基于Multi-Agent的无人机集群体系自主作战系统设计

针对无人集群自主作战体系设计中的关键问题,提出基于Multi-Agent的无人集群自主作战系统设计方法。建立无人集群各节点的Agent模型及其推演规则;对于仿真系统模块化和通用化的需求,设计系统互操作式接口和无人集群自主作战的交互关系;开展无人集群系统仿真推演验证。仿真结果表明,所提设计方案不仅能够有效开展并完成自主作战网络生成-集群演化-效能评估的全过程动态演示验证,而且能够通过重复随机试验进一步评估无人集群的协同作战效能,最后总结了集群协同作战的策略和经验。

基于Multi-Agent的水电站变压器故障诊断系统

为了精准、快速完成水电站变压器的故障诊断,设计基于Multi-Agent的水电站变压器故障诊断系统。变压器状态监控agent将检测到的变压器故障信息发送给系统管理agent,系统管理agent通过通信agent将变压器故障信息发送给变压器故障诊断agent,变压器故障诊断agent利用小波变换方法提取变压器故障特征,并将其作为IFOA-SVM模型输入,完成变压器故障分类后,获取变压器故障诊断结果,该结果通过通信agent显示给用户。实验表明,该系统可有效诊断变压器故障诊断,诊断成功率受系统故障信息丢失率的影响较小,诊断耗时、耗能小,并具有较高故障诊断成功率。

Establishment and validation of an adherence prediction system for lifestyle interventions in non-alcoholic fatty liver disease

BACKGROUND Non-alcoholic fatty liver disease(NAFLD)is the most common liver disease worldwide,affecting about 1/4th of the global population and causing a huge global economic burden.To date,no drugs have been approved for the treatment of NAFLD,making the correction of unhealthy lifestyles the principle method of treatment.Identifying patients with poor adherence to lifestyle correction and attempting to improve their adherence are therefore very important.AIM To develop and validate a scale that can rapidly assess the adherence of patients with NAFLD to lifestyle interventions.METHODS The Exercise and Diet Adherence Scale(EDAS)was designed based on com-pilation using the Delphi method,and its reliability was subsequently evaluated.Demographic and laboratory indicators were measured,and patients completed the EDAS questionnaire at baseline and after 6 months.The efficacy of the EDAS was evaluated in the initial cohort.Subsequently,the efficacy of the EDAS was internally verified in a validation cohort.RESULTS The EDAS consisted of 33 items in six dimensions,with a total of 165 points.Total EDAS score correlated significantly with daily number of exercise and daily reduction in calorie intake(P<0.05 each),but not with overall weight loss.A total score of 116 was excellent in predicting adherence to daily reduction in calorie intake(>500 kacl/d),(sensitivity/specificity was 100.0%/75.8%),while patients score below 97 could nearly rule out the possibility of daily exercise(sensitivity/specificity was 89.5%/44.4%).Total EDAS scores≥116,97-115,and<97 points were indicative of good,average,and poor adherence,respectively,to diet and exercise recommendations.CONCLUSION The EDAS can reliably assess the adherence of patients with NAFLD to lifestyle interventions and have clinical application in this population.

UAV-Assisted Dynamic Avatar Task Migration for Vehicular Metaverse Services: A Multi-Agent Deep Reinforcement Learning Approach

Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach outperforms the MAPPO approach by around 2% and effectively reduces approximately 20% of the latency of avatar task execution in UAV-assisted vehicular Metaverses.

Finite-time Prescribed Performance Time-Varying Formation Control for Second-Order Multi-Agent Systems With Non-Strict Feedback Based on a Neural Network Observer

This paper studies the problem of time-varying formation control with finite-time prescribed performance for nonstrict feedback second-order multi-agent systems with unmeasured states and unknown nonlinearities.To eliminate nonlinearities,neural networks are applied to approximate the inherent dynamics of the system.In addition,due to the limitations of the actual working conditions,each follower agent can only obtain the locally measurable partial state information of the leader agent.To address this problem,a neural network state observer based on the leader state information is designed.Then,a finite-time prescribed performance adaptive output feedback control strategy is proposed by restricting the sliding mode surface to a prescribed region,which ensures that the closed-loop system has practical finite-time stability and that formation errors of the multi-agent systems converge to the prescribed performance bound in finite time.Finally,a numerical simulation is provided to demonstrate the practicality and effectiveness of the developed algorithm.

