Innovative Model Research Articles

The Effectiveness and Student Satisfaction on Aerobics Instruction in Flipped Classroom Modality

Flipped classroom, as an innovative teaching model, has been widely applied and validated in various disciplines, but its effectiveness and applicability in professional fields such as aerobics teaching are still uncertain. This study randomly selected 368 college students from Sichuan University for Nationalities in Sichuan Province, China for a survey. Descriptive quantitative research methods were used to describe the effectiveness of flipped classroom implementation in college aerobics teaching and the current situation of student satisfaction. The aim was to provide insights for guiding the improvement of the effectiveness and student satisfaction of flipped classroom implementation in college aerobics teaching, and to understand the influencing factors and implementation conditions that affect these aspects, Specific suggestions have been put forward from a macro perspective to address the existing problems. These strategies contribute to an enriched learning experience, providing comprehensive support for students' aerobic education and overall learning journey.

Digital economy: opportunities for transformation of entepreneurial structures

Purpose. To analyze the stages of digital transformation of entrepreneurial structures and identify the levels of transformation. Methodology. In the process of scientific research on the digital economy and the transformation of entrepreneurial structures, the following methods were utilized: expert assessment (involving experts from various fields of economic activity allowed for additional conclusions and recommendations regarding the possibilities of implementing digital technologies in entrepreneurial structures), scenario modeling (by developing various scenarios for the implementation of digital initiatives, the potential consequences and results of each were investigated), systems analysis (enabled considering the interrelations between various aspects of digital transformation and its impact on the economy and society as a whole), and marketing research (helped identify market needs and requirements for the implementation of digital solutions and products). Findings. The research considered the stages of digital transformation of entrepreneurial structures, which involve assessing the current state and readiness of the enterprise for the implementation of digital transformation; studying the potential offered by digital transformation and its effective implementation; investing in advanced digital technologies and the development of new digital products; designing and releasing products and services based on advanced digital technologies; controlling the transformed business and implementing advanced digital technologies and innovative business models. Advantages of digital transformation of business models are considered, which involve increasing the number of customers, enhancing customer satisfaction, increasing lead generation, traffic growth. The authors identified six levels of “digital transformation” of entrepreneurial structures, describing the stages of changes in business models caused by digital transformations: unsystematic level, opportunities monitoring, replicable level, results-driven, achieved controlling, and optimized level. Originality. A stage of digital transformation of entrepreneurial structures has been proposed: controlling the transformed business and implementing advanced digital technologies, which allows tracking the implementation of the strategy and achieving goals in the context of digital development. The authors highlighted such stages of digital transformation of entrepreneurial structures as opportunities monitoring and achieved controlling, which, unlike those existing in the scientific community, play a key role in the path of digital transformation of entrepreneurial structures. Practical value. The analysis conducted confirms the relevance of issues related to the digital transformation of entrepreneurial structures, the formation of changes in views on stages and levels of digital transformation in accordance with current trends and uncertain conditions. The research results can be taken into account and practically implemented when forming policies for the digital transformation of entrepreneurial structures, regardless of the field of activity.

Microsurgical Training: A Review of Existing Methods and an Innovative Practice Model

Abstract Surgery under magnification with the use of the operating microscope has seen great advances, and numerous surgical procedures today depend on optical magnification. Training (to impart basic skills) in microsurgery is particularly essential to enable surgeons to take their place in the surgical team and learn further as they progressively observe, assist, and in time, perform microsurgical procedures. Various materials and models are used and have been objectively assessed and validated for simulation in microsurgical training. One such model, the live animal model (with all its disadvantages), has been the “gold standard” for simulation in microsurgical training. We have identified and put into use a new tissue model for training in microvascular surgery – the chicken mesentery, which will offer a good practical solution where the live animal model is unavailable. Further studies using this model for training at various centers will be required for validation and comparison of this tool against existing methods.

