The integration of visual elements,such as emojis,into educational content represents a promising approach to enhancing student engagement and comprehension.However,existing efforts in emoji integration often lack sys...The integration of visual elements,such as emojis,into educational content represents a promising approach to enhancing student engagement and comprehension.However,existing efforts in emoji integration often lack systematic frameworks capable of addressing the contextual and pedagogical nuances required for effective implementation.This paper introduces a novel framework that combines Data-Driven Error-Correcting Output Codes(DECOC),Long Short-Term Memory(LSTM)networks,and Multi-Layer Deep Neural Networks(ML-DNN)to identify optimal emoji placements within computer science course materials.The originality of the proposed system lies in its ability to leverage sentiment analysis techniques and contextual embeddings to align emoji recommendations with both the emotional tone and learning objectives of course content.A meticulously annotated dataset,comprising diverse topics in computer science,was developed to train and validate the model,ensuring its applicability across a wide range of educational contexts.Comprehensive validation demonstrated the system’s superior performance,achieving an accuracy of 92.4%,precision of 90.7%,recall of 89.3%,and an F1-score of 90.0%.Comparative analysis with baselinemodels and relatedworks confirms themodel’s ability tooutperformexisting approaches inbalancing accuracy,relevance,and contextual appropriateness.Beyond its technical advancements,this framework offers practical benefits for educators by providing an Artificial Intelligence-assisted(AI-assisted)tool that facilitates personalized content adaptation based on student sentiment and engagement patterns.By automating the identification of appropriate emoji placements,teachers can enhance digital course materials with minimal effort,improving the clarity of complex concepts and fostering an emotionally supportive learning environment.This paper contributes to the emerging field of AI-enhanced education by addressing critical gaps in personalized content delivery and pedagogical support.Its findings highlight the transformative potential of integrating AI-driven emoji placement systems into educational materials,offering an innovative tool for fostering student engagement and enhancing learning outcomes.The proposed framework establishes a foundation for future advancements in the visual augmentation of educational resources,emphasizing scalability and adaptability for broader applications in e-learning.展开更多
Learning analytics is a rapidly evolving research discipline that uses theinsights generated from data analysis to support learners as well as optimize boththe learning process and environment. This paper studied stud...Learning analytics is a rapidly evolving research discipline that uses theinsights generated from data analysis to support learners as well as optimize boththe learning process and environment. This paper studied students’ engagementlevel of the Learning Management System (LMS) via a learning analytics tool,student’s approach in managing their studies and possible learning analytic methods to analyze student data. Moreover, extensive systematic literature review(SLR) was employed for the selection, sorting and exclusion of articles fromdiverse renowned sources. The findings show that most of the engagement inLMS are driven by educators. Additionally, we have discussed the factors inLMS, causes of low engagement and ways of increasing engagement factorsvia the Learning Analytics approach. Nevertheless, apart from recognizing theLearning Analytics approach as being a successful method and technique for analyzing the LMS data, this research further highlighted the possibility of mergingthe learning analytics technique with the LMS engagement in every institution asbeing a direction for future research.展开更多
In the era of an energy revolution,grid decentralization has emerged as a viable solution to meet the increasing global energy demand by incorporating renewables at the distributed level.Microgrids are considered a dr...In the era of an energy revolution,grid decentralization has emerged as a viable solution to meet the increasing global energy demand by incorporating renewables at the distributed level.Microgrids are considered a driving component for accelerating grid decentralization.To optimally utilize the available resources and address potential challenges,there is a need to have an intelligent and reliable energy management system(EMS)for the microgrid.The artificial intelligence field has the potential to address the problems in EMS and can provide resilient,efficient,reliable,and scalable solutions.This paper presents an overview of existing conventional and AI-based techniques for energy management systems in microgrids.We analyze EMS methods for centralized,decentralized,and distributed microgrids separately.Then,we summarize machine learning techniques such as ANNs,federated learning,LSTMs,RNNs,and reinforcement learning for EMS objectives such as economic dispatch,optimal power flow,and scheduling.With the incorporation of AI,microgrids can achieve greater performance efficiency and more reliability for managing a large number of energy resources.However,challenges such as data privacy,security,scalability,explainability,etc.,need to be addressed.To conclude,the authors state the possible future research directions to explore AI-based EMS's potential in real-world applications.展开更多
Distributed Federated Learning(DFL)technology enables participants to cooperatively train a shared model while preserving the privacy of their local datasets,making it a desirable solution for decentralized and privac...Distributed Federated Learning(DFL)technology enables participants to cooperatively train a shared model while preserving the privacy of their local datasets,making it a desirable solution for decentralized and privacy-preserving Web3 scenarios.However,DFL faces incentive and security challenges in the decentralized framework.To address these issues,this paper presents a Hierarchical Blockchain-enabled DFL(HBDFL)system,which provides a generic solution framework for the DFL-related applications.The proposed system consists of four major components,including a model contribution-based reward mechanism,a Proof of Elapsed Time and Accuracy(PoETA)consensus algorithm,a Distributed Reputation-based Verification Mechanism(DRTM)and an Accuracy-Dependent Throughput Management(ADTM)mechanism.The model contribution-based rewarding mechanism incentivizes network nodes to train models with their local datasets,while the PoETA consensus algorithm optimizes the tradeoff between the shared model accuracy and system throughput.The DRTM improves the system efficiency in consensus,and the ADTM mechanism guarantees that the throughput performance remains within a predefined range while improving the shared model accuracy.The performance of the proposed HBDFL system is evaluated by numerical simulations,with the results showing that the system improves the accuracy of the shared model while maintaining high throughput and ensuring security.展开更多
The new energy vehicle plays a crucial role in green transportation,and the energy management strategy of hybrid power systems is essential for ensuring energy-efficient driving.This paper presents a state-of-the-art ...The new energy vehicle plays a crucial role in green transportation,and the energy management strategy of hybrid power systems is essential for ensuring energy-efficient driving.This paper presents a state-of-the-art survey and review of reinforcement learning-based energy management strategies for hybrid power systems.Additionally,it envisions the outlook for autonomous intelligent hybrid electric vehicles,with reinforcement learning as the foundational technology.First of all,to provide a macro view of historical development,the brief history of deep learning,reinforcement learning,and deep reinforcement learning is presented in the form of a timeline.Then,the comprehensive survey and review are conducted by collecting papers from mainstream academic databases.Enumerating most of the contributions based on three main directions—algorithm innovation,powertrain innovation,and environment innovation—provides an objective review of the research status.Finally,to advance the application of reinforcement learning in autonomous intelligent hybrid electric vehicles,future research plans positioned as“Alpha HEV”are envisioned,integrating Autopilot and energy-saving control.展开更多
