Good Interpretation Research Articles

Merging Counter-Propagation and Back-Propagation Algorithms: Overcoming the Limitations of Counter-Propagation Neural Network Models.

Artificial neural networks (ANNs) are nowadays applied as the most efficient methods in the majority of machine learning approaches, including data-driven modeling for assessment of the toxicity of chemicals. We developed a combined neural network methodology that can be used in the scope of new approach methodologies (NAMs) assessing chemical or drug toxicity. Here, we present QSAR models for predicting the physical and biochemical properties of molecules of three different datasets: aqueous solubility, acute fish toxicity toward fat head minnow, and bio-concentration factors. A novel neural network modeling method is developed by combining two neural network algorithms, namely, the counter-propagation modeling strategy (CP-ANN) with the back-propagation-of-errors algorithm (BPE-ANN). The advantage is a short training time, robustness, and good interpretability through the initial CP-ANN part, while the extension with BPE-ANN improves the precision of predictions in the range between minimal and maximal property values of the training data, regardless of the number of neurons in both neural networks, either CP-ANN or BPE-ANN.

Development and validation of prediction models for papillary thyroid cancer structural recurrence using machine learning approaches

BackgroundAlthough papillary thyroid cancer (PTC) patients are known to have an excellent prognosis, up to 30% of patients experience disease recurrence after initial treatment. Accurately predicting disease prognosis remains a challenge given that the predictive value of several predictors remains controversial. Thus, we investigated whether machine learning (ML) approaches based on comprehensive predictors can predict the risk of structural recurrence for PTC patients.MethodsA total of 2244 patients treated with thyroid surgery and radioiodine were included. Twenty-nine perioperative variables consisting of four dimensions (demographic characteristics and comorbidities, tumor-related variables, lymph node (LN)-related variables, and metabolic and inflammatory markers) were analyzed. We applied five ML algorithms—logistic regression (LR), support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), and neural network (NN)—to develop the models. The area under the receiver operating characteristic (AUC-ROC) curve, calibration curve, and variable importance were used to evaluate the models’ performance.ResultsDuring a median follow-up of 45.5 months, 179 patients (8.0%) experienced structural recurrence. The non-stimulated thyroglobulin, LN dissection, number of LNs dissected, lymph node metastasis ratio, N stage, comorbidity of hypertension, comorbidity of diabetes, body mass index, and low-density lipoprotein were used to develop the models. All models showed a greater AUC (AUC = 0.738 to 0.767) than did the ATA risk stratification (AUC = 0.620, DeLong test: P < 0.01). The SVM, XGBoost, and RF model showed greater sensitivity (0.568, 0.595, 0.676), specificity (0.903, 0.857, 0.784), accuracy (0.875, 0.835, 0.775), positive predictive value (PPV) (0.344, 0.272, 0.219), negative predictive value (NPV) (0.959, 0.959, 0.964), and F1 score (0.429, 0.373, 0.331) than did the ATA risk stratification (sensitivity = 0.432, specificity = 0.770, accuracy = 0.742, PPV = 0.144, NPV = 0.938, F1 score = 0.216). The RF model had generally consistent calibration compared with the other models. The Tg and the LNR were the top 2 important variables in all the models, the N stage was the top 5 important variables in all the models.ConclusionsThe RF model achieved the expected prediction performance with generally good discrimination, calibration and interpretability in this study. This study sheds light on the potential of ML approaches for improving the accuracy of risk stratification for PTC patients.Trial registrationRetrospectively registered at www.chictr.org.cn (trial registration number: ChiCTR2300075574, date of registration: 2023-09-08).

Development of Geographic Information System for Government With Extreme Programming and User-Centered Design Methods

Software development is among the most powerful needs in every organization and industry in the current generation. It is used to help the functionality of their system by using the software development guide named Software Development Life Cycle (SDLC). Various system developments have been conducted, including developing a public complaint service system. This research applies extreme programming (XP) and User-Centered Design (UCD) development methods to develop the geographic information system for the Badan Narkotika Nasional (BNN) Kediri City complaint service. These development methods are expected to meet user expectations. Also, it can reduce the time required to develop products with results that will be shown by conducting usability testing and validity tests. This research applied extreme programming and user-centered design development methods, both quantitative and qualitative for user testing. The application was successfully developed using XP and UCD development methods. The Kediri City BNN complaint service application was successfully developed in several stages: planning, implementing the design, and program code, followed by the evaluation stage. In the evaluation stage, usability testing results on the geotagging mobile application of the Kediri City BNN complaint service obtained a total score of 92.75% with a very good interpretation, and the validation testing results obtained a value of 100%. Applying extreme programming and user-centered design as a development method produces high usability testing and user experience because, in the development stage, it prioritizes interactions and user opinions.

