Interpretive Modeling Research Articles

AFSD-Physics: Exploring the governing equations of temperature evolution during additive friction stir deposition by a human-AI teaming approach

This paper presents a modeling effort to explore the underlying physics of temperature evolution during additive friction stir deposition (AFSD) by a human-AI teaming approach. AFSD is an emerging solid-state additive manufacturing technology that deposits materials without melting. However, both process modeling and modeling of the AFSD tool are at an early stage. In this paper, a human-AI teaming approach is proposed to combine models based on first principles with AI. The resulting human-informed machine learning method, denoted as AFSD-Physics, can effectively learn the governing equations of temperature evolution at the tool and the build from in-process measurements. Experiments are designed and conducted to collect in-process measurements for the deposition of aluminum 7075 with a total of 30 layers. The acquired governing equations are physically interpretable models with low computational cost and high accuracy. Model predictions show good agreement with the measurements. Experimental validation with new process parameters demonstrates the model’s generalizability and potential for use in tool temperature control and process optimization.

Expanding the associations between built environment characteristics and residential mobility in high-density neighborhood unit

Global trend of urbanization has led to frequent residential mobility and urban shrinkage issues. Planners and policy makers advocate for enhancing built environment quality of neighbourhood units to address these issues. Although the impact factors and degree of the influence of the built environment on residential mobility have been studied, the nonlinear effects at the neighbourhood level, and the relative importance when considered alongside other factors, remain unclear. In this study, the central area of Nanjing using mobile phone signalling data, the 5Ds framework, machine learning algorithms, and interpretable model Shapley Additive exPlanations (SHAP) are examined. The finding shows that (1) economy and neighbourhood ties are still key drivers of relocation. (2) Optimizing highly accessible road network for short-distance travel and developing low-density urban mode has become significant methods to attract relocators, interacting with other factors to influence residential mobility. (3) High-quality neighbourhood design, diverse amenities, and proximity to natural landscapes increase willingness to relocate, (4) while religion, socio-demographics, and large-scale transportation accessibility have minimal impact. The study offers four urban development recommendations to help municipal planners and policy makers create liveable cities and cohesive communities, providing essential insights for early or renewal stage urban planning stages.

Interpretable few-shot learning with online attribute selection

Few-shot learning (FSL) presents a challenging learning problem in which only a few samples are available for each class. Decision interpretation is more important in few-shot classification due to a greater chance of error compared to traditional classification. However, the majority of the previous FSL methods are black-box models. In this paper, we propose an inherently interpretable model for FSL based on human-friendly attributes. Previously, human-friendly attributes have been utilized to train models with the potential for human interaction and interpretability. However, such approaches are not directly extendible to the few-shot classification scenario. Moreover, we propose an online attribute selection mechanism to effectively filter out irrelevant attributes in each episode. The attribute selection mechanism improves accuracy and helps with interpretability by reducing the number of attributes that participate in each episode. We further propose a mechanism that automatically detects the episodes where the pool of available human-friendly attributes is insufficient, and subsequently augments it by engaging some learned unknown attributes. We demonstrate that the proposed method achieves results on par with black-box few-shot learning models on four widely used datasets. We also empirically evaluate the level of decision alignment between different models and human understanding and show that our model outperforms the comparison methods based on this criterion.

Malaysian Community College Graduates Employability Prediction Model Using Machine Learning Approach

Community College, as TVET institution under the Ministry of Higher Education, offers industry-relevant skills training to ensure graduates' employability in the global labor market. However, producing graduates who meet industry demands remains a challenge, and industries continue to face difficulties in obtaining skilled graduates. In Malaysia, there is limited research on predictive models for employability rates among graduates of TVET Malaysian institutions. This research utilizes Python to investigate the significant factors influencing employability among Malaysian Community College graduates, determined by a specific indicator of whether they will be employed. Our contribution lies in developing an accurate employability prediction model using machine learning algorithms such as Logistic Regression, Neural Networks, and Random Forest. The dataset used consisted of 10,427 instances and 14 attributes, from which six significant factors were identified. Among the models, Random Forest outperformed the other machine learning models, and hyperparameter tuning using RandomizedSearch further improved the accuracy of the model to 84.8%. This study aims to identify the most accurate and interpretable model, providing valuable insights for educational institutions to enhance their employability strategies.

