Interpretation Ability Research Articles

Differentiable modeling for soil moisture retrieval by unifying deep neural networks and water cloud model

Machine learning has been widely used in high-spatial-resolution surface soil moisture (SSM) retrieval studies, but in recent years, this purely data-driven retrieval method has been controversial due to its lack of physical interpretability and generalization ability. Physical retrieval models based on the theory of radiative transfer equations respect physical laws, but their retrieval accuracy is usually affected by many insufficient accurate inputs, the complex model structure, and parameter adjustment method. In order to explore the retrieval method of unifying these two types of models, in this study, a differentiable model (DM) was constructed to realize the soil moisture retrieval at 10 m resolution based on Sentinel data. The differentiable soil moisture retrieval model takes the water cloud model (WCM) as the skeleton, and united the WCM and neural networks by implementing differentiable programming of the WCM in a machine learning platform. The differentiability makes the retrieval model trained by the gradient descent method the same as the neural network, which allows the retrieval model to be physical while obtaining more accurate retrieval results. Luan River Basin, Shandian River Basin, Maqu, and Lake Tahoe study areas with various land cover types and climate types were selected for model evaluation, and the performances of DM were close to that of the random forest model with Pearson correlation coefficient (R) of 0.747, 0.853, 0.838 and 0.792 in four study areas, respectively. While in the assessment of extrapolation capability of retrieval models, the DM showed its strong generalization ability and retrieval performance that exceeded that of the other retrieval models, with R of 0.786, unbiased root mean square error (ubRMSE) of 5.523 vol% and bias of 0.054 vol%. The DM synthesizes the advantages of both physical and machine learning models while providing high-resolution SSM estimates with acceptable accuracy for the study areas. This study creates favorable conditions for the realization of large-scale soil moisture retrieval with high resolution and high accuracy, and provides new ideas for the combination of machine learning and physical knowledge in other retrieval studies.

Pragmatic Markers in Spoken Discourse

The roles, functions, and effects of pragmatic markers (PMs) in spoken discourse are explored in this study, with a focus on how language learners’ comprehension skills, classification and interpretation abilities, and interactions between verbal and non-verbal PMs are affected. A combination of quantitative and qualitative procedures was employed in this investigation. To evaluate how well PMs in spoken discourse were identified and understood, level 4, English Language Unit, Preparatory Studies Centre fifty participants from the University of Technology and Applied Sciences, Salalah, the Sultanate of Oman completed fifteen quick audio samples with a range of pragmatic characteristics, five additional filler audio segments, and pre-and post-test questionnaires. The study discovered that learners' comprehension of PMs—which regulate discourse structure, convey speaker purpose, and manage conversation flow—improved dramatically with targeted instruction. It emphasized the significance of PMs in the development of communication skills as well as the problems with categorizing PMs due to a lack of a standardized framework.

Software Defect Prediction Using Deep Q-Learning Network-Based Feature Extraction

Machine learning-based software defect prediction (SDP) approaches have been commonly proposed to help to deliver high-quality software. Unfortunately, all the previous research conducted without effective feature reduction suffers from high-dimensional data, leading to unsatisfactory prediction performance measures. Moreover, without proper feature reduction, the interpretability and generalization ability of machine learning models in SDP may be compromised, hindering their practical utility in diverse software development environments. In this paper, an SDP approach using deep Q-learning network (DQN)-based feature extraction is proposed to eliminate irrelevant, redundant, and noisy features and improve the classification performance. In the data preprocessing phase, the undersampling method of BalanceCascade is applied to divide the original datasets. As the first step of feature extraction, the weight ranking of all the metric elements is calculated according to the expected cross-entropy. Then, the relation matrix is constructed by applying random matrix theory. After that, the reward principle is defined for computing the Q value of Q-learning based on weight ranking, relation matrix, and the number of errors, according to which a convolutional neural network model is trained on datasets until the sequences of metric pairs are generated for all datasets acting as the revised feature set. Various experiments have been conducted on 11 NASA and 11 PROMISE repository datasets. Sensitive analysis experiments show that binary classification algorithms based on SDP approaches using the DQN-based feature extraction outperform those without using it. We also conducted experiments to compare our approach with four state-of-the-art approaches on common datasets, which show that our approach is superior to these methods in precision, F-measure, area under receiver operating characteristics curve, and Matthews correlation coefficient values.

