Proposed Framework Research Articles

Is There a "Best" Way for Patients to Participate in Pharmacovigilance?

The underreporting of suspected adverse drug reactions hinders pharmacovigilance. Solutions to underreporting are oftentimes directed at clinicians and healthcare professionals. However, given the recent rise of public inclusion in medical science, solutions may soon begin more actively involving patients. I aim to offer an evaluative framework for future possible proposals that would engage patients with the aim of mitigating underreporting. The framework may also have value in evaluating current reporting practices. The offered framework is composed of three criteria that are bioethical, social-epistemic, and pragmatic: (i) patients should not be exposed to undue harms, for example, nocebo effects; (ii) data should be collected, analyzed, and communicated while prioritizing pharmacovigilance's aims, that is, free from industry bias; and (iii) proposals should account for existing and foreseeable pragmatic constraints like clinician "buy in" and existing reporting infrastructure. Proposals to engage patients in pharmacovigilance that fulfil or address these criteria are preferable to those that do not.

A Human Resource Evaluation and Recommendation System based on Big Data Mining

This investigation presents a paradigm-shifting Human Resource (HR) Assessment and Recommendation Framework, leveraging progressed huge information mining procedures. Drawing bits of knowledge from cybersecurity, healthcare, education, and further detecting spaces, our framework utilizes a different cluster of calculations, counting Arbitrary Forests, Support Vector Machines, K-Means Clustering, and a Feedforward Neural Organize. The comparative investigation uncovers the Feedforward Neural Network as the standout entertainer, emphasizing its various levels including learning for complicated design acknowledgement inside HR measurements. Uniquely, this framework draws on methodologies and insights from varied domains such as cybersecurity, healthcare, and education, applying these rich, interdisciplinary perspectives to HR analytics. This cross-pollination of ideas enables the framework to adopt sophisticated data mining and pattern recognition techniques that are not traditionally utilized within HR, offering new avenues for detecting and interpreting complex employee data patterns. Result values illustrate the system’s adequacy, with a precision of 88%, an accuracy of 90%, a review of 87%, and an F1 score of 88%. These measurements emphasize the system’s capacity to comprehensively assess worker execution, giving exact suggestions for key HR decision-making. Ethical contemplations, innovation acknowledgement, and custom-fitted proposal frameworks, propelled by related works, are coordinates to guarantee the system’s reasonability over assorted organizational settings. This research contributes to the advancing scene of HR administration, offering a spearheading arrangement for organizations looking for data-driven, comprehensive, and morally sound approaches to workforce optimization.

A Proposed Frame Work for Enhancing Competitiveness of Small and Medium Enterprises (SMEs)

Small and medium enterprises (SMEs) are important agents of development throughout the world. Promoting a country’s SME sector plays a crucial role in maintaining high employment and income generation and is therefore critical for achieving sustainable grow by enhancing SMEs competitiveness. The general objective of this paper is to develop a theoretical frame work model for garment SMEs competitiveness that supports garment manufacturing small and medium enterprises (SMEs) to enhance their competitiveness by identifying the possible competitiveness factors. To achieve the presented objectives, a purposive sample basis on selected garments manufacturing SMEs found at three different clusters in Addis Abeba city administration is used. The data in this paper are both primary and secondary data. Primary data was collected though questionnaires, interviews and observations, while secondary data sources referred from company’s documents and several articles from reputable international journals. Both qualitative and quantitative approaches are used to analyse the collected data using various statistical programs. The results of the paper found that in garment manufacturing SMEs the main difficulties faced in performance dimension which is divided into financial performance and non-financial performance are the lack of collateral, the lack of proven track records, the lack of proper business plans and the need to show good sales turnover are the major financial performance parameters that deters the competitiveness. The SMEs do not have well established system to support effective and efficient implementation systems for productivity improvement. Finally the garment manufacturing SMEs are potentially wasting valuable and scarce resources since they don’t implement productivity improvement tools and techniques Lack of appropriate machinery and equipment are the main non-financial performance parameter that deters the competitiveness. To tackle the problems and enhance competitiveness of garment manufacturing firms, a theoretical conceptual model based on this requirement has been developed and the implementation requires a coordinated and well organized system among the actors (at macro and micro level) in the value chain. Some of the major problems such as lack of skilled manpower and infrastructure have to be tackled by the government and private sectors. And the other problems could be approached by using some modern management philosophies (such as just-in-time manufacturing, business process re-engineering, lean production) and scientific methods like production planning and control.