Symmetry and Graph Bi-Regularized Non-Negative Matrix Factorization for Precise Community Detection

Community is a fundamental and highly desired pattern in a Large-scale Undirected Network (LUN). Community detection is a vital issue when LUN representation learning is performed. Owing to its good scalability and interpretability, a Symmetric and Non-negative Matrix Factorization model is frequently utilized to tackle this issue. It adopts a unique Latent Factor (LF) matrix for precisely representing LUN’s symmetry, which, unfortunately, leads to a reduced LF space that decreases its representation learning ability to a target LUN. Motivated by this discovery, this study proposes a Symmetry and Graph Bi-regularized Non-negative Matrix Factorization (B-NMF) method that: a) leverages multiple LF matrices when representing LUN, thereby boosting the representation learning ability; b) constructs a symmetry regularization term that implies the equality constraint among its multiple LF matrices, thereby illustrating LUN’s intrinsic symmetry; and c) incorporates graph regularization into its learning objective, thereby illustrating LUN’s local geometry. A theoretical proof is given to theoretically validate B-NMF’s convergence ability. The regularization hyperparameters are selected by validating model modularity, thereby guaranteeing B-NMF’s practicability in addressing real application issues. Extensive experimental results on ten LUNs from real applications demonstrate that the proposed B-NMF-based community detector significantly outperforms several baseline and state-of-the-art models in achieving highly-accurate community detection results. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —LUNs are very-commonly seen in real applications like a social network system. Communities in LUNs are vital for various knowledge discovery-related applications. For accurately detecting them, a detector should guarantee its high representation learning ability to a target LUN. To do so, this paper presents a B-NMF model that is able to perform precise representation learning to LUNs, thereby achieving accurate community detection results. In comparison with conventional Symmetric and Non-negative Matrix Factorization-based community detectors, a B-NMF-based community detector enjoys its enlarged latent feature space, which ensures its higher representation ability to a target LUN. It depends on two regularization hyperparameters, which can be selected by performing grid-search on the target LUN via its modularity evaluation. This paper gives the empirical values of B-NMF’s regularization hyperparameters based on the parametersensitivity tests on the involved experimental datasets. The proposed B-NMF model is shown to be highly suitable for addressing community detection and clustering tasks on LUNs from real applications.

Interactions Between Alumina Inclusions at the Liquid Iron/Argon Gas Interface: Role of Contact Line Undulation

A deep understanding of the behavior of nonmetallic inclusions is essential for steel cleanliness control. The behavior of alumina inclusions at the liquid iron/argon gas interface is investigated using a high‐temperature confocal scanning laser microscope. The obtained images are used to determine the moving velocity of the inclusions on the interface. The obtained experimental data are quantitatively evaluated using the lateral capillary interaction model for multipole orders established by Danov–Kralchevsky while taking into account the resistive drag force. The attraction forces calculated from these data are in the range between ≈10−13 and ≈10−11 N. The best‐fitting model is assigned for each case. The multipole models almost counterbalance the drag force, indicating a good interpretation of the interaction between the inclusions. Moreover, the acting length of this interaction is examined and compared to the previous work on Ce2O3 inclusions. It is found that alumina inclusions generally exhibit a larger acting length at a large critical radius and a smaller acting length at a small critical radius when comparing them to their counterpart cerium oxide inclusions. Considering the particle shapes, high shape irregularity is better interpreted by higher orders of the multipoles.

Clinical Features Predicting COVID-19 Severity Risk at the Time of Hospitalization.

