Effective Model Research Articles

Cross-sectoral role and community empowerment in controlling schistosomiasis in Indonesia

The role of cross-sectors in synergy with community empowerment in controlling schistosomiasis is a very effective model. Until mid-2017, the incidence rate of disease in humans in 28 endemic villages still ranged 0.00-2.15%. This research aims to evaluate schistosomiasis control activities that have been carried out across sectors based on a road map for schistosomiasis eradication and community empowerment in controlling schistosomiasis. The study was mixed method. Data were obtained by in-depth interview with key informants and evaluation of the results of cross-sectoral and community activities. The research was carried out in an endemic area for schistosomiasis on the Bada Plateau, Indonesia, from January to November 2019. In conclusion, the potential of cross-sector collaboration in controlling schistosomiasis has not been fully realized due to budget constraints. Community empowerment is carried out to eliminate snail foci, increase the scope of feces collection and change community behavior for the better in order to avoid infection and always try to clean up snail foci.

Silver-graphene oxide nanocomposite doping chitosan/PVA membrane for arsenic (III) elimination from aqueous solution

Heavy metals and pathogens from contaminated water sources may undoubtedly be removed by creating an efficient bio-adsorbent based on functional spots. Thus, the goal of this work was to produce chitosan (Ch)-polyvinyl alcohol (PVA) biofilm decorated with graphene oxide (GO) sheets doped with silver nanoparticles (AgNPs). The nanostructure of prepared GO/Ag nanosheets is examined by transmission electron microscope (TEM). The fabricated film (GO/Ag Ch-PVA) is compared by the control films (Ch, PVA and Ch-PVA). Fourier transform infrared (FTIR) spectroscopy, X-ray diffraction (XRD), and tensile strength are used to study the films’ structure. Also, the antimicrobial activity was assessed for the films. After doping the polymer matrix with GO/Ag, it was discovered that the tensile strength increased to about 46.18 MPa. Moreover, adsorption experiment for arsenic As (III) ions is explored by the prepared film at different operating conditions. The obtained results validated the enhanced adsorption ability of the GO/Ag Ch-PVA film towards As (III) with the highest adsorption capacity of 54.3 mg g−1 obtained from the isotherm model of Langmuir. Moreover, kinetic mathematical models for the adsorption effectiveness of GO/Ag Ch-PVA film are assessed. The results gathered demonstrated that GO/Ag Ch-PVA film is a potentially useful material for eliminating As (III) and microbial strains from essential water resources.

Fast Graph Generation via Spectral Diffusion.

Generating graph-structured data is a challenging problem, which requires learning the underlying distribution of graphs. Various models such as graph VAE, graph GANs, and graph diffusion models have been proposed to generate meaningful and reliable graphs, among which the diffusion models have achieved state-of-the-art performance. In this paper, we argue that running full-rank diffusion SDEs on the whole graph adjacency matrix space hinders diffusion models from learning graph topology generation, and hence significantly deteriorates the quality of generated graph data. To address this limitation, we propose an efficient yet effective Graph Spectral Diffusion Model (GSDM), which is driven by low-rank diffusion SDEs on the graph spectrum space. Our spectral diffusion model is further proven to enjoy a substantially stronger theoretical guarantee than standard diffusion models. Extensive experiments across various datasets demonstrate that our proposed GSDM turns out to be the SOTA model, by exhibiting both significantly higher generation quality and much less computational consumption than the baselines.

Collaborative Knowledge Distillation via Multiknowledge Transfer.

Knowledge distillation (KD), as an efficient and effective model compression technique, has received considerable attention in deep learning. The key to its success is about transferring knowledge from a large teacher network to a small student network. However, most existing KD methods consider only one type of knowledge learned from either instance features or relations via a specific distillation strategy, failing to explore the idea of transferring different types of knowledge with different distillation strategies. Moreover, the widely used offline distillation also suffers from a limited learning capacity due to the fixed large-to-small teacher-student architecture. In this article, we devise a collaborative KD via multiknowledge transfer (CKD-MKT) that prompts both self-learning and collaborative learning in a unified framework. Specifically, CKD-MKT utilizes a multiple knowledge transfer framework that assembles self and online distillation strategies to effectively: 1) fuse different kinds of knowledge, which allows multiple students to learn knowledge from both individual instances and instance relations, and 2) guide each other by learning from themselves using collaborative and self-learning. Experiments and ablation studies on six image datasets demonstrate that the proposed CKD-MKT significantly outperforms recent state-of-the-art methods for KD.

