Electric Vehicle Charging Systems(EVCS)are increasingly vulnerable to cybersecurity threats as they integrate deeply into smart grids and Internet ofThings(IoT)environments,raising significant security challenges.Most...Electric Vehicle Charging Systems(EVCS)are increasingly vulnerable to cybersecurity threats as they integrate deeply into smart grids and Internet ofThings(IoT)environments,raising significant security challenges.Most existing research primarily emphasizes network-level anomaly detection,leaving critical vulnerabilities at the host level underexplored.This study introduces a novel forensic analysis framework leveraging host-level data,including system logs,kernel events,and Hardware Performance Counters(HPC),to detect and analyze sophisticated cyberattacks such as cryptojacking,Denial-of-Service(DoS),and reconnaissance activities targeting EVCS.Using comprehensive forensic analysis and machine learning models,the proposed framework significantly outperforms existing methods,achieving an accuracy of 98.81%.The findings offer insights into distinct behavioral signatures associated with specific cyber threats,enabling improved cybersecurity strategies and actionable recommendations for robust EVCS infrastructure protection.展开更多
This article delves into the analysis of performance and utilization of Support Vector Machines (SVMs) for the critical task of forest fire detection using image datasets. With the increasing threat of forest fires to...This article delves into the analysis of performance and utilization of Support Vector Machines (SVMs) for the critical task of forest fire detection using image datasets. With the increasing threat of forest fires to ecosystems and human settlements, the need for rapid and accurate detection systems is of utmost importance. SVMs, renowned for their strong classification capabilities, exhibit proficiency in recognizing patterns associated with fire within images. By training on labeled data, SVMs acquire the ability to identify distinctive attributes associated with fire, such as flames, smoke, or alterations in the visual characteristics of the forest area. The document thoroughly examines the use of SVMs, covering crucial elements like data preprocessing, feature extraction, and model training. It rigorously evaluates parameters such as accuracy, efficiency, and practical applicability. The knowledge gained from this study aids in the development of efficient forest fire detection systems, enabling prompt responses and improving disaster management. Moreover, the correlation between SVM accuracy and the difficulties presented by high-dimensional datasets is carefully investigated, demonstrated through a revealing case study. The relationship between accuracy scores and the different resolutions used for resizing the training datasets has also been discussed in this article. These comprehensive studies result in a definitive overview of the difficulties faced and the potential sectors requiring further improvement and focus.展开更多
BACKGROUND The early acquisition of skills required to perform hemostasis during endoscopy may be hindered by the lack of tools that allow assessments of the operator’s viewpoint.Understanding the operator’s viewpoi...BACKGROUND The early acquisition of skills required to perform hemostasis during endoscopy may be hindered by the lack of tools that allow assessments of the operator’s viewpoint.Understanding the operator’s viewpoint may facilitate the skills.AIM To evaluate the effects of a training system using operator gaze patterns during gastric endoscopic submucosal dissection(ESD)on hemostasis.METHODS An eye-tracking system was developed to record the operator’s viewpoints during gastric ESD,displaying the viewpoint as a circle.In phase 1,videos of three trainees’viewpoints were recorded.After reviewing these,trainees were recorded again in phase 2.The videos from both phases were retrospectively reviewed,and short clips were created to evaluate the hemostasis skills.Outcome measures included the time to recognize the bleeding point,the time to complete hemostasis,and the number of coagulation attempts.RESULTS Eight cases treated with ESD were reviewed,and 10 video clips of hemostasis were created.The time required to recognize the bleeding point during phase 2 was significantly shorter than that during phase 1(8.3±4.1 seconds vs 23.1±19.2 seconds;P=0.049).The time required to complete hemostasis during phase 1 and that during phase 2 were not significantly different(15.4±6.8 seconds vs 31.9±21.7 seconds;P=0.056).Significantly fewer coagulation attempts were performed during phase 2(1.8±0.7 vs 3.2±1.0;P=0.004).CONCLUSION Short-term training did not reduce hemostasis completion time but significantly improved bleeding point recognition and reduced coagulation attempts.Learning from the operator’s viewpoint can facilitate acquiring hemostasis skills during ESD.展开更多
The increased accessibility of social networking services(SNSs)has facilitated communication and information sharing among users.However,it has also heightened concerns about digital safety,particularly for children a...The increased accessibility of social networking services(SNSs)has facilitated communication and information sharing among users.However,it has also heightened concerns about digital safety,particularly for children and adolescents who are increasingly exposed to online grooming crimes.Early and accurate identification of grooming conversations is crucial in preventing long-term harm to victims.However,research on grooming detection in South Korea remains limited,as existing models trained primarily on English text and fail to reflect the unique linguistic features of SNS conversations,leading to inaccurate classifications.To address these issues,this study proposes a novel framework that integrates optical character recognition(OCR)technology with KcELECTRA,a deep learning-based natural language processing(NLP)model that shows excellent performance in processing the colloquial Korean language.In the proposed framework,the KcELECTRA model is fine-tuned by an extensive dataset,including Korean social media conversations,Korean ethical verification data from AI-Hub,and Korean hate speech data from Hug-gingFace,to enable more accurate classification of text extracted from social media conversation images.Experimental results show that the proposed framework achieves an accuracy of 0.953,outperforming existing transformer-based models.Furthermore,OCR technology shows high accuracy in extracting text from images,demonstrating that the proposed framework is effective for online grooming detection.The proposed framework is expected to contribute to the more accurate detection of grooming text and the prevention of grooming-related crimes.展开更多
BACKGROUND Sodium glucose cotransporter-2 inhibitors(SGLT-2i)are a class of drugs with modest antidiabetic efficacy,weight loss effect,and cardiovascular benefits as proven by multiple randomised controlled trials(RCT...BACKGROUND Sodium glucose cotransporter-2 inhibitors(SGLT-2i)are a class of drugs with modest antidiabetic efficacy,weight loss effect,and cardiovascular benefits as proven by multiple randomised controlled trials(RCTs).However,real-world data on the comparative efficacy and safety of individual SGLT-2i medications is sparse.AIM To study the comparative efficacy and safety of SGLT-2i using real-world clinical data.METHODS We evaluated the comparative efficacy data of 3 SGLT-2i drugs(dapagliflozin,canagliflozin,and empagliflozin)used for treating patients with type 2 diabetes mellitus.Data on the reduction of glycated hemoglobin(HbA1c),body weight,blood pressure(BP),urine albumin creatinine ratio(ACR),and adverse effects were recorded retrospectively.RESULTS Data from 467 patients with a median age of 64(14.8)years,294(62.96%)males and 375(80.5%)Caucasians were analysed.Median diabetes duration was 16.0(9.0)years,and the duration of SGLT-2i use was 3.6(2.1)years.SGLT-2i molecules used were dapagliflozin 10 mg(n=227;48.6%),canagliflozin 300 mg(n=160;34.3%),and empagliflozin 25 mg(n=80;17.1).Baseline median(interquartile range)HbA1c in mmol/mol were:dapagliflozin-78.0(25.3),canagliflozin-80.0(25.5),and empagliflozin-75.0(23.5)respectively.The respective median HbA1c reduction at 12 months and the latest review(just prior to the study)were:66.5(22.8)&69.0(24.0),67.0(16.3)&66.0(28.0),and 67.0(22.5)&66.5(25.8)respectively(P<0.001 for all comparisons from baseline).Significant improvements in body weight(in kilograms)from baseline to study end were noticed with dapagliflozin-101(29.5)to 92.2(25.6),and canagliflozin 100(28.3)to 95.3(27.5)only.Significant reductions in median systolic and diastolic BP,from 144(21)mmHg to 139(23)mmHg;(P=0.015),and from 82(16)mmHg to 78(19)mmHg;(P<0.001)respectively were also observed.A significant reduction of microalbuminuria was observed with canagliflozin only[ACR 14.6(42.6)at baseline to 8.9(23.7)at the study end;P=0.043].Adverse effects of SGLT-2i were as follows:genital thrush and urinary infection-20(8.8%)&17(7.5%)with dapagliflozin;9(5.6%)&5(3.13%)with canagliflozin;and 4(5%)&4(5%)with empagliflozin.Diabetic ketoacidosis was observed in 4(1.8%)with dapagliflozin and 1(0.63%)with canagliflozin.CONCLUSION Treatment of patients with SGLT-2i is associated with statistically significant reductions in HbA1c,body weight,and better than those reported in RCTs,with low side effect profiles.A review of large-scale real-world data is needed to inform better clinical practice decision making.展开更多
