Black Box Research Articles

Physics-informed neural networks in groundwater flow modeling: Advantages and future directions

In recent years, there has been enormous development in soft computing, especially artificial intelligence (AI), which has developed robust methods for solving complex engineering problems. Researchers in the field of water resources engineering have applied these AI methods to solve a variety of hydrological problems. Despite their widespread use in the surface and atmospheric hydrology fields, groundwater hydrologists have not widely used AI methods in their routine field-scale modeling efforts. This is because AI models have been primarily considered black box models that lack physical meaning. Furthermore, using AI models to generate the space-time distribution of transient groundwater level variations is challenging and requires further flux balance and mass transport analyses. More recently, a new type of physics-informed neural network (PINN) model has been developed to address several limitations by integrating governing physics (groundwater flow equations) into the AI tools. This study presents the systematic advantages of the PINN algorithm for solving groundwater problems using a set of classic test problems. As discussed in detail in the article, these advantages and potentials are associated with the meshless nature of PINN, its continuous time and space dimensions, its independence from time-stepping and incremental marching in space, and its efficiency in running time. However, despite PINN's promising attributes, it is important to acknowledge its nascent stage of development and the inherent limitations of all neural network models, such as training challenges and hyperparameter selection. Thus, collaborative efforts between groundwater modelers and computer scientists are imperative to explore and exploit the full potential of PINN in tackling increasingly complex groundwater problems and nurturing PINN into a dependable modeling tool in industry and academia.

AMBER Alert: An Ironic Antidote to “Missing White Girl Syndrome”?

“Missing White Girl Syndrome” (MWGS) has been coined in critique of news media coverage favoritism of victims fitting that description. The AMBER Alert child recovery system was in fact inspired by the abduction and murder of a missing white girl, and some have argued its issuance decisions reflect MWGS. We examine this question using secondary data, including the annual AMBER Alert reports provided by the National Center for Missing and Exploited Children (NCMEC), the National Incidence Studies of Missing, Abducted, Runaway, and Thrownaway Children (NISMART), and the National Crime Information Center (NCIS). We compared the demographics of victims from official AMBER Alert data (NCMEC) with cross-comparable demographics from the two official missing persons data sources to test for potential main-effect bias favoring whites or girls. A fourth dataset derived from media accounts of AMBER Alerts is used to test for any potential interaction effect of issuance preference for white girls. Overwhelmingly the findings suggest AMBER Alert issuance decisions do not reflect MWGS. Thus, we argue the system has the potential to function as an ironic “antidote” to MWGS by virtue of the identities of the children for whom it is routinely deployed. However, we qualify by acknowledging limitations with available data, and that the “black box” of AMBER Alert issuance decisions remains unstudied, leaving open the question of race and/or gender bias occurring at that point. Policy discourse and future research implications are discussed.

Explainable and visualizable machine learning models to predict biochemical recurrence of prostate cancer.

Machine learning (ML) models presented an excellent performance in the prognosis prediction. However, the black box characteristic of ML models limited the clinical applications. Here, we aimed to establish explainable and visualizable ML models to predict biochemical recurrence (BCR) of prostate cancer (PCa). A total of 647 PCa patients were retrospectively evaluated. Clinical parameters were identified using LASSO regression. Then, cohort was split into training and validation datasets with a ratio of 0.75:0.25 andBCR-related features were included in Cox regression and five ML algorithm to construct BCR prediction models. The clinical utility of each model wasevaluated by concordance index (C-index) values and decision curve analyses (DCA). Besides, Shapley Additive Explanation (SHAP) values were used to explain the features in the models. We identified 11 BCR-related features using LASSO regression, then establishing five ML-based models, including random survival forest (RSF), survival support vector machine (SSVM), survival Tree (sTree), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and a Cox regression model, C-index were 0.846 (95%CI 0.796-0.894), 0.774 (95%CI 0.712-0.834), 0.757 (95%CI 0.694-0.818), 0.820 (95%CI 0.765-0.869), 0.793 (95%CI 0.735-0.852), and 0.807 (95%CI 0.753-0.858), respectively. The DCA showed that RSF model had significant advantages over all models. In interpretability of ML models, the SHAP value demonstrated the tangible contribution of each feature in RSF model. Our score system provide reference for the identification for BCR, and the crafting of a framework for making therapeutic decisions for PCa on a personalized basis.

