Innovative Framework Research Articles

Assessing sensitivity to climate-related disasters in the context of a developing country: Evidence from the coastal region of Bangladesh

Climate-related disasters have become a major threat to human civilization. Since many climatic hazards cannot be prevented, recognizing the underlying factors that render societies more vulnerable might facilitate pragmatic measures for minimizing the likelihood of disasters. With this impulse, the current study developed an innovative framework for appraising various societal attributes, the interplay of which potentially adds to the vulnerabilities of the coastal region of Bangladesh. In our study, we harnessed the notion of sensitivity used in disaster discourse and proposed five major domains of sensitivity namely demographic setback, inadequacy of basic resources, economic marginality, socio-cultural impediments and fragility of policy and governance, based on the conceptual adaptation of the prior social vulnerability frameworks. A total of thirty-five context-specific variables were consolidated under these five domains. To determine the weights of the variables, the popular Analytic Hierarchy Process (AHP) technique was applied. Respective variables were summed up with appropriate weights to generate the five subindices which were eventually integrated using the additive (averaging) approach to develop a composite sensitivity index for the nineteen coastal districts. The outcomes of the sensitivity assessment were spatially mapped. Coxsbazar (0.60), Pirojpur (0.39) Bagerhat (0.38), Shariatpur (0.37), Patuakhali (0.34), and Chandpur (0.33) were the most sensitive districts, which is attributable to diverse key factors. Our study thus delineates the areas that require prioritized actions for reducing vulnerability and offers an opportunity to improve the prevailing interventions aimed at Disaster Risk Reduction across the coastal region of Bangladesh. Moreover, the integration of factors like child labor, violence against women, early marriage of girls, corruption, and crime that have not been previously considered, but often act as factors shaping increased vulnerability render the current framework a conceptual advancement for understanding sensitivity to climate-related disasters in other developing countries of the world.

Copernicus for urban resilience in Europe

The urban community faces a significant obstacle in effectively utilising Earth Observation (EO) intelligence, particularly the Copernicus EO program of the European Union, to address the multifaceted aspects of urban sustainability and bolster urban resilience in the face of climate change challenges. In this context, here we present the efforts of the CURE project, which received funding under the European Union’s Horizon 2020 Research and Innovation Framework Programme, to leverage the Copernicus Core Services (CCS) in supporting urban resilience. CURE provides spatially disaggregated environmental intelligence at a local scale, demonstrating that CCS can facilitate urban planning and management strategies to improve the resilience of cities. With a strong emphasis on stakeholder engagement, CURE has identified eleven cross-cutting applications between CCS that correspond to the major dimensions of urban sustainability and align with user needs. These applications have been integrated into a cloud-based platform known as DIAS (Data and Information Access Services), which is capable of delivering reliable, usable and relevant intelligence to support the development of downstream services towards enhancing resilience planning of cities throughout Europe.

Advancing the Management of Long COVID by Integrating into Health Informatics Domain: Current and Future Perspectives.

The ongoing COVID-19 pandemic has profoundly affected millions of lives globally, with some individuals experiencing persistent symptoms even after recovering. Understanding and managing the long-term sequelae of COVID-19 is crucial for research, prevention, and control. To effectively monitor the health of those affected, maintaining up-to-date health records is essential, and digital health informatics apps for surveillance play a pivotal role. In this review, we overview the existing literature on identifying and characterizing long COVID manifestations through hierarchical classification based on Human Phenotype Ontology (HPO). We outline the aspects of the National COVID Cohort Collaborative (N3C) and Researching COVID to Enhance Recovery (RECOVER) initiative in artificial intelligence (AI) to identify long COVID. Through knowledge exploration, we present a concept map of clinical pathways for long COVID, which offers insights into the data required and explores innovative frameworks for health informatics apps for tackling the long-term effects of COVID-19. This study achieves two main objectives by comprehensively reviewing long COVID identification and characterization techniques, making it the first paper to explore incorporating long COVID as a variable risk factor within a digital health informatics application. By achieving these objectives, it provides valuable insights on long COVID's challenges and impact on public health.