Background:Sleep disturbance is commonly seen in fibromyalgia syndrome (FMS);however,high quality studies involving manual therapies that target FMS-linked poor sleep quality are lacking for the Indian population.Obje...Background:Sleep disturbance is commonly seen in fibromyalgia syndrome (FMS);however,high quality studies involving manual therapies that target FMS-linked poor sleep quality are lacking for the Indian population.Objective:Craniosacral therapy (CST),Bowen therapy and exercises have been found to influence the autonomic nervous system,which plays a crucial role in sleep physiology.Given the paucity of evidence concerning these effects in individuals with FMS,our study tests the effectiveness of CST,Bowen therapy and a standard exercise program against static touch (the manual placebo group) on sleep quality in FMS.Design,setting,participants and intervention:A placebo-controlled randomized trial was conducted on132 FMS participants with poor sleep at a hospital in Bangalore.The participants were randomly allocated to one of the four study groups,including CST,Bowen therapy,standard exercise program,and a manual placebo control group that received static touch.CST,Bowen therapy and static touch treatments were administered in once-weekly 45-minute sessions for 12 weeks;the standard exercise group received weekly supervised exercises for 6 weeks with home exercises until 12 weeks.After 12 weeks,all study participants performed the standard exercises at home for another 12 weeks.Main outcome measures:Sleep quality,pressure pain threshold (PPT),quality of life and fibromyalgia impact,physical function,fatigue,pain catastrophizing,kinesiophobia,and positive–negative affect were recorded at baseline,and at weeks 12 and 24 of the intervention.Results:At the end of 12 weeks,the sleep quality improved significantly in the CST group (P=0.037) and Bowen therapy group (P=0.023),and the PPT improved significantly in the Bowen therapy group(P=0.002) and the standard exercise group (P<0.001),compared to the static touch group.These improvements were maintained at 24 weeks.No between-group differences were observed for other secondary outcomes.Conclusion:CST and Bowen therapy improved sleep quality,and Bowen therapy and standard exercises improved pain threshold in the short term.These improvements were retained within the groups in the long term by adding exercises.CST and Bowen therapy are treatment options to improve sleep and reduce pain in FMS.展开更多
Amid the landscape of Cloud Computing(CC),the Cloud Datacenter(DC)stands as a conglomerate of physical servers,whose performance can be hindered by bottlenecks within the realm of proliferating CC services.A linchpin ...Amid the landscape of Cloud Computing(CC),the Cloud Datacenter(DC)stands as a conglomerate of physical servers,whose performance can be hindered by bottlenecks within the realm of proliferating CC services.A linchpin in CC’s performance,the Cloud Service Broker(CSB),orchestrates DC selection.Failure to adroitly route user requests with suitable DCs transforms the CSB into a bottleneck,endangering service quality.To tackle this,deploying an efficient CSB policy becomes imperative,optimizing DC selection to meet stringent Qualityof-Service(QoS)demands.Amidst numerous CSB policies,their implementation grapples with challenges like costs and availability.This article undertakes a holistic review of diverse CSB policies,concurrently surveying the predicaments confronted by current policies.The foremost objective is to pinpoint research gaps and remedies to invigorate future policy development.Additionally,it extensively clarifies various DC selection methodologies employed in CC,enriching practitioners and researchers alike.Employing synthetic analysis,the article systematically assesses and compares myriad DC selection techniques.These analytical insights equip decision-makers with a pragmatic framework to discern the apt technique for their needs.In summation,this discourse resoundingly underscores the paramount importance of adept CSB policies in DC selection,highlighting the imperative role of efficient CSB policies in optimizing CC performance.By emphasizing the significance of these policies and their modeling implications,the article contributes to both the general modeling discourse and its practical applications in the CC domain.展开更多
Regular physical activity(PA)is known to enhance multifaceted health benefits,including both physical and mental health.However,traditional in-person physical activity programs have drawbacks,including time constraints...Regular physical activity(PA)is known to enhance multifaceted health benefits,including both physical and mental health.However,traditional in-person physical activity programs have drawbacks,including time constraints for busy people.Although evidence suggests positive impacts on mental health through mobile-based physical activity,effects of accumulated short bouts of physical activity using mobile devices are unexplored.Thus,this study aims to investigate these effects,focusing on depression,perceived stress,and negative affectivity among South Korean college students.Forty-six healthy college students were divided into the accumulated group(n=23,female=47.8%)and control group(n=23,female=47.6%).The accumulated group engaged in mobile-based physical activity,following guidelines to accumulate a minimum of two times per day and three times a week.Sessions were divided into short bouts,ensuing each bout lasted at least 10 min.The control group did not engage in any specific physical activity.The data analysis involved comparing the scores of the intervention and control groups using several statistical techniques,such as independent sample t-test,paired sample t-tests,and 2(time)×2(group)repeated measures analysis of variance.The demographic characteristics at the pre-test showed no statistically significant differences between the groups.The accumulated group had significant decreases in depression(t_(40)=2.59,p=0.013,Cohen’s D=0.84)and perceived stress(t_(40)=2.06,p=0.046,Cohen’s D=0.56)from the pre-to post-test.The control group exhibited no statistically significant differences in any variables.Furthermore,there were significant effects of time on depression scores(F1,36=4.77,p=0.036,η_(p)^(2)=0.12)while significant interaction effects were also observed for depression(F_(1,36)=6.59,p=0.015,η_(p)^(2)=0.16).This study offers informative insights into the potential advantages of mobile-based physical activity programs with accumulated periods for enhancing mental health,specifically in relation to depression.This study illuminates the current ongoing discussions on efficient approaches to encourage mobile-based physical activity and improve mental well-being,addressing various lifestyles and busy schedules.展开更多
Connected automated vehicles(CAVs)rely heavily on intelligent algorithms and remote sensors.If the control center or on-board sensors are under cyber-attack due to the security vulnerability of wireless communication,...Connected automated vehicles(CAVs)rely heavily on intelligent algorithms and remote sensors.If the control center or on-board sensors are under cyber-attack due to the security vulnerability of wireless communication,it can cause significant damage to CAVs or passengers.The primary objective of this study is to model cyberattacked traffic flow and evaluate the impacts of cyber-attack on the traffic system filled with CAVs in a connected environment.Based on the analysis on environmental perception system and possible cyber-attacks on sensors,a novel lane-changing model for CAVs is proposed and multiple traffic scenarios for cyber-attacks are designed.The impact of the proportion of cyber-attacked vehicles and the severity of the cyber-attack on the lanechanging process is then quantitatively analyzed.The evaluation indexes include spatio-temporal evolution of average speed,spatial distribution of selected lane-changing gaps,lane-changing rate distribution,lane-changing preparation search time,efficiency and safety.Finally,the numerical simulation results show that the freeway traffic near an off-ramp is more sensitive to the proportion of cyber-attacked vehicles than to the severity of the cyber-attack.Also,when the traffic system is under cyber-attack,more unsafe back gaps are chosen for lane-changing,especially in the center lane.Therefore,more lane-changing maneuvers are concentrated on approaching the off-ramp,causing severe congestions and potential rear-end collisions.In addition,as the number of cyber-attacked vehicles and the severity of cyber-attacks increase,the road capacity and safety level will rapidly decrease.The results of this study can provide a theoretical basis for accident avoidance and efficiency improvement for the design of CAVs and management of automated highway systems.展开更多
BACKGROUND Diabesity(diabetes as a consequence of obesity)has emerged as a huge healthcare challenge across the globe due to the obesity pandemic.Judicious use of antidiabetic medications including semaglutide is impo...BACKGROUND Diabesity(diabetes as a consequence of obesity)has emerged as a huge healthcare challenge across the globe due to the obesity pandemic.Judicious use of antidiabetic medications including semaglutide is important for optimal management of diabesity as proven by multiple randomized controlled trials.However,more real-world data is needed to further improve the clinical practice.AIM To study the real-world benefits and side effects of using semaglutide to manage patients with diabesity.METHODS We evaluated the efficacy and safety of semaglutide use in managing patients with diabesity in a large academic hospital in the United States.Several parameters were analyzed including demographic information,the data on improvement of glycated hemoglobin(HbA1c),body weight reduction and insulin dose adjustments at 6 and 12 months,as well as at the latest follow up period.The data was obtained from the electronic patient records between January 2019 to May 2023.RESULTS 106 patients(56 males)with type 2 diabetes mellitus(T2DM),mean age 60.8±11.2 years,mean durations of T2DM 12.4±7.2 years and mean semaglutide treatment for 2.6±1.1 years were included.Semaglutide treatment was associated with significant improvement in diabesity outcomes such as mean weight reductions from baseline 110.4±24.6 kg to 99.9±24.9 kg at 12 months and 96.8±22.9 kg at latest follow up and HbA1c improvement from baseline of 82±21 mmol/mol to 67±20 at 12 months and 71±23 mmol/mol at the latest follow up.An insulin dose reduction from mean baseline of 95±74 units to 76.5±56.2 units was also observed at the latest follow up.Side effects were mild and mainly gastrointestinal like bloating and nausea improving with prolonged use of semaglutide.CONCLUSION Semaglutide treatment is associated with significant improvement in diabesity outcomes such as reduction in body weight,HbA1c and insulin doses without major adverse effects.Reviews of largescale real-world data are expected to inform better clinical practice decision making to improve the care of patients with diabesity.展开更多