The global spread of COVID-19 has led to significant mortality and morbidity worldwide. Early identification of COVID-19 patients who are at high risk of developing severe disease can help in improved patient management, care, and treatment, as well as in the effective allocation of hospital resources. The severity prediction at the time of hospitalization can be extremely helpful in deciding the treatment of COVID-19 patients. To this end, this study presents an interpretable artificial intelligence (AI) model, named COVID-19 severity predictor (CoSP) that predicts COVID-19 severity using the clinical features at the time of hospital admission. We utilized a dataset comprising 64 demographic and laboratory features of 7,416 confirmed COVID-19 patients that were collected at the time of hospital admission. The proposed hierarchical CoSP model performs four-class COVID severity risk prediction into asymptomatic, mild, moderate, and severe categories. CoSP yielded better performance with good interpretability, as observed via Shapley analysis on COVID severity prediction compared to the other popular ML methods, with an area under the received operating characteristic curve (AUC-ROC) of 0.95, an area under the precision-recall curve (AUPRC) of 0.91, and a weighted F1-score of 0.83. Out of 64 initial features, 19 features were inferred as predictive of the severity of COVID-19 disease by the CoSP model. Therefore, an AI model predicting COVID-19 severity may be helpful for early intervention, optimizing resource allocation, and guiding personalized treatments, potentially enabling healthcare professionals to save lives and allocate resources effectively in the fight against the pandemic.

Analysis of Writing Styles in Bi Al-Ma'tsur's Tafsir Books

Tafsir Bi Al-Ma'tsur is explaining the meaning of the verses of the Qur'an with verses from the Qur'an or authentic Sunnah verses or the words of the companions of R.A. While the words narrated from the Tabi'in, some people classify them as al-ma'tsur on the grounds that the Tabi'in narrated from friends who studied with them, they also belong to the group of Salaf whose good words and interpretations adorn tafsir books such as the book of Ibn Jarir al- tabary and anyone who follows his method. Tafsir Bi Al-Ma'tsur existed during the time of the Companions, which was carried out by quoting interpretations from Rasulullah SAW, or from the Companions by the Companions, as well as from the Companions by the Tabi'in with a clear method of narration, this method is usually done orally. After that there was a period where the interpreters used the exegesis of the Companions' time which had been recorded and codified. At first this codification was included in the hadith books, but after tafsir became a separate scientific discipline, books were written and published specifically containing the Tafsir of Bi Al-Ma. 'tsur complete with sanad lines to the prophet Muhammad SAW, his companions, tabi'in al tabi'in.

Tensorized Label Learning on Anchor Graph

Graph-based multimedia data clustering has attracted much attention due to the impressive clustering performance for arbitrarily shaped multimedia data. However, existing graph-based clustering methods need post-processing to get labels for multimedia data with high computational complexity. Moreover, it is sub-optimal for label learning due to the fact that they exploit the complementary information embedded in data with different types pixel by pixel. To handle these problems, we present a novel label learning model with good interpretability for clustering. To be specific, our model decomposes anchor graph into the products of two matrices with orthogonal non-negative constraint to directly get soft label without any post-processing, which remarkably reduces the computational complexity. To well exploit the complementary information embedded in multimedia data, we introduce tensor Schatten p-norm regularization on the label tensor which is composed of soft labels of multimedia data. The solution can be obtained by iteratively optimizing four decoupled sub-problems, which can be solved more efficiently with good convergence. Experimental results on various datasets demonstrate the efficiency of our model.

The Application of the Discovery Learning Model in Improving Religious Understanding of Students in the Lessons of the Book of Sulam Al-Taufīq