Diabetic retinopathy(DR)remains a leading cause of vision impairment and blindness among individuals with diabetes,necessitating innovative approaches to screening and management.This editorial explores the transforma...Diabetic retinopathy(DR)remains a leading cause of vision impairment and blindness among individuals with diabetes,necessitating innovative approaches to screening and management.This editorial explores the transformative potential of artificial intelligence(AI)and machine learning(ML)in revolutionizing DR care.AI and ML technologies have demonstrated remarkable advancements in enhancing the accuracy,efficiency,and accessibility of DR screening,helping to overcome barriers to early detection.These technologies leverage vast datasets to identify patterns and predict disease progression with unprecedented precision,enabling clinicians to make more informed decisions.Furthermore,AI-driven solutions hold promise in personalizing management strategies for DR,incorpo-rating predictive analytics to tailor interventions and optimize treatment path-ways.By automating routine tasks,AI can reduce the burden on healthcare providers,allowing for a more focused allocation of resources towards complex patient care.This review aims to evaluate the current advancements and applic-ations of AI and ML in DR screening,and to discuss the potential of these techno-logies in developing personalized management strategies,ultimately aiming to improve patient outcomes and reduce the global burden of DR.The integration of AI and ML in DR care represents a paradigm shift,offering a glimpse into the future of ophthalmic healthcare.展开更多
A learning management system(LMS)is a software or web based application,commonly utilized for planning,designing,and assessing a particular learning procedure.Generally,the LMS offers a method of creating and deliveri...A learning management system(LMS)is a software or web based application,commonly utilized for planning,designing,and assessing a particular learning procedure.Generally,the LMS offers a method of creating and delivering content to the instructor,monitoring students’involvement,and validating their outcomes.Since mental health issues become common among studies in higher education globally,it is needed to properly determine it to improve mental stabi-lity.This article develops a new seven spot lady bird feature selection with opti-mal sparse autoencoder(SSLBFS-OSAE)model to assess students’mental health on LMS.The major aim of the SSLBFS-OSAE model is to determine the proper health status of the students with respect to depression,anxiety,and stress(DAS).The SSLBFS-OSAE model involves a new SSLBFS model to elect a useful set of features.In addition,OSAE model is applied for the classification of mental health conditions and the performance can be improved by the use of cuckoo search optimization(CSO)based parameter tuning process.The design of CSO algorithm for optimally tuning the SAE parameters results in enhanced classifica-tion outcomes.For examining the improved classifier results of the SSLBFS-OSAE model,a comprehensive results analysis is done and the obtained values highlighted the supremacy of the SSLBFS model over its recent methods interms of different measures.展开更多
Nepal and Japan, both are multi-hazard prone countries having experience of devastating disasters. It is difficult, if not impossible, to stop natural hazard events at source. However, the impact can be reduced signif...Nepal and Japan, both are multi-hazard prone countries having experience of devastating disasters. It is difficult, if not impossible, to stop natural hazard events at source. However, the impact can be reduced significantly by preventing them from turning into disasters. The impact of disasters can vary depending on the capacity to handle the situation;and the capacity depends on the level of preparedness and mitigation measures taken in advance. Japan has set example for the rest of the world when it comes to Disaster Risk Management (DRM). Recovery and reconstruction after disasters are not just to develop the area as it was earlier, but it has to be taken as an opportunity for developing better than earlier, which is called as “Build Back Better”. This concept was raised by Japanese Government in UN World conference, Sendai in 2015 [1]. Dynamic, evolutionary and proactive DRM policy and plans with innovation, and the use of science and technology to find solutions, and effective implementation of the policy and plans, coupled with the culture of safety among the citizens, and the spirit of never give up “Nana KarobiYa Oki” (Seven times fall down, Eight times get up), are the unique features that every country should learn from Japan’s DRM mechanism. This paper is an effort to buy-in the good practices from Japan to improve DRM system in Nepal. It is a product of three-month intensive research in the University of Tokyo under a PhD research that consisted of reviewing existing DRM documents and several interactive meetings with stakeholders in Japan.展开更多
An effective energy management strategy(EMS)is essential to optimize the energy efficiency of electric vehicles(EVs).With the advent of advanced machine learning techniques,the focus on developing sophisticated EMS fo...An effective energy management strategy(EMS)is essential to optimize the energy efficiency of electric vehicles(EVs).With the advent of advanced machine learning techniques,the focus on developing sophisticated EMS for EVs is increasing.Here,we introduce LearningEMS:a unified framework and open-source benchmark designed to facilitate rapid development and assessment of EMS.LearningEMS is distinguished by its ability to support a variety of EV configurations,including hybrid EVs,fuel cell EVs,and plug-in EVs,offering a general platform for the development of EMS.The framework enables detailed comparisons of several EMS algorithms,encompassing imitation learning,deep reinforcement learning(RL),offline RL,model predictive control,and dynamic programming.We rigorously evaluated these algorithms across multiple perspectives:energy efficiency,consistency,adaptability,and practicability.Furthermore,we discuss state,reward,and action settings for RL in EV energy management,introduce a policy extraction and reconstruction method for learning-based EMS deployment,and conduct hardware-in-the-loop experiments.In summary,we offer a unified and comprehensive framework that comes with three distinct EV platforms,over 10000 km of EMS policy data set,ten state-of-the-art algorithms,and over 160 benchmark tasks,along with three learning libraries.Its flexible design allows easy expansion for additional tasks and applications.The open-source algorithms,models,data sets,and deployment processes foster additional research and innovation in EV and broader engineering domains.展开更多