BACKGROUND Inflammatory bowel disease(IBD),with its rising prevalence rates is associated with an increased risk of cardiovascular and thromboembolic events.Antiplatelets and/or anticoagulants agents are often prescri...BACKGROUND Inflammatory bowel disease(IBD),with its rising prevalence rates is associated with an increased risk of cardiovascular and thromboembolic events.Antiplatelets and/or anticoagulants agents are often prescribed but the literature on the impact of long-term anticoagulation and/or antiplatelet use among patients hospitalized with IBD is scarce.The aim of this study is to assess the outcomes of patients hospitalized with IBD on antiplatelet and/or anticoagulant agents.AIM To investigate the effects of long-term use of antiplatelets/anticoagulants on clinical outcomes in patients hospitalized with IBD.METHODS We conducted a retrospective cohort study using the Nationwide Inpatient Sample database,including all adult IBD patients hospitalized in the United States from 2016 to 2019.Patient cohorts were stratified based on antiplatelet/anticoagulant therapy status.Multivariate regression analysis was done to assess outcomes,adjusting for potential confounders.The primary outcome was mortality,whereas length of stay(LOS),total parenteral nutrition,acute kidney injury,sepsis,shock,gastrointestinal bleeding,need for colonoscopy/sigmoidoscopy,abdominal surgery and total hospitalization charges were secondary outcomes.RESULTS Among 374744 hospitalized IBD patients,antiplatelet or anticoagulant therapy alone was associated with significantly lower in-hospital mortality and reduced healthcare utilization,including shorter LOS and decreased hospitalization costs.Combined therapy was associated with a protective effect on mortality,but did not reach statistical significance.Notably,therapy did not exacerbate disease severity or complications,although higher odds of gastrointestinal bleeding were observed.CONCLUSION Our study highlights the potential benefits of long-term anticoagulation/antiplatelet therapy in hospitalized IBD patients,with improved mortality outcomes and healthcare utilization.While concerns regarding gastrointestinal bleeding exist,the overall safety profile suggests a role for these agents in mitigating thromboembolic risks without exacerbating disease severity.Further research is needed to look at optimal treatment strategies and addressing limitations to guide clinical decision-making in this population.展开更多
This paper presents a detailed statistical exploration of crime trends in Chicago from 2001 to 2023, employing data from the Chicago Police Department’s publicly available crime database. The study aims to elucidate ...This paper presents a detailed statistical exploration of crime trends in Chicago from 2001 to 2023, employing data from the Chicago Police Department’s publicly available crime database. The study aims to elucidate the patterns, distribution, and variations in crime across different types and locations, providing a comprehensive picture of the city’s crime landscape through advanced data analytics and visualization techniques. Using exploratory data analysis (EDA), we identified significant insights into crime trends, including the prevalence of theft and battery, the impact of seasonal changes on crime rates, and spatial concentrations of criminal activities. The research leveraged a Power BI dashboard to visually represent crime data, facilitating an intuitive understanding of complex patterns and enabling dynamic interaction with the dataset. Key findings highlight notable disparities in crime occurrences by type, location, and time, offering a granular view of crime hotspots and temporal trends. Additionally, the study examines clearance rates, revealing variations in the resolution of cases across different crime categories. This analysis not only sheds light on the current state of urban safety but also serves as a critical tool for policymakers and law enforcement agencies to develop targeted interventions. The paper concludes with recommendations for enhancing public safety strategies and suggests directions for future research, emphasizing the need for continuous data-driven approaches to effectively address and mitigate urban crime. This study contributes to the broader discourse on urban safety, crime prevention, and the role of data analytics in public policy and community well-being.展开更多
Customer churn poses a significant challenge for the banking and finance industry in the United States, directly affecting profitability and market share. This study conducts a comprehensive comparative analysis of ma...Customer churn poses a significant challenge for the banking and finance industry in the United States, directly affecting profitability and market share. This study conducts a comprehensive comparative analysis of machine learning models for customer churn prediction, focusing on the U.S. context. The research evaluates the performance of logistic regression, random forest, and neural networks using industry-specific datasets, considering the economic impact and practical implications of the findings. The exploratory data analysis reveals unique patterns and trends in the U.S. banking and finance industry, such as the age distribution of customers and the prevalence of dormant accounts. The study incorporates macroeconomic factors to capture the potential influence of external conditions on customer churn behavior. The findings highlight the importance of leveraging advanced machine learning techniques and comprehensive customer data to develop effective churn prevention strategies in the U.S. context. By accurately predicting customer churn, financial institutions can proactively identify at-risk customers, implement targeted retention strategies, and optimize resource allocation. The study discusses the limitations and potential future improvements, serving as a roadmap for researchers and practitioners to further advance the field of customer churn prediction in the evolving landscape of the U.S. banking and finance industry.展开更多
The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by...The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by these interconnected devices,robust anomaly detection mechanisms are essential.Anomaly detection in this dynamic environment necessitates methods that can accurately distinguish between normal and anomalous behavior by learning intricate patterns.This paper presents a novel approach utilizing generative adversarial networks(GANs)for anomaly detection in IoT systems.However,optimizing GANs involves tuning hyper-parameters such as learning rate,batch size,and optimization algorithms,which can be challenging due to the non-convex nature of GAN loss functions.To address this,we propose a five-dimensional Gray wolf optimizer(5DGWO)to optimize GAN hyper-parameters.The 5DGWO introduces two new types of wolves:gamma(γ)for improved exploitation and convergence,and theta(θ)for enhanced exploration and escaping local minima.The proposed system framework comprises four key stages:1)preprocessing,2)generative model training,3)autoencoder(AE)training,and 4)predictive model training.The generative models are utilized to assist the AE training,and the final predictive models(including convolutional neural network(CNN),deep belief network(DBN),recurrent neural network(RNN),random forest(RF),and extreme gradient boosting(XGBoost))are trained using the generated data and AE-encoded features.We evaluated the system on three benchmark datasets:NSL-KDD,UNSW-NB15,and IoT-23.Experiments conducted on diverse IoT datasets show that our method outperforms existing anomaly detection strategies and significantly reduces false positives.The 5DGWO-GAN-CNNAE exhibits superior performance in various metrics,including accuracy,recall,precision,root mean square error(RMSE),and convergence trend.The proposed 5DGWO-GAN-CNNAE achieved the lowest RMSE values across the NSL-KDD,UNSW-NB15,and IoT-23 datasets,with values of 0.24,1.10,and 0.09,respectively.Additionally,it attained the highest accuracy,ranging from 94%to 100%.These results suggest a promising direction for future IoT security frameworks,offering a scalable and efficient solution to safeguard against evolving cyber threats.展开更多
Improving early diagnosis of autism spectrum disorder(ASD)in children increasingly relies on predictive models that are reliable and accessible to non-experts.This study aims to develop such models using Python-based ...Improving early diagnosis of autism spectrum disorder(ASD)in children increasingly relies on predictive models that are reliable and accessible to non-experts.This study aims to develop such models using Python-based tools to improve ASD diagnosis in clinical settings.We performed exploratory data analysis to ensure data quality and identify key patterns in pediatric ASD data.We selected the categorical boosting(CatBoost)algorithm to effectively handle the large number of categorical variables.We used the PyCaret automated machine learning(AutoML)tool to make the models user-friendly for clinicians without extensive machine learning expertise.In addition,we applied Shapley additive explanations(SHAP),an explainable artificial intelligence(XAI)technique,to improve the interpretability of the models.Models developed using CatBoost and other AI algorithms showed high accuracy in diagnosing ASD in children.SHAP provided clear insights into the influence of each variable on diagnostic outcomes,making model decisions transparent and understandable to healthcare professionals.By integrating robust machine learning methods with user-friendly tools such as PyCaret and leveraging XAI techniques such as SHAP,this study contributes to the development of reliable,interpretable,and accessible diagnostic tools for ASD.These advances hold great promise for supporting informed decision-making in clinical settings,ultimately improving early identification and intervention strategies for ASD in the pediatric population.However,the study is limited by the dataset’s demographic imbalance and the lack of external clinical validation,which should be addressed in future research.展开更多