Robotic Framework for Requirement Management, Estimations and Project Proposals

Robotic Framework for Requirement Management, Estimations and Project Proposals

Load identification for fatigue life assessment in ship hull structural elements

The harsh and uncertain operational profile that characterizes the service life of a ship vessel demands for developing robust methods able to monitor the degrada-tion of its structural integrity. Load recognition is a central part in condition moni-toring of ship hull structures and when realized both diagnostic and prognostic ca-pabilities will be enabled. In this work a structural health monitoring framework is proposed under the conceptual basis of digital twining. The present approach em-phasizes the inverse identification of loads acting on the ship’s hull by exploiting readings from strain sensors and is cast in a Bayesian setting. The loading profile is then applied to the numerical model of the subject vessel for the estimation of the stress field at critical areas prone to fatigue damage, i.e. hot spots. The pro-posed framework is evaluated by synthetic strain data derived from a finite ele-ment (FE) model of a containership. The results demonstrate the feasibility of the proposed approach for addressing the load identification problem and acts as a starting point for the development of a structural digital twin that will allow for monitoring fatigue accumulation in ship hull structures.

THE INNOVATION OF GOVERNMENT RISK MANAGEMENT MITIGATION FOR DISASTER MANAGEMENT IN INDONESIA

Purpose: The dynamics and complexity of governance in disaster management in Indonesia require disaster management through the implementation of GRC (Governance, Risk, Compliance). integrated. The aim of this research is to assess the readiness of GRC innovation in disaster management through risk management mitigation, supporting infrastructure, and developing an integrated GRC implementation development plan. Theoretical reference and Method: Types of qualitative and quantitative research through surveys, distribution of questionnaires, collection of regulatory documents and GRC system policies in an integrated manner, reinforced by interviews with respondents, use of GRC system infrastructure design through infrastructure preparedness in facing disasters which are formulated in the form of policy proposal frameworks and guidelines that refer to against the ISO Handbook Integrated Use of Management System Standard, an action examination (PDCA) sample of 124 respondents. Results and Conclusion: The research results can be explained: 1) The creation of risk management guidelines resulting from integrated GRC practices in disaster risk mitigation has not been standardized. 2) The infrastructure design resulting from a study regarding readiness to implement integrated GRC in government in disaster management in Indonesia has not been implemented in general. 3) Based on the results of the Delphi method, the implementation of GRC has not been integrated. Implications of research: The implications of the research results can be used as recommendations for risk management stakeholders in making decisions based on the implementation of integrated G/R/C. Measuring the level of effectiveness uses a maturity model approach (Maturity Assessment) according to ISO standards. Originality/value: Originality: This research contributes to the implementation of integrated GRC 1) risk management guidelines resulting from integrated GRC practices 2) Infrastructure design resulting from studies regarding disaster management in Indonesia. 3) Delphi method, GRC implementation is not yet integrated.

The white paper on artificial intelligence as a source for the formation of European Union legislation in the field of artificial intelligence

The article analyzes the provisions of the White Paper on artificial intelligence as a source of the formation of European Union legislation in the field of artificial intelligence. It is noted that the study of legal regulation of artificial intelligence in the European Union will contribute to the formation of the domestic source base in the field of application of artificial intelligence. It has been analyzed that in scientific circles, the provisions of the White Book on artificial intelligence are highlighted by domestic scientists in a fragmentary manner, which makes it difficult to comprehensively perceive the content and meaning of the White Book as a whole. The article states that the legislation of Ukraine needs improvement, which consists in compliance with European standards in the field of artificial intelligence. It has been established that it is advisable to enshrine provisions on the use of artificial intelligence at the legislative level. The article examines the provisions of the European Data Strategy, which recognizes artificial intelligence as an important component of the data economy. It has been studied that the provisions of the European Data Strategy provide for a combination of technology, industry, digital infrastructure and regulatory framework. It was noted that the provisions of the Strategy regarding artificial intelligence were further developed in the White Book. The article specifies the concept of artificial intelligence in accordance with the provisions of the White Book. It is noted that the Provisions of the White Book are aimed at ensuring consultation of interested parties, collection of feedback as a basis for future decision-making processes. It has been proven that the White Paper can be considered a political document containing the goals and possible actions of the European Commission regarding the regulation of artificial intelligence and contains a list of political proposals, intentions and recommendations. It is noted that the White Book is a framework for future legislative proposals on the formation of a legal framework related to artificial intelligence in the European Union. The article defines the structure of the main provisions of the White Book and establishes the fundamental principles that determine the development and implementation of artificial intelligence. Attention is focused on chapter 5 of the White Paper, which is devoted to the «Ecosystem of Trust: Regulatory Framework for Artificial Intelligence», which is devoted to the key elements of the regulatory framework for artificial intelligence in Europe.