Explainable AI (XAI) in healthcare: Enhancing trust and transparency in critical decision-making

The integration of artificial intelligence (AI) in healthcare is revolutionizing diagnostic and treatment procedures, offering unprecedented accuracy and efficiency. However, the opacity of many advanced AI models, often described as "black boxes," creates challenges in adoption due to concerns around trust, transparency, and interpretability, particularly in high-stakes environments like healthcare. Explainable AI (XAI) addresses these concerns by providing a framework that not only achieves high performance but also offers insight into how decisions are made. This research explores the application of XAI techniques in healthcare, focusing on critical areas such as disease diagnostics, predictive analytics, and personalized treatment recommendations. The study will analyse various XAI methods, including model-agnostic approaches (LIME, SHAP), interpretable deep learning models, and domain-specific applications of XAI. It also evaluates the ethical implications, such as accountability and bias mitigation, and how XAI can foster collaboration between clinicians and AI systems. Ultimately, the goal is to create AI systems that are both powerful and trustworthy, promoting broader adoption in the healthcare sector while ensuring ethical and safe outcomes for patients.

An empirical study for mitigating sustainable cloud computing challenges using ISM-ANN.

The significance of cloud computing methods in everyday life is growing as a result of the exponential advancement and refinement of artificial technology. As cloud computing makes more progress, it will bring with it new opportunities and threats that affect the long-term health of society and the environment. Many questions remain unanswered regarding sustainability, such as, "How will widely available computing systems affect environmental equilibrium"? When hundreds of millions of microcomputers are invisible to each other, what will society look like? What does this mean for social sustainability? This paper empirically investigates the ethical challenges and practices of cloud computing about sustainable development. We conducted a systematic literature review followed by a questionnaire survey and identified 11 sustainable cloud computing challenges (SCCCs) and 66 practices for addressing the identified challenges. Interpretive structural modeling (ISM) and Artificial Neural Networks (ANN) were then used to identify and analyze the interrelationship between the SCCCs. Then, based on the results of the ISM, 11 process areas were determined to develop the proposed sustainable cloud computing challenges mitigation model (SCCCMM). The SCCCMM includes four main categories: Requirements specification, Quality of Service (QoS) and Service Legal Agreement (SLA), Complexity and Cyber security, and Trust. The model was subsequently tested with a real-world case study that was connected to the environment. In a sustainable cloud computing organization, the results demonstrate that the proposed SCCCMM aids in estimating the level of mitigation. The participants in the case study also appreciated the suggested SCCCMM for its practicality, user-friendliness, and overall usefulness. When it comes to the sustainability of their software products, we believe that organizations involved in cloud computing can benefit from the suggested SCCCMM. Additionally, researchers and industry practitioners can expect the proposed model to provide a strong foundation for developing new sustainable methods and tools for cloud computing.

Evaluating the impact of digital and financial literacy on MSME performance

ABSTRACT The objective of this study was to determine the critical success factors that contribute to the performance of micro-, small, and medium-sized enterprises (MSMEs) in the context of digital and financial literacy. This study employed the total interpretive structural modeling approach to construct a hierarchical model of important success elements and analyze their direct and indirect interconnections. This article specifies six success factors that impact the performance of MSMEs, with the consideration of their effects and value generation leading to enhanced performance. The results indicate that entrepreneurial orientation and digital literacy are the primary components of the developed model, with all factors collectively contributing to overall performance. By identifying and categorizing key components within the strategic model, the study provides MSME founders with a systematic way to enhance business competency, which has significant consequences for business growth and success. The hierarchical model developed in this research assists policy makers and practitioners in improving the performance of MSMEs.