Background: Understanding of the material of the book is difficult, it is not surprising to question whether the understanding of the material has become neglected. Therefore, the religious understanding of students must be developed by the ustāẓ in the Islamic boarding school through the learning process. This can be done using the formulation of the discovery learning model which contains a comprehensive learning procedure design.&#x0D; Purpose:. This study aims to determine the application of the discovery learning model, and the religious understanding of students using discovery learning and non-discovery learning models, as well as increasing the religious understanding of students after using discovery learning and non-discovery learning models in Class 1 Aliyah Darul Falah Islamic Boarding School and Al-Mukhtariyah Islamic Boarding School West Bandung&#x0D; Method:. The research approach used is an experimental study with a quasi-experimental type in the form of a nonequivalent pre-test and post-test control group design. The research population was students of Class 1 Aliyah Darul Falah Islamic Boarding School and Al-Mukhtariyah Islamic Boarding School, West Bandung with a sample of 106 students consisting of experimental and control classes. The research instrument used was a 38-item questionnaire, providing 20 multiple-choice questions and 5 description questions. Data were analyzed using statistical tests&#x0D; Results: The results of the research show that the discovery learning model is very suitable to be applied to the Al-Taufīq Sulam Book lesson, at the Darul Falah Islamic boarding school it got an average score of 93.65% which shows a very good interpretation value, and at the Al-Mukhtariyah Islamic boarding school, it got an average score of 93.65%. an average of 90.42% which shows a very good interpretation value. The religious understanding of students using the discovery learning model at the Darul Falah Islamic boarding school is at high criteria with an average pretest score of 52.39 and posttest 82.85 which has increased by 30.46%, at Al-Mukhtariyah Islamic boarding school it is at sufficient criteria. The average pretest score was 43.57 and posttest 75.87, which was an increase of 32.3%.&#x0D; Conclusion: Meanwhile, non-discovery learning at the Darul Falah Islamic boarding school is at sufficient criteria with an average pretest score of 58.44 and posttest of 70.22, an increase of 11.78%, at the Al-Mukhtariyah Islamic boarding school it is at sufficient criteria with an average score -average pretest 51.22 and posttest 60.65, an increase of 9.43%

Prediction on compressive strength of recycled aggregate self-compacting concrete by machine learning method

The compressive strength is generally a crucial mechanical indicator for evaluating the quality of recycled aggregate self-compacting concrete (RASCC). To obtain a reliable prediction result of the compressive strength of RASCC, machine learning methods, including artificial neural network (ANN), random tree (RT), bagging, and random forest (RF), are utilized to predict the compressive strength of RASCC in this study. To build predictive models, 18 features and 289 data samples were collected from previous literature. The prediction effects of 4 artificial intelligence (AI) models on compressive strength of RASCC are compared. Four statistical parameters were used to evaluate the performance of the models, and a comparison was made between the model-predicted results and the experimental results. A good correlation between machine learning models and experimental results was obtained. Sensitivity investigation reveals that the cement content and the apparent density of natural coarse aggregate have the greatest influence on compressive strength. The study demonstrates the potential of ANN and RF models as useful tools that can support mortar design and/or optimization, with higher accuracy and good interpretability. According to this study, machine learning regression techniques hold great potential as instruments for forecasting RASCC's compressive strength.

A multi-scale graph convolutional network with contrastive-learning enhanced self-attention pooling for intelligent fault diagnosis of gearbox

Recently, the emerging graph convolutional network (GCN) has been applied into fault diagnosis with the aim of providing additional fault features through topological information. However, there are some limitations with these methods. First, the interactions between multi-frequency scales are ignored in existing studies, while they mainly focus on constructing graphs through the relationship between channels/instances. Second, the constructed graph cannot well reflect the topology of noisy samples and lacks robust hierarchical representation learning capability, and the learned graphs have limited interpretability. Hence, a Multi-Scale GCN with Contrastive-learning enhanced Self-attention Pooling (MSGCN-CSP) method is proposed for intelligent fault diagnosis of gearbox. Time–frequency distributions are converted into multi-scale graphs to extract fault features through topological relationships between multi-frequencies. Contrastive-learning is used to implement graph pooling, which enables hierarchical representation learning. Experimental results on two gearbox datasets illustrate that the proposed method offers competitive diagnostic performance and provides good interpretability in establishing GCN.

TMH: Two-Tower Multi-Head Attention neural network for CTR prediction.

Click-through rate (CTR) prediction is a term used to predict the probability of a user clicking on an ad or item and has become a popular research area in advertising. As the volume of Internet data increases, the labor costs of traditional feature engineering continue to rise. To reduce the dependence on feature interactions, this paper proposes a fusion model that combines explicit and implicit feature interactions, called the Two-Tower Multi-Head Attention Neural Network (TMH) approach. The model integrates multiple components such as multi-head attention, residual network, and deep neural networks into an end-to-end model that automatically obtains vector-level combinations of explicit and implicit features to predict click-through rates through higher-order explicit and implicit interactions. We evaluated the effectiveness of TMH in CTR prediction through numerous experiments using three real datasets. The results demonstrate that our proposed method not only outperforms existing prediction methods but also offers good interpretability.