Semi-Global Bipartite Fault-Tolerant Containment Control for Heterogeneous Multiagent Systems With Antagonistic Communication Networks and Input Saturation.

Semi-global bipartite fault-tolerant containment control framework on antagonistic communication networks is proposed in this article for heterogeneous multiagent systems (MASs) under the influence of input saturation and actuator faults. An observer is constructed to estimate the leaders' states on signed digraph, where the communication networks are antagonistic. A fully distributed virtual control approach is developed to acquire the containment trajectory. Based on the observer, a semi-global containment control method is developed to compensate for the detrimental impacts of both input saturation and actuator faults. Besides, the dynamics and state-space dimensions of the agents can be different. The proposed framework overcomes two drawbacks of the conventional containment control: 1) the containment trajectory is obtained under general antagonistic communication networks, which is more general in engineering applications and 2) both actuator faults and input saturation are solved for heterogeneous agents, which relaxes the limitation of homogeneous dynamics. Finally, a simulation example is conducted to test and verify the feasibility of the proposed method framework.

Music Recommendation Using Facial Emotion Recognition

It can be very befuddling for people to choose which music to tune in to from a wide run of alternatives accessible. Different proposal frameworks have been made for particular spaces like music, feasting, and shopping, catering to the user's inclinations. Our essential objective is to supply music recommendations that adjust with the user's taste. By analyzing facial expressions and client feelings, ready to pick up experiences into their current mental or enthusiastic state. Music and recordings offer a extraordinary opportunity to show clients with a huge number of choices based on their slants and past data. It is well known that humans make use of facial expressions to express more clearly what they want to say and the context in which they meant their words. More than 60 percent of the users believe that at a certain point of time the number of songs present in their songs library is so large that they are unable to figure out the song which they have to play. By developing a recommendation system, it could assist a user to make a decision regarding which music one should listen to helping the user to reduce his/her stress levels. The user would not have to waste any time in searching or to look up for songs and the best track matching the user’s mood is detected, and songs would be shown to the user according to his/her mood. The image of the user is captured with the help of a webcam. The user’s picture is taken and thenas per the mood/emotion of the user an appropriate song from the playlist of the user is shown matching the user’s requirement.

DeepHealthNet: Adolescent Obesity Prediction System Based on a Deep Learning Framework.

The global prevalence of childhood and adolescent obesity is a major concern due to its association with chronic diseases and long-term health risks. Artificial intelligence technology has been identified as a potential solution to accurately predict obesity rates and provide personalized feedback to adolescents. This study highlights the importance of early identification and prevention of obesity-related health issues. To develop effective algorithms for the prediction of obesity rates and provide personalized feedback, factors such as height, weight, waist circumference, calorie intake, physical activity levels, and other relevant health information must be taken into account. Therefore, by collecting health datasets from 321 adolescents who participated in Would You Do It! application, we proposed an adolescent obesity prediction system that provides personalized predictions and assists individuals in making informed health decisions. Our proposed deep learning framework, DeepHealthNet, effectively trains the model using data augmentation techniques, even when daily health data are limited, resulting in improved prediction accuracy (acc: 0.8842). Additionally, the study revealed variations in the prediction of the obesity rate between boys (acc: 0.9320) and girls (acc: 0.9163), allowing the identification of disparities and the determination of the optimal time to provide feedback. Statistical analysis revealed that the performance of the proposed deep learning framework was more statistically significant (p 0.001) compared to the other general models. The proposed system has the potential to effectively address childhood and adolescent obesity.

Generalized Weakly Supervised Object Localization.

