Augmented Model Research Articles

CMC/SWCNT biocomposites: A combined study on experiments, molecular simulations and continuum models

A comprehensive study is carried out including experimental, molecular dynamics (MD) simulations and continuum modelling of Carboxymethyl cellulose/Single walled carbon nanotube (CMC/SWCNT) biocomposites. The electrical, optical, and mechanical properties of CMC/SWCNT biocomposites were investigated in the experimental part of this work. In the result of measurements, it was determined that electrical conductivity (σdc), absorbance level (A) and tensile modulus (E) of the composites increased significantly with the increase of SWCNT content in the CMC matrix. These physical changes in the CMC/SWCNT composites were explained by the percolation theory and the electrical and optical percolation thresholds (Rσ and Rop) and the critical exponents (βσ and βop) of these composites were calculated. In addition, MD simulations were performed to estimate the material properties for the polymer composite structures. The results of the tensile test experiments were found to qualitatively overlap with the experiments at low concentration range. Moreover, a homogenous distribution of SWCNTs were observed in the CMC matrix together with a strong level of interactions in between. In the continuum modelling a two parameters augmentation model is used. A coupled Mori-Tanaka-self consistent method is utilized when obtaining effective properties of composites. Experimental, MD and continuum modelling results of composites were compared and reasonable agreement was obtained between results.

Navigating the Landscape of Precision Education: Insights From On-the-Ground Initiatives.

A central goal of precision education (PE) is efficiently delivering the right educational intervention to the right learner at the right time. This can be achieved through a PE cycle that involves gathering inputs, using analytics to generate insights, planning and implementing interventions, learning and assessing outcomes, and then using lessons learned to inform modifications to the cycle. In this paper, the authors describe 3 PE initiatives utilizing this cycle. The Graduate Medical Education Laboratory (GEL) uses longitudinal data on graduate trainee behavior, clinical skills, and wellness to improve clinical performance and professional fulfillment. The Transition to Residency Advantage (TRA) program uses learner data from medical school coupled with individualized coaching to improve the transition to residency. The Anesthesia Research Group for Educational Technology (TARGET) is developing an automated tool to deliver individualized education to anesthesia residents based on a longitudinal digital representation of the learner. The authors discuss strengths of the PE cycle and transferrable learnings for future PE innovations. Common challenges are identified, including related to data (e.g., volume, variety, sharing across institutions, using the electronic health record), analytics (e.g., validating augmented intelligence models), and interventions (e.g., scaling up learner assessments with limited resources). PE developers need to share their experiences in order to overcome these challenges, develop best practices, and ensure ethical development of future systems. Adapting a common framework to develop and assess PE initiatives will lead to a clearer understanding of their impact, help to mitigate potential risks, and allow deployment of successful practices on a larger scale.

Institutional quality and emigration nexus: Empirical evidence from Türkiye

AbstractThis study attempts to fill an important gap in the empirical literature by investigating the impact of institutional quality in destination countries on emigrants from Türkiye using bilateral migration data from 2010 through 2020. For this purpose, the study builds an augmented gravity model, including economic, geographic, and cultural variables in an exponential form and estimates it by the Poisson Pseudo Maximum Likelihood (PPML) method. Empirical results significantly confirm the pulling role of strong institutions in destination countries for emigrants from Türkiye since all institutional quality indicators are positively associated with emigrant movements, albeit just one of them, regulatory quality, is statistically insignificant. Among indicators of institutional quality, the most pulling ones for emigrants are voice and accountability and the rule of law, followed by government effectiveness, control of corruption, and political stability and absence of violence, respectively. Overall results indicate that institutions are front‐line players in the emigrants' migration decision and destination choice process. In this context, policy‐makers in both Türkiye and the destination country may implement an institutional policy considering the outcomes stemming from migration movements.

The impact of China’s One-Belt One-Road initiative on international trade and global value chains

ABSTRACT This study examines the potential effects of China’s ‘One-Belt One-Road’ initiative (OBOR) on trade flows and global value chain (GVC) connections. The empirical analysis is based on the augmented trade gravity model, which comprises 186 economies and 199 of their partners from 2000 to 2018. We also estimate the gravity model for involvement in GVC (domestic value added in intermediate exports, foreign value added in exports, and one country’s contributed value in another’s total exports). OBOR proves to be positively correlated with international trade and GVC, while some corridors seem to benefit more than others (e.g. China-Pakistan, China-Mongolia-Russian Federation, and Bangladesh-China-India-Myanmar).