The content optimization of supplementary cementitious materials in coral sand-seawater cement mortar: A focus on mechanical properties and transportation costs

This study examines how supplementary cementitious materials (SCMs) such as fly ash (FA), blast furnace slag (BFS), and metakaolin (MK) affect the mechanical properties and transportation costs of coral sand-seawater cement mortar (CSSC). The Dinger-Funk equation was used to obtain the most densely packed design and preparation of coral sand and cementitious materials. The mechanical properties of CSSC were assessed utilizing the RMT testing apparatus. A thorough examination of the mechanical properties and transportation costs of CSSC was undertaken using the principle of value engineering and the effectiveness coefficient approach. Research results show that BFS10 has outstanding mechanical qualities in the binary cementitious system. Within the ternary cementitious system, the mechanical qualities typically exceed those of the binary system, with FA15BFS15 demonstrating the highest performance. The best appropriate mix ratio is FA15BFS15, as determined by a thorough examination and cost-benefit analysis. This ratio offers temporal sensitivity and maximized transit capacity. The SVR model is highly proficient in forecasting the compressive strength of CSSC, showcasing accurate prediction and data interpretation abilities. The research findings provide practical evidence for optimizing the proportion of CSSC in calcium sulfoaluminate cement, considering transportation expenses and algorithm prediction needs.

Mothers' negative focus during memory‐sharing conversations is linked to negative interpretation and memory biases in young children

AbstractParent‐guided reminiscing helps children learn how to interpret and recollect personal experiences. These interpretive abilities are important because many experiences are ambiguous, and a tendency toward negative interpretation is associated with emotional disorders. Here, we explore whether naturally‐occurring variations in parent‐guided reminiscing are associated with children's interpretation and recall of novel ambiguous events. Mothers and their children (aged 5–6 years) reminisced about three shared negative events. Next, children were read several stories that described ambiguous social situations and were asked to invent endings that involved making an inference about motives of others in the stories. Later, children were asked questions to elicit story recall. Mothers who used more negative terms during reminiscing had children who were more likely to invent negative story endings and distort story recall negatively. Thus, mothers who frame memory‐sharing conversations with children negatively might put them at risk for developing negative interpretation and memory biases.

Combinatorial optimization of C4 olefin production conditions based on interpretable LSSVM&TPE

Due to the complexity of the products from the ethanol coupling reaction, the C4 olefin yield tends to be low. Finding the optimal ethanol reaction conditions requires repeated manual experiments. In this paper, a novel learning framework based on least squares support vector machine and tree-structured parzen estimator is proposed to solve the optimization problem of C4 olefin production conditions. And shapley value is introduced to improve the interpretation ability of modeling method. The experimental results show that the proposed learning framework can obtain the combination of ethanol reaction conditions that maximized the C4 olefin yield It is nearly 17.30% higher compared to the current highest yield of 4472.81% obtained from manual experiments.

“The Third Notebook of Travels” by Liudmyla Fedorova-Kohanska as an example of a bandurist’s concert repertoire

Statement of the problem. One of the central problems faced by the modern bandurа performer is the insufficient amount of current repertoire that would correspond to modern musical trends and, at the same time, the audience’s preferences. In order to solve the problem of updating the repertoire of a modern bandura player, it is important to attract in the performance practice the works by modern Ukrainian composers. The article examines the instrumental cycle for solo bandura titled “The Third Notebook of Travels” by Ukrainian composer Liudmyla Fedorova-Kohanska. The focus is on identifying important artistic and technical principles that play a significant role in the professional development of modern academic bandura players. The recent research and publications show that there is limited literature analyzing contemporary compositions for the bandura, particularly those by Liudmyla Fedorova-Kohanska. Prior research has primarily focused on traditional repertoires and techniques, leaving a gap in understanding the contribution of modern works to the evolution of bandura performance. Objectives, methods, and novelty of the study. The study aims to determine the artistic and pedagogical significance of “The Third Notebook of Travels” within the context of the repertoire needs of bandura players. By analyzing this cycle, the research seeks to highlight its impact on enhancing performance skills and its importance in the academic training of bandura musicians. The first scientific understanding of the cycle and its introduction into the musicological and, importantly, performance circulation determines the relevance and the novelty of the research topic. The study offers a novel perspective on the work`s role in developing comprehensive musicianship of a bandure player, including technical proficiency and interpretative abilities. The study employs a detailed analytical approach, examining the musical structure, thematic development, and technical requirements of the cycle. Results and conclusion. The analysis reveals that performing “The Third Notebook of Travels” as an entire cycle is crucial for developing bandura players’ artistry. It enhances their technical skills, endurance, and large-scale musical thinking. The cycle’s diverse technical demands and expressive range make it an essential component of the modern bandura repertoire, fostering a deeper understanding of contemporary Ukrainian music. “The Third Notebook of Travels” by Liudmyla Fedorova-Kohanska significantly contributes to the professional growth of bandura players. Its inclusion in academic programs can enhance the pedagogical framework, providing students with challenging and enriching repertoire. This cycle not only advances technical skills but also cultivates interpretative depth and musical versatility

