and yarn quality properties. In the same time this method is easier than the experimental mixing methods based on micronaire reading or fiber strength. on the other hand, it is very important process in cotton production economy.

Permeability Prediction from Well Log Data Using Artificial Neural Networks: A Case Study of the Hawaz Formation in D-Field, Libya

Permeability is an important parameter in the characterization of any hydrocarbon reservoir. Yet, despite its vital importance, it is one of the most difficult and controversial petrophysical properties to calculate accurately due to nonlinearity and uncertainty in the dataset. Formation permeability is often measured in the laboratory from cores or evaluated from well test data. Core analysis and well test data, however, are only available from a few wells in a field, while the majority of wells are logged. The aim of this paper is to design an artificial neural network (ANN) model to predict formation permeability using a dataset from the Hawaz Formation in the D-field NC-186 concession, East Murzuq Basin, Libya. In this study, a back-propagation neural network (BP-ANN) model was built using the Python programming language. A total of 950 core horizontal permeability measurements and their corresponding well log data were collected from four wells to build the model. Traditional statistical analysis of the porosity/permeability relationship in cored well data yielded no reliable correlations for predicting permeability in uncored wells with R2 less than 15%. A supervised BP-ANN model was trained successfully and was successfully able to predict the permeability of the formations. Despite the presence of high reservoir heterogeneity, the permeability profile predicted by the ANN model using well log data agrees well with core permeability, which clarifies the applicability of this method.

Machine Learning in Electroconvulsive Therapy

Abstract Despite years of research, we are still not able to reliably predict who might benefit from electroconvulsive therapy (ECT) treatment. As we exhaust what is possible using traditional statistical analysis, ECT remains a good candidate for machine learning approaches due to the large data sets with data captured through electroencephalography (EEG) and other objective measures. A systematic review of 6 databases led to the full-text examination of 26 articles using machine learning approaches in examining data predicting response to ECT treatment. The identified articles used a wide variety of data types covering structural and functional imaging data (n = 15), clinical data (n = 5), a combination of clinical and imaging data (n = 2), EEG (n = 3), and social media posts (n = 1). The clinical indications in which response prediction was assessed were depression (n = 21) and psychosis (n = 4). Changes in multiple anatomical regions in the brain were identified as holding a predictive value for response to ECT. These primarily centered on the limbic system and associated networks. Clinical features predicting good response to ECT in depression included shorter duration, lower severity, higher medication dose, psychotic features, low cortisol levels, and positive family history. It has also been possible to predict the likelihood of relapse of readmission with psychosis after ECT treatment, including a better response if higher transfer entropy was calculated from EEG signals. A transdisciplinary approach with an international consortium collecting a wide range of retrospective and prospective data may help to refine and extend these outcomes and translate them into clinical practice.

Hypergraph-Based Multitask Feature Selection with Temporally Constrained Group Sparsity Learning on fMRI

Localizing the brain regions affected by tasks is crucial to understanding the mechanisms of brain function. However, traditional statistical analysis does not accurately identify the brain regions of interest due to factors such as sample size, task design, and statistical effects. Here, we propose a hypergraph-based multitask feature selection framework, referred to as HMTFS, which we apply to a functional magnetic resonance imaging (fMRI) dataset to extract task-related brain regions. HMTFS is characterized by its ability to construct a hypergraph through correlations between subjects, treating each subject as a node to preserve high-order information of time-varying signals. Additionally, it manages feature selection across different time windows in fMRI data as multiple tasks, facilitating time-constrained group sparse learning with a smoothness constraint. We utilize a large fMRI dataset from the Human Connectome Project (HCP) to validate the performance of HMTFS in feature selection. Experimental results demonstrate that brain regions selected by HMTFS can provide higher accuracy for downstream classification tasks compared to other competing feature selection methods and align with findings from previous neuroscience studies.

Application of AI in urolithiasis risk of infection: a scoping review.

Artificial intelligence and machine learning are the new frontier in urology; they can assist the diagnostic work-up and in prognostication bring superior to the existing nomograms. Infectious events and in particular the septic risk, are one of the most common and in some cases life threatening complication in patients with urolithiasis. We performed a scoping review to provide an overview of the current application of AI in prediction the infectious complications in patients affected by urolithiasis. A systematic scoping review of the literature was performed in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analyses for Scoping Reviews (PRISMA-ScR) guidelines by screening Medline, PubMed, and Embase to detect pertinent studies. A total of 467 articles were found, of which nine met the inclusion criteria and were considered. All studies are retrospective and published between 2021 and 2023. Only two studies performed an external validation of the described models. The main event considered is urosepsis in four articles, urinary tract infection in two articles and diagnosis of infection stones in three articles. Different AI models were trained, each of which exploited several types and numbers of variables. All studies reveal good performance. Random forest and artificial neural networks seem to have higher AUC, specificity and sensibility and perform better than the traditional statistical analysis. Further prospective and multi-institutional studies with external validation are needed to better clarify which variables and AI models should be integrated in our clinical practice to predict infectious events.