CONSTRUCTION OF A TEACHING STRATEGY MODEL FOR CULTIVATING HIGHER-ORDER THINKING SKILLS IN COLLEGE STUDENTS

In the era of the knowledge economy, the intensification of the technological revolution and international competition have triggered a rethinking of the core competencies of talent in the 21st century by countries. Many countries have shifted their focus on talent development from specialized knowledge and skills to training in complex tasks and information-processing thinking. In higher education, guiding students to transition from lower-order thinking, such as memorisation and understanding of knowledge to higher-order thinking, such as analysis, synthesis, and evaluation of various information is a vital aspect of the new era's innovative teaching model and the enhancement of talent cultivation. This study was conducted face-to-face interviews with 12 teachers with practical experience cultivating higher-order thinking skills using purposive sampling. The collected interview data were analysed and coded using nvivo software and qualitative research methods, constructing five teaching strategy models for cultivating higher-order thinking skills in college students: scaffolding instruction, heuristic instruction, project-based instruction, collaborative learning, and diversified assessment feedback.

Studying the peculiarities of the universities students’ motivation for research activities

Introduction. The article substantiates the need for up-to-date knowledge about the state and possibilities of university students’ research activities, taking into account the necessity to increase the importance of such activities for education and personal development of future professionals in the field of science. The purpose of the article is to present the research results (2023) reflecting the problems of involving students into research activities and ways of solving these problems, as well as the results of investigating students’ motivation at the Herzen State Pedagogical University in Russia. The innovative model of preparing highly qualified scientific and academic staff is characterized. Materials and Methods. The research methodology is based on the ideas of a personality-centered approach. Theoretical and practical methods of scientific research were applied: theoretical analysis, synthesis, classification; the online questionnaire, which revealed various aspects of students’ motivation to participation in research activities, and mathematical methods of data processing. Results. The authors presented three groups of results: - the review and analysis of studies conducted in the 2000s by Russian and international researchers on various aspects of engaging university students in research activities; - the review of current research investigations conducted in Russian universities, reflecting practice of improving university students’ research activities in various regions of the country; - the results of the study conducted in 2023 at the Herzen State Pedagogical University of Russia - a survey of students majoring in the following fields: Education (Education science); Psychology (psychological sciences); Psychology and Education which reflect the key positions of organizing students’ research: the engagement of students in educational activities; motivation for research activities; satisfaction with research experience; the degree of participation in the student research society; self-assessment of the research skills; assessment of existing conditions for research activities and accessibility to them at the university. Conclusions. Students will choose research activities as a basis for their professional formation if research is considered to be a leading activity in the higher educational institution; where external and internal motives of involving students in research are taken into account and regulatory and research support of students in their scientific self-determination is manifested. One of the possible forms of creating such conditions is the model of a joint master’s and doctoral-level degree program.

Optimizing Cross-Dock Terminal Location Selection: A Multi-Step Approach Based on CI-DEA–IDOCRIW–MABAC for Enhanced Supply Chain Efficiency—A Case Study

Thedistribution of products stands out as one of the pivotal activities for logistics companies in recent years, particularly in the aftermath of the COVID-19 pandemic and other geopolitical events. Intense competition compels companies to efficiently execute their logistical processes, with cross-docking emerging as a frequently applied solution. However, the location of cross-dock terminals in urban areas remains a problem insufficiently addressed in the literature, with a dearth of studies and models tackling this issue. This paper introduces a novel and innovative model for locating cross-dock terminals based on the CI-DEA–IDOCRIW–MABAC (Composite Indicators–Data Envelopment Analysis-Integrated Determination of Objective Criteria Weights–Multi-Attributive Border Approximation Area Comparison) methods. In the process of defining input indicators, the following three sources were utilized: relevant literature, practical insights from logistics experts, and the knowledge and experience of the authors. Eight inputs and three outputs were considered (the number of users in the observed channel; the area served by the channel; the average distance a vehicle travels in one delivery; the required number of vehicles; labor availability; competition; construction, and expansion possibilities; proximity to the main infrastructure and traffic facilities; the average number of deliveries; average delivered quantity; and service level). The model underwent testing in a case study analyzing nine distribution channels (areas within the observed urban zone). The results indicated that alternative A4 (in the southwest area) ranked the highest since it was the best-ranked in accordance with the most important criteria, suggesting that the terminal is best located in the southwest zone. The accuracy of the results was confirmed by company management. By developing a completely new model and addressing the identified gap in the literature, this paper provides unequivocal scientific contributions.