Weighted Bayesian Belief Network for diabetics: a predictive model.

Diabetes is an enduring metabolic condition identified by heightened blood sugar levels stemming from insufficient production of insulin or ineffective utilization of insulin within the body. India is commonly labeled as the "diabetes capital of the world" owing to the widespread prevalence of this condition. To the best of the authors' last knowledge updated on September 2021, approximately 77 million adults in India were reported to be affected by diabetes, reported by the International Diabetes Federation. Owing to the concealed early symptoms, numerous diabetic patients go undiagnosed, leading to delayed treatment. While Computational Intelligence approaches have been utilized to improve the prediction rate, a significant portion of these methods lacks interpretability, primarily due to their inherent black box nature. Rule extraction is frequently utilized to elucidate the opaque nature inherent in machine learning algorithms. Moreover, to resolve the black box nature, a method for extracting strong rules based on Weighted Bayesian Association Rule Mining is used so that the extracted rules to diagnose any disease such as diabetes can be very transparent and easily analyzed by the clinical experts, enhancing the interpretability. The WBBN model is constructed utilizing the UCI machine learning repository, demonstrating a performance accuracy of 95.8%.

Interdependent Formation of Symbolic and Regulatory Boundaries: The Discursive Contestation Around the Home-Sharing Category

The formation of boundaries between established and emergent categories is a complex social process. Therein, our understanding of how symbolic boundaries translate into regulatory boundaries is underdeveloped. Extant research either treats laws and regulations for categories as given or assumes a seamless translation of a symbolic into a regulatory boundary. This sidelines that market participants actively contest and shape boundaries between categories. To address this lacuna, we open the black box of how symbolic boundaries are translated into regulatory boundaries. We adopt a discursive perspective and conduct a longitudinal study of the contestation around the categories of home sharing and short-term rental in Europe. Our analysis shows how symbolic and regulatory boundaries are formed in a causal sequential process, driven by shifts in the field positioning of market actors and in the discursive accounts they mobilize. We develop a theoretical model of the discursive foundation of category boundary formation. At the heart of our theorization are discursive accounts and how shifting coalitions of market participants mobilize them to shape the evolving symbolic and regulatory boundaries between an emergent and an established category. We contribute to category research by unearthing the interdependent formation of symbolic and regulatory boundaries and the role of discursive accounts in these processes.

More than the SRY: The Non-Coding Landscape of the Y Chromosome and Its Importance in Human Disease.

Historically, the Y chromosome has presented challenges to classical methodology and philosophy of understanding the differences between males and females. A genetic unsolved puzzle, the Y chromosome was the last chromosome to be fully sequenced. With the advent of the Human Genome Project came a realization that the human genome is more than just genes encoding proteins, and an entire universe of RNA was discovered. This dark matter of biology and the black box surrounding the Y chromosome have collided over the last few years, as increasing numbers of non-coding RNAs have been identified across the length of the Y chromosome, many of which have played significant roles in disease. In this review, we will uncover what is known about the connections between the Y chromosome and the non-coding RNA universe that originates from it, particularly as it relates to long non-coding RNAs, microRNAs and circular RNAs.

Improving traffic accident severity prediction using MobileNet transfer learning model and SHAP XAI technique.

Traffic accidents remain a leading cause of fatalities, injuries, and significant disruptions on highways. Comprehending the contributing factors to these occurrences is paramount in enhancing safety on road networks. Recent studies have demonstrated the utility of predictive modeling in gaining insights into the factors that precipitate accidents. However, there has been a dearth of focus on explaining the inner workings of complex machine learning and deep learning models and the manner in which various features influence accident prediction models. As a result, there is a risk that these models may be seen as black boxes, and their findings may not be fully trusted by stakeholders. The main objective of this study is to create predictive models using various transfer learning techniques and to provide insights into the most impactful factors using Shapley values. To predict the severity of injuries in accidents, Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Residual Networks (ResNet), EfficientNetB4, InceptionV3, Extreme Inception (Xception), and MobileNet are employed. Among the models, the MobileNet showed the highest results with 98.17% accuracy. Additionally, by understanding how different features affect accident prediction models, researchers can gain a deeper understanding of the factors that contribute to accidents and develop more effective interventions to prevent them.