Impact of frailty on outcomes of elderly patients undergoing percutaneous coronary intervention: A systematic review and metaanalysis

BACKGROUND Frailty is a common condition in elderly patients who receive percutaneous coronary intervention(PCI).However,how frailty affects clinical outcomes in this group is unclear.AIM To assess the link between frailty and the outcomes,such as in-hospital complic-ations,post-procedural complications,and mortality,in elderly patients post-PCI.METHODS The PubMed/MEDLINE,EMBASE,Cochrane Library,and Web of Science databases were screened for publications up to August 2023.The primary outcomes assessed were in-hospital and all-cause mortality,major adverse cardiovascular events(MACEs),and major bleeding.The Newcastle-Ottawa Scale was used for quality assessment.RESULTS Twenty-one studies with 739693 elderly patients undergoing PCI were included.Frailty was consistently associated with adverse outcomes.Frail patients had significantly higher risks of in-hospital mortality[risk ratio:3.45,95%confidence interval(95%CI):1.90-6.25],all-cause mortality[hazard ratio(HR):2.08,95%CI:1.78-2.43],MACEs(HR:2.92,95%CI:1.85-4.60),and major bleeding(HR:4.60,95%CI:2.89-7.32)compared to non-frail patients.CONCLUSION Frailty is a pivotal determinant in the prediction of risk of mortality,development of MACEs,and major bleeding in elderly individuals undergoing percutaneous coronary intervention.

Current interventional options for palliative care for patients with advanced-stage cholangiocarcinoma

Primary biliary tract tumors are malignancies that originate in the liver,bile ducts,or gallbladder.These tumors often present with jaundice of unknown etiology,leading to delayed diagnosis and advanced disease.Currently,several palliative treatment options are available for primary biliary tract tumors.They include percutaneous transhepatic biliary drainage(PTBD),biliary stenting,and surgical interventions such as biliary diversion.Systemic therapy is also commonly used for the palliative treatment of primary biliary tract tumors.It involves the administration of chemotherapy drugs,such as gemcitabine and cisplatin,which have shown promising results in improving overall survival in patients with advanced biliary tract tumors.PTBD is another palliative treatment option for patients with unresectable or inoperable malignant biliary obstruction.Biliary stenting can also be used as a palliative treatment option to alleviate symptoms in patients with unresectable or inoperable malignant biliary obstruction.Surgical interventions,such as biliary diversion,have traditionally been used as palliative options for primary biliary tract tumors.However,biliary diversion only provides temporary relief and does not remove the tumor.Primary biliary tract tumors often present in advanced stages,making palliative treatment the primary option for improving the quality of life of patients.

Psychological interventions for depression in children and adolescents:A bibliometric analysis

BACKGROUND Depression has gradually become a common psychological disorder among children and adolescents.Depression in children and adolescents affects their physical and mental development.Psychotherapy is considered to be one of the main treatment options for depressed children and adolescents.However,our understanding of the global performance and progress of psychological interventions for depression in children and adolescents(PIDCA)research is limited.AIM To identify collaborative research networks in this field and explore the current research status and hotspots through bibliometrics.METHODS Articles and reviews related to PIDCA from January 2010 to April 2023 were identified from the Web of Science Core Collection database.The Charticulator website,CiteSpace and VOSviewer software were used to visualize the trends in publications and citations,the collaborative research networks(countries,institutions,and authors),and the current research status and hotspots.RESULTS Until April 16,2023,1482 publications were identified.The number of documents published each year and citations had increased rapidly in this field.The United States had the highest productivity in this field.The most prolific institution was the University of London.Pim Cuijpers was the most prolific author.In the context of research related to PIDCA,both reference co-citation analysis and keywords co-occurrence analysis identified 10 research hotspots,including thirdwave cognitive behavior therapy,short-term psychoanalytic psychotherapy,cognitive behavioral analysis system of psychotherapy,family element in psychotherapy,modular treatment,mobile-health,emotion-regulation-based transdiagnostic intervention program,dementia risk in later life,predictors of the efficacy of psychological intervention,and risks of psychological intervention.CONCLUSION This bibliometric study provides a comprehensive overview of PIDCA from 2010 to present.Psychological intervention characterized as psychological-process-focused,short,family-involved,modular,internet-based,emotionregulation-based,and personalized may benefit more young people.