Application of modern digital technologies in the field of taxation: foreign experience and prospects for Ukraine

Problem setting. In the current conditions of digitalization of social relations, the implementation of the latest digital technologies in the sphere of public legal relations is of great importance. Tax relations are certainly one of such relations. Such technologies (FinTech, Blockchain) create both new opportunities for the participants of such relations (we are talking about the interaction of the state represented by regulatory authorities and taxpayers) and certain challenges for taxpayers. analysis of recent researches and publications. The issue of using modern digital technologies, including in the field of taxation, is currently very relevant. Some aspects of the use of digital technologies in the financial sector are covered in the works of such domestic scholars as: H. Bukharin, O. Dmytryk, R. Samsin, O. Terliuk, K. Tokarieva, V. Riadinska, ect. At the same time, no comprehensive research on this topic has yet been conducted. Purpose of the research is to analyze foreign experience and trends in the use of modern digital technologies in the field of taxation in Ukraine. article’s main body. Attention is focused on the lack of legislative consolidation of the category “blockchain” in Ukraine. It is emphasized that blockchain technology implements the principle of convenience of taxpayers’ tax liability fulfillment. In Ukraine, a similar principle has also been enshrined in legislation, namely, the principle of uniformity and convenience of payment, enshrined in Article 4 of the Tax Code of Ukraine. The author argues that in the context of the topic under study, this principle should be considered broader than just the convenience of payment, since taxpayers and regulatory authorities have relations not only with regard to payment of taxes and fees. It is noted that under martial law in Ukraine, the use of digital technologies and electronic services has greatly simplified the interaction of obligated and authorized participants to tax relations. It is stated that when using blockchain, the security of data (information) contained in the relevant registers or services is enhanced, and thus, the protection of taxpayers’ rights is ensured. This is one of the issues of great concern to taxpayers ensuring the security and protection of tax information transmitted between the relevant parties to tax relations. conclusions and prospects for the development. It is emphasized that the purposes of using this digital technology in taxation are different for each particular State, depending on the country’s tax policy. Based on the analysis of foreign experience of implementing blockchain technology in the tax area, the author emphasizes the importance of creating a high-quality legal framework for such innovations, since this will be crucial for further practical application of such mechanisms and will create relevant consequences, affect the quality of the State’s tax policy and form an appropriate model of interaction between regulatory authorities and taxpayers.

Source apportionment and source specific health risk assessment of HMs and PAHs in soils with an integrated framework in a typical cold agricultural region in China

A new innovative methodology system framework for source apportionment and source-specific risk assessment has been proposed and actively applied to identify the contamination characteristics, oriented sources and health risks associated with contamination levels of Heavy metals (HMs) and Polycyclic Aromatic Hydrocarbons (PAHs) in soils, a typical cold agricultural region in Northeastern China. To achieve this meaningful goal, a large-scale dataset including 1780 top soil samples, 10 HMs and 16 priority PAHs has been organized and collected from a typical study area in China. The total concentrations of the 10 selected HMs in study area range from 0.05 to 2147.40 mg/kg, with an average of 549.25 ± 541.37 mg/kg. The average concentrations of PAHs for (3–6)-rings are 16.60 ± 18.90, 26.40 ± 28.20, 9.51 ± 13.00 and 1.99 ± 5.30 ng/g, respectively. On the base of optimized literature source fingerprints for HM and PAH, a widely used receptor model, positive matrix factorization (PMF) has been applied to apportion the contamination sources HMs and PAHs in soils. Then source-specific health risk of soil HMs and PAHs have been assessed using the probabilistic incremental lifetime cancer risk model incorporated with source apportionment results data. Fertilizer residues/coke oven comprise the primary contamination source contributors of HMs and PAHs with corresponding contributions of 32.23 % and 27.93 % for HMs and 37.94 % for PAHs. Fertilizer/pesticide residues contributes most to the risks of soil HMs (28.8 %), followed by fossil fuel combustion (24.6 %), mining activities (20.2 %), traffic and vehicle emission (16.3 %) and electroplating/dyeing (14.1 %). Meanwhile, the ranking of health risks from the five identified contamination sources of soil PAHs are resident discharge, coal-fired boilers, coke oven emission, gasoline combustion and power plant, with the contribution of 27.1 %, 25.3 %, 17.3 %, 15.5 % and 14.8 %.And relatively, source-specific risk assessment demonstrates fossil fuel and coal combustion contribute the greatest impact to the total risk of HMs and PAHs (61.7 % and 56.1 %), respectively. This study provides a good example of how the source specific health risk assessment can be utilized to reduce the contamination in soils.