The nutritional management of patients with esophageal cancer(EC)presents significant complexities,with traditional approaches facing inherent limitations in data collection,real-time decision-making,and personalized ...The nutritional management of patients with esophageal cancer(EC)presents significant complexities,with traditional approaches facing inherent limitations in data collection,real-time decision-making,and personalized care.This narrative review explores the transformative potential of artificial intelligence(AI)and machine learning(ML),particularly deep learning(DL)and reinforcement learning(RL),in revolutionizing nutritional support for this vulnerable patient population.DL has demonstrated remarkable capabilities in enhancing the accuracy and objectivity of nutritional assessment through precise,automated body composition analysis from medical imaging,offering valuable prognostic insights.Concurrently,RL enables the dynamic optimization of nutritional interventions,adapting them in real time to individual patient responses,paving the way for truly personalized care paradigms.Although AI/ML offers potential advantages in efficiency,precision,and personalization by integrating multidimensional data for superior clinical decision support,its widespread adoption is accompanied by critical challenges.These include safeguarding data privacy and security,mitigating algorithmic bias,ensuring transparency and accountability,and establishing rigorous clinical validation.Early evidence suggests the feasibility of applying AI/ML in nutritional risk stratification and workflow optimization,but highquality prospective studies are needed to demonstrate the direct impact on clinical outcomes,including complications,readmissions,and survival.Overcoming these hurdles necessitates robust ethical governance,interdisciplinary collaboration,and continuous education.Ultimately,the strategic integration of AI/ML holds immense promise to profoundly improve patient outcomes,enhance quality of life,and optimize health care resource utilization in the nutritional management of esophageal cancer.展开更多
The aim of radiotherapy(RT)is to deliver prescribed doses to tumors while sparing neighboring organs at risk.As the demand for treatment precision increases in modern RT,intrafractional motion management becomes criti...The aim of radiotherapy(RT)is to deliver prescribed doses to tumors while sparing neighboring organs at risk.As the demand for treatment precision increases in modern RT,intrafractional motion management becomes critical for achieving high precision,particularly for tumors in the thorax and abdomen that are affected by respiration and other physiological motions.Deep learning(DL)has demonstrated strong po-tential in addressing the limitations of conventional methods by enabling rapid and accurate tumor motion detection,tumor location prediction,and management measures.This review provides a comprehensive overview of recent DL-based applications in intrafractional motion management,which are categorized into three areas:(1)tumor motion detection for real-time tumor localization,(2)tumor location prediction to compensate for the latency of the motion management system,and(3)management measures,including gating and real-time adaptive RT.In addition,this review discusses key challenges and their potential so-lutions for DL-based motion management.展开更多
Solar radiation is the main source of energy on Earth and plays a major role in the hydrological cycles,surface radiation balance,weather and climate changes,and vegetation photosynthesis.Accurate solar radiation pred...Solar radiation is the main source of energy on Earth and plays a major role in the hydrological cycles,surface radiation balance,weather and climate changes,and vegetation photosynthesis.Accurate solar radiation prediction is of paramount importance for both climate research and the solar industry.This prediction includes forecasting techniques and advanced modeling to evaluate the amount of solar energy available at a specific location during a given period.Solar energy is the cheapest form of clean energy,and due to the intermittent nature of the energy,accurate forecasting across multiple timeframes is necessary for efficient generation and demand management.Solar radiation prediction using deep learning(DL)includes the applications of neural network methods,namely Convolutional Neural Network(CNN)or Long Short-Term Memory(LSTM)models,to forecast and model solar irradiance patterns.By leveraging meteorological variables and historical solar radiation data,DL algorithms can capture complex spatial and temporal dependencies,resulting in accurate predictions.This article presents a novel Solar Radiation Prediction model utilizing a Boosted Coyote Optimization Algorithm with Deep Learning(SRP-BCOADL).The SRP-BCOADL model initially normalizes the input data using a min-max normalization approach to improve the robust nature under different scales.Besides,the SRP-BCOADL technique uses a Deep Long Short-Term Memory Autoencoder(DLSTM-AE)system for precisely forecasting solar radiation levels.The model’s accuracy is further improved through hyperparameter optimization using the BCOA.The performance analysis of the SRP-BCOADL technique is tested using solar radiation data.Extensive experimental outcomes prove that the SRP-BCOADL method obtains better results over other techniques.The Mean Squared Error(MSE)is just 0.13 kWh/m^(2),is much lower when compared to other models.The Root Mean Squared Error(RMSE)is also reduced to 0.36 kWh/m^(2),and the Mean Absolute Error(MAE)reaches a minimal level of 0.276 kWh/m^(2).展开更多
The rapid advancements in distributed generation technologies,the widespread adoption of distributed energy resources,and the integration of 5G technology have spurred sharing economy businesses within the electricity...The rapid advancements in distributed generation technologies,the widespread adoption of distributed energy resources,and the integration of 5G technology have spurred sharing economy businesses within the electricity sector.Revolutionary technologies such as blockchain,5G connectivity,and Internet of Things(IoT)devices have facilitated peer-to-peer distribution and real-time response to fluctuations in supply and demand.Nevertheless,sharing electricity within a smart community presents numerous challenges,including intricate design considerations,equitable allocation,and accurate forecasting due to the lack of well-organized temporal parameters.To address these challenges,this proposed system is focused on sharing extra electricity within the smart community.The working of the proposed system is composed of five main phases.In phase 1,we develop a model to forecast the energy consumption of the appliances using the Long Short-Term Memory(LSTM)integrated with the attention module.In phase 2,based on the predicted energy consumption,we designed a smart scheduler with attention-induced Genetic Algorithm(GA)to schedule the appliances to reduce energy consumption.In phase 3,a dynamic Feed-in Tariff(dFIT)algorithm makes real-time tariff adjustments using LSTM for demand prediction and SHapley Additive exPlanations(SHAP)values to improve model transparency.In phase 4,the energy saved from solar systems and smart scheduling is shared with the community grid.Finally,in phase 5,SDP security ensures the integrity and confidentiality of shared energy data.To evaluate the performance of energy sharing and scheduling for houses with and without solar support,we simulated the above phases using data obtained from the energy consumption of 17 household appliances in our IoT laboratory.Finally,the simulation results show that the proposed scheme reduces energy consumption and ensures secure and efficient distribution with peers,promoting a more sustainable energy management and resilient smart community.展开更多