Data Augmentation for Sample Efficient and Robust Document Ranking

Contextual ranking models have delivered impressive performance improvements over classical models in the document ranking task. However, these highly over-parameterized models tend to be data-hungry and require large amounts of data even for fine-tuning. In this article, we propose data-augmentation methods for effective and robust ranking performance. One of the key benefits of using data augmentation is in achieving sample efficiency or learning effectively when we have only a small amount of training data. We propose supervised and unsupervised data augmentation schemes by creating training data using parts of the relevant documents in the query-document pairs. We then adapt a family of contrastive losses for the document ranking task that can exploit the augmented data to learn an effective ranking model. Our extensive experiments on subsets of the MS MARCO and TREC-DL test sets show that data augmentation, along with the ranking-adapted contrastive losses, results in performance improvements under most dataset sizes. Apart from sample efficiency, we conclusively show that data augmentation results in robust models when transferred to out-of-domain benchmarks. Our performance improvements in in-domain and more prominently in out-of-domain benchmarks show that augmentation regularizes the ranking model and improves its robustness and generalization capability.

Overcoming Barriers to Collaborative Team Practice: A System Approach.

All healthcare systems are challenged to provide sufficient access to appropriate care for the individuals and communities they serve. Among the commonly discussed interventions in an era of clinical shortages is the establishment of team-based care, where team members can practice at the top of their license. This solution ensures that talent and ability are amplified. However, this vision has been thwarted by several barriers. Recognizing that complex causes prevent team-based care, CommonSpirit Health leadership has embarked on a multifaceted implementation of tactics to mitigate the barriers. The strategy addresses issues ranging from regulations, laws, and payment practices to a lack of knowledge and understanding between professions. A combination of solutions, rather than discrete tactics, holds the key to the system's strategy. The complement of actions put in place at CommonSpirit Health has included new executive roles, dyad leadership models, shared multidisciplinary education, targeted advocacy, best practice playbooks, and the flexibility to individualize local models as part of the journey to a more effective and efficient model of care.

CNN-CatBoost ensemble deep learning model for enhanced disease detection and classification of kidney disease

An efficient deep-learning prediction model for identifying chronic kidney disease (CKD) from exhaled breath is presented in this paper. The concentration of urea will be higher in CKD patients. Salivary urease breaks down the stored urea into ammonia, which is then excreted through breath. Thus, by monitoring the breath ammonia content, it is possible to identify the presence of high urea levels in the body. In this work, a novel sensing module is developed and applied to measure and assess the amount of ammonia in exhaled breath. Moreover, an effective deep learning prediction model that combines the CatBoost algorithm and convolutional neural network (CNN) is used to automate the prediction of disease. The proposed model, which combines the benefits of gradient-boosting and CNN, attained an exceptional accuracy of 98.37%. Experiments are conducted to evaluate the proposed model using real-time data and to assess how well it performs in comparison with existing deep learning methods. Our study's findings demonstrate that kidney disease can be accurately and noninvasively diagnosed using the proposed approach.

Improving student higher order thinking skills using SynecticHOTS-oriented learning model

The achievement of students’ learning outcomes in physics lessons has a low tendency, this is due to various factors, one of which is higher-order thinking skills (HOTS) based learning that has not been fully implemented in the learning process and assessment. This study aimed to determine the differences in the Synectic-HOTS learning model in physics compared to conventional learning models. This study used a quasi-experimental study with a pre-test–post-test nonequivalent control group design. The instrument used in this study is a two-tier test question that contains 20 items of HOTS aspect. The prerequisite test showed that the data was not homogeneous, while the results of the data homogeneity test were stated to be homogeneous. Therefore, a non-parametric test was carried out using the Mann-Whitney U-test. Based on the results of the data analysis, the Asymp. Sig. (2-tailed) for the pre-test was 0.111 and the post-test was 0.001 (p=.000<05). The effect size calculation shows that the Synectic learning model is effective in the medium category. These results indicate that the application of the SynecticHOTS model significantly improves HOTS when compared to conventional learning models. This work can open up insights to teachers about alternative, creative, and effective learning models to improve higher-order thinking skills and student learning outcomes.