The added value of exploring course innovations university-wide: an application of a multifaceted analytical course innovation framework

ABSTRACT In response to challenges emerging in society, universities are searching for ways to innovate their courses through novel institutional educational policies and practices. Those efforts, however, are often not informed by knowledge about course innovation characteristics university-wide, and are often not supported by processes of reflection questioning the ‘who’, ‘how’ and ‘for what’ of course innovations. This study applied the multifaceted analytical Course Innovation Framework (CIF) in order to explore characteristics of a large set of intended course innovations in a higher education institution in the Netherlands. The application of the CIF enabled a descriptive analysis of multiple characteristics of the intended course innovations. This analysis unveiled university-wide course innovation trends, upon which university stakeholders reflected in order to responsibly guide and transform policy and practices. The study findings show how the application of the CIF helps to gather situated knowledge on university-wide innovation trends, and how reflection on these trends empowers stakeholders to deliberate the culture and values of educational innovation they wish to promote within their institution.

Graph Convolutional Network and Contrastive Learning Small Nucleolar RNA (snoRNA) Disease Associations (GCLSDA): Predicting snoRNA-Disease Associations via Graph Convolutional Network and Contrastive Learning.

Small nucleolar RNAs (snoRNAs) constitute a prevalent class of noncoding RNAs localized within the nucleoli of eukaryotic cells. Their involvement in diverse diseases underscores the significance of forecasting associations between snoRNAs and diseases. However, conventional experimental techniques for such predictions suffer limitations in scalability, protracted timelines, and suboptimal success rates. Consequently, efficient computational methodologies are imperative to realize the accurate predictions of snoRNA-disease associations. Herein, we introduce GCLSDA-graph Convolutional Network and contrastive learning predict snoRNA disease associations. GCLSDA is an innovative framework that combines graph convolution networks and self-supervised learning for snoRNA-disease association prediction. Leveraging the repository of MNDR v4.0 and ncRPheno databases, we construct a robust snoRNA-disease association dataset, which serves as the foundation to create bipartite graphs. The computational prowess of the light graph convolutional network (LightGCN) is harnessed to acquire nuanced embedded representations of both snoRNAs and diseases. With careful consideration, GCLSDA intelligently incorporates contrast learning to address the challenging issues of sparsity and over-smoothing inside correlation matrices. This combination not only ensures the precision of predictions but also amplifies the model's robustness. Moreover, we introduce the augmentation technique of random noise to refine the embedded snoRNA representations, consequently enhancing the precision of predictions. Within the domain of contrast learning, we unite the tasks of contrast and recommendation. This harmonization streamlines the cross-layer contrast process, simplifying the information propagation and concurrently curtailing computational complexity. In the area of snoRNA-disease associations, GCLSDA constantly shows its promising capacity for prediction through extensive research. This success not only contributes valuable insights into the functional roles of snoRNAs in disease etiology, but also plays an instrumental role in identifying potential drug targets and catalyzing innovative treatment modalities.

Model-Free-Communication Federated Learning: Framework and application to Precision Medicine

The problem of executing machine learning algorithms over data while complying with data privacy is highly relevant in many application areas, including medicine in general and Precision Medicine in particular.In this paper, an innovative framework for Federated Learning is proposed that allows performing machine learning and effectively tackling the issue of data privacy while taking a step towards security during communication. Unlike the standard federated approaches where models should travel on the communication networks and would be subject to possible cyberattacks, the models proposed by our framework do not need to travel, thus moving in the direction of security improvement. Another very appealing feature is that it can be used with any machine learning algorithm provided that, during the learning phase, the model updating does not depend on the input data.To show its effectiveness, the learning process is here accomplished by an Evolutionary Algorithm, namely Grammatical Evolution, thus also obtaining explicit knowledge that can be provided to the domain experts to justify the decisions made. As a test case, glucose values prediction for a number of patients with type 1 diabetes is considered and is tackled as a classification problem, the goal being to predict for any future value a possible range. Finally, a comparison of the performance of the proposed framework is performed against that of a non-Federated Learning approach.