This paper explores the possibility of using machine learning algorithms to predict type 2 diabetes.We selected two commonly used classification models:random forest and logistic regression,modeled patients’clinical ...This paper explores the possibility of using machine learning algorithms to predict type 2 diabetes.We selected two commonly used classification models:random forest and logistic regression,modeled patients’clinical and lifestyle data,and compared their prediction performance.We found that the random forest model achieved the highest accuracy,demonstrated excellent classification results on the test set,and better distinguished between diabetic and non-diabetic patients by the confusion matrix and other evaluation metrics.The support vector machine and logistic regression perform slightly less well but achieve a high level of accuracy.The experimental results validate the effectiveness of the three machine learning algorithms,especially random forest,in the diabetes prediction task and provide useful practical experience for the intelligent prevention and control of chronic diseases.This study promotes the innovation of the diabetes prediction and management model,which is expected to alleviate the pressure on medical resources,reduce the burden of social health care,and improve the prognosis and quality of life of patients.In the future,we can consider expanding the data scale,exploring other machine learning algorithms,and integrating multimodal data to further realize the potential of artificial intelligence(AI)in the field of diabetes.展开更多
This paper presents a novel approach to dynamic pricing and distributed energy management in virtual power plant(VPP)networks using multi-agent reinforcement learning(MARL).As the energy landscape evolves towards grea...This paper presents a novel approach to dynamic pricing and distributed energy management in virtual power plant(VPP)networks using multi-agent reinforcement learning(MARL).As the energy landscape evolves towards greater decentralization and renewable integration,traditional optimization methods struggle to address the inherent complexities and uncertainties.Our proposed MARL framework enables adaptive,decentralized decision-making for both the distribution system operator and individual VPPs,optimizing economic efficiency while maintaining grid stability.We formulate the problem as a Markov decision process and develop a custom MARL algorithm that leverages actor-critic architectures and experience replay.Extensive simulations across diverse scenarios demonstrate that our approach consistently outperforms baseline methods,including Stackelberg game models and model predictive control,achieving an 18.73%reduction in costs and a 22.46%increase in VPP profits.The MARL framework shows particular strength in scenarios with high renewable energy penetration,where it improves system performance by 11.95%compared with traditional methods.Furthermore,our approach demonstrates superior adaptability to unexpected events and mis-predictions,highlighting its potential for real-world implementation.展开更多
Learning analytics is an emerging technique of analysing student par-ticipation and engagement.The recent COVID-19 pandemic has significantly increased the role of learning management systems(LMSs).LMSs previously only...Learning analytics is an emerging technique of analysing student par-ticipation and engagement.The recent COVID-19 pandemic has significantly increased the role of learning management systems(LMSs).LMSs previously only complemented face-to-face teaching,something which has not been possible between 2019 to 2020.To date,the existing body of literature on LMSs has not analysed learning in the context of the pandemic,where an LMS serves as the only interface between students and instructors.Consequently,productive results will remain elusive if the key factors that contribute towards engaging students in learning are notfirst identified.Therefore,this study aimed to perform an exten-sive literature review with which to design and develop a student engagement model for holistic involvement in an LMS.The required data was collected from an LMS that is currently utilised by a local Malaysian university.The model was validated by a panel of experts as well as discussions with students.It is our hope that the result of this study will help other institutions of higher learning determine factors of low engagement in their respective LMSs.展开更多
Learning Management System(LMS)is an application software that is used in automation,delivery,administration,tracking,and reporting of courses and programs in educational sector.The LMS which exploits machine learning...Learning Management System(LMS)is an application software that is used in automation,delivery,administration,tracking,and reporting of courses and programs in educational sector.The LMS which exploits machine learning(ML)has the ability of accessing user data and exploit it for improving the learning experience.The recently developed artificial intelligence(AI)and ML models helps to accomplish effective performance monitoring for LMS.Among the different processes involved in ML based LMS,feature selection and classification processesfind beneficial.In this motivation,this study introduces Glowworm-based Feature Selection with Machine Learning Enabled Performance Monitoring(GSO-MFWELM)technique for LMS.The key objective of the proposed GSO-MFWELM technique is to effectually monitor the performance in LMS.The pro-posed GSO-MFWELM technique involves GSO-based feature selection techni-que to select the optimal features.Besides,Weighted Extreme Learning Machine(WELM)model is applied for classification process whereas the parameters involved in WELM model are optimallyfine-tuned with the help of May-fly Optimization(MFO)algorithm.The design of GSO and MFO techniques result in reduced computation complexity and improved classification performance.The presented GSO-MFWELM technique was validated for its performance against benchmark dataset and the results were inspected under several aspects.The simulation results established the supremacy of GSO-MFWELM technique over recent approaches with the maximum classification accuracy of 0.9589.展开更多
Energy management is an inspiring domain in developing of renewable energy sources.However,the growth of decentralized energy production is revealing an increased complexity for power grid managers,inferring more qual...Energy management is an inspiring domain in developing of renewable energy sources.However,the growth of decentralized energy production is revealing an increased complexity for power grid managers,inferring more quality and reliability to regulate electricity flows and less imbalance between electricity production and demand.The major objective of an energy management system is to achieve optimum energy procurement and utilization throughout the organization,minimize energy costs without affecting production,and minimize environmental effects.Modern energy management is an essential and complex subject because of the excessive consumption in residential buildings,which necessitates energy optimization and increased user comfort.To address the issue of energy management,many researchers have developed various frameworks;while the objective of each framework was to sustain a balance between user comfort and energy consumption,this problem hasn’t been fully solved because of how difficult it is to solve it.An inclusive and Intelligent Energy Management System(IEMS)aims to provide overall energy efficiency regarding increased power generation,increase flexibility,increase renewable generation systems,improve energy consumption,reduce carbon dioxide emissions,improve stability,and reduce energy costs.Machine Learning(ML)is an emerging approach that may be beneficial to predict energy efficiency in a better way with the assistance of the Internet of Energy(IoE)network.The IoE network is playing a vital role in the energy sector for collecting effective data and usage,resulting in smart resource management.In this research work,an IEMS is proposed for Smart Cities(SC)using the ML technique to better resolve the energy management problem.The proposed system minimized the energy consumption with its intelligent nature and provided better outcomes than the previous approaches in terms of 92.11% accuracy,and 7.89% miss-rate.展开更多
基金funded by the Deanship of Postgraduate Studies and Scientific Research at Majmaah University,grant number[R-2025-1637].