Augmenting Three-Dimensional Model Annotation System with Enhanced Reality

This study proposes an augmented reality-based three-dimensional model annotation system, integrating cloud anchors, three-dimensional reconstruction, and augmented reality technology to achieve explicit three-dimensional annotations on models. Employing an improved ORB algorithm, the annotated model is persistently anchored in three-dimensional space through cloud anchors, presenting accurate spatial information and showcasing the depth of scenes and relationships between elements. The system supports multiple data types for annotations, such as text and images. Through a comparison with traditional two-dimensional annotation in a drone experiment, the system demonstrates higher experimental efficiency, providing more intuitive annotation guidance and enhancing remote guidance efficiency and user understanding of drones.

Pengembangan Lembar Kerja Peserta Didik (LKPD) dengan Model Discovery Learning Berbasis Augmented Reality pada Materi Ikatan Kimia untuk Meningkatkan Motivasi dan Hasil Belajar Siswa

This research aims to: (1) produce student worksheets with an augmented reality-based discovery learning model on chemical bond material that is appropriate for increasing student motivation and learning outcomes; (2) determine the effectiveness of Student Worksheets with augmented reality-based discovery learning models on chemical bond material in increasing student motivation and learning outcomes. This development research uses a 4D development model including the Define, Design, Development and Disseminate stages. The trial was carried out on Grade X Science students at SMA Sejahtera 1 Depok with a quasi-experimental design, nonequivalent control group design model. The research instruments used were validation sheets, learning motivation questionnaires and learning outcomes questions. The research results show that: (1) student worksheets with augmented reality based discovery learning model on chemical bonding material that has been developed has very decent quality, which can be proven by the results of the average validation value by material experts of 3.926, media experts of 3.969 and student responses of 3.93; (2) student worksheets with a discovery learning model based on augmented reality is effective in increasing student motivation and learning outcomes with the MANOVA test which obtained a significance value of 0.000 and had an effective contribution of 23.3%.

Text data augmentation and pre-trained Language Model for enhancing text classification of low-resource languages.

In the domain of natural language processing (NLP), the development and success of advanced language models are predominantly anchored in the richness of available linguistic resources. Languages such as Azerbaijani, which is classified as a low-resource, often face challenges arising from limited labeled datasets, consequently hindering effective model training. The primary objective of this study was to enhance the effectiveness and generalization capabilities of news text classification models using text augmentation techniques. In this study, we solve the problem of working with low-resource languages using translations using the Facebook mBart50 model, as well as the Google Translate API and a combination of mBart50 and Google Translate thus expanding the capabilities when working with text. The experimental outcomes reveal a promising uptick in classification performance when models are trained on the augmented dataset compared with their counterparts using the original data. This investigation underscores the immense potential of combined data augmentation strategies to bolster the NLP capabilities of underrepresented languages. As a result of our research, we have published our labeled text classification dataset and pre-trained RoBERTa model for the Azerbaijani language.

Data Augmentation and Large Language Model for Legal Case Retrieval and Entailment

Data Augmentation and Large Language Model for Legal Case Retrieval and Entailment

Analysis of the methods and performances for data augmentation: Image, text and audio

With the rapid development in computation ability as well as machine learning scenarios, various artificial intelligence applications can be achieved in recent years. With this in mind, this study will explore the application of data augmentation in machine learning and deep learning. To be specific, this paper first introduces the background and research history of data augmentation and then discusses the research progress in recent years. The basic description of this study describes the definition, common methods, and evaluation metrics of data augmentation in detail. At the same time, three data augmentation models, AutoAugment, AugGPT, and SpecAugment++, are introduced respectively, including their principles, experimental results, as well as evaluation. Finally, according to the analysis, the limitations and prospects of the field are discussed and demonstrated, as well as summarize the main findings and research implications of the full paper. Overall, these results shed light on guiding further exploration of data augmentation.

Augmented Commonsense Knowledge for Remote Object Grounding

The vision-and-language navigation (VLN) task necessitates an agent to perceive the surroundings, follow natural language instructions, and act in photo-realistic unseen environments. Most of the existing methods employ the entire image or object features to represent navigable viewpoints. However, these representations are insufficient for proper action prediction, especially for the REVERIE task, which uses concise high-level instructions, such as “Bring me the blue cushion in the master bedroom”. To address enhancing representation, we propose an augmented commonsense knowledge model (ACK) to leverage commonsense information as a spatio-temporal knowledge graph for improving agent navigation. Specifically, the proposed approach involves constructing a knowledge base by retrieving commonsense information from ConceptNet, followed by a refinement module to remove noisy and irrelevant knowledge. We further present ACK which consists of knowledge graph-aware cross-modal and concept aggregation modules to enhance visual representation and visual-textual data alignment by integrating visible objects, commonsense knowledge, and concept history, which includes object and knowledge temporal information. Moreover, we add a new pipeline for the commonsense-based decision-making process which leads to more accurate local action prediction. Experimental results demonstrate our proposed model noticeably outperforms the baseline and archives the state-of-the-art on the REVERIE benchmark. The source code is available at https://github.com/Bahram-Mohammadi/ACK.