Multidimensional perspective of Corporate Capital Efficiency and Financial Risk policies lead on Capital misallocation: The case of Pakistan

This work uses innovative and traditional analyses and explores innovative financial frameworks to increase capital efficacy, decrease financial risks, and address capital mismanagement issues. The analysis is carried out on Pakistan's listed non-financial companies' data, obtained from the Pakistan stock exchange (PSX). Pooled OLS and the robust, truncated, random-effect regression model were used for the analysis. According to the findings, capital mismanagement was quantified through the asset returns' dispersion and return on capital employed. Capital mismanagement was higher in the traditional analysis and lower in the innovative analysis. Traditional financial analysis shows a significant and positive relationship between capital efficiency and capital mismanagement, while innovative financial analysis shows a negative relationship. In contrast, according to innovative financial analysis, financial risk and capital mismanagement have a negative relationship. Capital mismanagement was a major impediment to firms moving towards greater capital efficiency. Policy evaluation should contrast changes in two financial analytic approaches for measuring capital and resource mismanagement.

Resilience Enhancement with Transportable Storage Systems and Repair Crews in Coupled Transportation and Distribution Networks

The significance of resilience within power system infrastructures has been progressively acknowledged. To address this challenge, this paper introduces an innovative framework to enhance distribution network (DN) resilience by incorporating transportable storage systems (TSSs). To do so, we take into account the interconnection between the DN and the transportation network (TN) to optimize the trajectory planning of TSSs. To account for real-world features, the traffic flow of TN is modeled according to traffic counter cameras of Sioux Falls city. In addition, the effects of blocked roads on TSSs' movements through microgrids (MGs), and clearing operation of obstructions by repair crews are considered as these factors have a great impact on system operational cost. Further, an optimal reconfiguration program is proposed to add more flexibility to the system. The developed model is formulated as mixed-integer linear programming (MILP) and various case studies are presented including analyzing TSSs and repair crews’ operations, both individually and concurrently. Different case studies reveal the positive impact of TSSs, reducing the total cost of the system by approximately 13.11%. In post-event, blocked roads directly increase the operation costs by 17.02%; however, repair crews' cooperation with TSSs, achieved a remarkable 12.75% reduction in operation costs.

IoT-Based Mushroom Cultivation System with Solar Renewable Energy Integration: Assessing the Sustainable Impact of the Yield and Quality

The conventional method of mushroom cultivation can be labor-intensive and produce limited yields. Due to the humidity and temperature in the summer season, mushroom production is significantly diminished. The growth of each mushroom species depends on the consistency of care, the skill of experienced farmers, and crucial cultivation parameters such as temperature, humidity, irrigation, and exposure to sunlight. This study aims to implement an IoT-enabled cultivation system to control and monitor the environmental parameters of Indian mushroom cultivation within the proposed innovative framework, as compared to conventional methods. The IoT-based cultivation system consists of hardware components, circuit connections, software, and algorithms. This study confirms that consistent control of environmental parameters, such as temperature and relative humidity, by a dynamic climate promotes mushroom growth that is superior to conventional cultivation. Our findings reveal a substantial increase in the yield and quality of mushrooms, demonstrating the tangible advantages of applying an innovative approach. Traditional cultivation yielded an average of 4.118 kg, whereas IoT-based cultivation systems produced an average of 5.306 kg. The t-test statistic comparing yields has highlighted the significance of the observed differences with a p-value of 0.0000. The research contributions are to design and demonstrate the IoT-enabled system innovation with solar renewable energy, illustrating the effect of mushroom production and quality on the economic market analysis of mushroom cultivation in the direction of environmentally sustainable and green agricultural practices. This study’s comprehensive perspective can provide farmers, agricultural professionals, and policymakers with valuable insights regarding the future of mushroom cultivation, particularly the reduction of carbon emissions and energy consumption.

