Complex Variables Research Articles

Review of Biomass Gasification and Pyrolysis Process Based on Long Short-Term Memory Network

Abstract. With the global energy crisis become escalated day by day, finding an effective way of exploring the renewable energy has become an important direction as its widely resources, comparatively low environment impact. This paper has concluded the biomass pyrolysis and gasification process based on long- and short-term memory (LSTM) method, including the LSTM principle, current application, faced challenges and future development. LSTM as a kind of special recurrent neural network, which could effectively solve the gradient vanish and explosion problem in time-series data. Research shows that, LSTM has an excellent performance in terms of reaction condition and optimization, which could be able to capture the relationship between complex variables, the pyrolysis efficiency could be improved, and prediction accuracy could over 90%. During the data preprocessing and model training stage, it is vital to make sure the quality of data, including data normalisation, outlier handling and time series splitting, etc. Through these steps, a better prediction accuracy could be achieved by LSTM. At the same time, the real application cases of LSTM used in biomass pyrolysis process have been discussed, it is shown that the combination of LSTM and other machine learning techniques could obviously improve the system stability and product quality. In addition, this paper has also looked forward to the enhancement of model explainability and the prospect of uncertainty quantification, which is helpful to improve the LSTM application and practical value.

Rapid and Specific Detection of Bacillus cereus Using Phage Protein-Based Lateral Flow Assays.

Rapid and precise diagnostic techniques are essential for identifying foodborne pathogens, including Bacillus cereus (B. cereus), which poses significant challenges to food safety. Traditional detection methods are limited by long incubation times and high costs. In this context, gold nanoparticle (AuNP)-based lateral flow assays (LFAs) are emerging as valuable tools for rapid screening. However, the use of antibodies in LFAs faces challenges, including complex production processes, ethical concerns, or variability. Here, we address these challenges by proposing an innovative approach using bacteriophage-derived proteins for pathogen detection on LFAs. We used the engineered endolysin cell-wall-binding domain (CBD) and distal tail proteins (Dit) from bacteriophages that specifically target B. cereus. The protein-binding properties, essential for the formation of efficient capture and detection biointerfaces in LFAs, were extensively characterized from the microstructural to the LFA device level. Machine-learning models leverage knowledge of the protein sequence to predict advantageous protein orientations on the nitrocellulose membrane and AuNPs. The study of the biointerface binding quantified the degree of attachment of AuNPs to bacteria, providing, for the first time, a microscopic model of the number of AuNPs binding to bacteria. It highlighted the binding of up to one hundred 40 nm AuNPs per bacterium in conditions mimicking LFAs. Eventually, phage proteins were demonstrated as efficient bioreceptors in a straightforward LFA prototype combining the two proteins, providing a rapid colorimetric response within 15 min upon the detection of 105 B. cereus cells. Recombinantly produced phage binding proteins present an opportunity to generate a customizable library of proteins with precise binding capabilities, offering a cost-effective and ethical alternative to antibodies. This study enhances our understanding of phage protein biointerfaces, laying the groundwork for their utilization as efficient bioreceptors in LFAs and rapid point-of-care diagnostic assays, thus potentially strengthening public health measures.

Functional traits mediate the elevational patterns of functional diversity and community structure of mosses in a tropical mountain area

Functional diversity refers to the value, range, and distribution of functional traits within a community, such as the morphological, physiological and behavioral characteristics of species that determine the role a species plays in an ecosystem. Assessing the drivers of elevational pattern of functional diversity is crucial to predict the effects of global change on functional diversity and community structure. In our research, we collected mosses species data from 65 sampling sites and measured 11 functional traits that are related to their ecological functions. We applied double canonical correspondence analysis (DCCA) to analyze species responses to environmental conditions based on their traits. We applied generalized additive models with a Gaussian function of variance to determine the elevational patterns of functional trait composition, diversity and community structure. We applied and compared boosted regression trees (BRT) without considering functional traits and piecewise structural equation modelling (SEM) mediated with functional traits to relate environmental variables with functional diversity and functional community structure, respectively. We found the first DCCA axis accounted for the largest dissimilarities between the two groups of species and correlated mainly with the water-utilization traits. Although both functional diversity and community structure displayed negatively skewed pattern along the elevational gradient, habitat complexity and climatic variables contributed differently to their respective patterns. The SEM approach consistently outperformed the BRT approach in explaining the variations in both functional diversity and community structure. Our findings highlight the important role of functional traits in mediating the relationship between the environment and functional diversity metrics. Both biotic and abiotic processes play a significant role in shaping the community assemblages, with environmental variables having distinct impacts. Traits related to structure maintenance, water absorption, cell hydration, and nutrient acquisition were found to be key drivers of functional diversity, while water-utilization traits were mainly responsible for regulating functional community structure.