Advancing Phishing Email Detection: A Comparative Study of Deep Learning Models.

Phishing is one of the most dangerous attacks targeting individuals, organizations, and nations. Although many traditional methods for email phishing detection exist, there is a need to improve accuracy and reduce false-positive rates. Our work investigates one-dimensional CNN-based models (1D-CNNPD) to detect phishing emails in order to address these challenges. Additionally, further improvement is achieved with the augmentation of the base 1D-CNNPD model with recurrent layers, namely, LSTM, Bi-LSTM, GRU, and Bi-GRU, and experimented with the four resulting models. Two benchmark datasets were used to evaluate the performance of our models: Phishing Corpus and Spam Assassin. Our results indicate that, in general, the augmentations improve the performance of the 1D-CNNPD base model. Specifically, the 1D-CNNPD with Bi-GRU yields the best results. Overall, the performance of our models is comparable to the state of the art of CNN-based phishing email detection. The Advanced 1D-CNNPD with Leaky ReLU and Bi-GRU achieved 100% precision, 99.68% accuracy, an F1 score of 99.66%, and a recall of 99.32%. We observe that increasing model depth typically leads to an initial performance improvement, succeeded by a decline. In conclusion, this study highlights the effectiveness of augmented 1D-CNNPD models in detecting phishing emails with improved accuracy. The reported performance measure values indicate the potential of these models in advancing the implementation of cybersecurity solutions to combat email phishing attacks.

Augmented support vector regression with an autoregressive process via an iterative procedure

The Support Vector Regression (SVR) technique can approximate intricate systems by addressing learning and estimation challenges within a reproducing kernel Hilbert space, devoid of reliance on specific parameter assumptions. However, when dealing with correlated data like time series, the SVR method often falls short in accounting for underlying temporal structures, leading to limited enhancements in prediction efficiency. We introduce an enhanced SVR method that considers temporal correlations (TemporalSVR) to overcome this constraint. Our proposed method extends kernel functions to include additional linear kernels, facilitating learning temporal patterns. Additionally, we develope an iterative training procedure for the augmented regression model. During model training, we estimate the hyper-parameter in the corresponding loss function using a ‘working’ likelihood approach, enhancing the generalization capabilities of the proposed regression. To demonstrate superior forecasting performance, we conduct extensive numerical simulations on both linear and nonlinear systems and the TemporalSVR achieves improvements ranging from 8% to 114% based on the RMSE ratio from the AR-X model. Furthermore, we investigate the forecasting performance of three basic models (NARX-NN, Statistical SVR, and SVR-ARIMA) and four deep learning (DL) techniques (Transformer, Informer, Reformer, Autormer, and Autoformer) by using a WTI forecasting study. Our proposed TemporalSVR achieves the smallest RMSE at 2.22 and attains the highest success ratio of stock direction prediction at 71.30%. All these numerical results highlight the effectiveness and advantages of our TemporalSVR in handling temporal data and making accurate predictions.

Stock Price Forecasting Based on Dynamic Factor Augmented Model Averaging Approach

Accurate forecasting of stock prices not only guides investor behavior but also assesses financial risk and promotes balanced economic and social development. This paper uses a dynamic factor-enhanced model averaging method to forecast the daily closing price of the Shanghai Composite Index, maximizing the use of valid information by weighting the forecast values of different models. Firstly, the common factor is extracted from the smoothed original explanatory variables; then the dynamic factor augmented model selection method and the model averaging method based on different criteria are used to predict different lag orders of the common factor and the explanatory variables, and the effectiveness of the dynamic factor augmented censored group cross-validation model averaging method is verified using multiple predictor error indicators as well as the DM test. The experimental results show that the dynamic factor augmented censored group cross-validation model averaging method has better prediction results and is more robust.