Artificial Intelligence, Lymphoid Neoplasms, and Prediction of MYC, BCL2, and BCL6 Gene Expression Using a Pan-Cancer Panel in Diffuse Large B-Cell Lymphoma

Background: Artificial intelligence in medicine is a field that is rapidly evolving. Machine learning and deep learning are used to improve disease identification and diagnosis, personalize disease treatment, analyze medical images, evaluate clinical trials, and speed drug development. Methods: First, relevant aspects of AI are revised in a comprehensive manner, including the classification of hematopoietic neoplasms, types of AI, applications in medicine and hematological neoplasia, generative pre-trained transformers (GPTs), and the architecture and interpretation of feedforward neural net-works (multilayer perceptron). Second, a series of 233 diffuse large B-cell lymphoma (DLBCL) patients treated with rituximab-CHOP from the Lymphoma/Leukemia Molecular Profiling Project (LLMPP) was analyzed. Results: Using conventional statistics, the high expression of MYC and BCL2 was associated with poor survival, but high BCL6 was associated with a favorable overall survival of the patients. Then, a neural network predicted MYC, BCL2, and BCL6 with high accuracy using a pan-cancer panel of 758 genes of immuno-oncology and translational research that includes clinically relevant actionable genes and pathways. A comparable analysis was performed using gene set enrichment analysis (GSEA). Conclusions: The mathematical way in which neural networks reach conclusions has been considered a black box, but a careful understanding and evaluation of the architectural design allows us to interpret the results logically. In diffuse large B-cell lymphoma, neural networks are a plausible data analysis approach.

Prediction and Elucidation of Physical Properties of Polycrystalline Materials Using Multichannel Machine Learning of Electron Backscattering Diffraction

AbstractThe application of machine learning in materials science has yielded several benefits, including the prediction of physical properties and the improvement of experimental efficiency. However, with complex models, such as convolutional neural networks (CNN), learning has become a black box, from which no universal physical knowledge can be obtained. In this study, a highly accurate prediction of the electrical properties of polycrystalline semiconductor thin films is achieved by learning multichannel CNN models from electron backscattering diffraction (EBSD) data, that is band contrasts, grain boundaries, and inverse pole figures. In addition, it examines how the CNN model learned the correlation between the crystallinity, grain boundaries, crystallographic orientation, and carrier mobility by polarizing certain EBSD data and checking the predicted changes in carrier mobility. Physical parameters affecting carrier mobility can be extracted, which is challenging via human image recognition. The methods proposed in this study will not only enable the prediction of electrical properties from EBSD data for all materials but also will contribute to the discovery of complex physical phenomena beyond the limits of human analysis.

A Meta Algorithm for Interpretable Ensemble Learning: The League of Experts

Background. The importance of explainable artificial intelligence and machine learning (XAI/XML) is increasingly being recognized, aiming to understand how information contributes to decisions, the method’s bias, or sensitivity to data pathologies. Efforts are often directed to post hoc explanations of black box models. These approaches add additional sources for errors without resolving their shortcomings. Less effort is directed into the design of intrinsically interpretable approaches. Methods. We introduce an intrinsically interpretable methodology motivated by ensemble learning: the League of Experts (LoE) model. We establish the theoretical framework first and then deduce a modular meta algorithm. In our description, we focus primarily on classification problems. However, LoE applies equally to regression problems. Specific to classification problems, we employ classical decision trees as classifier ensembles as a particular instance. This choice facilitates the derivation of human-understandable decision rules for the underlying classification problem, which results in a derived rule learning system denoted as RuleLoE. Results. In addition to 12 KEEL classification datasets, we employ two standard datasets from particularly relevant domains—medicine and finance—to illustrate the LoE algorithm. The performance of LoE with respect to its accuracy and rule coverage is comparable to common state-of-the-art classification methods. Moreover, LoE delivers a clearly understandable set of decision rules with adjustable complexity, describing the classification problem. Conclusions. LoE is a reliable method for classification and regression problems with an accuracy that seems to be appropriate for situations in which underlying causalities are in the center of interest rather than just accurate predictions or classifications.