Action Research on the Cultivation of Critical Thinking Ability in Cross-cultural English Teaching in Chinese Higher Vocational

In recent years, the English teaching reform in higher vocational colleges in China has gradually integrated heuristic teaching methods. However, a notable issue has emerged: students’ deficiency in critical thinking skills. This study aims to enhance the critical thinking skills of higher vocational students in China through action research. The research includes four cycles of teaching practice to improve students’ critical thinking ability in terms of analysis, evaluation, reasoning, and self-adjustment. Through the task design, the researcher promotes students’ in-depth thinking and critical analysis in cross-cultural English classes. It was found that vocational students made noticeable progress in the 16-week training process, as reflected by the changes in interpretation and analysis abilities and attitudes towards culture. These results provide valuable experience and enlightenment for English teaching in higher vocational colleges and emphasise the importance of cultivating students’ critical thinking ability to promote their development in academic and professional fields.

Computer Modeling Analysis of Electric Vehicle's Choice Behavior Considering Latent Variables

At present, there are few researches on the influence of psychological latent variables on the choice behavior of electric vehicles, and lack of consideration of individual heterogeneity. In this study, computer modeling was used to construct not only a traditional discrete choice model that takes into account individual heterogeneity, but also a hybrid choice model,which takes into account psychological latent variables are constructed to explore the mutual effects of observable personal attributes, vehicle attributes and difficult to directly observe psychological latent variables on consumers’ choice behavior of electric vehicles. The estimation results of hybrid choice model with psychological latent variables and the traditional discrete choice model without considering psychological latent variables are compared. The result show that perceived usefulness, perceived risk and purchasing attitude have a significant impact on consumers’ choice behavior of electric vehicles. Compared with traditional discrete choice model, the hybrid choice model, which takes into account psychological latent variables has significantly higher prediction accuracy and has better interpretation ability and fitting effect. The research results can provide theoretical support for further expanding the electric vehicle market and formulating relevant policieshe usage of the word Power quality in recent times acquired intensified interest due to the complex industrial processes. The usage of intelligent tools to improve power quality is increasing day by day, as assumption of present day power system as a linear model is unsatisfactory. This paper deals with analysis of Differential Evolution (DE), Hybrid Differential Evolution (HDE) and Variable Scaling Hybrid Differential Evolution for harmonic reduction in the source current with optimal tuning of PI controller gain values. Shunt Active power Filter is one of the better solution to suppress the source current harmonics which are induced into power system because of nonlinear loads. Current controller called HBCC is considered for gating operation of switches in Voltage Source Inverter. The Intelligent tuned PQ theory is used for reference current generation. The then obtained compensating currents are injected at point of common coupling for current disturbance mitigation. Simulations of MATLAB/SIMULINK environment of the present work shows the efficacy.