Concept-based AI interpretability in physiological time-series data: Example of abnormality detection in electroencephalography

Background and ObjectiveDespite recent performance advancements, deep learning models are not yet adopted in clinical practice on a wide scale. The intrinsic intransparency of such systems is commonly cited as one major reason for this reluctance. This has motivated methods that aim to provide explanations of model functioning. Known limitations of feature-based explanations have led to an increased interest in concept-based interpretability. Testing with Concept Activation Vectors (TCAV) employs human-understandable, abstract concepts to explain model behavior. The method has previously been applied to the medical domain in the context of electronic health records, retinal fundus images and magnetic resonance imaging. MethodsWe explore the usage of TCAV for building interpretable models on physiological time series, using an example of abnormality detection in electroencephalography (EEG). For this purpose, we adopt the XceptionTime model, which is suitable for multi-channel physiological data of variable sizes. The model provides state-of-the-art performance on raw EEG data and is publically available. We propose and test several ideas regarding concept definition through metadata mining, using additional labeled EEG data and extracting interpretable signal characteristics in the form of frequencies. By including our own hospital data with analog labeling, we further evaluate the robustness of our approach. ResultsThe tested concepts show a TCAV score distribution that is in line with the clinical expectations, i.e. concepts known to have strong links with EEG pathologies (such as epileptiform discharges) received higher scores than the neutral concepts (e.g. sex). The scores were consistent across the applied concept generation strategies. ConclusionsTCAV has the potential to improve interpretability of deep learning applied to multi-channel signals as well as to detect possible biases in the data. Still, further work on developing the strategies for concept definition and validation on clinical physiological time series is needed to better understand how to extract clinically relevant information from the concept sensitivity scores.

A novel interpretable hybrid model for multi-step ahead dissolved oxygen forecasting in the Mississippi River basin

A novel interpretable hybrid model for multi-step ahead dissolved oxygen forecasting in the Mississippi River basin

An advanced dual-layered framework for sustainable supply chain performance

Purpose This study aims to evaluate the sustainable supply chain performance indicators. At a macro level, the identification of the sustainable supply chain management (SSCM) performance indicators is done through exhaustive literature survey and interviews with experts. Furthermore, these indicators are evaluated through a hybrid approach, i.e. total weighted interpretive structural modelling (TWISM) followed by analytic hierarchical process (AHP). Design/methodology/approach Micro small and medium enterprises (MSMEs) in India are a major contributor to nation’s GDP. However, this sector struggles to comprehend benefits from implementation of SSCM due to a lack of appropriate performance evaluation metrics. The purpose of this paper is to contribute to the body of knowledge in SSCM by proposing and evaluating a set of SSCM performance indicators. Findings The paper highlights the SSCM performance indicators and concludes that business strategies, implementation planning and impact of stakeholders are the top SSCM performance indicators (SPIs). Therefore, the decision-makers must initially focus on strategic requirements which foster the implementation of SSCM, thereby ensuring profitability for all stakeholders. Research limitations/implications Although the proposed framework was validated through a case study on Indian automobile component manufacturing MSMEs, future research would explore the extension of the framework to other industries. Originality/value The originality of this study lies in the application of the novel TWISM-AHP tool. Furthermore, the SPIs identified in the study, consider the integration of the triple bottom line from the MSME perspective. The TWISM-AHP analysis will be beneficial for SC decision-makers to enhance the SSCM performance based on the identified indicators and their criticality.

Explainable machine learning model for predicting paratracheal lymph node metastasis in cN0 papillary thyroid cancer

Prophylactic dissection of paratracheal lymph nodes in clinically lymph node-negative (cN0) papillary thyroid carcinoma (PTC) remains controversial. This study aims to integrate preoperative and intraoperative variables to compare traditional nomograms and machine learning (ML) models, developing and validating an interpretable predictive model for paratracheal lymph node metastasis (PLNM) in cN0 PTC patients. We retrospectively selected 3213 PTC patients treated at the First Affiliated Hospital of Chongqing Medical University from 2016 to 2020. They were randomly divided into the training and test datasets with a 7:3 ratio. The 533 PTC patients treated at the Guangyuan Central Hospital from 2019 to 2022 were used as an external test sets. We developed and validated nine ML models using 10-fold cross-validation and grid search for hyperparameter tuning. The predictive performance was evaluated using ROC curves, decision curve analysis (DCA), calibration curves, and precision-recall curves. The best model was compared to a traditional logistic regression-based nomogram. The XGBoost model achieved AUC values of 0.935, 0.857, and 0.775 in the training, validation, and test sets, respectively, significantly outperforming the traditional nomogram model with AUCs of 0.85, 0.844, and 0.769, respectively. SHapley Additive exPlanations (SHAP)-based visualization identified the top 10 predictive features of the XGBoost model, and a web-based calculator was created based on these features. ML is a reliable tool for predicting PLNM in cN0 PTC patients. The SHAP method provides valuable insights into the XGBoost model, and the resultant web-based calculator is a clinically useful tool to assist in the surgical planning for paratracheal lymph node dissection.