Assessing the Impact of Environmental Conditions on Reflectance Values in Inland Waters Using Multispectral UAS Imagery

This study investigates the impact of environmental conditions on reflectance values obtained from multispectral Unmanned Aerial System (UAS) imagery in inland waters, focusing on sun glint, cloud glint, wind-generated waves, and cloud shading projections. Conducted in two reservoirs with differing water qualities, UAS platforms equipped with MicaSense Altum and DJI Phantom 4 Multispectral sensors were used to collect multispectral images. The results show that sun glint significantly increases reflectance variability as solar elevation rises, particularly beyond 54°, compromising data quality. Optimal flight operations should occur within a solar elevation angle range of 25° to 47° to minimize these effects. Cloud shading introduces complex variability, reducing median reflectance. Wind-generated waves enhance sun glint, increasing variability across all spectral bands, while cloud glints amplify reflectance non-uniformly, leading to inconsistent data variability. These findings underscore the need for precise correction techniques and strategic UAS deployment to mitigate environmental interferences. This study offers valuable insights for improving UAS-based monitoring and guiding future research in diverse aquatic environments.

Complex stochastic optimal control foundation of quantum mechanics

Abstract Recent studies have extended the use of the stochastic Hamilton-Jacobi-Bellman (HJB) equation to include complex variables for deriving quantum mechanical equations. However, these studies often assume that it is valid to apply the HJB equation directly to complex numbers, an approach that overlooks the fundamental problem of comparing complex numbers when finding optimal controls. This paper explores the application of the HJB equation in the context of complex variables. It provides an in-depth investigation of the stochastic movement of quantum particles within the framework of stochastic optimal control theory. We obtain the complex diffusion coefficient in the stochastic equation of motion using the Cauchy-Riemann theorem, considering that the particle’s stochastic movement is described by two perfectly correlated real and imaginary stochastic processes. During the development of the covariant form of the HJB equation, we demonstrate that if the temporal stochastic increments of the two processes are perfectly correlated, then the spatial stochastic increments must be perfectly anti-correlated, and vice versa. The diffusion coefficient we derive has a form that enables the linearization of the HJB equation. The method for linearizing the HJB equation, along with the subsequent derivation of the Dirac equation, was developed in our previous work [V. Yordanov, Scientific Reports 14, 6507 (2024)]. These insights deepen our understanding of quantum dynamics and enhance the application of stochastic optimal control theory to quantum mechanics.

Hybrid Feature Extraction for Breast Cancer Classification Using the Ensemble Residual VGG16 Deep Learning Model

Introduction: Breast Cancer (BC) is a significant cause of high mortality amongst women globally and probably will remain a disease posing challenges about its detectability. Advancements in medical imaging technology have improved the accuracy and efficiency of breast cancer classification. However, tumor features' complexity and imaging data variability still pose challenges. Method: This study proposes the Ensemble Residual-VGG-16 model as a novel combination of the Deep Residual Network (DRN) and VGG-16 architecture. This model is purposely engineered with maximal precision for the task of breast cancer diagnosis based on mammography images. We assessed its performance by accuracy, recall, precision, and the F1-Score. All these metrics indicated the high performance of this Residual-VGG-16 model. The diagnostic residual-VGG16 performed exceptionally well with an accuracy of 99.6%, precision of 99.4%, recall of 99.7%, F1 score of 98.6%, and Mean Intersection over Union (MIoU) of 99.8% with MIAS datasets. Result: Similarly, the INBreast dataset achieved an accuracy of 93.8%, a precision of 94.2%, a recall of 94.5%, and an F1-score of 93.4% Conclusion: The proposed model is a significant advancement in breast cancer diagnosis, with high accuracy and potential as an automated grading.