Hierarchical and dynamic graph attention network for drug-disease association prediction.

In the realm of biomedicine, the prediction of associations between drugs and diseases holds significant importance. Yet, conventional wet lab experiments often fall short of meeting the stringent demands for prediction accuracy and efficiency. Many prior studies have predominantly focused on drug and disease similarities to predict drug-disease associations, but overlooking the crucial interactions between drugs and diseases that are essential for enhancing prediction accuracy. Hence, in this paper, a resilient and effective model named Hierarchical and Dynamic Graph Attention Network (HDGAT) has been proposed to predict drug-disease associations. Firstly, it establishes a heterogeneous graph by leveraging the interplay of drug and disease similarities and associations. Subsequently, it harnesses the capabilities of graph convolutional networks and bidirectional long short-term memory networks (Bi-LSTM) to aggregate node-level information within the heterogeneous graph comprehensively. Furthermore, it incorporates a hierarchical attention mechanism between convolutional layers and a dynamic attention mechanism between nodes to learn embeddings for drugs and diseases. The hierarchical attention mechanism assigns varying weights to embeddings learned from different convolutional layers, and the dynamic attention mechanism efficiently prioritizes inter-node information by allocating each node with varying rankings of attention coefficients for neighbour nodes. Moreover, it employs residual connections to alleviate the over-smoothing issue in graph convolution operations. The latent drug-disease associations are quantified through the fusion of these embeddings ultimately. By conducting 5-fold cross-validation, HDGAT's performance surpasses the performance of existing state-of-the-art models across various evaluation metrics, which substantiates the exceptional efficacy of HDGAT in predicting drug-disease associations.

A simplified classification computational model of opinion mining using deep learning

Opinion and attempts to develop an automated system to determine people's viewpoints towards various units such as events, topics, products, services, organizations, individuals, and issues. Opinion analysis from the natural text can be regarded as a text and sequence classification problem which poses high feature space due to the involvement of dynamic information that needs to be addressed precisely. This paper introduces effective modelling of human opinion analysis from social media data subjected to complex and dynamic content. Firstly, a customized preprocessing operation based on natural language processing mechanisms as an effective data treatment process towards building quality-aware input data. On the other hand, a suitable deep learning technique, bidirectional long short term-memory (Bi-LSTM), is implemented for the opinion classification, followed by a data modelling process where truncating and padding is performed manually to achieve better data generalization in the training phase. The design and development of the model are carried on the MATLAB tool. The performance analysis has shown that the proposed system offers a significant advantage in terms of classification accuracy and less training time due to a reduction in the feature space by the data treatment operation.

The Dilemma of Quantum Neural Networks.

The core of quantum machine learning is to devise quantum models with good trainability and low generalization error bounds than their classical counterparts to ensure better reliability and interpretability. Recent studies confirmed that quantum neural networks (QNNs) have the ability to achieve this goal on specific datasets. In this regard, it is of great importance to understand whether these advantages are still preserved on real-world tasks. Through systematic numerical experiments, we empirically observe that current QNNs fail to provide any benefit over classical learning models. Concretely, our results deliver two key messages. First, QNNs suffer from the severely limited effective model capacity, which incurs poor generalization on real-world datasets. Second, the trainability of QNNs is insensitive to regularization techniques, which sharply contrasts with the classical scenario. These empirical results force us to rethink the role of current QNNs and to design novel protocols for solving real-world problems with quantum advantages.

Optimal Switching Sequence MPC for Four-Leg Two-Level Grid-Connected Converters

This paper presents a versatile and effective model predictive current control strategy based on optimal switching sequences for four–leg two–level grid–connected converters. The proposed control methodology, presents an excellent dynamic performance, good tracking of high-frequency reference signals, fixed switching frequency, and well-formed harmonic spectrum, enabling the proposed controller to govern shunt active filters and distributed generation applications based on four-leg converters. Experimental results demonstrate the effectiveness and high-quality performance obtained with the proposed strategy.