Robust adaptive leaderless consensus of unknown non-minimum phase linear multi-agent systems subject to disturbances and/or unmodeled dynamics

This article investigates the problem of robust adaptive leaderless consensus for heterogeneous uncertain nonminimumphase linear multi-agent systems over directed communication graphs. Each agent is assumed tobe of unknown nominal dynamics and also subject to external disturbances and/or unmodeled dynamics. Anovel distributed robust adaptive control strategy is proposed. It is shown that the robust adaptive leaderlessconsensus problem is solved with the proposed control strategy under some sufficient conditions. Two examplesare provided to demonstrate the efficacy of the proposed control strategy.

Effect of sequential nursing care combined with communication intervention on visual recovery and pain after cataract ultrasound emulsification

BACKGROUND Cataracts are a common ophthalmic disease and postoperative vision recovery is crucial to patient quality of life.Rational and efficient care models play an impor-tant role in promoting vision recovery.AIM To evaluate the clinical effectiveness of procedural nursing care combined with communication intervention in vision recovery after cataract ultrasound emulsi-fication.METHODS A randomized controlled study was conducted on 100 patients with cataracts who underwent ultrasound emulsification surgery.They were randomly assigned to an experimental group or a control group.The experimental group received procedural nursing combined with Connect,Introduce,Communicate,Ask,Respond,Exit(CICARE)communication intervention,whereas the control group received conventional nursing.The effectiveness of the nursing model was assessed by comparing differences in vision recovery,pain scores,and mental health status between the two groups.RESULTS It was found that over time the visual acuity of patients in both groups gradually recovered and patients in the experimental group had lower pain scores and superior mental health status than the control group(P<0.05).CONCLUSION Procedural nursing combined with CICARE communication intervention has positive effects on vision recovery in patients after cataract ultrasound emulsification.

Unloading and successful treatment with bioresorbable stents during percutaneous coronary intervention:A case report

BACKGROUND With the development of percutaneous coronary intervention(PCI),the number of interventional procedures without implantation,such as bioresorbable stents(BRS)and drug-coated balloons,has increased annually.Metal drug-eluting stent unloading is one of the most common clinical complications.Comparatively,BRS detachment is more concealed and harmful,but has yet to be reported in clinical research.In this study,we report a case of BRS unloading and successful rescue.This is a case of a 59-year-old male with the following medical history:“Type 2 diabetes mellitus”for 2 years,maintained with metformin extended-release tablets,1 g PO BID;“hypertension”for 20 years,with long-term use of metoprolol sustained-release tablets,47.5 mg PO QD;“hyperlipidemia”for 20 years,without regular medication.He was admitted to the emergency department of our hospital due to intermittent chest pain lasting 18 hours,on February 20,2022 at 15:35.Electrocardiogram results showed sinus rhythm,ST-segment elevation in leads I and avL,and poor R-wave progression in leads V1–3.High-sensitivity troponin I level was 4.59 ng/mL,indicating an acute high lateral wall myocardial infarction.The patient’s family requested treatment with BRS,without implanta-tion.During PCI,the BRS became unloaded but was successfully rescued.The patient was followed up for 2 years;he had no episodes of angina pectoris and was in generally good condition.CONCLUSION We describe a case of a 59-year-old male experienced BRS unloading and successful rescue.By analyzing images,the causes of BRS unloading and the treatment plan are discussed to provide insights for BRS release operations.We discuss preventive measures for BRS unloading.