ADVANCED PREDICTIVE MODELING FOR THE BIOFIRE FILMARRAY SYSTEM IN INFECTIOUS DISEASE DIAGNOSTICS

The Bio Fire Film Array System has emerged as a powerful tool in clinical diagnostics, offering rapid and multiplexed detection of infectious pathogens. This study presents the development of a comprehensive mathematical model aimed at predicting the accuracy and sensitivity of the BioFire FilmArray System under diverse conditions. Key factors such as sample type, pathogen load, specimen characteristics, and environmental variables were systematically analyzed to elucidate their impact on the system's performance. The model incorporates a range of parameters including sample volume, specimen complexity, microbial diversity, and system-specific variables to generate probabilistic estimates of diagnostic outcomes. By leveraging large datasets encompassing diverse clinical scenarios and pathogen profiles, the model achieves robustness and generalizability, thereby facilitating its applicability across different healthcare settings and populations. Validation of the model against independent datasets demonstrates its efficacy in accurately predicting the performance of the BioFire FilmArray System across a spectrum of conditions. Overall, this mathematical model represents a significant advancement in optimizing the utility of the BioFire FilmArray System for infectious disease diagnosis. Its integration into clinical practice holds promise for improving patient care, guiding sample processing protocols, and informing decision-making processes in infectious disease management.

AnimeSketchNet: Integrating traditional sketching and anime art via an innovative dataset

Abstract. Recent advancements in text-to-image synthesis have shown promise, yet many models struggle with generalizability and adaptability, particularly in specialized genres like anime sketches. To overcome these challenges, we introduce AnimeSketchNet, a novel framework designed to enhance model performance by effectively capturing the complexity and stylistic variability unique to anime. AnimeSketchNet leverages a diverse collection of anime sketch styles with varying levels of detail, enabling the model to learn and adapt to the distinct artistic style of anime. Our dual-branch architecture, featuring a decoupled attention mechanism, seamlessly assimilates textual descriptions along with visual features, producing high-quality anime sketch that are both detailed and faithful the reference sketch. Experimental results demonstrate that AnimeSketchNet surpasses existing state-of-the-art models in both qualitative and quantitative evaluations. This work significantly advances text-to-image synthesis by offering a powerful and flexible tool tailored specifically to the unique demands of anime art.

Harnessing Ascidians as Model Organisms for Environmental Risk Assessment

Environmental Risk Assessment (ERA) often relies on a restricted set of species as bio-indicators, introducing uncertainty when modeling complex environmental variables. This may lead to oversimplified or erroneous risk assessments. Ascidians, marine filter-feeding sessile chordates, are valuable models for scientific research in various biological fields such as stem cell biology, embryogenesis, regeneration, innate immunity, and developmental biology. Their global distribution, sensitivity to pollutants, high abundance, mass sexual reproduction, and habitation in coastal areas impacted by anthropogenic pollution make them excellent indicators for monitoring marine pollution and global environmental changes, including biological invasions and species diversity diminution cases. Despite their potential as environmental bioindicators, ascidians remain underutilized in ERAs (≤0.13% of ERA studies), particularly in the field of chemical pollution impact assessment, primarily due to a lack of standardization. This underrepresentation poses a challenge for accurate modeling, especially in models relying on a broad range of species (e.g., Species Sensitivity Distributions). Given these constraints, expanding the use of ascidians in ERAs could improve the comprehension and precision of environmental changes and their assessments. This underscores the necessity for future research to establish standardized testing protocols and choose the most suitable ascidian species for inclusion in ERAs.

A self-organizing map clustering adaptive artificial neural network model for analysis critical success factors in different phases of MTO projects case study: electrical equipment manufacturer and supplier in Iran

PurposeThe purpose of this paper is to investigate the benefit of critical success factors (CSFs) clustering in different phases of make-to-order (MTO) projects and develop standards for management.Design/methodology/approachThis study is based on a questionnaire survey. First of all, collecting data by structured interviews, relying on a questionnaire and second from leader contractors who are active in the engineering and steel industry (in Iran). So, the requirements and objective of the research are presented to the top management of MTO projects to gain their support in data collection. Then 20 CSFs were identified by the literature review so a questionnaire survey was prepared for the CSFs assessment and interview with the experts. Finally analyzing the importance and performance of CSFs in project phases and cluster them in different project phases with self-organizing map as one of the artificial neural network (ANN) approaches due to high predictive accuracy. Review the research result with the top management of MTO project and examine the results obtained from neural networks and validation indices.FindingsCluster analysis shows that the implementation phase is the most important stage in MTO organizations and the other phases like feasibility and start-up, design and planning, delivery and end-phase should be also considered as effective phases in determining the level of organization performance. Different industries with additional data at different periodic times will verify the result. Furthermore, testing the other ANN model will improve risk analysis and could shift this classification approach to a regression type.Research limitations/implicationsThe main limitation of the research is related to the sample. Research findings are limited to the time of data collection so validity is limited to the mentioned time. Different industries with additional data will verify the result. Furthermore, testing different ANN models such as K-MEANS, non-negative matrix factorization (NMF) analyses will improve risk analysis and could meet different classification results to find gaps.Practical implicationsIn this paper, CSF and project phase dimensions are viewed together which is necessary to meet better results for simplifying social and economic benefits. Merge the new findings and latest technologies could prepare the best results and enable managers to create a better framework or implement key factors for minimizing waste.Originality/valueThis paper moves the definition of MTO organizations beyond measuring cost, complexity and financial variables by clustering CSFs in different phases of projects. So, the results enable managers to use this concept in their daily production to minimize waste and could be implemented to efficiently choose factors.