文摘The integration of visual elements,such as emojis,into educational content represents a promising approach to enhancing student engagement and comprehension.However,existing efforts in emoji integration often lack systematic frameworks capable of addressing the contextual and pedagogical nuances required for effective implementation.This paper introduces a novel framework that combines Data-Driven Error-Correcting Output Codes(DECOC),Long Short-Term Memory(LSTM)networks,and Multi-Layer Deep Neural Networks(ML-DNN)to identify optimal emoji placements within computer science course materials.The originality of the proposed system lies in its ability to leverage sentiment analysis techniques and contextual embeddings to align emoji recommendations with both the emotional tone and learning objectives of course content.A meticulously annotated dataset,comprising diverse topics in computer science,was developed to train and validate the model,ensuring its applicability across a wide range of educational contexts.Comprehensive validation demonstrated the system’s superior performance,achieving an accuracy of 92.4%,precision of 90.7%,recall of 89.3%,and an F1-score of 90.0%.Comparative analysis with baselinemodels and relatedworks confirms themodel’s ability tooutperformexisting approaches inbalancing accuracy,relevance,and contextual appropriateness.Beyond its technical advancements,this framework offers practical benefits for educators by providing an Artificial Intelligence-assisted(AI-assisted)tool that facilitates personalized content adaptation based on student sentiment and engagement patterns.By automating the identification of appropriate emoji placements,teachers can enhance digital course materials with minimal effort,improving the clarity of complex concepts and fostering an emotionally supportive learning environment.This paper contributes to the emerging field of AI-enhanced education by addressing critical gaps in personalized content delivery and pedagogical support.Its findings highlight the transformative potential of integrating AI-driven emoji placement systems into educational materials,offering an innovative tool for fostering student engagement and enhancing learning outcomes.The proposed framework establishes a foundation for future advancements in the visual augmentation of educational resources,emphasizing scalability and adaptability for broader applications in e-learning.
基金supported by the University of Malaya,Bantuan Khas Penyelidikan under the research grant of BKS083-2017Fundamental Research Grant Scheme(FRGS)under Grant number FP112-2018A from the Ministry of Education Malaysia,Higher Education.
文摘Learning analytics is a rapidly evolving research discipline that uses theinsights generated from data analysis to support learners as well as optimize boththe learning process and environment. This paper studied students’ engagementlevel of the Learning Management System (LMS) via a learning analytics tool,student’s approach in managing their studies and possible learning analytic methods to analyze student data. Moreover, extensive systematic literature review(SLR) was employed for the selection, sorting and exclusion of articles fromdiverse renowned sources. The findings show that most of the engagement inLMS are driven by educators. Additionally, we have discussed the factors inLMS, causes of low engagement and ways of increasing engagement factorsvia the Learning Analytics approach. Nevertheless, apart from recognizing theLearning Analytics approach as being a successful method and technique for analyzing the LMS data, this research further highlighted the possibility of mergingthe learning analytics technique with the LMS engagement in every institution asbeing a direction for future research.
文摘In the era of an energy revolution,grid decentralization has emerged as a viable solution to meet the increasing global energy demand by incorporating renewables at the distributed level.Microgrids are considered a driving component for accelerating grid decentralization.To optimally utilize the available resources and address potential challenges,there is a need to have an intelligent and reliable energy management system(EMS)for the microgrid.The artificial intelligence field has the potential to address the problems in EMS and can provide resilient,efficient,reliable,and scalable solutions.This paper presents an overview of existing conventional and AI-based techniques for energy management systems in microgrids.We analyze EMS methods for centralized,decentralized,and distributed microgrids separately.Then,we summarize machine learning techniques such as ANNs,federated learning,LSTMs,RNNs,and reinforcement learning for EMS objectives such as economic dispatch,optimal power flow,and scheduling.With the incorporation of AI,microgrids can achieve greater performance efficiency and more reliability for managing a large number of energy resources.However,challenges such as data privacy,security,scalability,explainability,etc.,need to be addressed.To conclude,the authors state the possible future research directions to explore AI-based EMS's potential in real-world applications.
文摘Distributed Federated Learning(DFL)technology enables participants to cooperatively train a shared model while preserving the privacy of their local datasets,making it a desirable solution for decentralized and privacy-preserving Web3 scenarios.However,DFL faces incentive and security challenges in the decentralized framework.To address these issues,this paper presents a Hierarchical Blockchain-enabled DFL(HBDFL)system,which provides a generic solution framework for the DFL-related applications.The proposed system consists of four major components,including a model contribution-based reward mechanism,a Proof of Elapsed Time and Accuracy(PoETA)consensus algorithm,a Distributed Reputation-based Verification Mechanism(DRTM)and an Accuracy-Dependent Throughput Management(ADTM)mechanism.The model contribution-based rewarding mechanism incentivizes network nodes to train models with their local datasets,while the PoETA consensus algorithm optimizes the tradeoff between the shared model accuracy and system throughput.The DRTM improves the system efficiency in consensus,and the ADTM mechanism guarantees that the throughput performance remains within a predefined range while improving the shared model accuracy.The performance of the proposed HBDFL system is evaluated by numerical simulations,with the results showing that the system improves the accuracy of the shared model while maintaining high throughput and ensuring security.