Surgical intervention combined with weight-bearing walking training promotes recovery in patients with chronic spinal cord injury:a randomized controlled study

For patients with chronic spinal cord injury,the co nventional treatment is rehabilitation and treatment of spinal cord injury complications such as urinary tract infection,pressure sores,osteoporosis,and deep vein thrombosis.Surgery is rarely perfo rmed on spinal co rd injury in the chronic phase,and few treatments have been proven effective in chronic spinal cord injury patients.Development of effective therapies fo r chronic spinal co rd injury patients is needed.We conducted a randomized controlled clinical trial in patients with chronic complete thoracic spinal co rd injury to compare intensive rehabilitation(weight-bearing walking training)alone with surgical intervention plus intensive rehabilitation.This clinical trial was registered at ClinicalTrials.gov(NCT02663310).The goal of surgical intervention was spinal cord detethering,restoration of cerebrospinal fluid flow,and elimination of residual spinal cord compression.We found that surgical intervention plus weight-bearing walking training was associated with a higher incidence of American Spinal Injury Association Impairment Scale improvement,reduced spasticity,and more rapid bowel and bladder functional recovery than weight-bearing walking training alone.Overall,the surgical procedures and intensive rehabilitation were safe.American Spinal Injury Association Impairment Scale improvement was more common in T7-T11 injuries than in T2-T6 injuries.Surgery combined with rehabilitation appears to have a role in treatment of chronic spinal cord injury patients.

Pharmacological interventions targeting the microcirculation following traumatic spinal cord injury

Traumatic spinal cord injury is a devastating disorder chara cterized by sensory,motor,and autonomic dysfunction that seve rely compromises an individual's ability to perform activities of daily living.These adve rse outcomes are closely related to the complex mechanism of spinal cord injury,the limited regenerative capacity of central neurons,and the inhibitory environment fo rmed by traumatic injury.Disruption to the microcirculation is an important pathophysiological mechanism of spinal cord injury.A number of therapeutic agents have been shown to improve the injury environment,mitigate secondary damage,and/or promote regeneration and repair.Among them,the spinal cord microcirculation has become an important target for the treatment of spinal cord injury.Drug inte rventions targeting the microcirculation can improve the microenvironment and promote recovery following spinal cord injury.These drugs target the structure and function of the spinal cord microcirculation and are essential for maintaining the normal function of spinal neuro ns,axons,and glial cells.This review discusses the pathophysiological role of spinal cord microcirculation in spinal cord injury,including its structure and histopathological changes.Further,it summarizes the progress of drug therapies targeting the spinal cord mic rocirc ulation after spinal cord injury.

Sleep quality in middle-aged and elderly hemodialysis patients:Impact of a structured nursing intervention program

BACKGROUND Poor sleep quality is common among hemodialysis patients and can significantly impact their well-being.This study aimed to evaluate the effectiveness of a structured nursing intervention program in improving sleep quality in middleaged and elderly hemodialysis patients.AIM To evaluate the impact of nursing intervention on sleep quality in hemodialysis patients.METHODS This cross-sectional study was conducted in a tertiary hospital,the First Affiliated Hospital of Nanchang University,in 2023.This study included 105 middle-aged and elderly hemodialysis patients aged≥45 years who underwent maintenance hemodialysis for at least 3 mo,utilizing the Pittsburgh Sleep Quality Index(PSQI)to identify poor sleepers.Those identified underwent a 12-wk nursing intervention program focusing on education,relaxation techniques,and counseling.Post-intervention,sleep quality was reassessed using the PSQI.RESULTS The study found that 68.6%of hemodialysis patients were poor sleepers.Following the 12-wk nursing intervention program,there was a significant decrease in the mean global PSQI score from 8.9±3.2 to 5.1±2.7(P<0.001),indicating improved sleep quality.This demonstrated the effectiveness of the structured nursing intervention in enhancing sleep quality for middle-aged and elderly hemodialysis patients.CONCLUSION The structured nursing intervention program focusing on sleep hygiene education,relaxation techniques,and counseling effectively improved sleep quality among middle-aged and elderly hemodialysis patients.The significant decrease in the mean global PSQI score post-intervention indicates the positive impact of tailored nursing interventions in addressing poor sleep quality in this patient population.These findings emphasize the importance of implementing targeted nursing interventions to enhance the quality of life for hemodialysis patients by addressing the prevalent issue of poor sleep quality.