GAMBUT field measurement of emissions from a tropical peatland fire experiment: from ignition to spread to suppression

Background Accurate quantification of emissions from peatland wildfire is crucial for understanding their feedback to the atmospheric and Earth system. However, current knowledge on this topic is limited to a few laboratory and field studies, which report substantial variability in terms of the fire emission factors (EFs). Aims We aim to understand how emissions vary across the life cycle of a peatland fire. Methods In August/September 2018, we conducted the largest and longest to-date field-scale experimental burn on a tropical peatland in Sumatra, Indonesia. Field measurements of gas emissions from the fire experiment were conducted using an open-path Fourier transform infrared spectroscopy to retrieve mole fractions of 11 gas species. Key results For the first time, we calculated and reported EFs from 40 measurement sessions conducted over 2 weeks of burning, encompassing different fire stages (e.g. ignition, smouldering spread, and suppression) and weather events (e.g. rainfall). Our findings provide field evidence to indicate that EFs vary significantly among fire stages and weather events. We also observed that the heterogeneous physicochemical properties of peatland site (e.g. moisture content) influenced the EFs. We also found that modified combustion efficiency was highly sensitive to complex field variables and could introduce large uncertainties when determining the regimes of a peat fire. Conclusions and implications Further studies to investigate peat fire emissions are needed, and more comprehensive mapping of peatland heterogeneity and land use for emissions inventories, accounting for spatial and temporal variability in EFs since the initiation of a fire event is required.

Swirling Flow Quantification in Helical Stents Using Ultrasound Velocimetry.

Helical stents have been developed to treat peripheral arterial disease (PAD) in the superficial femoral artery (SFA), with the premise that their particular geometry could promote swirling flow in the blood. The aim of this work is to provide evidence on the existence of this swirling flow by quantifying its signatures. This study consists of in vitro and in vivo parts. For the in vitro part, 3 helical stent models of different helicity degrees and 1 straight model were fabricated, and the flow was assessed at the inlet and outlet of each model. For the in vivo part, only 1 patient, treated with the helical stent, was eligible to participate in the study. The stent implanted in the SFA of the patient was evaluated in 2 leg postures (straight and flexed), and flow was assessed in 12 locations along the SFA. The in vivo study was approved by an ethical board (NL80130.091.21) in the Netherlands. High-frame-rate ultrasound was used to acquire data from the regions of interest (ROIs), using microbubbles as contrast agents. After processing the data via a correlation-based algorithm (echo particle image velocimetry or echoPIV), the velocity vector field within each ROI was extracted and analyzed for parameters such as vector complexity and velocity profile skewedness. The results show that in the outlet of the helical stents, when compared with the inlet, the flow vector field is more complex and the velocity profile is more skewed. For the in vivo case, the outcomes demonstrate more complexity and higher variability in the sign of skewedness inside the stent when compared with the flow in the proximal to the stent. Helical stents make the vector field of the flow more complex and the velocity profile more skewed, both of which are signatures of swirling flow. Further studies are needed to evaluate whether these features can benefit patients in terms of patency rates. This study demonstrates that helical stent models alter the blood flow when compared with straight stent models. Particularly, the flow grows more complex and its velocity profile becomes more skewed, both of which hint at the existence of swirling flow inside the helical stent. These observations, alongside with population-based studies that are currently being carriet out, may provide the evidence that helical stents have some advantages over straight stents for the patients.

Complex potentials solutions for isotropic Cosserat bodies with voids

This paper aims to obtain solutions in terms of the complex potential structure for the plain strain problem of an elastic micropolar and isotropic body with pores. The constitutive equations on which the method is applied and is useful are the well-known equations of the elasticity theory for the above-mentioned body. We intend to solve the Kirch problem using the procedure of complex variables.