Implementation of a PAFV turbulence model for airfoil flow simulation on OpenFOAM

To further develop a more effective turbulence model and to improve the calculation accuracy of the flow around airfoil, a new PAFV turbulence model has here been constructed by using a deformation rate tensor and the grouping of an average fluctuation velocity. To evaluate the applicability of the PAFV turbulence model, the numerical calculations of flow around the airfoil have here been implemented, which was based on the OpenFOAM calculation platform. On the basis of grid independence research, the model was used to calculate the low-speed flow-around problem for the plano-convex airfoil NACA4412 and the symmetric airfoil NACA0012. It was also compared with the S-A (Spalart-Allmaras) and SST (Shear Stress Transport) k-ω turbulence models. Firstly, the maximum lift angle-of-attack case of the NACA4412 airfoil was calculated. Thereafter, numerical calculations were performed for the flow around the airfoil in the multi-angle-of-attack case of the NACA0012 airfoil. The results showed that the NACA4412 airfoil had an obviously separated vortex at the trailing edge of the airfoil at the maximum lift angle of attack. Also, there was a certain velocity loss downstream of the trailing edge, which was calculated by all three models. However, the results of the PAFV turbulence model were found to be better than those of the S-A and SST turbulence models. The three turbulence models showed comparable accuracies for the calculations of the surface pressure coefficients of the NACA0012 airfoil. However, the S-A and SST k-ω turbulence models were slightly better for the calculations of the mean velocity profiles of the NACA0012 airfoil. Also, the PAFV turbulence model was more accurate for the calculations of the lift and drag coefficients. In conclusion, the PAFV model can make effective predictions of the airfoil low-speed flow around the problem at hand, which in turn preliminarily verifies the applicability of this turbulence model for the low-speed flow around the airfoil problems.

Social work collective leadership in a large urban hospital during an era of unprecedented transformational change

This Department of Social Work Services (the Department) is one of the largest hospital social work departments in the country, with almost 600 staff, in the largest of eight hospitals and one medical school of a major health system. The Department’s senior directors (three current and one former) share its innovative and effective collective leadership model that was initially developed in response to a confluence of unprecedented complex events stemming from the Covid-19 pandemic. The experiences of these co-leaders, an evaluation of the model, future internal considerations as its applicability to other health care settings will be discussed.

To be green or not to be: How governmental regulation shapes financial institutions' greenwashing behaviors in green finance

Green finance provides important economic support for environmental protection and carbon reduction. However, some financial institutions engage in greenwashing behaviors (GWBs), which raise funds through green finance products (GFPs) without investing in green projects and falsely disclosing environmental information. The GWBs of financial institutions result in tremendous pressure on governmental regulation. From the perspective of information disclosure, under incomplete information, we constructed a signaling game between governments and financial institutions to explore the formation mechanism of financial institutions' GWBs. Subsequently, the separating equilibrium, pooling equilibrium, and hybrid equilibrium are investigated. The corresponding conditions for financial institutions choosing positive information disclosure were derived. We also evaluated the effects of different regulatory measures, including rewards, penalties, standards, and certifications on curbing GWBs. Finally, countermeasures to shape financial institutions to undertake their environmental responsibilities and conduct positive information disclosure are proposed. This study provides a theoretical explanation for GWBs and sheds new light on an effective governance model in green finance.

Topological Phase Diagram of an Interacting Kitaev Chain: Mean Field versus DMRG Study

In this work, we study the topological phase transitions of a Kitaev chain generalized by the addition of nearest-neighbor Coulomb interaction. We show the presence of a robust topological phase as a function of the interaction strength and of the on-site energy with associated non-zero energy Majorana states localized at the chain edges. We provide an effective mean-field model that allows for the self-consistent computation of the mean value of the local particle number operator, and we also perform Density Matrix Renormalization Group numerical simulations based on a tensor network approach. We find that the two methods show a good agreement in reporting the phase transition between trivial and topological superconductivity. Temperature robustness within a physically relevant threshold has also been demonstrated. These findings shed light on an entire class of topological interacting one-dimensional systems in which the effects of residual Coulomb interactions play a relevant role.