Optimization of nursing interventions for postoperative mental status recovery in patients with cerebral hemorrhage

BACKGROUND Hypertensive cerebral hemorrhage(HCH),the most common chronic diseases,has become a topic of global public health discussions.AIM To investigate the role of rehabilitative nursing interventions in optimizing the postoperative mental status recovery phase and to provide clinical value for future rehabilitation of patients with HCH.METHODS This randomized controlled study included 120 patients with cerebral HCH who were contained to our neurosurgery department between May 2021–May 2023 as the participants.The participants have randomly sampled and grouped into the observation and control groups.The observation group received the rehabilitation nursing model,whereas the control group have given conventional nursing.The conscious state of the patients was assessed at 7,14,21,and 30 d postoperatively.After one month of care,sleep quality,anxiety,and depression were compared between the two groups.Patient and family satisfaction were assessed using a nursing care model.RESULTS The results showed that the state of consciousness scores of the patients in both groups significantly increased(P<0.05)after surgical treatment.From the 14th day onwards,differences in the state of consciousness scores between the two groups of patients began to appear(P<0.05).After one month of care,the sleep quality,anxiety state,and depression state of patients were significantly better in the observation group than in the control group(P<0.05).Satisfaction with nursing care was higher in the observation group than in the control group(P<0.05).CONCLUSION The rehabilitation nursing model has a more complete system compared to conventional nursing,which can effectively improve the postoperative quality of life of patients with cerebral hemorrhage and improve the efficiency of mental state recovery;however,further analysis and research are needed to provide more scientific evidence.

Impact of primary percutaneous coronary intervention on ST-segment elevation myocardial infarction patients:A comprehensive analysis

BACKGROUND Myocardial infarction,particularly ST-segment elevation myocardial infarction(STEMI),is a key global mortality cause.Our study investigated predictors of mortality in 96 STEMI patients undergoing primary percutaneous coronary intervention at Erbil Cardiac Center.Multiple factors were identified influencing in-hospital mortality.Significantly,time from symptom onset to hospital arrival emerged as a decisive factor.Consequently,our study hypothesis is:"Reducing time from symptom onset to hospital arrival significantly improves STEMI prognosis."AIM To determine the key factors influencing mortality rates in STEMI patients.METHODS We studied 96 consecutive STEMI patients undergoing primary percutaneous coronary intervention(PPCI)at the Erbil Cardiac Center.Their clinical histories were compiled,and coronary evaluations were performed via angiography on admission.Data included comorbid conditions,onset of cardiogenic shock,complications during PPCI,and more.Post-discharge,one-month follow-up assessments were completed.Statistical significance was set at P<0.05.RESULTS Our results unearthed several significant findings.The in-hospital and 30-d mortality rates among the 96 STEMI patients were 11.2%and 2.3%respectively.On the investigation of independent predictors of in-hospital mortality,we identified atypical presentation,onset of cardiogenic shock,presence of chronic kidney disease,Thrombolysis In Myocardial Infarction grades 0/1/2,triple vessel disease,ventricular tachycardia/ventricular fibrillation,coronary dissection,and the no-reflow phenomenon.Specifically,the recorded average time from symptom onset to hospital arrival amongst patients who did not survive was significantly longer(6.92±3.86 h)compared to those who survived(3.61±1.67 h),P<0.001.These findings underscore the critical role of timely intervention in improving the survival outcomes of STEMI patients.CONCLUSION Our results affirm that early hospital arrival after symptom onset significantly improves survival rates in STEMI patients,highlighting the critical need for prompt intervention.