Jane Jacobs's urban vitality focusing on three-facet criteria and its confluence with urban physical complexity

Urban vitality is crucial for sustainability, contributing to social cohesion, information exchange, and overall quality of life. Understanding and quantifying urban vitality is essential for effective planning and policymaking, yet it remains a complex task. Previous studies have primarily focused on single-dimensional measures of urban vitality, overlooking the multifaceted nature emphasized by Jane Jacobs, including spatiotemporal dimensions. This study revisits Jacobs's urban vitality, focusing on three key indicators of intensity, diversity, and consistency of urban vitality. Additionally, we explore the relationships between urban complexity and urban vitality. We employ variety, uniformity, and connectivity metrics to assess urban complexity, which examines the physical structures of buildings, streets, and blocks. Linear regression and Maximal Information-based Nonparametric Exploration statistics for non-linearity analysis are used to determine the associations between urban complexity and urban vitality. Our findings reveal nuanced details of the relationships. Notably, variety and connectivity variables have more significant influences on urban vitality than those related to uniformity. Furthermore, the analysis highlights the differential impacts of complexity variables on different types of vitality. These insights provide valuable guidance for planners and policymakers, facilitating the design of sustainable and vibrant cities by considering optimal complexity measures of built environment that enhance urban vitality.

Is there dietary macronutrient malabsorption in children with environmental enteropathy?

Assessing the digestive and absorptive capacity of the gastro-intestinal tract (GIT) using minimally- or non-invasive methods, particularly in children, has been difficult owing to the complex physiology and variability in functional measurements. However, measuring GIT function is increasingly important with the emerging relevance of childhood environmental enteropathy (EE) as a mediating factor in linear growth faltering, severe acute malnutrition, poor oral vaccine uptake and impaired cognition. In EE, sub-optimal nutrient digestion and absorption (malabsorption) forms the critical link to the conditions mentioned above. The present narrative review discusses probable mechanisms that can cause malabsorption of macronutrients, along with mechanistic and experimental evidence, in children (if not, in adults) with EE. The strengths and limitations of the human experimental studies are examined in relation to a battery of existing and potential tests that are used to measure malabsorption. From the available studies conducted in children, lactose and fat malabsorption are more likely to occur in EE. Breath tests (non-invasive) measuring carbohydrate (13C-starch/sucrose/lactose), fat (13C-mixed triglyceride) and dipeptide (benzoyl-L-tyrosyl-L-1-13C-alanine) malabsorption with modifications to the existing protocols seem suitable for use in children with EE. Future research should focus on understanding the degree of macronutrient malabsorption using these tests, in different settings, and link them to functional outcomes (such as growth, muscle strength, cognition).

Green Hrm and Employee Performance: How Organizational Culture Plays A Mediating Role

This research looks at how green HR management affects employee performance through the medium of organizational culture. With the increasing demand for environmentally friendly practices, businesses are feeling the heat to adopt eco-friendly policies that benefit society and our environment. Green HRM is believed to promote environmentally conscious behavior among employees, thereby enhancing their performance. This study takes a quantitative approach by using Partial Least Squares (PLS) as its statistical method. PLS is well-suited for analyzing correlations between complex variables. Maximizing explained variance enhances prediction accuracy, which is why PLS is chosen. The study ensures full data representation by using a saturation sampling strategy, which encompasses all relevant population members. Although green HR management has a major effect on company culture, the results show that it has little to no effect on employee performance. Furthermore, corporate culture mediates the relationship between green HR management and staff effectiveness, which in turn has a substantial impact on worker performance. The study concludes that for effective implementation of green HRM, it is essential to integrate it with an organizational culture that aligns with sustainability values. For this reason, green human resource management practices ought to be an essential component of the culture of every organization that aspires to raise the level of productivity achieved by its workforce.

Endoscopic third ventriculostomy assisted by augmented reality.