Mesh-Agnostic Decoders for Supercritical Airfoil Prediction and Inverse Design

Mesh-agnostic models have advantages in terms of processing unstructured spatial data and incorporating partial differential equations. Recently, they have been widely studied for constructing physics-informed neural networks, but they need to be trained on a case-by-case basis and require long training times. On the other hand, fast prediction and design tools are desired for aerodynamic shape designs, and data-driven mesh-based models have achieved great performance. Therefore, this paper proposes a data-driven mesh-agnostic decoder that combines the fast prediction ability of data-driven models and the flexibility of mesh-agnostic models. The model is denoted by an implicit decoder, which consists of two subnetworks, i.e., ShapeNet and HyperNet. ShapeNet is based on implicit neural representation, and HyperNet is a simple neural network. The implicit decoder is trained for the fast prediction of supercritical airfoils. Different activation functions are compared, and a spatial constraint is proposed to improve the interpretability and generalization ability of the model. Then, the implicit decoder is used together with a mesh-based encoder to build a generative model, which is used for the inverse design of supercritical airfoils with specified physical features.

Developmental Language Disorder: Do Speech and Language Therapies Help to Address the Problem?

Developmental language disorder (DLD) is a common language disorder affecting children (Laasonen et al., 2018). A child suffers from the disorder when the child exhibits difficulty in learning, understanding, and using a language. The disorder thus affects various aspects of a child’s development process, particularly those relating to speaking, listening, reading, and writing. As a language disorder, DLD affects the ability of a child to communicate due to difficulty in expressing meaning or interpreting communication from others. DLD can either be receptive, expressive, or both. A child suffers from receptive language disorder if they find it difficult to understand the meaning of the words used by others. It is expressive if the child finds it difficult to find the right words to help him/her convey meaning through talking. Based on its nature, several indicators can help show that a child suffers from DLD (Laasonen et al., 2018). Some of the common indicators include delayed ability to put words together to construct sentences, difficulty in learning new words and engaging in a conversation with peers, and general difficulty in following instructions due to poor interpretive ability to communicate messages.

Hubungan Motivasi Belajar dan Kecemasan Berbahasa terhadap Keterampilan Mengalihbahasakan Bahasa Korea-Indonesia

This study aims to determine the correlation between learning motivation and language anxiety with the ability to interpretation Korean-Indonesian. Correlation and ex-post facto research were used in this quantitative study. This research is completed by 36 undergraduate 4th year students of the Korean Education Study Program in Indonesia University of Education who had completed Korean for Science Technology course. The Likert-scale questionnaire on learning motivation using indicators of learning motivation (Uno, 2018), language anxiety using aspects of language anxiety (Horwitz, 1986), were used to collect the data for this research. Document analysis was used to analyze their final score in Korean for Science Technology course. The research results showed that there is a positive and significant correlation between learning motivation and Korean-Indonesian language interpretation ability, there is a significant negative relationship between language anxiety and Korean-Indonesian interpretation ability, there is a positive and not significant correlation simultaneously learning motivation and language anxiety with Korean-Indonesian interpretation ability. Learning motivation and language anxiety are the inner variable that functions as a stimulus and gives an effect on the students ability.

Characterizing multimorbidity in ALIVE: comparing single and ensemble clustering methods.

Multimorbidity, defined as having 2 or more chronic conditions, is a growing public health concern, but research in this area is complicated by the fact that multimorbidity is a highly heterogenous outcome. Individuals in a sample may have a differing number and varied combinations of conditions. Clustering methods, such as unsupervised machine learning algorithms, may allow us to tease out the unique multimorbidity phenotypes. However, many clustering methods exist, and choosing which to use is challenging because we do not know the true underlying clusters. Here, we demonstrate the use of 3 individual algorithms (partition around medoids, hierarchical clustering, and probabilistic clustering) and a clustering ensemble approach (which pools different clustering approaches) to identify multimorbidity clusters in the AIDS Linked to the Intravenous Experience cohort study. We show how the clusters can be compared based on cluster quality, interpretability, and predictive ability. In practice, it is critical to compare the clustering results from multiple algorithms and to choose the approach that performs best in the domain(s) that aligns with plans to use the clusters in future analyses.

Interpretable Cognitive Ability Prediction: A Comprehensive Gated Graph Transformer Framework for Analyzing Functional Brain Networks.

