A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a force...A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.展开更多
Purpose:The aim of this umbrella review was to determine the impact of resistance training(RT)and individual RT prescription variables on muscle mass,strength,and physical function in healthy adults.Methods:Following ...Purpose:The aim of this umbrella review was to determine the impact of resistance training(RT)and individual RT prescription variables on muscle mass,strength,and physical function in healthy adults.Methods:Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses(PRISMA)guidelines,we systematically searched and screened eligible systematic reviews reporting the effects of differing RT prescription variables on muscle mass(or its proxies),strength,and/or physical function in healthy adults aged>18 years.Results:We identified 44 systematic reviews that met our inclusion criteria.The methodological quality of these reviews was assessed using A Measurement Tool to Assess Systematic Reviews;standardized effectiveness statements were generated.We found that RT was consistently a potent stimulus for increasing skeletal muscle mass(4/4 reviews provide some or sufficient evidence),strength(4/6 reviews provided some or sufficient evidence),and physical function(1/1 review provided some evidence).RT load(6/8 reviews provided some or sufficient evidence),weekly frequency(2/4 reviews provided some or sufficient evidence),volume(3/7 reviews provided some or sufficient evidence),and exercise order(1/1 review provided some evidence)impacted RT-induced increases in muscular strength.We discovered that 2/3 reviews provided some or sufficient evidence that RT volume and contraction velocity influenced skeletal muscle mass,while 4/7 reviews provided insufficient evidence in favor of RT load impacting skeletal muscle mass.There was insufficient evidence to conclude that time of day,periodization,inter-set rest,set configuration,set end point,contraction velocity/time under tension,or exercise order(only pertaining to hypertrophy)influenced skeletal muscle adaptations.A paucity of data limited insights into the impact of RT prescription variables on physical function.Conclusion:Overall,RT increased muscle mass,strength,and physical function compared to no exercise.RT intensity(load)and weekly frequency impacted RT-induced increases in muscular strength but not muscle hypertrophy.RT volume(number of sets)influenced muscular strength and hypertrophy.展开更多
Traditional large-scale multi-objective optimization algorithms(LSMOEAs)encounter difficulties when dealing with sparse large-scale multi-objective optimization problems(SLM-OPs)where most decision variables are zero....Traditional large-scale multi-objective optimization algorithms(LSMOEAs)encounter difficulties when dealing with sparse large-scale multi-objective optimization problems(SLM-OPs)where most decision variables are zero.As a result,many algorithms use a two-layer encoding approach to optimize binary variable Mask and real variable Dec separately.Nevertheless,existing optimizers often focus on locating non-zero variable posi-tions to optimize the binary variables Mask.However,approxi-mating the sparse distribution of real Pareto optimal solutions does not necessarily mean that the objective function is optimized.In data mining,it is common to mine frequent itemsets appear-ing together in a dataset to reveal the correlation between data.Inspired by this,we propose a novel two-layer encoding learning swarm optimizer based on frequent itemsets(TELSO)to address these SLMOPs.TELSO mined the frequent terms of multiple particles with better target values to find mask combinations that can obtain better objective values for fast convergence.Experi-mental results on five real-world problems and eight benchmark sets demonstrate that TELSO outperforms existing state-of-the-art sparse large-scale multi-objective evolutionary algorithms(SLMOEAs)in terms of performance and convergence speed.展开更多
Sparse large-scale multi-objective optimization problems(SLMOPs)are common in science and engineering.However,the large-scale problem represents the high dimensionality of the decision space,requiring algorithms to tr...Sparse large-scale multi-objective optimization problems(SLMOPs)are common in science and engineering.However,the large-scale problem represents the high dimensionality of the decision space,requiring algorithms to traverse vast expanse with limited computational resources.Furthermore,in the context of sparse,most variables in Pareto optimal solutions are zero,making it difficult for algorithms to identify non-zero variables efficiently.This paper is dedicated to addressing the challenges posed by SLMOPs.To start,we introduce innovative objective functions customized to mine maximum and minimum candidate sets.This substantial enhancement dramatically improves the efficacy of frequent pattern mining.In this way,selecting candidate sets is no longer based on the quantity of nonzero variables they contain but on a higher proportion of nonzero variables within specific dimensions.Additionally,we unveil a novel approach to association rule mining,which delves into the intricate relationships between non-zero variables.This novel methodology aids in identifying sparse distributions that can potentially expedite reductions in the objective function value.We extensively tested our algorithm across eight benchmark problems and four real-world SLMOPs.The results demonstrate that our approach achieves competitive solutions across various challenges.展开更多