XAI-SALPAD: Explainable deep learning techniques for Saudi Arabia license plate automatic detection

In recent decades, automatic license plate recognition (ALPR) has emerged as a critical application of artificial intelligence in intelligent transportation systems (ITS), addressing a multitude of existing issues. Several algorithms have been developed to improve ALPR accuracy under a variety of conditions, each with its own set of strengths and limitations. The KSA intends to digitize traditional services as part of its Vision 2030 initiative. In this methodology, the ALPR system for accurately recognizing KSA's license plates (LP) leverages deep neural networks (DNNs) as a powerful technique, capable of performing effectively in unconstrained environments with images taken under various conditions, even when the training data is limited. The approach employs YOLOv8 to detect LPs and alphanumeric characters in real-time, followed by using a convolutional neural network (CNN) for character recognition. According to our finding, the YOLOv8 model outperforms other models in the identification of LPs, achieving remarkable accuracy and F1 scores (mAP@0.5 = 0.96 and mAP@0.95 = 0.97). As a result, YOLOv8 was chosen for SLP character recognition. This strategy is appropriate for ITS since it tackles a number of issues, like decreasing car theft and improving public safety. Furthermore, a locally interpretable agnostic model (LIME) offers justifications that help users better understand the model. The system's provision of clear explanations for its decisions not only satisfies performance standards but also corresponds with the increasing need for explainable AI, guaranteeing an efficient and responsible implementation.

WIMOAD: Weighted Integration of Multi-Omics data for Alzheimer's Disease (AD) Diagnosis.

As the most common subtype of dementia, Alzheimer's disease (AD) is characterized by a progressive decline in cognitive functions, especially in memory, thinking, and reasoning ability. Early diagnosis and interventions enable the implementation of measures to reduce or slow further regression of the disease, preventing individuals from severe brain function decline. The current framework of AD diagnosis depends on A/T/(N) biomarkers detection from cerebrospinal fluid or brain imaging data, which is invasive and expensive during the data acquisition process. Moreover, the pathophysiological changes of AD accumulate in amino acids, metabolism, neuroinflammation, etc., resulting in heterogeneity in newly registered patients. Recently, next generation sequencing (NGS) technologies have found to be a non-invasive, efficient and less-costly alternative on AD screening. However, most of existing studies rely on single omics only. To address these concerns, we introduce WIMOAD, a weighted integration of multi-omics data for AD diagnosis. WIMOAD synergistically leverages specialized classifiers for patients' paired gene expression and methylation data for multi-stage classification. The resulting scores were then stacked with MLP-based meta-models for performance improvement. The prediction results of two distinct meta-models were integrated with optimized weights for the final decision-making of the model, providing higher performance than using single omics only. Remarkably, WIMOAD achieves significantly higher performance than using single omics alone in the classification tasks. The model's overall performance also outperformed most existing approaches, highlighting its ability to effectively discern intricate patterns in multi-omics data and their correlations with clinical diagnosis results. In addition, WIMOAD also stands out as a biologically interpretable model by leveraging the SHapley Additive exPlanations (SHAP) to elucidate the contributions of each gene from each omics to the model output. We believe WIMOAD is a very promising tool for accurate AD diagnosis and effective biomarker discovery across different progression stages, which eventually will have consequential impacts on early treatment intervention and personalized therapy design on AD.

Interpretable machine learning models for the prediction of all-cause mortality and time to death in hemodialysis patients.