Discovering Latent Variables for the Tasks With Confounders in Multi-Agent Reinforcement Learning

Efficient exploration in complex coordination tasks has been considered a challenging problem in multi-agent reinforcement learning(MARL). It is significantly more difficult for those tasks with latent variables that agents cannot directly observe. However, most of the existing latent variable discovery methods lack a clear representation of latent variables and an effective evaluation of the influence of latent variables on the agent. In this paper, we propose a new MARL algorithm based on the soft actor-critic method for complex continuous control tasks with confounders. It is called the multi-agent soft actor-critic with latent variable(MASAC-LV) algorithm, which uses variational inference theory to infer the compact latent variables representation space from a large amount of offline experience.Besides, we derive the counterfactual policy whose input has no latent variables and quantify the difference between the actual policy and the counterfactual policy via a distance function. This quantified difference is considered an intrinsic motivation that gives additional rewards based on how much the latent variable affects each agent. The proposed algorithm is evaluated on two collaboration tasks with confounders, and the experimental results demonstrate the effectiveness of MASAC-LV compared to other baseline algorithms.

Development of Multi-Agent-Based Indoor 3D Reconstruction

Large-scale indoor 3D reconstruction with multiple robots faces challenges in core enabling technologies.This work contributes to a framework addressing localization,coordination,and vision processing for multi-agent reconstruction.A system architecture fusing visible light positioning,multi-agent path finding via reinforcement learning,and 360°camera techniques for 3D reconstruction is proposed.Our visible light positioning algorithm leverages existing lighting for centimeter-level localization without additional infrastructure.Meanwhile,a decentralized reinforcement learning approach is developed to solve the multi-agent path finding problem,with communications among agents optimized.Our 3D reconstruction pipeline utilizes equirectangular projection from 360°cameras to facilitate depth-independent reconstruction from posed monocular images using neural networks.Experimental validation demonstrates centimeter-level indoor navigation and 3D scene reconstruction capabilities of our framework.The challenges and limitations stemming from the above enabling technologies are discussed at the end of each corresponding section.In summary,this research advances fundamental techniques for multi-robot indoor 3D modeling,contributing to automated,data-driven applications through coordinated robot navigation,perception,and modeling.

Analysis of the Clinical Value of Psychological Intervention in Gastric Cancer Care

Objective: To analyze the application value of psychological intervention in gastric cancer nursing. Methods: This study analyzes gastric cancer patients admitted to hospitals from May 2022 to May 2023. Based on research requirements and patient willingness, 80 patients were selected and divided into observation and control groups using a lottery method. The control group received conventional nursing care, while the observation group received psychological intervention in addition to conventional nursing care. Results: After the psychological intervention, patients in the observation group showed significant improvements in anxiety and depression, better sleep quality, remarkable enhancement in psychological resilience, higher levels of health literacy, and increased nursing satisfaction compared to the control group (P < 0.05). Conclusion: Incorporating psychological intervention into the nursing care of gastric cancer patients enhances their psychological adjustment ability and improves treatment adherence.

A survey on multi-agent reinforcement learning and its application

Multi-agent reinforcement learning(MARL)has been a rapidly evolving field.This paper presents a comprehensive survey of MARL and its applications.We trace the historical evolution of MARL,highlight its progress,and discuss related survey works.Then,we review the existing works addressing inherent challenges and those focusing on diverse applications.Some representative stochastic games,MARL means,spatial forms of MARL,and task classification are revisited.We then conduct an in-depth exploration of a variety of challenges encountered in MARL applications.We also address critical operational aspects,such as hyperparameter tuning and computational complexity,which are pivotal in practical implementations of MARL.Afterward,we make a thorough overview of the applications of MARL to intelligent machines and devices,chemical engineering,biotechnology,healthcare,and societal issues,which highlights the extensive potential and relevance of MARL within both current and future technological contexts.Our survey also encompasses a detailed examination of benchmark environments used in MARL research,which are instrumental in evaluating MARL algorithms and demonstrate the adaptability of MARL to diverse application scenarios.In the end,we give our prospect for MARL and discuss their related techniques and potential future applications.