This paper studies the renewable power forecasting task with a more advanced formulation,the probabilistic forecasts of day-ahead power generation sequences of multiple renewable power plants without breaching the pri...This paper studies the renewable power forecasting task with a more advanced formulation,the probabilistic forecasts of day-ahead power generation sequences of multiple renewable power plants without breaching the privacy of data in each plant.To realize such a task,an advanced domain-invariant feature learning embedded federated learning(DIFL)framework is proposed to coordinate the development of a system of deep networkbased models serving as multiple clients and one server.In DIFL,each client,which serves each local renew-able power plant,maps its raw data input into latent features via a local feature extractor and generates power output sequence probabilistic forecasts via a locally hosted forecasting model.The cloud-hosted server first aggregates the knowledge from models of clients and next dispatches the aggregated model back to each client for facilitating each local feature extractor to identify domain-invariant features via interacting with a server-side discriminator.Therefore,only desensitized data,such as parameters of the models,are allowed to be transmitted among end users for preserving local data privacy of power plants.To verify the advantages of the DIFL,a preliminary exploration of its theoretical property is first conducted.Next,computational studies are performed to benchmark the DIFL against famous baselines based on datasets collected from commercial renewable power plants.Results further confirm that,in terms of the averaged performance,the DIFL consistently realizes im-provements against all benchmarks based on both real wind farm and solar power plant datasets.展开更多
In this study,we investigated privacy-preserving ID3 Decision Tree(PPID3)training and inference based on fully homomorphic encryption(FHE),which has not been actively explored due to the high computational cost associ...In this study,we investigated privacy-preserving ID3 Decision Tree(PPID3)training and inference based on fully homomorphic encryption(FHE),which has not been actively explored due to the high computational cost associated with managing numerous child nodes in an ID3 tree.We propose HEaaN-ID3,a novel approach to realize PPID3 using the Cheon-Kim-Kim-Song(CKKS)scheme.HEaaN-ID3 is the first FHE-based ID3 framework that completes both training and inference without any intermediate decryption,which is especially valuable when decryption keys are inaccessible or a single-cloud security domain is assumed.To enhance computational efficiency,we adopt a modified Gini impurity(MGI)score instead of entropy to evaluate information gain,thereby avoiding costly inverse operations.In addition,we fully leverage the Single Instruction Multiple Data(SIMD)property of CKKS to parallelize computations at multiple tree nodes.Unlike previous approaches that require decryption at each node or rely on two-party secure computation,our method enables a fully non-interactive training and inference pipeline in the encrypted domain.We validated the proposed scheme using UCI datasets with both numerical and nominal features,demonstrating inference accuracy comparable to plaintext implementations in Scikit-Learn.Moreover,experiments show that HEaaN-ID3 significantly reduces training and inference time per node relative to earlier FHE-based approaches.展开更多
The uncertain nature of mapping user tasks to Virtual Machines(VMs) causes system failure or execution delay in Cloud Computing.To maximize cloud resource throughput and decrease user response time,load balancing is n...The uncertain nature of mapping user tasks to Virtual Machines(VMs) causes system failure or execution delay in Cloud Computing.To maximize cloud resource throughput and decrease user response time,load balancing is needed.Possible load balancing is needed to overcome user task execution delay and system failure.Most swarm intelligent dynamic load balancing solutions that used hybrid metaheuristic algorithms failed to balance exploitation and exploration.Most load balancing methods were insufficient to handle the growing uncertainty in job distribution to VMs.Thus,the Hybrid Spotted Hyena and Whale Optimization Algorithm-based Dynamic Load Balancing Mechanism(HSHWOA) partitions traffic among numerous VMs or servers to guarantee user chores are completed quickly.This load balancing approach improved performance by considering average network latency,dependability,and throughput.This hybridization of SHOA and WOA aims to improve the trade-off between exploration and exploitation,assign jobs to VMs with more solution diversity,and prevent the solution from reaching a local optimality.Pysim-based experimental verification and testing for the proposed HSHWOA showed a 12.38% improvement in minimized makespan,16.21% increase in mean throughput,and 14.84% increase in network stability compared to baseline load balancing strategies like Fractional Improved Whale Social Optimization Based VM Migration Strategy FIWSOA,HDWOA,and Binary Bird Swap.展开更多
Cardiovascular disease prediction is a significant area of research in healthcare management systems(HMS).We will only be able to reduce the number of deaths if we anticipate cardiac problems in advance.The existing h...Cardiovascular disease prediction is a significant area of research in healthcare management systems(HMS).We will only be able to reduce the number of deaths if we anticipate cardiac problems in advance.The existing heart disease detection systems using machine learning have not yet produced sufficient results due to the reliance on available data.We present Clustered Butterfly Optimization Techniques(RoughK-means+BOA)as a new hybrid method for predicting heart disease.This method comprises two phases:clustering data using Roughk-means(RKM)and data analysis using the butterfly optimization algorithm(BOA).The benchmark dataset from the UCI repository is used for our experiments.The experiments are divided into three sets:the first set involves the RKM clustering technique,the next set evaluates the classification outcomes,and the last set validates the performance of the proposed hybrid model.The proposed RoughK-means+BOA has achieved a reasonable accuracy of 97.03 and a minimal error rate of 2.97.This result is comparatively better than other combinations of optimization techniques.In addition,this approach effectively enhances data segmentation,optimization,and classification performance.展开更多
Surveillance systems can take various forms,but gait-based surveillance is emerging as a powerful approach due to its ability to identify individuals without requiring their cooperation.In the existing studies,several...Surveillance systems can take various forms,but gait-based surveillance is emerging as a powerful approach due to its ability to identify individuals without requiring their cooperation.In the existing studies,several approaches have been suggested for gait recognition;nevertheless,the performance of existing systems is often degraded in real-world conditions due to covariate factors such as occlusions,clothing changes,walking speed,and varying camera viewpoints.Furthermore,most existing research focuses on single-person gait recognition;however,counting,tracking,detecting,and recognizing individuals in dual-subject settings with occlusions remains a challenging task.Therefore,this research proposed a variant of an automated gait model for occluded dual-subject walk scenarios.More precisely,in the proposed method,we have designed a deep learning(DL)-based dual-subject gait model(DSG)involving three modules.The first module handles silhouette segmentation,localization,and counting(SLC)using Mask-RCNN with MobileNetV2.The next stage uses a Convolutional block attention module(CBAM)-based Siamese network for frame-level tracking with a modified gallery setting.Following the last,gait recognition based on regionbased deep learning is proposed for dual-subject gait recognition.The proposed method,tested on Shri Mata Vaishno Devi University(SMVDU)-Multi-Gait and Single-Gait datasets,shows strong performance with 94.00%segmentation,58.36%tracking,and 63.04%gait recognition accuracy in dual-subject walk scenarios.展开更多
文摘Electric Vehicle Charging Systems(EVCS)are increasingly vulnerable to cybersecurity threats as they integrate deeply into smart grids and Internet ofThings(IoT)environments,raising significant security challenges.Most existing research primarily emphasizes network-level anomaly detection,leaving critical vulnerabilities at the host level underexplored.This study introduces a novel forensic analysis framework leveraging host-level data,including system logs,kernel events,and Hardware Performance Counters(HPC),to detect and analyze sophisticated cyberattacks such as cryptojacking,Denial-of-Service(DoS),and reconnaissance activities targeting EVCS.Using comprehensive forensic analysis and machine learning models,the proposed framework significantly outperforms existing methods,achieving an accuracy of 98.81%.The findings offer insights into distinct behavioral signatures associated with specific cyber threats,enabling improved cybersecurity strategies and actionable recommendations for robust EVCS infrastructure protection.