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 th...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.展开更多
BACKGROUND Eighty percent of stroke patients develop upper limb dysfunction,especially hand dysfunction,which has a very slow recovery,resulting in economic burden to families and society.AIM To investigate the impact...BACKGROUND Eighty percent of stroke patients develop upper limb dysfunction,especially hand dysfunction,which has a very slow recovery,resulting in economic burden to families and society.AIM To investigate the impact of task-oriented training based on acupuncture therapy on upper extremity function in patients with early stroke.METHODS Patients with early stroke hemiplegia who visited our hospital between January 2021 and October 2022 were divided into a control group and an observation group,each with 50 cases.The control group underwent head acupuncture plus routine upper limb rehabilitation training(acupuncture therapy).In addition to acupuncture and rehabilitation,the observation group underwent upper limb task-oriented training(30 min).Each group underwent treatment 5 d/wk for 4 wk.Upper extremity function was assessed in both groups using the Fugl-Meyer Assessment-Upper Extremity(FMA-UE),Wolf Motor Function Rating Scale(WMFT),modified Barthel Index(MBI),and Canadian Occupational Performance Measure(COPM).Quality of life was evaluated using the Short-Form 36-Item Health Survey(SF-36).Clinical efficacy of the interventions was also evaluated.RESULTS Before intervention,no significant differences were observed in the FMA-UE,MBI,and WMFT scores between the two groups(P>0.05).After intervention,the FMA-UE,WMFT,MBI,COPM-Functional Mobility and Satisfaction,and SF-36 scores increased in both groups(P<0.05),with even higher scores in the observation group(P<0.05).The observation group also obtained a higher total effective rate than the control group(P<0.05).CONCLUSION Task-oriented training based on acupuncture rehabilitation significantly enhanced upper extremity mobility,quality of life,and clinical efficacy in patients with early stroke.展开更多
Assessment of past-climate simulations of regional climate models(RCMs)is important for understanding the reliability of RCMs when used to project future regional climate.Here,we assess the performance and discuss pos...Assessment of past-climate simulations of regional climate models(RCMs)is important for understanding the reliability of RCMs when used to project future regional climate.Here,we assess the performance and discuss possible causes of biases in a WRF-based RCM with a grid spacing of 50 km,named WRFG,from the North American Regional Climate Change Assessment Program(NARCCAP)in simulating wet season precipitation over the Central United States for a period when observational data are available.The RCM reproduces key features of the precipitation distribution characteristics during late spring to early summer,although it tends to underestimate the magnitude of precipitation.This dry bias is partially due to the model’s lack of skill in simulating nocturnal precipitation related to the lack of eastward propagating convective systems in the simulation.Inaccuracy in reproducing large-scale circulation and environmental conditions is another contributing factor.The too weak simulated pressure gradient between the Rocky Mountains and the Gulf of Mexico results in weaker southerly winds in between,leading to a reduction of warm moist air transport from the Gulf to the Central Great Plains.The simulated low-level horizontal convergence fields are less favorable for upward motion than in the NARR and hence,for the development of moist convection as well.Therefore,a careful examination of an RCM’s deficiencies and the identification of the source of errors are important when using the RCM to project precipitation changes in future climate scenarios.展开更多