The elevated mortality and hospitalization rates among hemodialysis (HD) patients underscore the necessity for the development of accurate predictive tools. This study developed two models for predicting all-cause mortality and time to death-one using a comprehensive database and another simpler model based on demographic and clinical data without laboratory tests. A retrospective cohort study was conducted from January 2017 to June 2023. Two models were created: Model A with 85 variables and Model B with 22 variables. We assessed the models using random forest (RF), support vector machine, and logistic regression, comparing their performance via the AU-ROC. The RF regression model was used to predict time to death. To identify the most relevant factors for prediction, the Shapley value method was used. Among 359 HD patients, the RF model provided the most reliable prediction. The optimized Model A showed an AU-ROC of 0.86 ± 0.07, a sensitivity of 0.86, and a specificity of 0.75 for predicting all-cause mortality. It also had an R2 of 0.59 for predicting time to death. The optimized Model B had an AU-ROC of 0.80 ± 0.06, a sensitivity of 0.81, and a specificity of 0.70 for predicting all-cause mortality. In addition, it had an R2 of 0.81 for predicting time to death. Two new interpretable clinical tools have been proposed to predict all-cause mortality and time to death in HD patients using machine learning models. The minimal and readily accessible data on which Model B is based makes it a valuable tool for integrating into clinical decision-making processes.

Comparative analysis of some linear predictive models in the presence of multicollinearity

This paper investigates the comparative performance of some linear predictive models in the presence of multicollinearity. By examining the efficacy of Ordinary Least Squares (OLS), Ridge Regression, Lasso Regression, and Elastic Net Regression, this study aimed to figure out the best method for building robust and interpretable models under such conditions. The research explores how these models address multicollinearity, focusing on coefficient stability, prediction accuracy, and variable selection. Through a rigorous analysis of simulated and real-world datasets, the study shows the strengths and weaknesses of each model, providing valuable insights for researchers and practitioners looking to mitigate the challenges posed by multicollinearity in selecting the most proper method for regression modeling. This will lead to the creation of a model with increased interpretability of the relationships between variables, less variance, and more dependable coefficient estimations.

Predicting bacterial fitness in Mycobacterium tuberculosis with transcriptional regulatory network-informed interpretable machine learning.

Mycobacterium tuberculosis (Mtb) is the causative agent of tuberculosis disease, the greatest source of global mortality by a bacterial pathogen. Mtb adapts and responds to diverse stresses such as antibiotics by inducing transcriptional stress-response regulatory programs. Understanding how and when these mycobacterial regulatory programs are activated could enable novel treatment strategies for potentiating the efficacy of new and existing drugs. Here we sought to define and analyze Mtb regulatory programs that modulate bacterial fitness. We assembled a large Mtb RNA expression compendium and applied these to infer a comprehensive Mtb transcriptional regulatory network and compute condition-specific transcription factor activity profiles. We utilized transcriptomic and functional genomics data to train an interpretable machine learning model that can predict Mtb fitness from transcription factor activity profiles. We demonstrated that this transcription factor activity-based model can successfully predict Mtb growth arrest and growth resumption under hypoxia and reaeration using only RNA-seq expression data as a starting point. These integrative network modeling and machine learning analyses thus enable the prediction of mycobacterial fitness under different environmental and genetic contexts. We envision these models can potentially inform the future design of prognostic assays and therapeutic intervention that can cripple Mtb growth and survival to cure tuberculosis disease.

A multi-task learning model for clinically interpretable sesamoiditis grading

Sesamoiditis is a common equine disease with varying severity, leading to increased injury risks and performance degradation in horses. Accurate grading of sesamoiditis is crucial for effective treatment. Although deep learning-based approaches for grading sesamoiditis show promise, they remain underexplored and often lack clinical interpretability. To address this issue, we propose a novel, clinically interpretable multi-task learning model that integrates clinical knowledge with machine learning. The proposed model employs a dual-branch decoder to simultaneously perform sesamoiditis grading and vascular channel segmentation. Feature fusion is utilized to transfer knowledge between these tasks, enabling the identification of subtle radiographic variations. Additionally, our model generates a diagnostic report that, along with the vascular channel mask, serves as an explanation of the model’s grading decisions, thereby increasing the transparency of the decision-making process. We validate our model on two datasets, demonstrating its superior performance compared to state-of-the-art models in terms of accuracy and generalization. This study provides a foundational framework for the interpretable grading of similar diseases.