文摘This article delves into the analysis of performance and utilization of Support Vector Machines (SVMs) for the critical task of forest fire detection using image datasets. With the increasing threat of forest fires to ecosystems and human settlements, the need for rapid and accurate detection systems is of utmost importance. SVMs, renowned for their strong classification capabilities, exhibit proficiency in recognizing patterns associated with fire within images. By training on labeled data, SVMs acquire the ability to identify distinctive attributes associated with fire, such as flames, smoke, or alterations in the visual characteristics of the forest area. The document thoroughly examines the use of SVMs, covering crucial elements like data preprocessing, feature extraction, and model training. It rigorously evaluates parameters such as accuracy, efficiency, and practical applicability. The knowledge gained from this study aids in the development of efficient forest fire detection systems, enabling prompt responses and improving disaster management. Moreover, the correlation between SVM accuracy and the difficulties presented by high-dimensional datasets is carefully investigated, demonstrated through a revealing case study. The relationship between accuracy scores and the different resolutions used for resizing the training datasets has also been discussed in this article. These comprehensive studies result in a definitive overview of the difficulties faced and the potential sectors requiring further improvement and focus.
基金Supported by the Japan Society for the Promotion of Science Grant-in-Aid for Scientific Research,No.23K11902.
文摘BACKGROUND The early acquisition of skills required to perform hemostasis during endoscopy may be hindered by the lack of tools that allow assessments of the operator’s viewpoint.Understanding the operator’s viewpoint may facilitate the skills.AIM To evaluate the effects of a training system using operator gaze patterns during gastric endoscopic submucosal dissection(ESD)on hemostasis.METHODS An eye-tracking system was developed to record the operator’s viewpoints during gastric ESD,displaying the viewpoint as a circle.In phase 1,videos of three trainees’viewpoints were recorded.After reviewing these,trainees were recorded again in phase 2.The videos from both phases were retrospectively reviewed,and short clips were created to evaluate the hemostasis skills.Outcome measures included the time to recognize the bleeding point,the time to complete hemostasis,and the number of coagulation attempts.RESULTS Eight cases treated with ESD were reviewed,and 10 video clips of hemostasis were created.The time required to recognize the bleeding point during phase 2 was significantly shorter than that during phase 1(8.3±4.1 seconds vs 23.1±19.2 seconds;P=0.049).The time required to complete hemostasis during phase 1 and that during phase 2 were not significantly different(15.4±6.8 seconds vs 31.9±21.7 seconds;P=0.056).Significantly fewer coagulation attempts were performed during phase 2(1.8±0.7 vs 3.2±1.0;P=0.004).CONCLUSION Short-term training did not reduce hemostasis completion time but significantly improved bleeding point recognition and reduced coagulation attempts.Learning from the operator’s viewpoint can facilitate acquiring hemostasis skills during ESD.
基金supported by the IITP(Institute of Information&Communications Technology Planning&Evaluation)-ITRC(Information Technology Research Center)grant funded by the Korean government(Ministry of Science and ICT)(IITP-2025-RS-2024-00438056).
文摘The increased accessibility of social networking services(SNSs)has facilitated communication and information sharing among users.However,it has also heightened concerns about digital safety,particularly for children and adolescents who are increasingly exposed to online grooming crimes.Early and accurate identification of grooming conversations is crucial in preventing long-term harm to victims.However,research on grooming detection in South Korea remains limited,as existing models trained primarily on English text and fail to reflect the unique linguistic features of SNS conversations,leading to inaccurate classifications.To address these issues,this study proposes a novel framework that integrates optical character recognition(OCR)technology with KcELECTRA,a deep learning-based natural language processing(NLP)model that shows excellent performance in processing the colloquial Korean language.In the proposed framework,the KcELECTRA model is fine-tuned by an extensive dataset,including Korean social media conversations,Korean ethical verification data from AI-Hub,and Korean hate speech data from Hug-gingFace,to enable more accurate classification of text extracted from social media conversation images.Experimental results show that the proposed framework achieves an accuracy of 0.953,outperforming existing transformer-based models.Furthermore,OCR technology shows high accuracy in extracting text from images,demonstrating that the proposed framework is effective for online grooming detection.The proposed framework is expected to contribute to the more accurate detection of grooming text and the prevention of grooming-related crimes.
文摘BACKGROUND Sodium glucose cotransporter-2 inhibitors(SGLT-2i)are a class of drugs with modest antidiabetic efficacy,weight loss effect,and cardiovascular benefits as proven by multiple randomised controlled trials(RCTs).However,real-world data on the comparative efficacy and safety of individual SGLT-2i medications is sparse.AIM To study the comparative efficacy and safety of SGLT-2i using real-world clinical data.METHODS We evaluated the comparative efficacy data of 3 SGLT-2i drugs(dapagliflozin,canagliflozin,and empagliflozin)used for treating patients with type 2 diabetes mellitus.Data on the reduction of glycated hemoglobin(HbA1c),body weight,blood pressure(BP),urine albumin creatinine ratio(ACR),and adverse effects were recorded retrospectively.RESULTS Data from 467 patients with a median age of 64(14.8)years,294(62.96%)males and 375(80.5%)Caucasians were analysed.Median diabetes duration was 16.0(9.0)years,and the duration of SGLT-2i use was 3.6(2.1)years.SGLT-2i molecules used were dapagliflozin 10 mg(n=227;48.6%),canagliflozin 300 mg(n=160;34.3%),and empagliflozin 25 mg(n=80;17.1).Baseline median(interquartile range)HbA1c in mmol/mol were:dapagliflozin-78.0(25.3),canagliflozin-80.0(25.5),and empagliflozin-75.0(23.5)respectively.The respective median HbA1c reduction at 12 months and the latest review(just prior to the study)were:66.5(22.8)&69.0(24.0),67.0(16.3)&66.0(28.0),and 67.0(22.5)&66.5(25.8)respectively(P<0.001 for all comparisons from baseline).Significant improvements in body weight(in kilograms)from baseline to study end were noticed with dapagliflozin-101(29.5)to 92.2(25.6),and canagliflozin 100(28.3)to 95.3(27.5)only.Significant reductions in median systolic and diastolic BP,from 144(21)mmHg to 139(23)mmHg;(P=0.015),and from 82(16)mmHg to 78(19)mmHg;(P<0.001)respectively were also observed.A significant reduction of microalbuminuria was observed with canagliflozin only[ACR 14.6(42.6)at baseline to 8.9(23.7)at the study end;P=0.043].Adverse effects of SGLT-2i were as follows:genital thrush and urinary infection-20(8.8%)&17(7.5%)with dapagliflozin;9(5.6%)&5(3.13%)with canagliflozin;and 4(5%)&4(5%)with empagliflozin.Diabetic ketoacidosis was observed in 4(1.8%)with dapagliflozin and 1(0.63%)with canagliflozin.CONCLUSION Treatment of patients with SGLT-2i is associated with statistically significant reductions in HbA1c,body weight,and better than those reported in RCTs,with low side effect profiles.A review of large-scale real-world data is needed to inform better clinical practice decision making.