Pancreatitis with use of new diabetic medications: a real-world data study using the post-marketing FDA adverse event reporting system (FAERS) database.

Background: Pancreatitis is characterized by inflammation of the pancreas and significantly affects quality of life. Less than 5% of pancreatitis cases are drug-induced, but recent evidence suggests a substantial risk associated with glucagon-like peptide-1 receptor agonists (GLP-1 RAs). The aim of this study was to compare the risk of developing pancreatitis between those using GLP-1 RAs and those using sodium-glucose transport protein 2 (SGLT2) inhibitors and dipeptidyl peptidase 4 (DPP-4) inhibitors. Methods: This study was done using the FDA Adverse Event Reporting System (FAERS) database from 2019 to 2021. This database contains information from diverse submissions from healthcare providers, patients, and manufacturers. To ensure fairness and accuracy, the risk of pancreatitis associated with other hypoglycemic agents (SGLT2 inhibitors and DPP-4 inhibitors) was also investigated. Traditional and Bayesian statistical analysis methods were used to identify disproportionate statistics and included the reporting odds ratio (ROR), proportional reporting ratio (PRR), empirical Bayes geometric mean (EBGM), and information component (IC). A drug-adverse-event combination that met the criteria of all four indices was deemed a signal. Results: The analysis of 2,313 pancreatitis reports linked to hypoglycemic agents revealed a predominant association with GLP-1 RA (70.2%) compared to DPP-4 inhibitors (15%) and SGLT2 (14.7%). Most of these reports involved female patients (50.4%), and the highest incidence occurred in those over 50 years old (38.4%). Additionally, 17.7% of the reports were associated with serious events. The ROR was significant for the risk of pancreatitis when using DPP-4 (13.2, 95% confidence interval (CI) 11.84-14.70), while the ROR for GLP-1 was 9.65 (95% CI 9.17-10.16). The EBGM was highest with DPP-4 (12.25), followed by GLP-1 (8.64), while IC was highest with DPP-4 inhibitors (3.61). Liraglutide had the greatest association with pancreatitis among the GLP-1 RAs (ROR: 6.83, 95% CI 6.60-7.07). Conclusion: The findings show that pancreatitis has a strong link with DPP-4 inhibitors and GPL1 agonists, which pose a greater risk. Among the GLP-1 agonist medications, liraglutide has been found to have an association with pancreatitis.

The Impact of Music Therapy in a Pediatric Oncology Setting: An Italian Observational Network Study.

Music Therapy (MT) is a non-pharmacological, art-based intervention that employs music experiences within a therapeutic alliance to attend to clients' physical, emotional, cognitive, and social requirements. This is the first study aiming at investigating the impact of MT on the psychological facets of children suffering from cancer. The study, combining the AQR and m-YPAS assessment tools, evaluated behavioral, sound-musical, and interactive parameters in pediatric oncology patients undergoing MT sessions during hospitalization. Fifty patients admitted to the Paediatric Oncology and Haematology Unit at Policlinico S. Orsola Hospital in Bologna, Italy, were enrolled, irrespective of their treatment regimen. Data collection occurred on the first day of the MT session between 3 p.m. and 5 p.m., with observations conducted by independent observers. In addition to traditional statistical analysis, network analysis was used to explore the combined interactions of all parameters, effectively discerning the distinctive roles played by each one during therapy sessions and their influence on all others. Network analysis highlighted distinct patterns of interactions among parameters during the various sessions, emphasizing the role of positive emotions and a calm setting, the child's ability to take the initiative in sessions, their sense of agency, and the parent's role in guiding them. Significant differences were recorded at each time point between all variables considered. The results of this innovative study may pave the way for future multicenter studies aimed at further exploring the role of MT in children undergoing both curative and palliative treatments for cancer.

A Statistical Evaluation Method Based on Fuzzy Failure Data for Multi-State Equipment Reliability

For complex equipment, it is easy to over-evaluate the impact of failure on production by estimating the reliability level only through failure probability. To remedy this problem, this paper proposes a statistical evaluation method based on fuzzy failure data considering the multi-state characteristics of equipment failures. In this method, the new reliability-evaluation scheme is firstly presented based on the traditional statistical analysis method using the Weibull distribution function. For this scheme, the failure-grade index is defined, and a fuzzy-evaluation method is also proposed by comprehensively considering failure severity, failure maintenance, time, and cost; this is then combined with the time between failures to characterize the failure state. Based on the fuzzy failure data, an improved adaptive-failure small-sample-expansion method is proposed based on the classical bootstrap method and the deviation judgment between distributions of the original and newborn samples. Finally, a novel reliability-evaluation model, related to the failure grade and its membership degree, is established to quantify the reliability level of equipment more realistically. Example cases for three methods of the scheme (the failure-grade fuzzy-evaluation method, the sample-expansion method, and the reliability-evaluation modeling method) are presented, respectively, to validate the effectiveness and significance of the proposed reliability-evaluation technology.