Revealing the potential of FinTech innovation through knowledge assets: a study of firm financial performance

Purpose This study aims to investigate the association of FinTech innovation (FinTechINN) and firm performance (FP) by considering the role of knowledge assets (KA) as a causal mechanism underlying the FinTechINN – FP association. Design/methodology/approach In this study, the authors consider panel data of 1,049 Chinese A-listed firm and construct a structural model for corporate FinTech innovation, knowledge assets and firm performance while considering endogeneity issues in analyses over the period of 2014–2022. The modified value added intellectual capital (VAIC) and research and development (R&D) expenses are used as a proxy measure for knowledge assets, considering governance and corporate performance measures. Findings According to the findings of this study FinTech innovation (FinTechINN) has a positive significant effect on firm performance. Particularly; the findings disclose that FinTech innovations has a link with knowledge assets, FinTech innovations indirectly affects firm performance, and the association between FinTech innovation and firm performance is partially mediated by knowledge assets (MVAIC and R&D expenses). Originality/value Rooted in the dynamic capability and resource-based view, this study pioneers an empirical exploration of the association of FinTech innovation with firm performance. Moreover, it introduces the novel dimension of knowledge assets (on firm-level), acting as a mediating factor with in this relationship.

The Impact of Digital Finance on the Green Utilization Efficiency of Urban Land: Evidence from 281 Cities in China

In the era of digital economy, digital finance, as an innovative financial model, plays an important role in driving urban industrial transformation and development, technological innovation, industrial upgrading and sustainable utilization of energy, and has a significant impact on sustainable urban development. At present, in the process of building a new pattern of Chinese-style modernization in China, it is of great significance to improve the green use efficiency of urban land through digital finance and realize the sustainable use of land resources and the sustainable development of the city. The current study employed 281 Chinese cities from 2010 to 2020 as research samples to investigate the effects of technological financing on the productivity of city land green usage. Based on the ideas of responsible growth and efficient urban development, an assessment index system was developed. Comprehensive empirical tests, such as the Super-SBM model, fixed effect model, and mediation effect model, were implemented in the research. The study’s findings indicate that: (1) Throughout the research period, the benchmark model’s regression outcomes demonstrate that digital banking impacts urban land’s green development efficiency, with positive moderating effects offered by environmental legislation; the optimization of industrial structure has not yet played a positive regulating effect. (2) Urban area green usage performance is more clearly impacted by the extent of use and the degree of digitization, according to the regression results of digital financing heterogeneity. The positive effect of online financial services on a city’s green use efficiency occurs mainly in eastern cities and southern cities, given the results of urban development level difference. In light of resource endowment unpredictability, “non-resource cities” stand to gain more from global finance’s encouragement of resource-efficient urban land use than do “resource cities”. The results of the mechanism test indicate that there is a strong mediating influence from digital finance, city land environmental use productivity, and green technological breakthroughs. In consideration of these results, the following measures are suggested in this paper: (1) Persist in advocating for the transformation of traditional finance into online financing. (2) Intensify the impact of significant variables on the environmentally friendly use of urban areas. (3) Encourage technology creativity and execution through the application of technological economics.