文摘Background:Sleep disturbance is commonly seen in fibromyalgia syndrome (FMS);however,high quality studies involving manual therapies that target FMS-linked poor sleep quality are lacking for the Indian population.Objective:Craniosacral therapy (CST),Bowen therapy and exercises have been found to influence the autonomic nervous system,which plays a crucial role in sleep physiology.Given the paucity of evidence concerning these effects in individuals with FMS,our study tests the effectiveness of CST,Bowen therapy and a standard exercise program against static touch (the manual placebo group) on sleep quality in FMS.Design,setting,participants and intervention:A placebo-controlled randomized trial was conducted on132 FMS participants with poor sleep at a hospital in Bangalore.The participants were randomly allocated to one of the four study groups,including CST,Bowen therapy,standard exercise program,and a manual placebo control group that received static touch.CST,Bowen therapy and static touch treatments were administered in once-weekly 45-minute sessions for 12 weeks;the standard exercise group received weekly supervised exercises for 6 weeks with home exercises until 12 weeks.After 12 weeks,all study participants performed the standard exercises at home for another 12 weeks.Main outcome measures:Sleep quality,pressure pain threshold (PPT),quality of life and fibromyalgia impact,physical function,fatigue,pain catastrophizing,kinesiophobia,and positive–negative affect were recorded at baseline,and at weeks 12 and 24 of the intervention.Results:At the end of 12 weeks,the sleep quality improved significantly in the CST group (P=0.037) and Bowen therapy group (P=0.023),and the PPT improved significantly in the Bowen therapy group(P=0.002) and the standard exercise group (P<0.001),compared to the static touch group.These improvements were maintained at 24 weeks.No between-group differences were observed for other secondary outcomes.Conclusion:CST and Bowen therapy improved sleep quality,and Bowen therapy and standard exercises improved pain threshold in the short term.These improvements were retained within the groups in the long term by adding exercises.CST and Bowen therapy are treatment options to improve sleep and reduce pain in FMS.
文摘Amid the landscape of Cloud Computing(CC),the Cloud Datacenter(DC)stands as a conglomerate of physical servers,whose performance can be hindered by bottlenecks within the realm of proliferating CC services.A linchpin in CC’s performance,the Cloud Service Broker(CSB),orchestrates DC selection.Failure to adroitly route user requests with suitable DCs transforms the CSB into a bottleneck,endangering service quality.To tackle this,deploying an efficient CSB policy becomes imperative,optimizing DC selection to meet stringent Qualityof-Service(QoS)demands.Amidst numerous CSB policies,their implementation grapples with challenges like costs and availability.This article undertakes a holistic review of diverse CSB policies,concurrently surveying the predicaments confronted by current policies.The foremost objective is to pinpoint research gaps and remedies to invigorate future policy development.Additionally,it extensively clarifies various DC selection methodologies employed in CC,enriching practitioners and researchers alike.Employing synthetic analysis,the article systematically assesses and compares myriad DC selection techniques.These analytical insights equip decision-makers with a pragmatic framework to discern the apt technique for their needs.In summation,this discourse resoundingly underscores the paramount importance of adept CSB policies in DC selection,highlighting the imperative role of efficient CSB policies in optimizing CC performance.By emphasizing the significance of these policies and their modeling implications,the article contributes to both the general modeling discourse and its practical applications in the CC domain.
基金supported by the Bio&Medical Technology Development Program of the National Research Foundation(NRF)funded by the Korean government(MSIT)(NRF-2021M3A9E4080780)Hankuk University of Foreign Studies(2023).
文摘Regular physical activity(PA)is known to enhance multifaceted health benefits,including both physical and mental health.However,traditional in-person physical activity programs have drawbacks,including time constraints for busy people.Although evidence suggests positive impacts on mental health through mobile-based physical activity,effects of accumulated short bouts of physical activity using mobile devices are unexplored.Thus,this study aims to investigate these effects,focusing on depression,perceived stress,and negative affectivity among South Korean college students.Forty-six healthy college students were divided into the accumulated group(n=23,female=47.8%)and control group(n=23,female=47.6%).The accumulated group engaged in mobile-based physical activity,following guidelines to accumulate a minimum of two times per day and three times a week.Sessions were divided into short bouts,ensuing each bout lasted at least 10 min.The control group did not engage in any specific physical activity.The data analysis involved comparing the scores of the intervention and control groups using several statistical techniques,such as independent sample t-test,paired sample t-tests,and 2(time)×2(group)repeated measures analysis of variance.The demographic characteristics at the pre-test showed no statistically significant differences between the groups.The accumulated group had significant decreases in depression(t_(40)=2.59,p=0.013,Cohen’s D=0.84)and perceived stress(t_(40)=2.06,p=0.046,Cohen’s D=0.56)from the pre-to post-test.The control group exhibited no statistically significant differences in any variables.Furthermore,there were significant effects of time on depression scores(F1,36=4.77,p=0.036,η_(p)^(2)=0.12)while significant interaction effects were also observed for depression(F_(1,36)=6.59,p=0.015,η_(p)^(2)=0.16).This study offers informative insights into the potential advantages of mobile-based physical activity programs with accumulated periods for enhancing mental health,specifically in relation to depression.This study illuminates the current ongoing discussions on efficient approaches to encourage mobile-based physical activity and improve mental well-being,addressing various lifestyles and busy schedules.
基金jointly supported by the National Key Research and Development Program of China(No.2022ZD0115600)National Natural Science Foundation of China(No.52072067)+3 种基金Natural Science Foundation of Jiangsu Province(No.BK20210249)China Postdoctoral Science Foundation(No.2020M681466)Jiangsu Planned Projects for Postdoctoral Research Funds(No.SBK2021041144)Jiangsu Planned Projects for Postdoctoral Research Funds(No.2021K094A)。
文摘Connected automated vehicles(CAVs)rely heavily on intelligent algorithms and remote sensors.If the control center or on-board sensors are under cyber-attack due to the security vulnerability of wireless communication,it can cause significant damage to CAVs or passengers.The primary objective of this study is to model cyberattacked traffic flow and evaluate the impacts of cyber-attack on the traffic system filled with CAVs in a connected environment.Based on the analysis on environmental perception system and possible cyber-attacks on sensors,a novel lane-changing model for CAVs is proposed and multiple traffic scenarios for cyber-attacks are designed.The impact of the proportion of cyber-attacked vehicles and the severity of the cyber-attack on the lanechanging process is then quantitatively analyzed.The evaluation indexes include spatio-temporal evolution of average speed,spatial distribution of selected lane-changing gaps,lane-changing rate distribution,lane-changing preparation search time,efficiency and safety.Finally,the numerical simulation results show that the freeway traffic near an off-ramp is more sensitive to the proportion of cyber-attacked vehicles than to the severity of the cyber-attack.Also,when the traffic system is under cyber-attack,more unsafe back gaps are chosen for lane-changing,especially in the center lane.Therefore,more lane-changing maneuvers are concentrated on approaching the off-ramp,causing severe congestions and potential rear-end collisions.In addition,as the number of cyber-attacked vehicles and the severity of cyber-attacks increase,the road capacity and safety level will rapidly decrease.The results of this study can provide a theoretical basis for accident avoidance and efficiency improvement for the design of CAVs and management of automated highway systems.