Percentages and reasons: AI explainability and ultimate human responsibility within the medical field

With regard to current debates on the ethical implementation of AI, especially two demands are linked: the call for explainability and for ultimate human responsibility. In the medical field, both are condensed into the role of one person: It is the physician to whom AI output should be explainable and who should thus bear ultimate responsibility for diagnostic or treatment decisions that are based on such AI output. In this article, we argue that a black box AI indeed creates a rationally irresolvable epistemic situation for the physician involved. Specifically, strange errors that are occasionally made by AI sometimes detach its output from human reasoning. Within this article it is further argued that such an epistemic situation is problematic in the context of ultimate human responsibility. Since said strange errors limit the promises of explainability and the concept of explainability frequently appears irrelevant or insignificant when applied to a diverse set of medical applications, we deem it worthwhile to reconsider the call for ultimate human responsibility.

Niche-dependent sponge hologenome expression profiles and the host-microbes interplay: a case of the hawaiian demosponge Mycale Grandis.

Most researches on sponge holobionts focus primarily on symbiotic microbes, yet data at the level of the sponge hologenome are still relatively scarce. Understanding of the sponge host and its microbial gene expression profiles and the host-microbes interplay in different niches represents a key aspect of sponge hologenome. Using the Hawaiian demosponge Mycale grandis in different niches as a model, i.e. on rocks, on the surface of coral Porites compressa, under alga Gracilaria salicornia, we compared the bacterial and fungal community structure, functional gene diversity, expression pattern and the host transcriptome by integrating open-format (deep sequencing) and closed-format (GeoChip microarray) high-throughput techniques. Little inter-niche variation in bacterial and fungal phylogenetic diversity was detected for M. grandis in different niches, but a clear niche-dependent variability in the functional gene diversity and expression pattern of M. grandis host and its symbiotic microbiota was uncovered by GeoChip microarray and transcriptome analyses. Particularly, sponge host genes related to innate immunity and microbial recognition showed a strong correlation with the microbial symbionts' functional gene diversity and transcriptional richness in different niches. The cross-niche variability with respect to the symbiont functional gene diversity and the transcriptional richness of M. grandis holobiont putatively reflects the interplay of niche-specific selective pressure and the symbiont functional diversity. Niche-dependent gene expression profiles of M. grandis hologenome and the host-microbes interplay were suggested though little inter-niche variation in bacterial and fungal diversity was detected, particularly the sponge innate immunity was found to be closely related to the symbiotic microbes. Altogether, these findings provide novel insights into the black box of one sponge holobiont in different niches at the hologenome level.

Aplikasi Dispensasi Berbasis Web Menggunakan Metode Waterfall pada SMKS TI Airlangga Samarinda

The problem at SMKS IT Airlangga is that the student dispensation process is still carried out using dispensation form paper and students who wish to apply for a permit must visit the student waka kesiswaan in the room, this takes time. the purpose of this research is to have a dispensation application at SMKS IT Airlangga Samarinda. This student dispensation application is a website-based application that functions to make it easier for students to do permits while at the same time making it easier for the student waka kesiswaan to give permission to students without having to come to the room and reduce paper use. For analysis and application design using several tools, namely: Use Case diagrams, Activity diagrams, Sequence diagrams and Class diagrams. As for the system development method using the waterfall method. This application was built using Visual Studio Code based on the PHP programming language, for database management using MySQL. Besides that, the Black Box method is used as a system testing method to find out all functions can run properly.