Advanced Deep Learning Model for Predicting the Academic Performances of Students in Educational Institutions

Educational institutions are increasingly focused on supporting students who may be facing academic challenges, aiming to enhance their educational outcomes through targeted interventions. Within this framework, leveraging advanced deep learning techniques to develop recommendation systems becomes essential. These systems are designed to identify students at risk of underperforming by analyzing patterns in their historical academic data, thereby facilitating personalized support strategies. This research introduces an innovative deep learning model tailored for pinpointing students in need of academic assistance. Utilizing a Gated Recurrent Neural Network (GRU) architecture, the model is rich with features such as a dense layer, max-pooling layer, and the ADAM optimization method used to optimize performance. The effectiveness of this model was tested using a comprehensive dataset containing 15,165 records of student assessments collected across several academic institutions. A comparative analysis with existing educational recommendation models, like Recurrent Neural Network (RNN), AdaBoost, and Artificial Immune Recognition System v2, highlights the superior accuracy of the proposed GRU model, which achieved an impressive overall accuracy of 99.70%. This breakthrough underscores the model’s potential in aiding educational institutions to proactively support students, thereby mitigating the risks of underachievement and dropout.

The ENGAGE study: a 3-arm randomized hybrid type 1 effectiveness and implementation study of an in-home, collaborative PCP model of remote telegenetic services to increase uptake of cancer genetic services in childhood cancer survivors

BackgroundGermline cancer genetic testing has become a standard evidence-based practice, with established risk reduction and screening guidelines for genetic carriers. Access to genetic services is limited in many places, which leaves many genetic carriers unidentified and at risk for late diagnosis of cancers and poor outcomes. This poses a problem for childhood cancer survivors, as this is a population with an increased risk for subsequent malignant neoplasms (SMN) due to cancer therapy or inherited cancer predisposition. The ENGaging and Activating cancer survivors in Genetic services (ENGAGE) study evaluates the effectiveness of an in-home, collaborative PCP model of remote telegenetic services to increase uptake of cancer genetic testing in childhood cancer survivors compared to usual care options for genetic testing.MethodsThe ENGAGE study is a 3-arm randomized hybrid type 1 effectiveness and implementation study within the Childhood Cancer Survivor Study population which tests a clinical intervention while gathering information on its delivery during the effectiveness trial and its potential for future implementation among 360 participants. Participants are randomized into three arms. Those randomized to Arm A receive genetic services via videoconferencing, those in Arm B receive these services by phone, and those randomized to Arm C will receive usual care services.DiscussionWith many barriers to accessing genetic services, innovative delivery models are needed to address this gap and increase uptake of genetic services. The ENGAGE study evaluates the effectiveness of an adapted model of remote delivery of genetic services to increase the uptake of recommended genetic testing in childhood cancer survivors. This study assesses the uptake in remote genetic services and identify barriers to uptake to inform future recommendations and a theoretically-informed process evaluation which can inform modifications to enhance dissemination beyond this study population and to realize the benefits of precision medicine.Trial registrationThis protocol was registered at clinicaltrials.gov (NCT04455698) on July 2, 2020.

MAC: EPILEPSY EEG SIGNAL RECOGNITION BASED ON THE MLP-SELF-ATTENTION MODEL AND COSINE DISTANCE

In current epilepsy disease research, accurate identification of epilepsy electroencephalogram (EEG) signals is crucial for improving diagnostic efficiency and developing personalized treatment plans. This study proposes an innovative epilepsy recognition model, MAC, which combines the unique advantages of a multilayer perceptron (MLP), a self-attention mechanism and the cosine distance. This model uses a MLP as the basic model and effectively reduces individual differences among epilepsy patients through its superior linear fitting ability. To more accurately measure the difference between two EEG signals, we introduced the cosine distance as a new feature metric. This metric enhances the performance of epilepsy EEG classification by using the cosine value of the angle in vector space to precisely assess the difference between two individuals. In addition, we introduced a self-attention mechanism into the model to enhance the impact of various factors on the final EEG data. Our experiments employed the EEG database of the Epilepsy Research Center of the University of Bonn. Through comparative experiments, it was proven that the proposed MAC model achieved significant improvement in performance on the epilepsy EEG signal recognition task. This study fills the existing research gap in the field of epilepsy identification and provides a powerful tool for the accurate diagnosis of epilepsy diseases in the future. We believe that the introduction of the MAC model will promote new breakthroughs in epilepsy EEG signal recognition and lay a solid foundation for the development of related fields. This research provides an important theoretical and practical reference for advancing the field of epilepsy identification.