Research on the Interrelationship of Sustainable Development Goals Based on Multilayer Network Modeling

The Sustainable Development Goals are not just a call to action, but a vision of hope for a better world. To achieve sustainable development, it is critical to study relationship between SDGs and select the most effective priority goals. A multi-layer network approach was employed to establish a model for analyzing the interrelationships and impacts of SDGs.The ffnal model was derived by computing the Pearson correlation coefffcient matrix and network connections. The network models for 10 regions were visualized, revealing that in the WLD region, SDG8 had a positive impact on other SDGs, particularly on SDG4, while SDG17 had a negative impact on 14 SDGs.We have concluded that our model has strong robustness, high stability, and good interpretability. This provides scientiffc guidance and support for achieving the SDGs.

Interpretable Siamese dual attention enhancement transfer compound diagnostic model for unbalanced samples

The intelligent transfer diagnosis model is used to address the issue of feature drift caused by the changing working conditions of rotating parts in engineering. However, few models can perform transfer diagnosis on multiple unbalanced samples of rotating parts simultaneously, and even fewer models can visually enhance the domain-invariant features, making them more interpretable. To address these issues, we propose a novel interpretable Siamese dual attention enhancement transfer compound diagnosis model for unbalanced samples. The model can diagnose multiple rotating parts simultaneously and consists of a channel feature attention enhancement (CFAE) network, a fragment feature attention enhancement (FFAE) network, and a Siamese feature fusion (SFF) network. The CFAE network enhances features of different convolutional channels, the FFAE network improves segment features in various frequency domains, and the SFF network extracts domain-invariant features of diverse rotating components under varying working conditions. The model is validated using bearing fault data collected under different loads and planetary gear fault data obtained at varying speeds. Its diagnostic accuracy remains above 96.4%, and the diagnostic variance is controlled within 1.0%. The model has good interpretability for imbalanced sample domain-invariant features, providing an effective tool for interpretable transfer diagnosis in this compound engineering situation.

A New Automated Prognostic Prediction Method Based on Multi-Sequence Magnetic Resonance Imaging for Hepatic Resection of Colorectal Cancer Liver Metastases.

Colorectal cancer is a prevalent and life-threatening disease, where colorectal cancer liver metastasis (CRLM) exhibits the highest mortality rate. Currently, surgery stands as the most effective curative option for eligible patients. However, due to the insufficient performance of traditional methods and the lack of multi-modality MRI feature complementarity in existing deep learning methods, the prognosis of CRLM surgical resection has not been fully explored. This paper proposes a new method, multi-modal guided complementary network (MGCNet), which employs multi-sequence MRI to predict 1-year recurrence and recurrence-free survival in patients after CRLM resection. In light of the complexity and redundancy of features in the liver region, we designed the multi-modal guided local feature fusion module to utilize the tumor features to guide the dynamic fusion of prognostically relevant local features within the liver. On the other hand, to solve the loss of spatial information during multi-sequence MRI fusion, the cross-modal complementary external attention module designed an external mask branch to establish inter-layer correlation. The results show that the model has accuracy (ACC) of 0.79, the area under the curve (AUC) of 0.84, C-Index of 0.73, and hazard ratio (HR) of 4.0, which is a significant improvement over state-of-the-art methods. Additionally, MGCNet exhibits good interpretability.

CODENET: A deep learning model for COVID-19 detection

Conventional COVID-19 testing methods have some flaws: they are expensive and time-consuming. Chest X-ray (CXR) diagnostic approaches can alleviate these flaws to some extent. However, there is no accurate and practical automatic diagnostic framework with good interpretability. The application of artificial intelligence (AI) technology to medical radiography can help to accurately detect the disease, reduce the burden on healthcare organizations, and provide good interpretability. Therefore, this study proposes a new deep neural network (CNN) based on CXR for COVID-19 diagnosis – CodeNet. This method uses contrastive learning to make full use of latent image data to enhance the model's ability to extract features and generalize across different data domains. On the evaluation dataset, the proposed method achieves an accuracy as high as 94.20%, outperforming several other existing methods used for comparison. Ablation studies validate the efficacy of the proposed method, while interpretability analysis shows that the method can effectively guide clinical professionals. This work demonstrates the superior detection performance of a CNN using contrastive learning techniques on CXR images, paving the way for computer vision and artificial intelligence technologies to leverage massive medical data for disease diagnosis.