Translating meaning in sport coaching research: reflexivity and translation at work

ABSTRACT Despite a well-placed desire among sport coaching researchers to study diverse and international settings, discussions on the role of language translation have remained largely silent. While much of the research in sport coaching is produced in English, the issue of language translation is all too often left as a conceptual and practical black box. In this critical commentary, we open-up the discussion concerning the nature of language translation, the practical issues, and its role within the research process. Drawing upon the experiences of the authors (first and third), we use various examples of translation issues in sport coaching research as a way to encourage reflexive critical treatment of data. It is hoped the discussion illustrates how translation can be a thorny, yet critical feature of rigorous qualitative research in sport coaching.

AiWATERS: an artificial intelligence framework for the water sector

The presence of Artificial Intelligence (AI) and Machine Learning (ML) applications has led to its widespread adoption across diverse domains. AI is making its way into industry, beyond research and academia. Concurrently, the water sector is undergoing a digital transformation. Water utilities in the United States are at different stages in their journey of digital transformation, and the decision makers in water sector, who are non-expert stakeholders in AI applications, need to better understand this technology to make informed decisions. While AI has numerous benefits to offer, there are also many challenges related to data, model development, knowledge integration and ethical concerns that should be considered before implementing it for real world applications. Civil engineering is a licensed profession where critical decision making is involved. Therefore, trust in any decision support technology is critical for its acceptance in real-world applications. Therefore, this research proposes a framework called aiWATERS (Artificial Intelligence for the Water Sector) which can serve as a guide for the water utilities to successfully implement AI in their system. Based on this framework, we conduct pilot interviews and surveys with various small, medium, and large water utilities in the United States (US) to capture their current state of AI implementation and identify the challenges faced by them. The research findings reveal that most of the water utilities in the United States are at an early stage of implementing AI as they face concerns regarding the black box nature, trustworthiness, and sustainability of AI technology in their system. The aiWATERS framework is intended to help the utilities navigate through these issues in their journey of digital transformation.

Facial soft-biometrics obfuscation through adversarial attacks

Sharing facial pictures through online services, especially on social networks, has become a common habit for thousands of users. This practice hides a possible threat to privacy: the owners of such services, as well as malicious users, could automatically extract information from faces using modern and effective neural networks. In this paper, we propose the harmless use of adversarial attacks, i.e. variations of images that are almost imperceptible to the human eye and that are typically generated with the malicious purpose to mislead Convolutional Neural Networks (CNNs). Such attacks have been instead adopted to (i) obfuscate soft biometrics (gender, age, ethnicity) but (ii) without degrading the quality of the face images posted online. We achieve the above mentioned two conflicting goals by modifying the implementations of four of the most popular adversarial attacks, namely FGSM, PGD, DeepFool and C&W, in order to constrain the average amount of noise they generate on the image and the maximum perturbation they add on the single pixel. We demonstrate, in an experimental framework including three popular CNNs, namely VGG16, SENet and MobileNetV3, that the considered obfuscation method, which requires at most four seconds for each image, is effective not only when we have a complete knowledge of the neural network that extracts the soft biometrics (white box attacks), but also when the adversarial attacks are generated in a more realistic black box scenario. Finally, we prove that an opponent can implement defense techniques to partially reduce the effect of the obfuscation, but substantially paying in terms of accuracy over clean images; this result, confirmed by the experiments carried out with three popular defense methods, namely adversarial training, denoising autoencoder and Kullback-Leibler autoencoder, shows that it is not convenient for the opponent to defend himself and that the proposed approach is robust to defenses.