基金Supported by National Natural Science Foundation of China (Grant Nos.52222215,52072051)Fundamental Research Funds for the Central Universities in China (Grant No.2023CDJXY-025)Chongqing Municipal Natural Science Foundation of China (Grant No.CSTB2023NSCQ-JQX0003)。
文摘The new energy vehicle plays a crucial role in green transportation,and the energy management strategy of hybrid power systems is essential for ensuring energy-efficient driving.This paper presents a state-of-the-art survey and review of reinforcement learning-based energy management strategies for hybrid power systems.Additionally,it envisions the outlook for autonomous intelligent hybrid electric vehicles,with reinforcement learning as the foundational technology.First of all,to provide a macro view of historical development,the brief history of deep learning,reinforcement learning,and deep reinforcement learning is presented in the form of a timeline.Then,the comprehensive survey and review are conducted by collecting papers from mainstream academic databases.Enumerating most of the contributions based on three main directions—algorithm innovation,powertrain innovation,and environment innovation—provides an objective review of the research status.Finally,to advance the application of reinforcement learning in autonomous intelligent hybrid electric vehicles,future research plans positioned as“Alpha HEV”are envisioned,integrating Autopilot and energy-saving control.
文摘Diabetic retinopathy(DR)remains a leading cause of vision impairment and blindness among individuals with diabetes,necessitating innovative approaches to screening and management.This editorial explores the transformative potential of artificial intelligence(AI)and machine learning(ML)in revolutionizing DR care.AI and ML technologies have demonstrated remarkable advancements in enhancing the accuracy,efficiency,and accessibility of DR screening,helping to overcome barriers to early detection.These technologies leverage vast datasets to identify patterns and predict disease progression with unprecedented precision,enabling clinicians to make more informed decisions.Furthermore,AI-driven solutions hold promise in personalizing management strategies for DR,incorpo-rating predictive analytics to tailor interventions and optimize treatment path-ways.By automating routine tasks,AI can reduce the burden on healthcare providers,allowing for a more focused allocation of resources towards complex patient care.This review aims to evaluate the current advancements and applic-ations of AI and ML in DR screening,and to discuss the potential of these techno-logies in developing personalized management strategies,ultimately aiming to improve patient outcomes and reduce the global burden of DR.The integration of AI and ML in DR care represents a paradigm shift,offering a glimpse into the future of ophthalmic healthcare.
基金supported by the Researchers Supporting Program(TUMA-Project-2021-31)supported by the Researchers Supporting Program(TUMA-Project-2021-27)Almaarefa University,Riyadh,Saudi Arabia.
文摘A learning management system(LMS)is a software or web based application,commonly utilized for planning,designing,and assessing a particular learning procedure.Generally,the LMS offers a method of creating and delivering content to the instructor,monitoring students’involvement,and validating their outcomes.Since mental health issues become common among studies in higher education globally,it is needed to properly determine it to improve mental stabi-lity.This article develops a new seven spot lady bird feature selection with opti-mal sparse autoencoder(SSLBFS-OSAE)model to assess students’mental health on LMS.The major aim of the SSLBFS-OSAE model is to determine the proper health status of the students with respect to depression,anxiety,and stress(DAS).The SSLBFS-OSAE model involves a new SSLBFS model to elect a useful set of features.In addition,OSAE model is applied for the classification of mental health conditions and the performance can be improved by the use of cuckoo search optimization(CSO)based parameter tuning process.The design of CSO algorithm for optimally tuning the SAE parameters results in enhanced classifica-tion outcomes.For examining the improved classifier results of the SSLBFS-OSAE model,a comprehensive results analysis is done and the obtained values highlighted the supremacy of the SSLBFS model over its recent methods interms of different measures.
文摘Nepal and Japan, both are multi-hazard prone countries having experience of devastating disasters. It is difficult, if not impossible, to stop natural hazard events at source. However, the impact can be reduced significantly by preventing them from turning into disasters. The impact of disasters can vary depending on the capacity to handle the situation;and the capacity depends on the level of preparedness and mitigation measures taken in advance. Japan has set example for the rest of the world when it comes to Disaster Risk Management (DRM). Recovery and reconstruction after disasters are not just to develop the area as it was earlier, but it has to be taken as an opportunity for developing better than earlier, which is called as “Build Back Better”. This concept was raised by Japanese Government in UN World conference, Sendai in 2015 [1]. Dynamic, evolutionary and proactive DRM policy and plans with innovation, and the use of science and technology to find solutions, and effective implementation of the policy and plans, coupled with the culture of safety among the citizens, and the spirit of never give up “Nana KarobiYa Oki” (Seven times fall down, Eight times get up), are the unique features that every country should learn from Japan’s DRM mechanism. This paper is an effort to buy-in the good practices from Japan to improve DRM system in Nepal. It is a product of three-month intensive research in the University of Tokyo under a PhD research that consisted of reviewing existing DRM documents and several interactive meetings with stakeholders in Japan.
基金supported in part by the National Natural Science Foundation of China(52172377).
文摘An effective energy management strategy(EMS)is essential to optimize the energy efficiency of electric vehicles(EVs).With the advent of advanced machine learning techniques,the focus on developing sophisticated EMS for EVs is increasing.Here,we introduce LearningEMS:a unified framework and open-source benchmark designed to facilitate rapid development and assessment of EMS.LearningEMS is distinguished by its ability to support a variety of EV configurations,including hybrid EVs,fuel cell EVs,and plug-in EVs,offering a general platform for the development of EMS.The framework enables detailed comparisons of several EMS algorithms,encompassing imitation learning,deep reinforcement learning(RL),offline RL,model predictive control,and dynamic programming.We rigorously evaluated these algorithms across multiple perspectives:energy efficiency,consistency,adaptability,and practicability.Furthermore,we discuss state,reward,and action settings for RL in EV energy management,introduce a policy extraction and reconstruction method for learning-based EMS deployment,and conduct hardware-in-the-loop experiments.In summary,we offer a unified and comprehensive framework that comes with three distinct EV platforms,over 10000 km of EMS policy data set,ten state-of-the-art algorithms,and over 160 benchmark tasks,along with three learning libraries.Its flexible design allows easy expansion for additional tasks and applications.The open-source algorithms,models,data sets,and deployment processes foster additional research and innovation in EV and broader engineering domains.