With the goal of learning to localize specific object semantics using the low-cost image-level annotation, weakly supervised object localization (WSOL) has been receiving increasing attention in recent years. Although existing literatures have studied a number of major issues in this field, one important yet challenging scenario, where the test object semantics may appear in the training phase (seen categories) or never been observed before (unseen categories), is still beyond the exploration of the existing works. We define this scenario as the generalized WSOL (GWSOL) and make a pioneering effort to study it in this article. By leveraging attribute vectors to associate seen and unseen categories, we involve threefold modeling components, i.e., the class-sensitive modeling, semantic-agnostic modeling, and content-aware modeling, into a unified end-to-end learning framework. Such design enables our model to recognize and localize unconstrained object semantics, learn compact and discriminative features that could represent the potential unseen categories, and customize content-aware attribute weights to avoid localizing on misleading attribute elements. To advance this research direction, we contribute the bounding-box manual annotations to the widely used AwA2 dataset and benchmark the GWSOL methods. Comprehensive experiments demonstrate the effectiveness of our proposed learning framework and each of the considered modeling components.

A Proposed Frame work for External Auditor using of Root Cause Analysis in Fraud Detection and Analysis

A Proposed Frame work for External Auditor using of Root Cause Analysis in Fraud Detection and Analysis

Enhancing the medical diagnosis of COVID-19 with learning based decision support systems

Since late December 2019, the COVID-19 pandemic has had substantial impact and long-lasting impact on numerous lives. The surge in patients has overwhelmed hospitals and exhausted essential resources such as masks and gloves. However, in response to this crisis, we have developed a robust solution that can ease the burden on emergency services and manage the influx of patients. Our proposed framework comprises deep learning and machine learning models that can predict and manage patient demand with high accuracy. The first model, is specifically designed to classify computed tomography (CT) scan images for COVID or non-COVID cases. We trained multiple convolutional neural network (CNN) models on a large dataset of CT scan images and evaluated their performance on a separate test set. Our evaluation showed that the ResNet50 model was the most effective, achieving an accuracy of 93.28%. The second model uses patient measurements dataset to predict the likelihood of intensive care unit (ICU) admission for COVID-19 patients. We experimented with the XGBoost machine learning algorithm and found that the accuracy score achieved 88.40%.

Confidence Intervals for Parameters of Unobserved Events

Consider a finite sample from an unknown distribution over a countable alphabet. Unobserved events are alphabet symbols which do not appear in the sample. Estimating the probabilities of unobserved events is a basic problem in statistics and related fields, which was extensively studied in the context of point estimation. In this work we introduce a novel interval estimation scheme for unobserved events. Our proposed framework applies selective inference, as we construct confidence intervals (CIs) for the desired set of parameters. Interestingly, we show that obtained CIs are dimension-free, as they do not grow with the alphabet size. Further, we show that these CIs are (almost) tight, in the sense that they cannot be further improved without violating the prescribed coverage rate. We demonstrate the performance of our proposed scheme in synthetic and real-world experiments, showing a significant improvement over the alternatives. Finally, we apply our proposed scheme to large alphabet modeling. We introduce a novel simultaneous CI scheme for large alphabet distributions which outperforms currently known methods while maintaining the prescribed coverage rate. Supplementary materials for this article are available online including a standardized description of the materials available for reproducing the work.

A theoretical framework to investigate the effect ofhighpermittivity materials in MRI using anatomy-mimicking cylinders.

Recent numerical and empirical results proved that high permittivity materials (HPM) used in pads placed near the subject or directly integrated with coils can increase the SNR and reduce the specific absorption rate (SAR) in MRI. In this paper, we propose an analytical investigation of the effect on the magnetic field distribution of a layer of HPM surrounding an anatomy-mimicking cylindrical sample. The study is based on a reformulation of the Mie scattering for cylindrical geometry, following an approach recently introduced for spherical samples. The total field in each medium is decomposed in terms of inward and outward electromagnetic waves, and the fields are expressed as series of cylindrical harmonics, whose coefficients can be interpreted as classical reflection and transmission coefficients. Our new formulation allows a quantitative evaluation of the effect of the HPM layer for varying permittivity and thickness, and it provides an intuitive understanding of such effect in terms of propagation and scattering of the RF field. We show how HPM can filter out the modes that only contribute to the noise or RF power deposition, resulting in higher SNR or lower SAR, respectively. Our proposed framework provides physical insight on how to properly design HPM for MRI applications.