The genetic architecture of protein stability

There are more ways to synthesize a 100-amino acid (aa) protein (20100) than there are atoms in the universe. Only a very small fraction of such a vast sequence space can ever be experimentally or computationally surveyed. Deep neural networks are increasingly being used to navigate high-dimensional sequence spaces1. However, these models are extremely complicated. Here, by experimentally sampling from sequence spaces larger than 1010, we show that the genetic architecture of at least some proteins is remarkably simple, allowing accurate genetic prediction in high-dimensional sequence spaces with fully interpretable energy models. These models capture the nonlinear relationships between free energies and phenotypes but otherwise consist of additive free energy changes with a small contribution from pairwise energetic couplings. These energetic couplings are sparse and associated with structural contacts and backbone proximity. Our results indicate that protein genetics is actually both rather simple and intelligible.

Examining the impact of green entrepreneurship drivers on sustainable development in the context of emerging country

PurposeGreen entrepreneurship (GE) is a novel concept in business and enhances environmentally friendly production and operation activities for “sustainable development” (SD). The aim of this study is to determine the drivers that contribute to the growth and success of “micro, small, and medium enterprises” (MSMEs) in the manufacturing sector in India. The study also examines the mutual and cause-and-effect relationships among these identified drivers.Design/methodology/approachThe study used integrated research methodology and identified nine key drivers of GE (GEDs) through extensive literature reviews, theoretical perspectives (i.e. “resource-based view” (RBV), “natural resource-based view” (NRBV) and “critical success factor theory” (CSFT)), and expert opinions. Further, “total interpretive structural modeling” (TISM) and “matrice d'impacts croisés multiplication appliquée á un classment” (MICMAC) analysis are used here to develop a hierarchical model and cluster the drivers, and fuzzy “decision-making trial and evaluation laboratory” (fuzzy-DEMATEL) is used to develop causal relationships among the drivers. Further, a sensitivity analysis is conducted to ensure the robustness of the results.FindingsResults indicated that green manufacturing and operation capability development, green business process management and attitudes toward developing sustainable business models significantly impacted GE and SD. The findings of this study help managers, policymakers, and practitioners gain an in-depth understanding of the drivers of GE.Research limitations/implicationsThe study considers a limited number of drivers and is specific to Indian manufacturing MSMEs only. Further, a limited number of experts from different enterprises are considered for data analysis. This study is also based on interrelationships and their relative importance based on multicriteria decision-making techniques. This study aids government decision-making, policy formulation and strategic decision-making for manufacturing businesses in achieving SD goals. In addition, this research also encourages green entrepreneurs to start eco-driven companies and facilitate the use of environmentally friendly goods to offset environmental challenges and accomplish sustainable development goals.Originality/valueThis study proposes an integrated methodology that will benefit managers, practitioners and others in developing strategies and innovations to improve and develop green practices. This study further helps with responsive, sustainable business development in various manufacturing MSMEs.

Factors Influencing Green Construction Practices in Context of COVID-19 Pandemic: Empirical Evidence from China

Green construction practices (GCPs) are essential for the construction industry to achieve carbon neutral and sustainable development. However, the promotion of GCPs faces multifaceted challenges, particularly within the context of recent global uncertainties. The COVID-19 pandemic has wrought substantial disruption upon the construction sector, which makes it a good candidate as a case study for enhancing future risk management strategies. Currently, there is limited research on the factors influencing GCPs in the global uncertainty context. To bridge this research gap, this study first identifies 26 factors affecting GCPs in the context of the COVID-19 pandemic through a comprehensive literature review. Subsequently, based on feedback from 22 experts, Interpretative Structural Modeling (ISM) and Matrice d’Impacts Croisés Multiplication Appliquée à un Classement (MICMAC) methodologies are adopted to illustrate the intricate relationships among influencing factors and further classify their relative importance. The results underscore the pivotal role of factors such as technology development, the difficulty of construction, materials, and equipment performance, as well as identify 13 factors that have a fundamental impact. This research provides insights for decision-makers to enhance risk management strategies for GCPs in the global uncertainty context, prioritize the determinants, and facilitate the optimal allocation of resources to advance GCPs.