Graph convolutional deep learning has emerged as a promising method to explore the functional organization of the human brain in neuroscience research. This paper presents a novel framework that utilizes the gated graph transformer (GGT) model to predict individuals' cognitive ability based on functional connectivity (FC) derived from fMRI. Our framework incorporates prior spatial knowledge and uses a random-walk diffusion strategy that captures the intricate structural and functional relationships between different brain regions. Specifically, our approach employs learnable structural and positional encodings (LSPE) in conjunction with a gating mechanism to efficiently disentangle the learning of positional encoding (PE) and graph embeddings. Additionally, we utilize the attention mechanism to derive multi-view node feature embeddings and dynamically distribute propagation weights between each node and its neighbors, which facilitates the identification of significant biomarkers from functional brain networks and thus enhances the interpretability of the findings. To evaluate our proposed model in cognitive ability prediction, we conduct experiments on two large-scale brain imaging datasets: the Philadelphia Neurodevelopmental Cohort (PNC) and the Human Connectome Project (HCP). The results show that our approach not only outperforms existing methods in prediction accuracy but also provides superior explainability, which can be used to identify important FCs underlying cognitive behaviors.

ChatGPT in dentomaxillofacial radiology education

Aims: Artificial intelligence refers to the ability of computer systems or machines to perform cognitive functions and tasks that are similar to humans’. The aim of this study is to assess the knowledge and interpretative abilities of ChatGPT-versions by administering a dentomaxillofacial-radiology exam, comparing its performance with that of dentistry-students in Türkiye, and questioning the effectiveness of different languages.
 Methods: It is a descriptive research comparing the data of ChatGPT versions 3.5 and 4 in both Turkish and English.
 Results: Firstly 20 test-questions were evaluated. There is a significant difference(p

Symbolic Cognitive Diagnosis via Hybrid Optimization for Intelligent Education Systems

Cognitive diagnosis assessment is a fundamental and crucial task for student learning. It models the student-exercise interaction, and discovers the students' proficiency levels on each knowledge attribute. In real-world intelligent education systems, generalization and interpretability of cognitive diagnosis methods are of equal importance. However, most existing methods can hardly make the best of both worlds due to the complicated student-exercise interaction. To this end, this paper proposes a symbolic cognitive diagnosis~(SCD) framework to simultaneously enhance generalization and interpretability. The SCD framework incorporates the symbolic tree to explicably represent the complicated student-exercise interaction function, and utilizes gradient-based optimization methods to effectively learn the student and exercise parameters. Meanwhile, the accompanying challenge is that we need to tunnel the discrete symbolic representation and continuous parameter optimization. To address this challenge, we propose to hybridly optimize the representation and parameters in an alternating manner. To fulfill SCD, it alternately learns the symbolic tree by derivative-free genetic programming and learns the student and exercise parameters via gradient-based Adam. The extensive experimental results on various real-world datasets show the superiority of SCD on both generalization and interpretability. The ablation study verifies the efficacy of each ingredient in SCD, and the case study explicitly showcases how the interpretable ability of SCD works.

Traceability of Microplastic Fragments from Waste Plastic Express Packages Using Near-Infrared Spectroscopy Combined with Chemometrics.

The pollution from waste plastic express packages (WPEPs), especially microplastic (MP) fragments, caused by the blowout development of the express delivery industry has attracted widespread attention. On account of the variety of additives, strong complexity, and high diversity of plastic express packages (PEPs), the multi-class classification of WPEPs is a typical large-class-number classification (LCNC). The traceability and identification of microplastic fragments from WPEPs is very challenging. An effective chemometric method for large-class-number classification would be very beneficial for the comprehensive treatment of WPEP pollution through the recycling and reuse of waste plastic express packages, including microplastic fragments and plastic debris. Rather than using the traditional one-against-one (OAO) and one-against-all (OAA) dichotomies, an exhaustive and parallel half-against-half (EPHAH) decomposition, which overcomes the defects of the OAO's classifier learning limitations and the OAA's data proportion imbalance, is proposed for feature selection. EPHAH analysis, combined with partial least squares discriminant analysis (PLS-DA) for large-class-number classification, was performed on 750 microplastic fragments of polyethylene WPEPs from 10 major courier companies using near-infrared (NIR) spectroscopy. After the removal of abnormal samples through robust principal component analysis (RPCA), the root mean square error of cross-validation (RMSECV) value for the model was reduced to 0.01, which was 21.5% lower than that including the abnormal samples. The best models of PLS-DA were obtained using SNV combined with SG-17 smoothing and 2D (SNV+SG-17+2D); the latent variables (LVs), the error rates of Monte Carlo cross-validation (ERMCCVs), and the final classification accuracies were 6.35, 0.155, and 88.67% for OAO-PLSDA; 5.37, 0.103, and 87.33% for OAA-PLSDA; and 3.12, 0.054, and 96.00% for EPHAH-PLSDA. The results showed that the EPHAH strategy can completely learn the complex LCNC decision boundaries for 10 classes, effectively break the tie problem, and greatly improve the voting resolution, thereby demonstrating significant superiority to both the OAO and OAA strategies in terms of classification accuracy. Meanwhile, PLS-DA further maximized the covariance and data interpretation abilities between the potential variables and categories of microplastic debris, thereby establishing an ideal performance identification model with a recognition rate of 96.00%.