Optimal Integration of Machine Learning for Distinct Classification and Activity State Determination in Multiple Sclerosis and Neuromyelitis Optica

The intricate neuroinflammatory diseases multiple sclerosis (MS) and neuromyelitis optica (NMO) often present similar clinical symptoms, creating challenges in their precise detection via magnetic resonance imaging (MRI). This challenge is further compounded when detecting the active and inactive states of MS. To address this diagnostic problem, we introduce an innovative framework that incorporates state-of-the-art machine learning algorithms applied to features culled from MRI scans by pre-trained deep learning models, VGG-NET and InceptionV3. To develop and test this methodology, we utilized a robust dataset obtained from the King Abdullah University Hospital in Jordan, encompassing cases diagnosed with both MS and NMO. We benchmarked thirteen distinct machine learning algorithms and discovered that support vector machine (SVM) and K-nearest neighbor (KNN) algorithms performed superiorly in our context. Our results demonstrated KNN’s exceptional performance in differentiating between MS and NMO, with precision, recall, F1-score, and accuracy values of 0.98, 0.99, 0.99, and 0.99, respectively, using leveraging features extracted from VGG16. In contrast, SVM excelled in classifying active versus inactive states of MS, achieving precision, recall, F1-score, and accuracy values of 0.99, 0.97, 0.98, and 0.98, respectively, using leveraging features extracted from VGG16 and VGG19. Our advanced methodology outshines previous studies, providing clinicians with a highly accurate, efficient tool for diagnosing these diseases. The immediate implication of our research is the potential to streamline treatment processes, thereby delivering timely, appropriate care to patients suffering from these complex diseases.

Ability in Intellectual Disability: The Culture of Inequality in Nigeria and Other Jurisdictions

This paper examines the disputable issue of the culture of inequality in providing legal protection for children living with intellectual disabilities. It argues the disparity in the provision of educational and health services for persons living with intellectual disabilities by the Nigerian Government and identifies the gaps in the provisions of Sections 20 and 21 of the Nigerian Discrimination Act. These deficiencies obscure the ability of children living with disabilities (Down syndrome and Autism), which culminates in a domino effect from delayed intervention. It draws a comparative analysis from the United Kingdom and the United States of America as a standard for innovative legal frameworks in Nigeria. It concludes that non-governmental organisations must collaborate with the government to ameliorate Nigeria's poor education and health care, with a differential detour that rights to free education and health care for those with intellectual disabilities be justiciable for the Act's practicability.

Efficient and Controllable Model Compression through Sequential Knowledge Distillation and Pruning

Efficient model deployment is a key focus in deep learning. This has led to the exploration of methods such as knowledge distillation and network pruning to compress models and increase their performance. In this study, we investigate the potential synergy between knowledge distillation and network pruning to achieve optimal model efficiency and improved generalization. We introduce an innovative framework for model compression that combines knowledge distillation, pruning, and fine-tuning to achieve enhanced compression while providing control over the degree of compactness. Our research is conducted on popular datasets, CIFAR-10 and CIFAR-100, employing diverse model architectures, including ResNet, DenseNet, and EfficientNet. We could calibrate the amount of compression achieved. This allows us to produce models with different degrees of compression while still being just as accurate, or even better. Notably, we demonstrate its efficacy by producing two compressed variants of ResNet 101: ResNet 50 and ResNet 18. Our results reveal intriguing findings. In most cases, the pruned and distilled student models exhibit comparable or superior accuracy to the distilled student models while utilizing significantly fewer parameters.

Underrepresented Students in Gifted and Talented Education: Using Positive Psychology to Identify and Serve

The representation gap in gifted and talented education poses a persistent challenge in educational systems worldwide. This theoretical manuscript presents the Bull’s Eye Model for Affective Development—Expansion (BEM-e) an innovative framework designed to address this gap. By incorporating elements from positive psychology, the BEM-e aims to identify and nurture traditionally underrepresented students who possess camouflaged gifted and talented abilities. Drawing upon the Engagement, Perseverance, Optimism, Connectedness, and Happiness model (EPOCH), along with measures of hope and metacognition, BEM-e provides a comprehensive approach to talent identification and service. The model emphasizes the holistic development of individuals by considering affective factors, engagement, perseverance, optimism, connectedness, happiness, hope, and metacognition. Additionally, dynamic assessment is integrated during the implementation of BEM-e modules, allowing for personalized and adaptive identification processes.