A framework for image-based counterfeit coin detection using pruned fuzzy associative classifier

Counterfeit coins pose a significant challenge in various real-world applications, from vending machines to currency exchange systems, making their reliable detection a matter of utmost importance. This research presents a novel framework designed to tackle this issue by harnessing the power of image-mining techniques. Our proposed framework is developed in two modules. In the first module, a method to detect the region of interest (ROIs) is applied that focuses on blob detection. In the second module, image mining is applied to find image patterns present in coin images using fuzzy association rules mining. The enhancement lies in utilizing Particle Swarm Optimization (PSO) within the image mining module. PSO refines the threshold parameters, thereby improving the efficiency of the fuzzy association rules mining process. This integration allows for the automatic determination of optimal values, contributing to the overall robustness of the counterfeit coin detection system. Comprising two modules, this framework offers a unique advantage as a compress, serving as a knowledge attainment tool. By harnessing the full power of fuzzy association rule mining, this paper introduces pruning methods to reduce redundant and insignificant rules. Moreover, we propose a novel algorithm for feature selection and a pruned-based fuzzy associative classifier to establish a robust counterfeit coin detection system. Comparative analysis with other methods using the same dataset showcases the superiority of our framework, exhibiting lower feature dimensions, smoother boundaries, and maintaining satisfactory accuracy. The generality of this study's problem formulation offers a common framework for addressing similar challenges across various domains.

Federated Condition Monitoring Signal Prediction With Improved Generalization

Revolutionary advances in Internet of Things technologies have paved the way for a significant increase in computational resources at edge devices that collect condition monitoring (CM) data. This poses a significant opportunity for federated analytics (FA), which exploits edge computing resources to distribute model learning, reduce communication traffic, and circumvent the need to share raw data. In this article, we study CM signal prediction where operating units that have data storage and computational capabilities jointly learn models without sharing their collected CM signals. The key challenge we aim to address is learning effective FA models in the presence of heterogeneity, which is often intrinsic to CM signals. To this end, we first introduce a federated framework for CM signal prediction that tries to improve generalization by encouraging flat solutions through distributed computations. Then, a personalization approach is proposed to adapt the learned model to new clients without losing old knowledge. We examine our proposed framework on CM signals from aircraft turbofan engines under three realistic federated CM scenarios. Experimental results highlight the capability of our model to decentralize model inference while improving generalization and robustness to heterogeneity across CM signals.

A Progressive Subnetwork Searching Framework for Dynamic Inference.

Deep neural network (DNN) model compression is a popular and important optimization method for efficient and fast hardware acceleration. However, the compressed model is usually fixed, without the capability to tune the computing complexity (i.e., latency in hardware) on-the-fly, depending on dynamic latency requirements, workloads, and computing hardware resource allocation. To address this challenge, dynamic DNN with run-time adaption of computing structures has been constructed through training with a cross-entropy objective function consisting of multiple subnets sampled from the supernet. Our investigations in this work show that the performance of dynamic inference highly relies on the quality of subnet sampling. To construct a dynamic DNN with multiple high-quality subnets, we propose a progressive subnetwork searching framework, which is embedded with several proposed new techniques, including trainable noise ranking, channel-group sampling, selective fine-tuning, and subnet filtering. Our proposed framework empowers the target dynamic DNN with higher accuracy for all the subnets compared with prior works on both the Canadian Institute for Advanced Research dataset with 10 classes (CIFAR-10) and ImageNet datasets. Specifically, compared with United States-Neural Network (US-NN), our method achieves 0.9% average accuracy gain for Alexnet, 2.5% for ResNet18, 1.1% for Visual Geometry Group (VGG)11, and 0.58% for MobileNetv1, on the ImageNet dataset, respectively. Moreover, to demonstrate run-time tuning of computing latency of dynamic DNN in real computing system, we have deployed our constructed dynamic networks into Nvidia Titan graphics processing unit (GPU) and Intel Xeon central processing unit (CPU), showing great improvement over prior works. The code is available at https://github.com/ASU-ESIC-FAN-Lab/Dynamic-inference.