文摘BACKGROUND Diabesity(diabetes as a consequence of obesity)has emerged as a huge healthcare challenge across the globe due to the obesity pandemic.Judicious use of antidiabetic medications including semaglutide is important for optimal management of diabesity as proven by multiple randomized controlled trials.However,more real-world data is needed to further improve the clinical practice.AIM To study the real-world benefits and side effects of using semaglutide to manage patients with diabesity.METHODS We evaluated the efficacy and safety of semaglutide use in managing patients with diabesity in a large academic hospital in the United States.Several parameters were analyzed including demographic information,the data on improvement of glycated hemoglobin(HbA1c),body weight reduction and insulin dose adjustments at 6 and 12 months,as well as at the latest follow up period.The data was obtained from the electronic patient records between January 2019 to May 2023.RESULTS 106 patients(56 males)with type 2 diabetes mellitus(T2DM),mean age 60.8±11.2 years,mean durations of T2DM 12.4±7.2 years and mean semaglutide treatment for 2.6±1.1 years were included.Semaglutide treatment was associated with significant improvement in diabesity outcomes such as mean weight reductions from baseline 110.4±24.6 kg to 99.9±24.9 kg at 12 months and 96.8±22.9 kg at latest follow up and HbA1c improvement from baseline of 82±21 mmol/mol to 67±20 at 12 months and 71±23 mmol/mol at the latest follow up.An insulin dose reduction from mean baseline of 95±74 units to 76.5±56.2 units was also observed at the latest follow up.Side effects were mild and mainly gastrointestinal like bloating and nausea improving with prolonged use of semaglutide.CONCLUSION Semaglutide treatment is associated with significant improvement in diabesity outcomes such as reduction in body weight,HbA1c and insulin doses without major adverse effects.Reviews of largescale real-world data are expected to inform better clinical practice decision making to improve the care of patients with diabesity.
文摘BACKGROUND Inflammatory bowel disease(IBD),with its rising prevalence rates is associated with an increased risk of cardiovascular and thromboembolic events.Antiplatelets and/or anticoagulants agents are often prescribed but the literature on the impact of long-term anticoagulation and/or antiplatelet use among patients hospitalized with IBD is scarce.The aim of this study is to assess the outcomes of patients hospitalized with IBD on antiplatelet and/or anticoagulant agents.AIM To investigate the effects of long-term use of antiplatelets/anticoagulants on clinical outcomes in patients hospitalized with IBD.METHODS We conducted a retrospective cohort study using the Nationwide Inpatient Sample database,including all adult IBD patients hospitalized in the United States from 2016 to 2019.Patient cohorts were stratified based on antiplatelet/anticoagulant therapy status.Multivariate regression analysis was done to assess outcomes,adjusting for potential confounders.The primary outcome was mortality,whereas length of stay(LOS),total parenteral nutrition,acute kidney injury,sepsis,shock,gastrointestinal bleeding,need for colonoscopy/sigmoidoscopy,abdominal surgery and total hospitalization charges were secondary outcomes.RESULTS Among 374744 hospitalized IBD patients,antiplatelet or anticoagulant therapy alone was associated with significantly lower in-hospital mortality and reduced healthcare utilization,including shorter LOS and decreased hospitalization costs.Combined therapy was associated with a protective effect on mortality,but did not reach statistical significance.Notably,therapy did not exacerbate disease severity or complications,although higher odds of gastrointestinal bleeding were observed.CONCLUSION Our study highlights the potential benefits of long-term anticoagulation/antiplatelet therapy in hospitalized IBD patients,with improved mortality outcomes and healthcare utilization.While concerns regarding gastrointestinal bleeding exist,the overall safety profile suggests a role for these agents in mitigating thromboembolic risks without exacerbating disease severity.Further research is needed to look at optimal treatment strategies and addressing limitations to guide clinical decision-making in this population.
文摘This paper presents a detailed statistical exploration of crime trends in Chicago from 2001 to 2023, employing data from the Chicago Police Department’s publicly available crime database. The study aims to elucidate the patterns, distribution, and variations in crime across different types and locations, providing a comprehensive picture of the city’s crime landscape through advanced data analytics and visualization techniques. Using exploratory data analysis (EDA), we identified significant insights into crime trends, including the prevalence of theft and battery, the impact of seasonal changes on crime rates, and spatial concentrations of criminal activities. The research leveraged a Power BI dashboard to visually represent crime data, facilitating an intuitive understanding of complex patterns and enabling dynamic interaction with the dataset. Key findings highlight notable disparities in crime occurrences by type, location, and time, offering a granular view of crime hotspots and temporal trends. Additionally, the study examines clearance rates, revealing variations in the resolution of cases across different crime categories. This analysis not only sheds light on the current state of urban safety but also serves as a critical tool for policymakers and law enforcement agencies to develop targeted interventions. The paper concludes with recommendations for enhancing public safety strategies and suggests directions for future research, emphasizing the need for continuous data-driven approaches to effectively address and mitigate urban crime. This study contributes to the broader discourse on urban safety, crime prevention, and the role of data analytics in public policy and community well-being.
文摘Customer churn poses a significant challenge for the banking and finance industry in the United States, directly affecting profitability and market share. This study conducts a comprehensive comparative analysis of machine learning models for customer churn prediction, focusing on the U.S. context. The research evaluates the performance of logistic regression, random forest, and neural networks using industry-specific datasets, considering the economic impact and practical implications of the findings. The exploratory data analysis reveals unique patterns and trends in the U.S. banking and finance industry, such as the age distribution of customers and the prevalence of dormant accounts. The study incorporates macroeconomic factors to capture the potential influence of external conditions on customer churn behavior. The findings highlight the importance of leveraging advanced machine learning techniques and comprehensive customer data to develop effective churn prevention strategies in the U.S. context. By accurately predicting customer churn, financial institutions can proactively identify at-risk customers, implement targeted retention strategies, and optimize resource allocation. The study discusses the limitations and potential future improvements, serving as a roadmap for researchers and practitioners to further advance the field of customer churn prediction in the evolving landscape of the U.S. banking and finance industry.
基金described in this paper has been developed with in the project PRESECREL(PID2021-124502OB-C43)。
文摘The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control systems.With the exponential increase in data generated by these interconnected devices,robust anomaly detection mechanisms are essential.Anomaly detection in this dynamic environment necessitates methods that can accurately distinguish between normal and anomalous behavior by learning intricate patterns.This paper presents a novel approach utilizing generative adversarial networks(GANs)for anomaly detection in IoT systems.However,optimizing GANs involves tuning hyper-parameters such as learning rate,batch size,and optimization algorithms,which can be challenging due to the non-convex nature of GAN loss functions.To address this,we propose a five-dimensional Gray wolf optimizer(5DGWO)to optimize GAN hyper-parameters.The 5DGWO introduces two new types of wolves:gamma(γ)for improved exploitation and convergence,and theta(θ)for enhanced exploration and escaping local minima.The proposed system framework comprises four key stages:1)preprocessing,2)generative model training,3)autoencoder(AE)training,and 4)predictive model training.The generative models are utilized to assist the AE training,and the final predictive models(including convolutional neural network(CNN),deep belief network(DBN),recurrent neural network(RNN),random forest(RF),and extreme gradient boosting(XGBoost))are trained using the generated data and AE-encoded features.We evaluated the system on three benchmark datasets:NSL-KDD,UNSW-NB15,and IoT-23.Experiments conducted on diverse IoT datasets show that our method outperforms existing anomaly detection strategies and significantly reduces false positives.The 5DGWO-GAN-CNNAE exhibits superior performance in various metrics,including accuracy,recall,precision,root mean square error(RMSE),and convergence trend.The proposed 5DGWO-GAN-CNNAE achieved the lowest RMSE values across the NSL-KDD,UNSW-NB15,and IoT-23 datasets,with values of 0.24,1.10,and 0.09,respectively.Additionally,it attained the highest accuracy,ranging from 94%to 100%.These results suggest a promising direction for future IoT security frameworks,offering a scalable and efficient solution to safeguard against evolving cyber threats.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korean government(MSIT)(No.RS-2023-00218176)the Soonchunhyang University Research Fund.