Research on vacuum glass insulation performance prediction based on unsteady state multivariate data screening and multi-model fusion self-optimization

A self-optimization regression method based on multivariate data screening and multi-model fusion is proposed for the regression prediction of vacuum glass insulation performance. Firstly, we analyzed the positive correlation between the temperature change rate and heat transfer coefficient. Secondly, we combined the technique of multi-distribution overall diffusion to generate virtual sample data with multiple variables corresponding to the small neighborhood of the target variable, addressing the issue of insufficient sample size. We conducted quantity and threshold screening on the generated data to enhance the effectiveness of the virtual sample data. The screened data and original training set data are integrated to form new training samples. Then, the limited-memory Broyden Fletcher Goldfarb Shanno with boundary constraints (L-BFGS-B) algorithm is introduced to optimize the parameters of multiple models to improve the accuracy of model regression prediction. Finally, through the self-searching optimization framework structure, the virtual sample data screening and optimization of various model parameters are updated. Eventually, the optimal model for predicting the heat transfer coefficient of vacuum glass insulation performance is determined from multiple models. In order to validate the effectiveness of self-optimization regression method, we conducted insulation performance heat transfer coefficient predictions under 30 different ways for vacuum glass. Experimental results demonstrate that the self-optimization regression method based on multivariate data screening and multi-model fusion can obtain the most effective regression prediction model, achieving accurate, rapid and intelligent prediction of vacuum glass insulation performance.

Credit Risk Prediction Using Explainable AI

Despite advancements in machine-learning prediction techniques, the majority of lenders continue to rely on conventional methods for predicting credit defaults, largely due to their lack of transparency and explainability. This reluctance to embrace newer approaches persists as there is a compelling need for credit default prediction models to be explainable. This study introduces credit default prediction models employing several tree-based ensemble methods, with the most effective model, XGBoost, being further utilized to enhance explainability. We implement SHapley Additive exPlanations (SHAP) in ML-based credit scoring models using data from the US-based P2P Lending Platform, Lending Club. Detailed discussions on the results, along with explanations using SHAP values, are also provided. The model explainability generated by Shapely values enables its applicability to a broad spectrum of industry applications.

Sarcasm Detection in Pidgin Tweets Using Machine Learning Techniques

Detecting sarcasm in social media is of growing importance for applications such as monitoring, consumer feedback, and sentiment analysis. However, detecting sarcasm in Pidgin tweets poses unique challenges due to the blend of English and Pidgin languages, along with local cultural references. Existing models for sarcasm detection in English lack appropriate annotated data for Pidgin. This scarcity hinders the development of effective machine learning models. This research aims to address these challenges and create a model for accurate sarcasm detection in Pidgin tweets. Logistic Regression, XGBoost, Random Forest, and Vanilla Artificial Neural Network (ANN) classifiers were assessed, focusing on accuracy, precision, recall, and F1-score metrics on sarcasm data collected by curating and pre-processing a dataset of Nigerian Pidgin tweets. The XGBoost model demonstrated notable performance, attaining an accuracy of 85.78%, precision of 88.57%, recall of 94.44%, and F1-score of 91.41%. These outcomes underscored the model's prowess in discerning sarcastic and non-sarcastic expressions. By unfolding the intricacies of language in the Nigerian context, this research into sarcasm identification in Nigerian Pidgin text data introduced a comprehensive pipeline encompassing data curation, exploratory analysis, culturally tailored pre-processing, model training, evaluation, and prediction.

Entangled dark state mediated by a dielectric cavity within epsilon-near-zero materials.

Two emitters can be entangled by manipulating them through optical fields within a photonic cavity. However, maintaining entanglement for a long time is challenging due to the decoherence of the entangled qubits, primarily caused by cavity loss and atomic decay. Here, we found the entangled dark state between two emitters mediated by a dielectric cavity within epsilon-near-zero (ENZ) materials, ensuring entanglement maintenance over an extended period. To obtain the entangled dark state, we derived an effective model with degenerate mode modulation. In the dielectric cavities within ENZ materials, the decay rate of emitters can be regarded as 0, which is the key to achieving the entangled dark state. Meanwhile, the dark state immune to cavity loss exists when two emitters are in symmetric positions in the dielectric cavity. Additionally, by adjusting the emitters to specific asymmetric positions, it is possible to achieve transient entanglement with higher concurrence. By overcoming the decoherence of the entangled qubits, this study demonstrates stable, long-term entanglement with ENZ materials, holding significant importance for applications such as nanodevice design for quantum communication and quantum information processing.