EVALUATION OF ISLAMIC RELIGIOUS EDUCATION AND CHARACTER LEARNING USING COUNTENANCE STAKE MODEL

This research aims to describe the implementation of teaching of Islamic and religious education at Senior High School Jember Regency which includes planning, learning, and learning assessment, and student KKM result. It is an evaluation study using a quantitative descriptive approach with the Countenance Stake model with three phases: antecedent, transaction, outcome. The research sample comprised 9 PAI (Islamic Religious Education) teachers and 298 grade XI. The data were collected through documentation, observation, questionnaires, and interviews. The validation of the instrument was conducted through content validity and construct validity and reliability with Alpha Cronbach. The data analysis technique used the ideal criteria from Azwar. The results of this study show that: (1) The Antecedent aspects of learning planning have a 98.46% achievement with good categories. (2) The Transaction aspect includes implementing a 89.07% learning belonging to good categories and a 84.34% learning assessment with good categories. The Outcome aspect as seen from the learning outcomes of one theme has not fulfilled the Minimal submission criteria. 1) The need for learning device training, 2) The use of innovative learning models, 3) The need for periodical clinical supervision.

Reviewing healthcare financial management: Strategies for cost-effective care

This research investigates the dynamic interplay between healthcare financial management and the pursuit of cost-effective care. The study explores operational efficiency strategies, value-based care models, and technological innovations. It explores their impact on economic outcomes and regulatory compliance. Governed by acts like the Affordable Care Act and initiatives like MACRA, the regulatory landscape significantly shapes financial strategies. Technology, including data analytics and electronic health records, emerges as a critical enabler for optimizing financial efficiency. Evaluating financial outcomes, emphasizing return on investment and cost-effectiveness ratios, reveals the intricate link between fiscal responsibility and enhanced patient care. While challenges persist, including resistance to change and limited resources, the study underscores the imperative for a balanced approach, recommending continued research into long-term financial impacts and innovative financial models aligned with value-based care.

Exploring Crowd Funding as a Sustainable Financing Option among MSME in Odisha: A Case Study in Khurda District

The Micro, Small, and Medium Enterprises (MSMEs) sector is an essential and dynamic part of the Indian economy. However, these small businesses often face challenges when it comes to raising funds. Crowd funding has become a revolutionary concept in the field of finance, transforming how people and organisations raise money for their endeavours. This study aims to assess the factors affecting crowd funding as a sustainable financing option among Micro, Small, and Medium Enterprises (MSMEs) in Odisha. It also focuses on understanding the level of awareness and knowledge about crowd funding as a new and innovative financial model among the Populace of Odisha. Based upon review of literature and further interviews with the managers of MSME the five key variables which affects the adoption of crowd funding was identified. The survey involved 385 MSMEs from various industrial clusters across Khurda district in Odisha and the samples were selected using the convenience sampling technique. The findings of the study revealed that there is a moderate level of awareness of crowd funding among MSMEs in Odisha. By understanding the current perceptions and attitudes of people of MSMEs in Odisha towards crowd funding, various stakeholders such as investors, regulators, and policymakers can make more informed decisions that can potentially empower the MSME sector and drive economic growth in the region.

A Hierarchical Modeling Framework for Electrochemical Behaviors in Lithium‐Ion Batteries with Detailed Structures

The accurate representation of lithium plating and aging phenomena has posed a persistent challenge within the battery research community. Empirical evidence underscores the pivotal role of cell structure in influencing aging behaviors and lithium plating within lithium‐ion batteries (LIBs). Available lithium‐ion plating models often falter in detailed description when integrating the structural intricacies. To address this challenge, this study proposes an innovative hierarchical model that intricately incorporates the layered rolling structure in cells. Notably, our model demonstrates a remarkable capacity to predict the non‐uniform distribution of current density and overpotential along the rolling direction of LIBs. Subsequently, we delve into an insightful exploration of the structural factors that influence lithium plating behavior, leveraging the foundation laid by our established model. Furthermore, we easily update the hierarchical model by considering aging factors. This aging model effectively anticipates capacity fatigue and lithium plating tendencies across individual layers of LIBs, all while maintaining computational efficiency. In light of our findings, this model yields novel perspectives on capacity fatigue dynamics and local lithium plating behaviors, offering a substantial advancement compared to existing models. This research paves the way for more efficient and tailored LIB design and operation, with broad implications for energy storage technologies.