Glaucoma Detection Using Explainable AI and Deep Learning

INTRODUCTION: Glaucoma is an incurable eye syndrome and the second leading reason of vision loss. A retinal scan is usually used to detect it. Glaucoma poses a challenge to predict in its nascent stages because the side effects of glaucoma are not recognized until the advanced stages of the disease are reached. Therefore, regular eye examinations are important and recommended. Manual glaucoma screening methods are labour-intensive and time-consuming processes. However, deep learning-based glaucoma detection methods reduce the need for manual work and improve accuracy and speed.
 OBJECTIVES: conduct a literature analysis of latest technical publications using various AI, Machine learning, and Deep learning methodologies for automated glaucoma detection.
 RESULTS: There are 329 Scopus articles on glaucoma detection using retinal images. The quantitative review presented state-of-art methods from different research publications and articles and the usage of a fundus image database for qualitative and quantitative analysis. This paper presents the execution of Explainable AI for Glaucoma prediction Analysis. Explainable AI (XAI) is artificial intelligence (AI) that allows humans to understand AI decisions and predictions. This contrasts with the machine learning “black box” concept, where even the designer cannot explain why the AI made certain decisions. XAI is committed to improving user performance. To provide reliable explanations for Glaucoma forecasting from unhealthy and diseased photos, XAI primarily employs an Adaptive Neuro-fuzzy Inference System (ANFIS).
 CONCLUSION: This article proposes and compares the performance metrics of ANFIS & SNN fuzzy layers, VGG19, AlexNet, ResNet, and MobileNet.

A Study on the Explainability of Inception Network-Derived Image Classification AI Using National Defense Data

In the last 10 years, AI has made rapid progress, and image classification, in particular, are showing excellent performance based on deep learning. Nevertheless, due to the nature of deep learning represented by a black box, it is difficult to actually use it in critical decision-making situations such as national defense, autonomous driving, medical care, and finance due to the lack of explainability of judgement results. In order to overcome these limitations, in this study, a model description algorithm capable of local interpretation was applied to the inception network-derived AI to analyze what grounds they made when classifying national defense data. Specifically, we conduct a comparative analysis of explainability based on confidence values by performing LIME analysis from the Inception v2_resnet model and verify the similarity between human interpretations and LIME explanations. Furthermore, by comparing the LIME explanation results through the Top1 output results for Inception v3, Inception v2_resnet, and Xception models, we confirm the feasibility of comparing the efficiency and availability of deep learning networks using XAI.

How to Improve an Enterprise’s Innovation Capability from the Perspective of High- and Low-Level Enterprises Using Fuzzy-Set Qualitative Comparative Analysis

An enterprise’s capability is based on the quantity and collocation pattern of the heterogeneous resources it possesses. Innovation resources are the source of enterprise innovation capability. However, there is still a “black box” problem of the impact of the intensity of government support on enterprise innovation. Therefore, it is necessary to study high- or low-level enterprise innovation capability by combining the internal and external factors of the enterprise—the background characteristics of R&D personnel and the degree of government support. Based on the configuration perspective, this study uses the qualitative comparative analysis (fsQCA) method to conduct a comparative analysis of the innovation capabilities of enterprises in five time windows over six years with the longitudinal database of China’s industrial enterprises whose operating income exceeds RMB 20 million from 2010 to 2015. This paper summarizes two ways of realizing high-level enterprise innovation capability: female and highly educated R&D personnel type, and highly educated R&D personnel and high government investment type. The enterprise innovation capability is affected simultaneously by multiple conditional variables, and the impact of each conditional variable on enterprise innovation capability has a trend. Further, it analyzes the impact of every antecedent variable comparing high- to low-level enterprise innovation.

Effect of laparoscopic handle size on surgical performance: A randomized crossover trial

Laparoscopic instrument handles design and dimensions are crucial to determine the configuration of surgeons' hand grip and, therefore, can have a deleterious effect on overall surgical efficiency and surgeons' comfort. The aim of this study is to investigate the impact of laparoscopic handle size and hand surface area on surgical task performance. A single-blind, randomized crossover trial was carried out with 29 novice medical students. Participants performed three simulated tasks in "black box" simulators using two scissor-type handles of different sizes. Surgical performance was assessed by the number of errors and time required to complete each task. Hand anthropometric data were measured using a 3D scanner. Execution time was significantly higher when cutting and suturing tasks were performed with the smaller handle. In addition, hand surface area was positively correlated with peg transfer task time when performed with the standard handle and was correlated with cutting task time in small and standard handle groups. We also found positive correlations between execution time and the number of errors executed by larger-handed participants. Our findings indicate that laparoscopic handle size and hand area influence surgical performance, highlighting the importance of considering hand anthropometry variances in surgical instrument design.