DeepReality: An open source framework to develop AI-based augmented reality applications

Augmented reality (AR) and Artificial Intelligence (AI) are technologies pioneers in innovation and alteration in several domains. AR allows the creation of an entirely new and interactive experience for users. However, there are several drawbacks in developing AR applications, such as the marker identification process and the creation of content itself. These are very time-consuming procedures and require ad-hoc development. The advantages of using AI to solve AR limitations have recently been explored in literature. Motivated by these findings, in this paper it is proposed DeepReality, a software toolkit plug-in for Unity 3D. It is conceived for allowing developers to integrate any Deep Learning (DL) models into Unity, through AR Foundation and Barracuda inference engine. DeepReality is aimed at simplifying and streamlining the usage of DL models in conjunction with AR. As such, users skilled in Unity and DL can easily create mobile applications (iOS and Android) to: extract visual features of real-world objects (framed with the device camera) via DL; Show on-screen content on top of those real-world objects, via AR. DeepReality performs object semantic processing within the scene, and extended semantic effects for incongruent objects, overcoming the environmental tracking, which is feature-based. In order to test DeepReality usability, experiments have been performed on the execution time and memory usage data, demonstrating the feasibility and possibility of integrating and using DNNs models in mobile applications for AR. The complexity analysis confirms that DeepReality can be completely executed on mobile devices. DeepReality is also open-source and it is freely available in the Unity asset store. By fostering accessible AI-AR integration, DeepReality addresses key shortcomings in existing approaches, encapsulating contributions such as versatile DL integration, open-source accessibility, operational validation, and comprehensive metrics analysis. DeepReality empowers developers to transcend boundaries, enriching AR applications with AI’s transformative potential. Our proposed framework fosters benchmarking, comparison, and a future harmonised by AR-AI synergy.

Automated and reusable deep learning (AutoRDL) framework for predicting response to neoadjuvant chemotherapy and axillary lymph node metastasis in breast cancer using ultrasound images: a retrospective, multicentre study

Previous deep learning models have been proposed to predict the pathological complete response (pCR) and axillary lymph node metastasis (ALNM) in breast cancer. Yet, the models often leveraged multiple frameworks, required manual annotation, and discarded low-quality images. We aimed to develop an automated and reusable deep learning (AutoRDL) framework for tumor detection and prediction of pCR and ALNM using ultrasound images with diverse qualities. The AutoRDL framework includes a You Only Look Once version 5 (YOLOv5) network for tumor detection and a progressive multi-granularity (PMG) network for pCR and ALNM prediction. The training cohort and the internal validation cohort were recruited from Guangdong Provincial People's Hospital (GPPH) between November 2012 and May 2021. The two external validation cohorts were recruited from the First Affiliated Hospital of Kunming Medical University (KMUH), between January 2016 and December 2019, and Shunde Hospital of Southern Medical University (SHSMU) between January 2014 and July 2015. Prior to model training, super-resolution via iterative refinement (SR3) was employed to improve the spatial resolution of low-quality images from the KMUH. We developed three models for predicting pCR and ALNM: a clinical model using multivariable logistic regression analysis, an image model utilizing the PMG network, and a combined model that integrates both clinical and image data using the PMG network. The YOLOv5 network demonstrated excellent accuracy in tumor detection, achieving average precisions of 0.880-0.921 during validation. In terms of pCR prediction, the combined modelpost-SR3 outperformed the combined modelpre-SR3, image modelpost-SR3, image modelpre-SR3, and clinical model (AUC: 0.833 vs 0.822 vs 0.806 vs 0.790 vs 0.712, all p<0.05) in the external validation cohort (KMUH). Consistently, the combined modelpost-SR3 exhibited the highest accuracy in ALNM prediction, surpassing the combined modelpre-SR3, image modelpost-SR3, image modelpre-SR3, and clinical model (AUC: 0.825 vs 0.806 vs 0.802 vs 0.787 vs 0.703, all p<0.05) in the external validation cohort 1 (KMUH). In the external validation cohort 2 (SHSMU), the combined model also showed superiority over the clinical and image models (0.819 vs 0.712 vs 0.806, both p<0.05). Our proposed AutoRDL framework is feasible in automatically predicting pCR and ALNM in real-world settings, which has the potential to assist clinicians in optimizing individualized treatment options for patients. National Key Research and Development Program of China (2023YFF1204600); National Natural Science Foundation of China (82227802, 82302306); Clinical Frontier Technology Program of the First Affiliated Hospital of Jinan University, China (JNU1AF-CFTP-2022-a01201); Science and Technology Projects in Guangzhou (202201020022, 2023A03J1036, 2023A03J1038); Science and Technology Youth Talent Nurturing Program of Jinan University (21623209); and Postdoctoral Science Foundation of China (2022M721349).