Reduced Rank Spatio-temporal Models

To simultaneously model the cross-sectional dependency and dynamic time dependency among n units, most research in spatial econometrics parameterizes the coefficient matrices among the n units as functions of known weights matrices. This modeling framework is over-simplified and faces the risk of misspecification when constructing the weights matrices. In this article, we propose a novel reduced-rank spatio-temporal model by assuming the coefficient matrices follow a reduced-rank structure. This specification avoids construction of the weights matrices and provides a good interpretation, especially for financial data. To estimate the unknown parameters, a quasi-maximum likelihood estimator (QMLE) is proposed and obtained via the Gradient descent algorithm with Armijo line search. We establish the asymptotic properties of QMLE when the number of units and the number of time periods both diverge to infinity. To determine the rank, we propose a ridge-type ratio estimator and demonstrate its rank selection consistency. The proposed methodology is illustrated via extensive simulation studies. Finally, a Chinese stock dataset is analyzed to investigate the cross-sectional and temporal spillover effects among stock returns.

Critical Review of Postcolonial Theory of Homi Bhabha’s Hybridity: A Study of “The Location of Culture”

Homi K. Bhabha's The Location of Culture, published in 1994, is one of the foundational texts of the branch of literary theory known as postcolonialism. Although postcolonialism has many facets, the central question lies in the interpretation and understanding of the encounters between the Western colonial powers and the nations of the world to which they belong, and colonization is not only an economic, military or political process but also a process that profoundly affects cultures and identities around the world. This is an area in which interpretation takes centre stage, and its strength depends in large part on its ability to address the complex legacy of colonial encounters with careful and constant attention to the significance of the marks they left on colonial cultures. What Bhabha do writings show, like so much other postcolonial thought, is that the art of clarification and definition underpinning good interpretation is rarely the same as simplification. Indeed, making good interpretations often involves pointing out and dividing the different types of complexity going on within a single process or term. For Bhabha, the main object is identity, as embodied in the idea of colonial powers. According to his interpretation, what at first glance appears to be the cohesive set of ideas behind colonialism quickly breaks down into a complex mass of shifting views – creating something much closer to postcolonial thought than it might seem at first glance.

Analisis Respon Siswa Pada Pembelajaran Biologi Kelas X SMA Negeri 3 Siak Hulu

This research is motivated by problems that arise in the learning process. This research aims to reveal students' responses to biology learning. The subjects of this research were students of SMAN 3 Siak Hulu. The research population was class X of SMAN 3 Siak Hulu, more specifically classes X4 and X5. The sample in this study consisted of 40 students from 2 different classes selected through random sampling techniques. The data collected is the result of distributing an online questionnaire using Google Form. The results of the research show that student learning motivation in biology subjects produces an average percentage of 95.4% with very good interpretation criteria.

A revisit of the normalized eight-point algorithm and a self-supervised deep solution

The normalized eight-point algorithm has been widely viewed as the cornerstone in two-view geometry computation, where the seminal Hartley’s normalization has greatly improved the performance of the direct linear transformation algorithm. A natural question is, whether there are and how to find other normalization methods that can further improve the performance for each input sample. In this paper, we provide a novel perspective and propose two contributions to this fundamental problem: (1) we revisit the normalized eight-point algorithm and make a theoretical contribution by presenting the existence of different and better normalization algorithms; (2) we introduce a deep convolutional neural network with a self-supervised learning strategy for normalization. Given eight pairs of correspondences, our network directly predicts the normalization matrices, thus learning to normalize each input sample. Our learning-based normalization module can be integrated with both traditional (e.g., RANSAC) and deep learning frameworks (affording good interpretability) with minimal effort. Extensive experiments on both synthetic and real images demonstrate the effectiveness of our proposed approach.