PulmoNet: a novel deep learning based pulmonary diseases detection model

Pulmonary diseases are various pathological conditions that affect respiratory tissues and organs, making the exchange of gas challenging for animals inhaling and exhaling. It varies from gentle and self-limiting such as the common cold and catarrh, to life-threatening ones, such as viral pneumonia (VP), bacterial pneumonia (BP), and tuberculosis, as well as a severe acute respiratory syndrome, such as the coronavirus 2019 (COVID-19). The cost of diagnosis and treatment of pulmonary infections is on the high side, most especially in developing countries, and since radiography images (X-ray and computed tomography (CT) scan images) have proven beneficial in detecting various pulmonary infections, many machine learning (ML) models and image processing procedures have been utilized to identify these infections. The need for timely and accurate detection can be lifesaving, especially during a pandemic. This paper, therefore, suggested a deep convolutional neural network (DCNN) founded image detection model, optimized with image augmentation technique, to detect three (3) different pulmonary diseases (COVID-19, bacterial pneumonia, and viral pneumonia). The dataset containing four (4) different classes (healthy (10,325), COVID-19 (3,749), BP (883), and VP (1,478)) was utilized as training/testing data for the suggested model. The model’s performance indicates high potential in detecting the three (3) classes of pulmonary diseases. The model recorded average detection accuracy of 94%, 95.4%, 99.4%, and 98.30%, and training/detection time of about 60/50 s. This result indicates the proficiency of the suggested approach when likened to the traditional texture descriptors technique of pulmonary disease recognition utilizing X-ray and CT scan images. This study introduces an innovative deep convolutional neural network model to enhance the detection of pulmonary diseases like COVID-19 and pneumonia using radiography. This model, notable for its accuracy and efficiency, promises significant advancements in medical diagnostics, particularly beneficial in developing countries due to its potential to surpass traditional diagnostic methods.

Determining the Availability of Continuous Systems in Open Pits Using ANFIS and a Simulation Model

This paper presents a model for determining the availability of continuous systems at open pits using the neuro-fuzzy system. The concept of availability is divided into partial indicators (synthetic indicators and sub-indicators). The presented model in relation to already existing models for determining availability uses a combination of the advantages of artificial neural networks and fuzzy logic. The case study addressed the I ECC (bucket wheel excavator–conveyors–crushing plant) system of the open pit Drmno, Kostolac. In this paper, in addition to the ANFIS model for determining the availability of continuous systems, a simulation model was developed. The obtained results of the ANFIS model were verified with the help of a simulation model that uses certain assumptions about the distribution of failures. This paper was created as a result of several years of field and theoretical research into the availability of continuous systems in open pits, and completes a cycle that consists of several published articles on the subject of modeling the behavior of these systems in real time using a time picture of the state, expert assessment, simulation and AI models, while respecting the multidisciplinarity of the problem (mining technological, mechanical, and information technological aspects). The developed ANFIS model is a key instrument for improving operational efficiency and resource management in the mining sector. Its ability to accurately predict the availability of the ECC system brings not only operational benefits through reduced downtime and optimized maintenance, but also a potential reduction in overall costs at coal open pits. Such an innovative model marks a significant step forward in the mining industry, especially when it comes to continuous systems in coal open pits.