文摘The nutritional management of patients with esophageal cancer(EC)presents significant complexities,with traditional approaches facing inherent limitations in data collection,real-time decision-making,and personalized care.This narrative review explores the transformative potential of artificial intelligence(AI)and machine learning(ML),particularly deep learning(DL)and reinforcement learning(RL),in revolutionizing nutritional support for this vulnerable patient population.DL has demonstrated remarkable capabilities in enhancing the accuracy and objectivity of nutritional assessment through precise,automated body composition analysis from medical imaging,offering valuable prognostic insights.Concurrently,RL enables the dynamic optimization of nutritional interventions,adapting them in real time to individual patient responses,paving the way for truly personalized care paradigms.Although AI/ML offers potential advantages in efficiency,precision,and personalization by integrating multidimensional data for superior clinical decision support,its widespread adoption is accompanied by critical challenges.These include safeguarding data privacy and security,mitigating algorithmic bias,ensuring transparency and accountability,and establishing rigorous clinical validation.Early evidence suggests the feasibility of applying AI/ML in nutritional risk stratification and workflow optimization,but highquality prospective studies are needed to demonstrate the direct impact on clinical outcomes,including complications,readmissions,and survival.Overcoming these hurdles necessitates robust ethical governance,interdisciplinary collaboration,and continuous education.Ultimately,the strategic integration of AI/ML holds immense promise to profoundly improve patient outcomes,enhance quality of life,and optimize health care resource utilization in the nutritional management of esophageal cancer.
基金funded by Beijing Natural Science Foundation(Grant No.:7242112,1242036)the National Natural Science Foundation of China(Grant No.:12205375,12205376)Beijing Hope Run Special Fund of Cancer Foundation of China(Grant No.:LC2022B28).
文摘The aim of radiotherapy(RT)is to deliver prescribed doses to tumors while sparing neighboring organs at risk.As the demand for treatment precision increases in modern RT,intrafractional motion management becomes critical for achieving high precision,particularly for tumors in the thorax and abdomen that are affected by respiration and other physiological motions.Deep learning(DL)has demonstrated strong po-tential in addressing the limitations of conventional methods by enabling rapid and accurate tumor motion detection,tumor location prediction,and management measures.This review provides a comprehensive overview of recent DL-based applications in intrafractional motion management,which are categorized into three areas:(1)tumor motion detection for real-time tumor localization,(2)tumor location prediction to compensate for the latency of the motion management system,and(3)management measures,including gating and real-time adaptive RT.In addition,this review discusses key challenges and their potential so-lutions for DL-based motion management.
基金funded by the Deanship of Scientific Research and Libraries,Princess Nourah Bint Abdulrahman University,through the Program of Research Project Funding after Publication,grant No.(RPFAP-79-1445).
文摘Solar radiation is the main source of energy on Earth and plays a major role in the hydrological cycles,surface radiation balance,weather and climate changes,and vegetation photosynthesis.Accurate solar radiation prediction is of paramount importance for both climate research and the solar industry.This prediction includes forecasting techniques and advanced modeling to evaluate the amount of solar energy available at a specific location during a given period.Solar energy is the cheapest form of clean energy,and due to the intermittent nature of the energy,accurate forecasting across multiple timeframes is necessary for efficient generation and demand management.Solar radiation prediction using deep learning(DL)includes the applications of neural network methods,namely Convolutional Neural Network(CNN)or Long Short-Term Memory(LSTM)models,to forecast and model solar irradiance patterns.By leveraging meteorological variables and historical solar radiation data,DL algorithms can capture complex spatial and temporal dependencies,resulting in accurate predictions.This article presents a novel Solar Radiation Prediction model utilizing a Boosted Coyote Optimization Algorithm with Deep Learning(SRP-BCOADL).The SRP-BCOADL model initially normalizes the input data using a min-max normalization approach to improve the robust nature under different scales.Besides,the SRP-BCOADL technique uses a Deep Long Short-Term Memory Autoencoder(DLSTM-AE)system for precisely forecasting solar radiation levels.The model’s accuracy is further improved through hyperparameter optimization using the BCOA.The performance analysis of the SRP-BCOADL technique is tested using solar radiation data.Extensive experimental outcomes prove that the SRP-BCOADL method obtains better results over other techniques.The Mean Squared Error(MSE)is just 0.13 kWh/m^(2),is much lower when compared to other models.The Root Mean Squared Error(RMSE)is also reduced to 0.36 kWh/m^(2),and the Mean Absolute Error(MAE)reaches a minimal level of 0.276 kWh/m^(2).
基金Funded by Kuwait Foundation for the Advancement of Sciences(KFAS)under project code:PN23-15EM-1901.
文摘The rapid advancements in distributed generation technologies,the widespread adoption of distributed energy resources,and the integration of 5G technology have spurred sharing economy businesses within the electricity sector.Revolutionary technologies such as blockchain,5G connectivity,and Internet of Things(IoT)devices have facilitated peer-to-peer distribution and real-time response to fluctuations in supply and demand.Nevertheless,sharing electricity within a smart community presents numerous challenges,including intricate design considerations,equitable allocation,and accurate forecasting due to the lack of well-organized temporal parameters.To address these challenges,this proposed system is focused on sharing extra electricity within the smart community.The working of the proposed system is composed of five main phases.In phase 1,we develop a model to forecast the energy consumption of the appliances using the Long Short-Term Memory(LSTM)integrated with the attention module.In phase 2,based on the predicted energy consumption,we designed a smart scheduler with attention-induced Genetic Algorithm(GA)to schedule the appliances to reduce energy consumption.In phase 3,a dynamic Feed-in Tariff(dFIT)algorithm makes real-time tariff adjustments using LSTM for demand prediction and SHapley Additive exPlanations(SHAP)values to improve model transparency.In phase 4,the energy saved from solar systems and smart scheduling is shared with the community grid.Finally,in phase 5,SDP security ensures the integrity and confidentiality of shared energy data.To evaluate the performance of energy sharing and scheduling for houses with and without solar support,we simulated the above phases using data obtained from the energy consumption of 17 household appliances in our IoT laboratory.Finally,the simulation results show that the proposed scheme reduces energy consumption and ensures secure and efficient distribution with peers,promoting a more sustainable energy management and resilient smart community.