Augmented reality (AR) technology has witnessed remarkable advancements in recent years, revolutionizing various fields, including medicine and surgery. In neurosurgery, AR holds immense promise for improving the accuracy, efficiency, and safety of various procedures. Augmented reality allows a user to visualize digital information such as 3D models, superimposed on their real-world field of view. Lately, there has been increased use of this technology for various procedures such as tumor resection, ventriculostomy, and pedicle screw insertion. Despite this, integration of AR into the field of neurosurgery is still in its infancy. As such, it is imperative that physicians continue to explore and document new clinical uses of AR. In this report, we describe the novel integration of AR into an endoscopic third ventriculostomy (ETV) case. ETV is a minimally invasive technique used to treat hydrocephalus, which involves creating a new pathway for cerebrospinal fluid (CSF) drainage within the brain's ventricular system. The integration of AR into ETV procedures offers unprecedented opportunities to enhance surgical visualization, navigation, and decision-making, ultimately leading to improved patient outcomes. Traditionally, neurosurgeons rely on pre-operative imaging, intraoperative neuronavigation systems, and their anatomical knowledge to perform an ETV. However, the complex neuroanatomy and variability among patients pose challenges to accurate navigation and spatial orientation prior to and during surgery. AR technology addresses these challenges by overlaying digital information-such as three-dimensional models, anatomical landmarks, and surgical trajectories-onto the surgeon's view of the patient in real-time.

SICALC - A new tool for aircraft noise calculations

This paper investigates how aircraft noise calculations can be made available for everyone. Traditionally, tools for aircraft noise calculations have been characterized by high complexity and numerous variables that users must consider. This complexity has necessitated expert competence to conduct calculations, limiting the accessibility of these calculations. SICALC (SINTEF Noise Calculator) is a new web-application tool that aims to challenge this practice and make noise calculation available to everyone while ensuring high-quality, reliable, uniform, and error-free results. The paper will discuss how the aircraft noise calculation method, NORTIM (the Norwegian Topography Integrated Model), has incorporated new technology and design principles into SICALC. It will also address the various challenges associated with this development.

Investigation of Chinese College Students’ Perceptions, Needs, and Self-Assessment of Spoken English Competency

Spoken English Competency (SEC) remains a critical weakness in English Proficiency (EP) of Chinese college students, particularly when compared with their English competency in writing and reading. Despite years of English learning since elementary school, Chinese college students often struggle to master SEC. Although previous studies have explored Chinese students’ SEC from various perspectives, there is still a significant knowledge gap, especially from students’ perspectives. This study aims to analyze students’ Perceptions and Needs of Spoken English (PNSE) and their Self-Assessment of Spoken English Competency (SA-SEC) with the language output evaluation indicators (including three dimensions: complexity, accuracy, and fluency [CAF]). The study analyzed 2,677 (male = 1,340, female = 1,337) online questionnaires from college students across four English proficiency distinct groups. There are four identified aspects of PNSE (i.e., oral importance, difficulty, purpose, and improvement willingness). Similarly, SA-SEC was analyzed with three dimensions of CAF, namely complexity, accuracy, fluency, and nominal variables like pause type. The findings revealed that gender and EP significantly influenced PNSE and SA-SEC, and correlations were observed between paired variables of PNSE and dimensions of CAF in the SA-SEC section. Notably, complexity was identified as the weakest dimension of CAF for most students. Future studies are imperative to further explore the intricate relationship between PNSE and SA-SEC, and how factors such as pause type influence students’ spoken English performance.

Robust brain MRI image classification with SIBOW-SVM

Primary Central Nervous System tumors in the brain are among the most aggressive diseases affecting humans. Early detection and classification of brain tumor types, whether benign or malignant, glial or non-glial, is critical for cancer prevention and treatment, ultimately improving human life expectancy. Magnetic Resonance Imaging (MRI) is the most effective technique for brain tumor detection, generating comprehensive brain scans. However, human examination can be error-prone and inefficient due to the complexity, size, and location variability of brain tumors. Recently, automated classification techniques using machine learning methods, such as Convolutional Neural Networks (CNNs), have demonstrated significantly higher accuracy than manual screening. However, deep learning-based image classification methods, including CNNs, face challenges in estimating class probabilities without proper model calibration (Guo et al., 2017; Minderer et al., 2021). In this paper, we propose a novel brain tumor image classification method called SIBOW-SVM, which integrates the Bag-of-Features model with SIFT feature extraction and weighted Support Vector Machines. This new approach can effectively extract hidden image features, enabling differentiation of various tumor types, provide accurate label predictions, and estimate probabilities of images belonging to each class, offering high-confidence classification decisions. We have also developed scalable and parallelable algorithms to facilitate the practical implementation of SIBOW-SVM for massive image datasets. To benchmark our method, we apply SIBOW-SVM to a public dataset of brain tumor MRI images containing four classes: glioma, meningioma, pituitary, and normal. Our results demonstrate that the new method outperforms state-of-the-art techniques, including CNNs, in terms of uncertianty quantification, classification accuracy, computational efficiency, and data robustness.