Predicting structure performance of urban critical infrastructure: an augmented attention-based LSTM model

PurposeAccurate prediction of the structural condition of urban critical infrastructure is crucial for predictive maintenance. However, the existing prediction methods lack precision due to limitations in utilizing heterogeneous sensing data and domain knowledge as well as insufficient generalizability resulting from limited data samples. This paper integrates implicit and qualitative expert knowledge into quantifiable values in tunnel condition assessment and proposes a tunnel structure prediction algorithm that augments a state-of-the-art attention-based long short-term memory (LSTM) model with expert rating knowledge to achieve robust prediction results to reasonably allocate maintenance resources.Design/methodology/approachThrough formalizing domain experts' knowledge into quantitative tunnel condition index (TCI) with analytic hierarchy process (AHP), a fusion approach using sequence smoothing and sliding time window techniques is applied to the TCI and time-series sensing data. By incorporating both sensing data and expert ratings, an attention-based LSTM model is developed to improve prediction accuracy and reduce the uncertainty of structural influencing factors.FindingsThe empirical experiment in Dalian Road Tunnel in Shanghai, China showcases the effectiveness of the proposed method, which can comprehensively evaluate the tunnel structure condition and significantly improve prediction performance.Originality/valueThis study proposes a novel structure condition prediction algorithm that augments a state-of-the-art attention-based LSTM model with expert rating knowledge for robust prediction of structure condition of complex projects.

Decomposition approach for examining effects of logistic performance on exports: A case study of Vietnam

The study evaluates to what extent logistics performance and its components impact Vietnam’s bilateral export value. The augmented Gravity model is applied on panel data in the period from 2010 to 2018. Logistics efficiency is measured by Logistic performance index (LPI) and its sub-indices developed by the World Bank. A variety of diagnostic tests and estimation methods are employed to ensure the stability of the results. The main findings confirm that all explanatory variables demonstrate the expected signs, and aggregate logistics performance and its sub-indices have positive impacts on Vietnam’s export flows, with the magnitude of logistics impacts is greater than other factors in the research model. Among LPI components of Vietnam, Ease of arranging shipments index is the most influential factor on exports, followed by Infrastructure, Timeliness, and Quality of logistics services. These export’s effects are also identified by partners’ LPI indicators namely Quality of logistics services, Customs, Infrastructure, and Tracking and tracing.

Enhancing Fruit Fly Detection in Complex Backgrounds Using Transformer Architecture with Step Attention Mechanism

This study introduces a novel high-accuracy fruit fly detection model based on the Transformer structure, specifically aimed at addressing the unique challenges in fruit fly detection such as identification of small targets and accurate localization against complex backgrounds. By integrating a step attention mechanism and a cross-loss function, this model significantly enhances the recognition and localization of fruit flies within complex backgrounds, particularly improving the model’s effectiveness in handling small-sized targets and its adaptability under varying environmental conditions. Experimental results demonstrate that the model achieves a precision of 0.96, a recall rate of 0.95, an accuracy of 0.95, and an F1-score of 0.95 on the fruit fly detection task, significantly outperforming leading object detection models such as YOLOv8 and DETR. Specifically, this research delves into and optimizes for challenges faced in fruit fly detection, such as recognition issues under significant light variation, small target size, and complex backgrounds. Through ablation experiments comparing different data augmentation techniques and model configurations, the critical contributions of the step attention mechanism and cross-loss function to enhancing model performance under these complex conditions are further validated. These achievements not only highlight the innovativeness and effectiveness of the proposed method, but also provide robust technical support for solving practical fruit fly detection problems in real-world applications, paving new paths for future research in object detection technology.

How Much Can Machines Learn Finance from Chinese Text Data?

How much can we learn finance directly from text data? This paper presents a new framework for learning textual data based on the factor augmentation model and sparsity regularization, called the factor-augmented regularized model for prediction (FarmPredict), to let machines learn financial returns directly from news. FarmPredict allows the model itself to extract information directly from articles without predefined information, such as dictionaries or pretrained models as in most studies. Using unsupervised learned factors to augment the predictors would benefit our method with a “double-robust” feature: that the machine would learn to balance between individual words or text factors/topics. It also avoids the information loss of factor regression in dimensionality reduction. We apply our model to the Chinese stock market with a large proportion of retail investors by using Chinese news data to predict financial returns. We show that positive sentiments scored by our FarmPredict approach from news generate on average 83 basic points (bps) stock daily excess returns, and negative news has an adverse impact of 26 bps on the days of news announcements, where both effects can last for a few days. This asymmetric effect aligns well with the short-sale constraints in the Chinese equity market. The result shows that the machine-learned prediction does provide sizeable predictive power with an annualized return of 54% at most with a simple investment strategy. Compared with other statistical and machine learning methods, FarmPredict significantly outperforms them on model prediction and portfolio performance. Our study demonstrates the far-reaching potential of using machines to learn text data. This paper was accepted by Kay Giesecke, finance. Funding: This study was supported by the National Natural Science Foundation of China [Grants 71991471, 71991470, and 72204049], the National Key Research and Development Program [Grant 2020YFA0608604], the Shanghai Pujiang Scholar Project [Grant 21PJC010], the Shanghai Science Project [Grant 23692119300], and the China Postdoctoral Science Project [Grants 2019M650076 and 2020T130107]. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2022.01468 .