Accurate positioning is one of the essential requirements for numerous applications of remote sensing data,especially in the event of a noisy or unreliable satellite signal.Toward this end,we present a novel framework...Accurate positioning is one of the essential requirements for numerous applications of remote sensing data,especially in the event of a noisy or unreliable satellite signal.Toward this end,we present a novel framework for aircraft geo-localization in a large range that only requires a downward-facing monocular camera,an altimeter,a compass,and an open-source Vector Map(VMAP).The algorithm combines the matching and particle filter methods.Shape vector and correlation between two building contour vectors are defined,and a coarse-to-fine building vector matching(CFBVM)method is proposed in the matching stage,for which the original matching results are described by the Gaussian mixture model(GMM).Subsequently,an improved resampling strategy is designed to reduce computing expenses with a huge number of initial particles,and a credibility indicator is designed to avoid location mistakes in the particle filter stage.An experimental evaluation of the approach based on flight data is provided.On a flight at a height of 0.2 km over a flight distance of 2 km,the aircraft is geo-localized in a reference map of 11,025 km~2using 0.09 km~2aerial images without any prior information.The absolute localization error is less than 10 m.展开更多
This article introduces the concept of load aggregation,which involves a comprehensive analysis of loads to acquire their external characteristics for the purpose of modeling and analyzing power systems.The online ide...This article introduces the concept of load aggregation,which involves a comprehensive analysis of loads to acquire their external characteristics for the purpose of modeling and analyzing power systems.The online identification method is a computer-involved approach for data collection,processing,and system identification,commonly used for adaptive control and prediction.This paper proposes a method for dynamically aggregating large-scale adjustable loads to support high proportions of new energy integration,aiming to study the aggregation characteristics of regional large-scale adjustable loads using online identification techniques and feature extraction methods.The experiment selected 300 central air conditioners as the research subject and analyzed their regulation characteristics,economic efficiency,and comfort.The experimental results show that as the adjustment time of the air conditioner increases from 5 minutes to 35 minutes,the stable adjustment quantity during the adjustment period decreases from 28.46 to 3.57,indicating that air conditioning loads can be controlled over a long period and have better adjustment effects in the short term.Overall,the experimental results of this paper demonstrate that analyzing the aggregation characteristics of regional large-scale adjustable loads using online identification techniques and feature extraction algorithms is effective.展开更多
Objective:Transurethral resection of bladder tumor is one of the most common everyday urological procedures.This kind of surgery demands a set of skills that need training and experience.In this review,we aimed to inv...Objective:Transurethral resection of bladder tumor is one of the most common everyday urological procedures.This kind of surgery demands a set of skills that need training and experience.In this review,we aimed to investigate the current literature to find out if simulators,phantoms,and other training models could be used as a tool for teaching urologists.Methods:A systematic review was performed according to the Preferred Reporting Items for Systematic reviews and Meta-Analyses statement and the recommendations of the European Association of Urology guidelines for conducting systematic reviews.Fifteen out of 932 studies met our inclusion criteria and are presented in the current review.Results:The UroTrainer(Karl Storz GmbH,Tuttlingen,Germany),a virtual reality training simulator,achieved positive feedback and an excellent face and construct validity by the participants.The inspection of bladder mucosa,blood loss,tumor resection,and procedural time was improved after the training,especially for inexperienced urologists and medical students.The construct validity of UroSim®(VirtaMed,Zurich,Switzerland)was established.SIMBLA simulator(Samed GmbH,Dresden,Germany)was found to be a realistic and useful tool by experts and urologists with intermediate experience.The test objective competency model based on SIMBLA simulator could be used for evaluating urologists.The porcine model of the Asian Urological Surgery Training and Education Group also received positive feedback by the participants that tried it.The Simulation and Technology Enhanced Learning Initiative Project had an extraordinary face and content validity,and 60%of participants would like to use the simulators in the future.The 5-day multimodal training curriculum“Boot Camp”in the United Kingdom achieved an increase of the level of confidence of the participants that lasted months after the project.Conclusion:Simulators and courses or curricula based on a simulator training could be a valuable learning tool for any surgeon,and there is no doubt that they should be a part of every urologist's technical education.展开更多