Efficient Wheat Lodging Detection Using UAV Remote Sensing Images and an Innovative Multi-Branch Classification Framework

Wheat lodging has a significant impact on yields and quality, necessitating the accurate acquisition of lodging information for effective disaster assessment and damage evaluation. This study presents a novel approach for wheat lodging detection in large and heterogeneous fields using UAV remote sensing images. A comprehensive dataset spanning an area of 2.3117 km2 was meticulously collected and labeled, constituting a valuable resource for this study. Through a comprehensive comparison of algorithmic models, remote sensing data types, and model frameworks, this study demonstrates that the Deeplabv3+ model outperforms various other models, including U-net, Bisenetv2, FastSCN, RTFormer, Bisenetv2, and HRNet, achieving a noteworthy F1 score of 90.22% for detecting wheat lodging. Intriguingly, by leveraging RGB image data alone, the current model achieves high-accuracy rates in wheat lodging detection compared to models trained with multispectral datasets at the same resolution. Moreover, we introduce an innovative multi-branch binary classification framework that surpasses the traditional single-branch multi-classification framework. The proposed framework yielded an outstanding F1 score of 90.30% for detecting wheat lodging and an accuracy of 86.94% for area extraction of wheat lodging, surpassing the single-branch multi-classification framework by an improvement of 7.22%. Significantly, the present comprehensive experimental results showcase the capacity of UAVs and deep learning to detect wheat lodging in expansive areas, demonstrating high efficiency and cost-effectiveness under heterogeneous field conditions. This study offers valuable insights for leveraging UAV remote sensing technology to identify post-disaster damage areas and assess the extent of the damage.

AN EXPLORATION OF HEALTHY AGRICULTURAL PRODUCT DEVELOPMENT STRATEGIES WITHIN INDONESIAN SMALL AND MEDIUM-SIZED ENTERPRISES (SMES)

For the first time, this study aims to comprehensively explore the landscape of innovation and healthy product development within Indonesian Small and medium-sized enterprises (SMEs) in the food and drinks industry. By addressing existing gaps, the paper provides insights into the context-specific factors, the role of healthy product variants, and the interconnected dynamics that drive innovation. The research employs a thorough literature review. The literature review establishes the foundation by identifying gaps and theoretical frameworks, including the Innovation Ecosystem Theory, to guide the analysis. The findings illuminate several key contributions of this research. First, the study crystallizes the specific new product development practices within Indonesian SMEs, addressing the lack of context-specific insights. It highlights the significance of healthy product development within a changing consumer landscape. The analysis reveals diverse strategies, challenges, and successes, emphasizing the role of networking, creative innovation drivers, and the absence of financial constraints. Furthermore, the introduction of a unified framework for innovation provides a holistic understanding that bridges theoretical constructs and practical applications. This study identifies flaws in the current innovation policy, suggesting actionable recommendations for improvement. In conclusion, this paper fills critical gaps in the literature, offering a comprehensive exploration of innovation and healthy product development within Indonesian SMEs in the food and drinks industry. By integrating context-specific insights, addressing gaps, and providing practical value for stakeholders and policymakers, the research significantly advances our understanding of healthy agricultural product development.

Neurophysiological Assessment of An Innovative Maritime Safety System in Terms of Ship Operators' Mental Workload, Stress, and Attention in the Full Mission Bridge Simulator.

The current industrial environment relies heavily on maritime transportation. Despite the continuous technological advances for the development of innovative safety software and hardware systems, there is a consistent gap in the scientific literature regarding the objective evaluation of the performance of maritime operators. The human factor is profoundly affected by changes in human performance or psychological state. The difficulty lies in the fact that the technology, tools, and protocols for investigating human performance are not fully mature or suitable for experimental investigation. The present research aims to integrate these two concepts by (i) objectively characterizing the psychological state of mariners, i.e., mental workload, stress, and attention, through their electroencephalographic (EEG) signal analysis, and (ii) validating an innovative safety framework countermeasure, defined as Human Risk-Informed Design (HURID), through the aforementioned neurophysiological approach. The proposed study involved 26 mariners within a high-fidelity bridge simulator while encountering collision risk in congested waters with and without the HURID. Subjective, behavioral, and neurophysiological data, i.e., EEG, were collected throughout the experimental activities. The results showed that the participants experienced a statistically significant higher mental workload and stress while performing the maritime activities without the HURID, while their attention level was statistically lower compared to the condition in which they performed the experiments with the HURID (all p < 0.05). Therefore, the presented study confirmed the effectiveness of the HURID during maritime operations in critical scenarios and led the way to extend the neurophysiological evaluation of the HFs of maritime operators during the performance of critical and/or standard shipboard tasks.