文摘This paper explores the possibility of using machine learning algorithms to predict type 2 diabetes.We selected two commonly used classification models:random forest and logistic regression,modeled patients’clinical and lifestyle data,and compared their prediction performance.We found that the random forest model achieved the highest accuracy,demonstrated excellent classification results on the test set,and better distinguished between diabetic and non-diabetic patients by the confusion matrix and other evaluation metrics.The support vector machine and logistic regression perform slightly less well but achieve a high level of accuracy.The experimental results validate the effectiveness of the three machine learning algorithms,especially random forest,in the diabetes prediction task and provide useful practical experience for the intelligent prevention and control of chronic diseases.This study promotes the innovation of the diabetes prediction and management model,which is expected to alleviate the pressure on medical resources,reduce the burden of social health care,and improve the prognosis and quality of life of patients.In the future,we can consider expanding the data scale,exploring other machine learning algorithms,and integrating multimodal data to further realize the potential of artificial intelligence(AI)in the field of diabetes.
基金supported by the Science and Technology Project of State Grid Sichuan Electric Power Company Chengdu Power Supply Company under Grant No.521904240005.
文摘This paper presents a novel approach to dynamic pricing and distributed energy management in virtual power plant(VPP)networks using multi-agent reinforcement learning(MARL).As the energy landscape evolves towards greater decentralization and renewable integration,traditional optimization methods struggle to address the inherent complexities and uncertainties.Our proposed MARL framework enables adaptive,decentralized decision-making for both the distribution system operator and individual VPPs,optimizing economic efficiency while maintaining grid stability.We formulate the problem as a Markov decision process and develop a custom MARL algorithm that leverages actor-critic architectures and experience replay.Extensive simulations across diverse scenarios demonstrate that our approach consistently outperforms baseline methods,including Stackelberg game models and model predictive control,achieving an 18.73%reduction in costs and a 22.46%increase in VPP profits.The MARL framework shows particular strength in scenarios with high renewable energy penetration,where it improves system performance by 11.95%compared with traditional methods.Furthermore,our approach demonstrates superior adaptability to unexpected events and mis-predictions,highlighting its potential for real-world implementation.
文摘Learning analytics is an emerging technique of analysing student par-ticipation and engagement.The recent COVID-19 pandemic has significantly increased the role of learning management systems(LMSs).LMSs previously only complemented face-to-face teaching,something which has not been possible between 2019 to 2020.To date,the existing body of literature on LMSs has not analysed learning in the context of the pandemic,where an LMS serves as the only interface between students and instructors.Consequently,productive results will remain elusive if the key factors that contribute towards engaging students in learning are notfirst identified.Therefore,this study aimed to perform an exten-sive literature review with which to design and develop a student engagement model for holistic involvement in an LMS.The required data was collected from an LMS that is currently utilised by a local Malaysian university.The model was validated by a panel of experts as well as discussions with students.It is our hope that the result of this study will help other institutions of higher learning determine factors of low engagement in their respective LMSs.
基金supported by the Researchers Supporting Program(TUMA-Project2021-27)Almaarefa University,RiyadhSaudi Arabia.Taif University Researchers Supporting Project number(TURSP-2020/161)Taif University,Taif,Saudi Arabia.
文摘Learning Management System(LMS)is an application software that is used in automation,delivery,administration,tracking,and reporting of courses and programs in educational sector.The LMS which exploits machine learning(ML)has the ability of accessing user data and exploit it for improving the learning experience.The recently developed artificial intelligence(AI)and ML models helps to accomplish effective performance monitoring for LMS.Among the different processes involved in ML based LMS,feature selection and classification processesfind beneficial.In this motivation,this study introduces Glowworm-based Feature Selection with Machine Learning Enabled Performance Monitoring(GSO-MFWELM)technique for LMS.The key objective of the proposed GSO-MFWELM technique is to effectually monitor the performance in LMS.The pro-posed GSO-MFWELM technique involves GSO-based feature selection techni-que to select the optimal features.Besides,Weighted Extreme Learning Machine(WELM)model is applied for classification process whereas the parameters involved in WELM model are optimallyfine-tuned with the help of May-fly Optimization(MFO)algorithm.The design of GSO and MFO techniques result in reduced computation complexity and improved classification performance.The presented GSO-MFWELM technique was validated for its performance against benchmark dataset and the results were inspected under several aspects.The simulation results established the supremacy of GSO-MFWELM technique over recent approaches with the maximum classification accuracy of 0.9589.
文摘Energy management is an inspiring domain in developing of renewable energy sources.However,the growth of decentralized energy production is revealing an increased complexity for power grid managers,inferring more quality and reliability to regulate electricity flows and less imbalance between electricity production and demand.The major objective of an energy management system is to achieve optimum energy procurement and utilization throughout the organization,minimize energy costs without affecting production,and minimize environmental effects.Modern energy management is an essential and complex subject because of the excessive consumption in residential buildings,which necessitates energy optimization and increased user comfort.To address the issue of energy management,many researchers have developed various frameworks;while the objective of each framework was to sustain a balance between user comfort and energy consumption,this problem hasn’t been fully solved because of how difficult it is to solve it.An inclusive and Intelligent Energy Management System(IEMS)aims to provide overall energy efficiency regarding increased power generation,increase flexibility,increase renewable generation systems,improve energy consumption,reduce carbon dioxide emissions,improve stability,and reduce energy costs.Machine Learning(ML)is an emerging approach that may be beneficial to predict energy efficiency in a better way with the assistance of the Internet of Energy(IoE)network.The IoE network is playing a vital role in the energy sector for collecting effective data and usage,resulting in smart resource management.In this research work,an IEMS is proposed for Smart Cities(SC)using the ML technique to better resolve the energy management problem.The proposed system minimized the energy consumption with its intelligent nature and provided better outcomes than the previous approaches in terms of 92.11% accuracy,and 7.89% miss-rate.