Communicating on millimeter wave(mmWave)bands is ushering in a new epoch of mobile communication which provides the availability of 10 Gbps high data rate transmission.However,mmWave links are easily prone to short tr...Communicating on millimeter wave(mmWave)bands is ushering in a new epoch of mobile communication which provides the availability of 10 Gbps high data rate transmission.However,mmWave links are easily prone to short transmission range communication because of the serious free space path loss and the blockage by obstacles.To overcome these challenges,highly directional beams are exploited to achieve robust links by hybrid beamforming.Accurately aligning the transmitter and receiver beams,i.e.beam training,is vitally important to high data rate transmission.However,it may cause huge overhead which has negative effects on initial access,handover,and tracking.Besides,the mobility patterns of users are complicated and dynamic,which may cause tracking error and large tracking latency.An efficient beam tracking method has a positive effect on sustaining robust links.This article provides an overview of the beam training and tracking technologies on mmWave bands and reveals the insights for future research in the 6th Generation(6G)mobile network.Especially,some open research problems are proposed to realize fast,accurate,and robust beam training and tracking.We hope that this survey provides guidelines for the researchers in the area of mmWave communications.展开更多
Purpose:This meta-analytical study aimed to explore the effects of resistance training(RT) volume on body adiposity,metabolic risk,and inflammation in postmenopausal and older females.Methods:A systematic search was p...Purpose:This meta-analytical study aimed to explore the effects of resistance training(RT) volume on body adiposity,metabolic risk,and inflammation in postmenopausal and older females.Methods:A systematic search was performed for randomized controlled trials in PubMed,Scopus,Web of Science,and SciELO.Randomized controlled trials with postmenopausal and older females that compared RT effects on body adiposity,metabolic risk,and inflammation with a control group(CG) were included.Independent reviewers selected the studies,extracted the data,and performed the risk of bias and certainty of the evidence(Grading of Recommendations,Assessment,Development,and Evaluation(GRADE)) evaluations.Total body and abdominal adiposity,blood lipids,glucose,and C-reactive protein were included for meta-analysis.A random-effects model,standardized mean difference(Hedges’ g),and 95% confidence interval(95%CI) were used for meta-analysis.Results:Twenty randomized controlled trials(overall risk of bias:some concerns;GRADE:low to very low) with overweight/obese postmenopausal and older females were included.RT groups were divided into low-volume RT(LVRT,~44 sets/week) and high-volume RT(HVRT,~77 sets/week).Both RT groups presented improved body adiposity,metabolic risk,and inflammation when compared to CG.However,HVRT demonstrated higher effect sizes than LVRT for glucose(HVRT=-1.19;95%CI:-1.63 to-0.74;LVRT=-0.78;95%CI:-1.15 to-0.41) and C-reactive protein(HVRT=-1.00;95%CI:-1.32 to-0.67;LVRT=-0.34;95%CI,-0.63 to-0.04)) when compared to CG.Conclusion:Compared to CG,HVRT protocols elicit greater improvements in metabolic risk and inflammation outcomes than LVRT in overweight/obese postmenopausal and older females.展开更多
The large-scale multi-objective optimization algorithm(LSMOA),based on the grouping of decision variables,is an advanced method for handling high-dimensional decision variables.However,in practical problems,the intera...The large-scale multi-objective optimization algorithm(LSMOA),based on the grouping of decision variables,is an advanced method for handling high-dimensional decision variables.However,in practical problems,the interaction among decision variables is intricate,leading to large group sizes and suboptimal optimization effects;hence a large-scale multi-objective optimization algorithm based on weighted overlapping grouping of decision variables(MOEAWOD)is proposed in this paper.Initially,the decision variables are perturbed and categorized into convergence and diversity variables;subsequently,the convergence variables are subdivided into groups based on the interactions among different decision variables.If the size of a group surpasses the set threshold,that group undergoes a process of weighting and overlapping grouping.Specifically,the interaction strength is evaluated based on the interaction frequency and number of objectives among various decision variables.The decision variable with the highest interaction in the group is identified and disregarded,and the remaining variables are then reclassified into subgroups.Finally,the decision variable with the strongest interaction is added to each subgroup.MOEAWOD minimizes the interactivity between different groups and maximizes the interactivity of decision variables within groups,which contributed to the optimized direction of convergence and diversity exploration with different groups.MOEAWOD was subjected to testing on 18 benchmark large-scale optimization problems,and the experimental results demonstrate the effectiveness of our methods.Compared with the other algorithms,our method is still at an advantage.展开更多