Implementation of Artificial Intelligence for Financial Process Innovation of Commercial Banks

Purpose: The purpose of this study is to investigate and illuminate the transformative potential of artificial intelligence (AI) in the context of enhancing financial services within Jordanian commercial banks, with a specific focus on credit risk management. By researching into the applications of AI within this sector, the study aims to provide insights into how AI technologies can reshape traditional banking practices and improve the overall efficiency and effectiveness of credit risk management processes.&#x0D; &#x0D; Theoretical framework: The study is grounded in the theoretical framework of technological innovation and strategic management. It draws from the literature on AI adoption in the financial industry and its implications for operational efficiency, risk assessment, and customer experience. Additionally, the study incorporates concepts related to data analysis, machine learning, and predictive modeling as key components of AI-driven transformation within the banking sector.&#x0D; &#x0D; Method/design/approach: To achieve the research objectives, a systematic research design is employed, utilizing survey methods as the primary data collection tool. A sample of 143 employees from major banks located in Amman, Jordan, is selected for participation. The survey encompasses questions designed to gather information about the current state of AI integration, challenges faced, and potential benefits within credit risk management and other financial services. This quantitative approach allows for the collection of structured data that can be statistically analyzed to uncover trends and patterns.&#x0D; &#x0D; Results and conclusion: The findings of the study highlight the substantial potential of AI integration in revolutionizing the operations of Jordanian commercial banks. AI technologies enable more accurate credit assessment, precise analysis of market risks, enhanced financial forecasting capabilities, robust validation of risk models, and advanced evaluation of creditworthiness. Furthermore, the study reveals that AI offers the opportunity for personalized customer service solutions, thereby improving the user experience and guiding customers toward suitable financial services. In conclusion, the study underscores the positive impact of leveraging AI-driven innovation on financial performance and profitability within Jordan's banking sector.&#x0D; &#x0D; Research implications: This study has implications for academia and the banking industry, contributing to knowledge about AI's strategic use in financial innovation and its application in Jordanian commercial banks for credit risk management and customer service enhancement.&#x0D; &#x0D; Originality/value: This research stands out by focusing on Jordanian banks' AI adoption, providing distinct insights into challenges and opportunities in a specific context. Its value lies in guiding banks to effectively integrate AI, enhancing credit risk management and financial services for improved performance and innovation.

Prediction of diabetes disease using an ensemble of machine learning multi-classifier models

Background and objectiveDiabetes is a life-threatening chronic disease with a growing global prevalence, necessitating early diagnosis and treatment to prevent severe complications. Machine learning has emerged as a promising approach for diabetes diagnosis, but challenges such as limited labeled data, frequent missing values, and dataset imbalance hinder the development of accurate prediction models. Therefore, a novel framework is required to address these challenges and improve performance.MethodsIn this study, we propose an innovative pipeline-based multi-classification framework to predict diabetes in three classes: diabetic, non-diabetic, and prediabetes, using the imbalanced Iraqi Patient Dataset of Diabetes. Our framework incorporates various pre-processing techniques, including duplicate sample removal, attribute conversion, missing value imputation, data normalization and standardization, feature selection, and k-fold cross-validation. Furthermore, we implement multiple machine learning models, such as k-NN, SVM, DT, RF, AdaBoost, and GNB, and introduce a weighted ensemble approach based on the Area Under the Receiver Operating Characteristic Curve (AUC) to address dataset imbalance. Performance optimization is achieved through grid search and Bayesian optimization for hyper-parameter tuning.ResultsOur proposed model outperforms other machine learning models, including k-NN, SVM, DT, RF, AdaBoost, and GNB, in predicting diabetes. The model achieves high average accuracy, precision, recall, F1-score, and AUC values of 0.9887, 0.9861, 0.9792, 0.9851, and 0.999, respectively.ConclusionOur pipeline-based multi-classification framework demonstrates promising results in accurately predicting diabetes using an imbalanced dataset of Iraqi diabetic patients. The proposed framework addresses the challenges associated with limited labeled data, missing values, and dataset imbalance, leading to improved prediction performance. This study highlights the potential of machine learning techniques in diabetes diagnosis and management, and the proposed framework can serve as a valuable tool for accurate prediction and improved patient care. Further research can build upon our work to refine and optimize the framework and explore its applicability in diverse datasets and populations.