文摘Improving early diagnosis of autism spectrum disorder(ASD)in children increasingly relies on predictive models that are reliable and accessible to non-experts.This study aims to develop such models using Python-based tools to improve ASD diagnosis in clinical settings.We performed exploratory data analysis to ensure data quality and identify key patterns in pediatric ASD data.We selected the categorical boosting(CatBoost)algorithm to effectively handle the large number of categorical variables.We used the PyCaret automated machine learning(AutoML)tool to make the models user-friendly for clinicians without extensive machine learning expertise.In addition,we applied Shapley additive explanations(SHAP),an explainable artificial intelligence(XAI)technique,to improve the interpretability of the models.Models developed using CatBoost and other AI algorithms showed high accuracy in diagnosing ASD in children.SHAP provided clear insights into the influence of each variable on diagnostic outcomes,making model decisions transparent and understandable to healthcare professionals.By integrating robust machine learning methods with user-friendly tools such as PyCaret and leveraging XAI techniques such as SHAP,this study contributes to the development of reliable,interpretable,and accessible diagnostic tools for ASD.These advances hold great promise for supporting informed decision-making in clinical settings,ultimately improving early identification and intervention strategies for ASD in the pediatric population.However,the study is limited by the dataset’s demographic imbalance and the lack of external clinical validation,which should be addressed in future research.
基金supported in part by the Hong Kong RGC General Research Fund Project with No.11213124in part by Hong Kong ITC Innovation and Technology Fund Project with No.ITS/034/22MS+2 种基金in part by in part by Guangdong Provincial Basic and Applied Basic Research-Offshore Wind Power Joint Fund Project under Grant 2022A1515240066in part by Guangdong Province Technological Project with No.2023A0505030014in part by the Shenzhen-Hong Kong-Macao Science&Technology Category C Project with No.SGDX20220530111205037.
文摘This paper studies the renewable power forecasting task with a more advanced formulation,the probabilistic forecasts of day-ahead power generation sequences of multiple renewable power plants without breaching the privacy of data in each plant.To realize such a task,an advanced domain-invariant feature learning embedded federated learning(DIFL)framework is proposed to coordinate the development of a system of deep networkbased models serving as multiple clients and one server.In DIFL,each client,which serves each local renew-able power plant,maps its raw data input into latent features via a local feature extractor and generates power output sequence probabilistic forecasts via a locally hosted forecasting model.The cloud-hosted server first aggregates the knowledge from models of clients and next dispatches the aggregated model back to each client for facilitating each local feature extractor to identify domain-invariant features via interacting with a server-side discriminator.Therefore,only desensitized data,such as parameters of the models,are allowed to be transmitted among end users for preserving local data privacy of power plants.To verify the advantages of the DIFL,a preliminary exploration of its theoretical property is first conducted.Next,computational studies are performed to benchmark the DIFL against famous baselines based on datasets collected from commercial renewable power plants.Results further confirm that,in terms of the averaged performance,the DIFL consistently realizes im-provements against all benchmarks based on both real wind farm and solar power plant datasets.
基金supported by Institute of Information communications Technology Planning Evaluation(IITP)grant funded by theKorea government(MSIT)[No.2022-0-01047,Development of statistical analysis algorithm and module using homomorphic encryption based on real number operation,100%].
文摘In this study,we investigated privacy-preserving ID3 Decision Tree(PPID3)training and inference based on fully homomorphic encryption(FHE),which has not been actively explored due to the high computational cost associated with managing numerous child nodes in an ID3 tree.We propose HEaaN-ID3,a novel approach to realize PPID3 using the Cheon-Kim-Kim-Song(CKKS)scheme.HEaaN-ID3 is the first FHE-based ID3 framework that completes both training and inference without any intermediate decryption,which is especially valuable when decryption keys are inaccessible or a single-cloud security domain is assumed.To enhance computational efficiency,we adopt a modified Gini impurity(MGI)score instead of entropy to evaluate information gain,thereby avoiding costly inverse operations.In addition,we fully leverage the Single Instruction Multiple Data(SIMD)property of CKKS to parallelize computations at multiple tree nodes.Unlike previous approaches that require decryption at each node or rely on two-party secure computation,our method enables a fully non-interactive training and inference pipeline in the encrypted domain.We validated the proposed scheme using UCI datasets with both numerical and nominal features,demonstrating inference accuracy comparable to plaintext implementations in Scikit-Learn.Moreover,experiments show that HEaaN-ID3 significantly reduces training and inference time per node relative to earlier FHE-based approaches.
文摘The uncertain nature of mapping user tasks to Virtual Machines(VMs) causes system failure or execution delay in Cloud Computing.To maximize cloud resource throughput and decrease user response time,load balancing is needed.Possible load balancing is needed to overcome user task execution delay and system failure.Most swarm intelligent dynamic load balancing solutions that used hybrid metaheuristic algorithms failed to balance exploitation and exploration.Most load balancing methods were insufficient to handle the growing uncertainty in job distribution to VMs.Thus,the Hybrid Spotted Hyena and Whale Optimization Algorithm-based Dynamic Load Balancing Mechanism(HSHWOA) partitions traffic among numerous VMs or servers to guarantee user chores are completed quickly.This load balancing approach improved performance by considering average network latency,dependability,and throughput.This hybridization of SHOA and WOA aims to improve the trade-off between exploration and exploitation,assign jobs to VMs with more solution diversity,and prevent the solution from reaching a local optimality.Pysim-based experimental verification and testing for the proposed HSHWOA showed a 12.38% improvement in minimized makespan,16.21% increase in mean throughput,and 14.84% increase in network stability compared to baseline load balancing strategies like Fractional Improved Whale Social Optimization Based VM Migration Strategy FIWSOA,HDWOA,and Binary Bird Swap.
基金supported by the Research Incentive Grant 23200 of Zayed University,United Arab Emirates.
文摘Cardiovascular disease prediction is a significant area of research in healthcare management systems(HMS).We will only be able to reduce the number of deaths if we anticipate cardiac problems in advance.The existing heart disease detection systems using machine learning have not yet produced sufficient results due to the reliance on available data.We present Clustered Butterfly Optimization Techniques(RoughK-means+BOA)as a new hybrid method for predicting heart disease.This method comprises two phases:clustering data using Roughk-means(RKM)and data analysis using the butterfly optimization algorithm(BOA).The benchmark dataset from the UCI repository is used for our experiments.The experiments are divided into three sets:the first set involves the RKM clustering technique,the next set evaluates the classification outcomes,and the last set validates the performance of the proposed hybrid model.The proposed RoughK-means+BOA has achieved a reasonable accuracy of 97.03 and a minimal error rate of 2.97.This result is comparatively better than other combinations of optimization techniques.In addition,this approach effectively enhances data segmentation,optimization,and classification performance.
基金supported by the MSIT(Ministry of Science and ICT),Republic of Korea,under the Convergence Security Core Talent Training Business Support Program(IITP-2025-RS-2023-00266605)supervised by the IITP(Institute for Information&Communications Technology Planning&Evaluation).
文摘Surveillance systems can take various forms,but gait-based surveillance is emerging as a powerful approach due to its ability to identify individuals without requiring their cooperation.In the existing studies,several approaches have been suggested for gait recognition;nevertheless,the performance of existing systems is often degraded in real-world conditions due to covariate factors such as occlusions,clothing changes,walking speed,and varying camera viewpoints.Furthermore,most existing research focuses on single-person gait recognition;however,counting,tracking,detecting,and recognizing individuals in dual-subject settings with occlusions remains a challenging task.Therefore,this research proposed a variant of an automated gait model for occluded dual-subject walk scenarios.More precisely,in the proposed method,we have designed a deep learning(DL)-based dual-subject gait model(DSG)involving three modules.The first module handles silhouette segmentation,localization,and counting(SLC)using Mask-RCNN with MobileNetV2.The next stage uses a Convolutional block attention module(CBAM)-based Siamese network for frame-level tracking with a modified gallery setting.Following the last,gait recognition based on regionbased deep learning is proposed for dual-subject gait recognition.The proposed method,tested on Shri Mata Vaishno Devi University(SMVDU)-Multi-Gait and Single-Gait datasets,shows strong performance with 94.00%segmentation,58.36%tracking,and 63.04%gait recognition accuracy in dual-subject walk scenarios.