A Deep Learning Model for Markerless Pose Estimation Based on Keypoint Augmentation: What Factors Influence Errors in Biomechanical Applications?

In biomechanics, movement is typically recorded by tracking the trajectories of anatomical landmarks previously marked using passive instrumentation, which entails several inconveniences. To overcome these disadvantages, researchers are exploring different markerless methods, such as pose estimation networks, to capture movement with equivalent accuracy to marker-based photogrammetry. However, pose estimation models usually only provide joint centers, which are incomplete data for calculating joint angles in all anatomical axes. Recently, marker augmentation models based on deep learning have emerged. These models transform pose estimation data into complete anatomical data. Building on this concept, this study presents three marker augmentation models of varying complexity that were compared to a photogrammetry system. The errors in anatomical landmark positions and the derived joint angles were calculated, and a statistical analysis of the errors was performed to identify the factors that most influence their magnitude. The proposed Transformer model improved upon the errors reported in the literature, yielding position errors of less than 1.5 cm for anatomical landmarks and 4.4 degrees for all seven movements evaluated. Anthropometric data did not influence the errors, while anatomical landmarks and movement influenced position errors, and model, rotation axis, and movement influenced joint angle errors.

Statistical shape analysis and computational modeling reveal novel relationships between tibiofemoral bony geometry and knee mechanics in young, female athletes

Young female athletes participating in sports requiring rapid changes of direction are at heightened risk of suffering traumatic knee injury, especially noncontact rupture of the anterior cruciate ligament (ACL). Clinical studies have revealed that geometric features of the tibiofemoral joint are associated with increased risk of suffering noncontact ACL injury. However, the relationship between three-dimensional (3D) tibiofemoral geometry and knee mechanics in young female athletes is not well understood. We developed a statistically augmented computational modeling workflow to determine relationships between 3D geometry of the knee and tibiofemoral kinematics and ACL force in response to an applied loading sequence of compression, valgus, and anterior force, which is known to load the ACL. This workflow included 3D characterization of tibiofemoral bony geometry via principal component analysis and multibody dynamics models incorporating subject-specific knee geometries. A combination of geometric features of both the tibia and the femur that spanned all three anatomical planes was related to increased ACL force and to increased kinematic coupling (i.e., anterior, medial, and distal tibial translations and internal tibial rotation) in response to the applied loads. In contrast, a uniplanar measure of tibiofemoral geometry that is associated with ACL injury risk, sagittal plane slope of the lateral tibial plateau subchondral bone, was not related to ACL force. Thus, our workflow may aid in developing mechanics-based ACL injury screening tools for young, active females based on a unique combination of bony geometric features that are related to increased ACL loading.

Clinical decision support for bipolar depression using large language models

Management of depressive episodes in bipolar disorder remains challenging for clinicians despite the availability of treatment guidelines. In other contexts, large language models have yielded promising results for supporting clinical decisionmaking. We developed 50 sets of clinical vignettes reflecting bipolar depression and presented them to experts in bipolar disorder, who were asked to identify 5 optimal next-step pharmacotherapies and 5 poor or contraindicated choices. The same vignettes were then presented to a large language model (GPT4-turbo; gpt-4-1106-preview), with or without augmentation by prompting with recent bipolar treatment guidelines, and asked to identify the optimal next-step pharmacotherapy. Overlap between model output and gold standard was estimated. The augmented model prioritized the expert-designated optimal choice for 508/1000 vignettes (50.8%, 95% CI 47.7–53.9%; Cohen’s kappa = 0.31, 95% CI 0.28–0.35). For 120 vignettes (12.0%), at least one model choice was among the poor or contraindicated treatments. Results were not meaningfully different when gender or race of the vignette was permuted to examine risk for bias. By comparison, an un-augmented model identified the optimal treatment for 234 (23.0%, 95% CI 20.8–26.0%; McNemar’s p < 0.001 versus augmented model) of the vignettes. A sample of community clinicians scoring the same vignettes identified the optimal choice for 23.1% (95% CI 15.7–30.5%) of vignettes, on average; McNemar’s p < 0.001 versus augmented model. Large language models prompted with evidence-based guidelines represent a promising, scalable strategy for clinical decision support. In addition to prospective studies of efficacy, strategies to avoid clinician overreliance on such models, and address the possibility of bias, will be needed.