The Application and Development of Image Recognition Technology in the Field of Computer Vision

Image recognition is an important field of computer vision research. With the emergence of convolutional neural networks, image recognition has rapidly developed in many fields and has entered people's daily lives. This article reviews image recognition applications and future prospects in three representative fields: healthcare, intelligent driving, and security monitoring. In medical image analysis, image recognition technology can improve medical image interpretation speed and accuracy by automatically learning image features, providing doctors with more comprehensive information and decision-making support. Regarding intelligent driving, image recognition can help vehicles perceive and understand the traffic environment in real time, improving driving safety and automation level. In terms of security monitoring, image recognition plays a vital role in facial recognition, object detection, and behavior analysis, providing intelligent monitoring and security guarantees. However, these areas still have challenges, such as large data volumes, labeling difficulties, and privacy issues. In the future, people can look forward to combining image recognition technology with other technologies to improve models' interpretability and decision-making ability and further promote the development of these fields.

Fortune favors the invariant: Enhancing GNNs’ generalizability with Invariant Graph Learning

Generalizable and transferrable graph representation learning endows graph neural networks (GNN) with the ability to extrapolate potential test distributions. Nonetheless, current endeavors recklessly ascribe the demoralizing performance on a single entity (feature or edge) distribution shift and resort to uncontrollable augmentation. By inheriting the philosophy of Invariant graph learning (IGL), which characterizes a full graph as an invariant core subgraph (rationale) and a complementary trivial part (environment), we propose a universal operator termed InMvie to release GNN’s out-of-distribution generation potential. The advantages of our proposal can be attributed to two main factors: the comprehensive and customized insight on each local subgraph, and the systematical encapsulation of environmental interventions. Concretely, a rationale miner is designed to find a small subset of the input graph — rationale, which injects the model with feature invariance while filtering out the spurious patterns, i.e., environment. Then, we utilize systematic environment intervention to ensure the out-of-distribution awareness of the model. Our InMvie has been validated through experiments on both synthetic and real-world datasets, proving its superiority in terms of interpretability and generalization ability for node classification over the leading baselines.

Predicting Chinese stock market using XGBoost multi-objective optimization with optimal weighting.

The application of artificial intelligence (AI) technology in various fields has been a recent research hotspot. As a representative technology of AI, the specific application of machine learning models in the field of economics and finance undoubtedly holds significant research value. This article proposes Extreme Gradient Boosting Multi-Objective Optimization Model with Optimal Weights (OW-XGBoost) to comprehensively balance the returns and risks of investment portfolios. The model utilizes fusing label with optimal weights to achieve multi-objective tasks, effectively controlling the impact of various risk and return indicators on the model, thus improving the interpretability and generalization ability of the model. In the experiments, we tested the model using China A-share data from October 2022 to April 2023 and conducted a series of robustness tests. The results indicate that: (1) The OW-XGBoost outperforms the XGBoost Model with Yield as Label (YL-XGBoost), XGBoost Multi-Label Classification Model (MLC-XGBoost) in controlling risk or achieving returns. (2) OW-XGBoost performs better overall compared to baseline models. (3) The robustness tests demonstrate that the model performs well under different market conditions, stock pools, and training set durations. The model performs best in moderately fluctuating stock markets, stock pools comprising high market value stocks, and training set durations measured in months. The methodology and results of this study provide a new perspective and approach for fundamental quantitative investment and also create new possibilities and avenues for the integration of AI, machine learning, and financial quantitative research.