The needs of a metacognitive-based learning model in elementary schools

Purpose: This research aims to analyze the need for developing metacognitive-based learning models in elementary schools.
 Design/Methodology/Approach: This research uses mixed methods. The mixed-methods research design used in this research is concurrent embedded mixed methods. The population of this study was 2,416 elementary schools. Sample selection: 476 elementary school teachers were involved in the development needs analysis survey. Methods of data collection include observation, interviews, surveys and questionnaires. The data collection instrument uses a questionnaire sheet. The data analysis technique uses qualitative and quantitative descriptive analysis.
 Findings: The research results show that 28.8% of respondents stated that they had implemented the independent curriculum, 65.1% combined the independent curriculum and the 2013 curriculum and 6.1% still used the 2013 curriculum. The survey results on learning support facilities showed that adequate facilities supported learning. 93.7% of teachers said that they always use innovative learning models. The remaining 6.3% still rarely implement innovative models. The survey results showed that 69.54% of teachers reported understanding metacognition sufficiently. However, 97.47% of teachers rarely or never integrate the concept of metacognition into their teaching methods.
 Conclusion: It is essential that elementary schools adopt metacognitive-based learning approaches in order to equip students with the critical and creative thinking skills necessary to become lifelong learners. This skill is useful for overcoming obstacles in daily life as well as in the field of education.

Interpretable wind speed forecasting with meteorological feature exploring and two-stage decomposition

Wind speed plays a pivotal role in ensuring the stability of power grid operations. However, the inherent high volatility and non-stationarity of wind patterns pose significant challenges to achieving accurate predictions. To tackle this issue and enhance the interpretability of existing wind speed prediction models, this study proposes an innovative short-term wind speed prediction model that combines two-stage decomposition, meteorological data feature engineering, adaptive differential evolution with optional external archive (JADE) algorithm, and temporal fusion transformers (TFT). To begin, the wind speed data is subjected to decomposition using improved complete ensemble empirical mode decomposition with adaptive noise (IEEMD), yielding multiple eigenmode functions. Subsequently, the nonlinear decomposition subsequence undergoes further decomposition into multiple submodes via empirical wavelet transform (EWT), followed by the careful screening of nonlinear quadratic decomposition submodes. Additionally, meteorological features are ingeniously reconstructed into combined and statistical meteorological features, enhancing the effectiveness of input features. Next, the hyperparameters of the TFT are meticulously optimized using the powerful JADE algorithm. Empirical results unequivocally demonstrate that the IEEMD-EWT-JADE-TFT model achieves remarkably high prediction accuracy. Meanwhile, this interpretative experimental process and its results chart a novel path for decision-makers seeking reliable wind speed forecasting processes and outcomes.

Deciphering the Efficacy of No-Attention Architectures in Computed Tomography Image Classification: A Paradigm Shift

The burgeoning domain of medical imaging has witnessed a paradigm shift with the integration of AI, particularly deep learning, enhancing diagnostic precision and expediting the analysis of Computed Tomography (CT) images. This study introduces an innovative Multilayer Perceptron-driven model, DiagnosticMLP, which sidesteps the computational intensity of attention-based mechanisms, favoring a no-attention architecture that leverages Fourier Transforms for global information capture and spatial gating units for local feature emphasis. This study’s methodology encompasses a sophisticated augmentation and patching strategy at the input level, followed by a series of MLP blocks designed to extract hierarchical features and spatial relationships, culminating in a global average pooling layer before classification. Evaluated against state-of-the-art MLP-based models including MLP-Mixer, FNet, gMLP, and ResMLP across diverse and extensive CT datasets, including abdominal, and chest scans, DiagnosticMLP demonstrated a remarkable ability to converge efficiently, with competitive accuracy, F1 scores, and AUC metrics. Notably, in datasets featuring kidney and abdomen disorders, the model showcased superior generalization capabilities, underpinned by its unique design that addresses the complexity inherent in CT imaging. The findings in terms of accuracy and precision-recall balance posit DiagnosticMLP as an exceptional outperforming alternative to attention-reliant models, paving the way for streamlined, efficient, and scalable AI tools in medical diagnostics, reinforcing the potential for AI-augmented precision medicine without the dependency on attention-based architectures.