Time Series Analysis and Algorithm for Fluctuation Pattern Recognition and Forecasting of Economic Indicators

This study examines the use of artificial neural network (ANN) algorithms in machine learning for recognizing fluctuation patterns and forecasting economic indicators in the field of political economy. In today's changing global economic scene, economic forecasting is critical for informing policy decisions, directing strategic planning, and managing risks. Traditional statistical approaches and time series analysis have long been used for this purpose, but the advent of ANN algorithms provides a new way to capture the intricate dynamics of economic systems. Using ANNs' intrinsic flexibility and nonlinear modelling capabilities, this study analyzes their ability to effectively forecast future swings in economic indices. This work intends to understand the strengths, limits, and practical consequences of ANN-based forecasting models by conducting a complete assessment of literature, methodological methods, and empirical studies. This study adds to the continuing discussion of economic forecasting approaches by diving into theoretical frameworks, methodological concerns, and empirical data. Finally, incorporating ANN algorithms into machine learning offers promising opportunities for improving the understanding of economic processes and supporting informed decision-making in the political economy.

Genetically modified Wnt signaling data analysed using machine learning

Signaling pathways are vital for the development of organisms, orchestrating a plethora of biological processes. Pathways failing to function properly can cause numerous disorders, including neurodegenerative diseases and malignant tumors. Only a handful of highly conserved signaling pathways are able to specify cell fates during development. Wnt signaling is one of those and it is known to be involved in development, tissue maintenance and homeostasis. Wnt signalling’s importance is underlined by its conserved presence in almost all mammalian organisms. Mis-regulation of Wnt signaling can result in numerous diseases. We used previously published Rna-seq datasets, deriving from gene edited Hek293T cell lines. Those cells lines lack major components of the Wnt signalling pathway. Here, we are combining machine learning together with traditional statistical analysis methods, in order to analyze the RNA-seq data, but also to compare the robustness of machine learning versus traditional statistical analysis methods. In addition, enrichment analysis based both on machine learning and statistical analysis, is been introduced. Finally, we reveal numerous genes, which are potentially linked to diseases for the first time, utilizing our A.I. analysis.

Predictive Modeling and Optimization of Plywood Drying: An Artificial Neural Network Approach

Introduction: This investigation delves into the optimization of the plywood drying process through the development of predictive models for output moisture content (MC_Out) and waviness. It focuses on bridging the gap in current methodologies by employing artificial neural networks (ANNs), optimized with genetic algorithms, to enhance prediction accuracy and process efficiency. Materials and Methods: A comprehensive experimental design was employed, analyzing the effects of three wood types (Doncel, Tamburo, and Zapote), two thickness levels, and three drying speeds on MC_Out and waviness. Data collected were subjected to both traditional statistical analysis and ANNs. The ANNs were fine-tuned through genetic algorithms, exploring different network architectures to achieve optimal predictive performance. Results: Statistical models revealed the significant influence of wood type, thickness, and drying speed on MC_Out and waviness, explaining 95.9% and 84.3% of the variations, respectively. The optimized ANN models, however, demonstrated superior accuracy, with the MC_Out model achieving fitted R-squared values of 0.940 and 0.757 for training and validation sets, respectively, thus outperforming traditional models in predicting drying outcomes. Discussion: The study underscores the effectiveness of ANNs in capturing complex nonlinear relationships within the plywood drying data, which traditional statistical models might not fully elucidate. The successful optimization of ANN architecture via genetic algorithms further highlights the potential of machine learning approaches in industrial applications, offering a more precise and reliable method for predicting drying process outcomes. Conclusion: The integration of artificial neural networks, optimized through genetic algorithms, represents a significant advancement in the predictive modeling of plywood drying processes. This approach not only offers enhanced prediction accuracy for key variables such as MC_Out and waviness but also paves the way for more efficient and controlled drying operations, ultimately contributing to the production of higher-quality plywood.

Explainability in AI-based behavioral malware detection systems

Nowadays, our security and privacy are strongly threatened by malware programs which aim to steal our confidential data and make our systems out of service, among other things. While traditional signature-based malware detection methods or statistical analysis have proven to be ineffective and time-consuming, recently data-driven Artificial Intelligence (AI) techniques, i.e. Machine Learning (ML) and Deep Learning (DL) approaches, have been successfully applied leveraging the behavior of malware in terms of API calls, and achieving promising performances. However, their black-box behavior leads to a lack of explainability thus preventing their application in real world scenarios. In light of this, eXplainable Artificial Intelligence (XAI) methodologies and tools can be effectively embedded within an AI-based malware detection process in order to make more understandable the produced results. In this paper, we propose a XAI framework for behavioral malware detection problems and evaluate the usefulness of four XAI methods (SHAP, LIME, LRP and Attention mechanism) on three datasets with different size, sequence length and number of classes, by which we could evaluate the strengths and weaknesses – from effectiveness and efficiency point of views – of recurrent deep architectures (i.e. Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) models), and their applicability in the modern Cyber Security (CS) scenarios.