In recent years,various adversarial defense methods have been proposed to improve the robustness of deep neural networks.Adversarial training is one of the most potent methods to defend against adversarial attacks.How...In recent years,various adversarial defense methods have been proposed to improve the robustness of deep neural networks.Adversarial training is one of the most potent methods to defend against adversarial attacks.However,the difference in the feature space between natural and adversarial examples hinders the accuracy and robustness of the model in adversarial training.This paper proposes a learnable distribution adversarial training method,aiming to construct the same distribution for training data utilizing the Gaussian mixture model.The distribution centroid is built to classify samples and constrain the distribution of the sample features.The natural and adversarial examples are pushed to the same distribution centroid to improve the accuracy and robustness of the model.The proposed method generates adversarial examples to close the distribution gap between the natural and adversarial examples through an attack algorithm explicitly designed for adversarial training.This algorithm gradually increases the accuracy and robustness of the model by scaling perturbation.Finally,the proposed method outputs the predicted labels and the distance between the sample and the distribution centroid.The distribution characteristics of the samples can be utilized to detect adversarial cases that can potentially evade the model defense.The effectiveness of the proposed method is demonstrated through comprehensive experiments.展开更多
With the rapid development of machine learning,the demand for high-efficient computing becomes more and more urgent.To break the bottleneck of the traditional Von Neumann architecture,computing-in-memory(CIM)has attra...With the rapid development of machine learning,the demand for high-efficient computing becomes more and more urgent.To break the bottleneck of the traditional Von Neumann architecture,computing-in-memory(CIM)has attracted increasing attention in recent years.In this work,to provide a feasible CIM solution for the large-scale neural networks(NN)requiring continuous weight updating in online training,a flash-based computing-in-memory with high endurance(10^(9) cycles)and ultrafast programming speed is investigated.On the one hand,the proposed programming scheme of channel hot electron injection(CHEI)and hot hole injection(HHI)demonstrate high linearity,symmetric potentiation,and a depression process,which help to improve the training speed and accuracy.On the other hand,the low-damage programming scheme and memory window(MW)optimizations can suppress cell degradation effectively with improved computing accuracy.Even after 109 cycles,the leakage current(I_(off))of cells remains sub-10pA,ensuring the large-scale computing ability of memory.Further characterizations are done on read disturb to demonstrate its robust reliabilities.By processing CIFAR-10 tasks,it is evident that~90%accuracy can be achieved after 109 cycles in both ResNet50 and VGG16 NN.Our results suggest that flash-based CIM has great potential to overcome the limitations of traditional Von Neumann architectures and enable high-performance NN online training,which pave the way for further development of artificial intelligence(AI)accelerators.展开更多
With the development of big data and social computing,large-scale group decisionmaking(LGDM)is nowmerging with social networks.Using social network analysis(SNA),this study proposes an LGDM consensus model that consid...With the development of big data and social computing,large-scale group decisionmaking(LGDM)is nowmerging with social networks.Using social network analysis(SNA),this study proposes an LGDM consensus model that considers the trust relationship among decisionmakers(DMs).In the process of consensusmeasurement:the social network is constructed according to the social relationship among DMs,and the Louvain method is introduced to classify social networks to form subgroups.In this study,the weights of each decision maker and each subgroup are computed by comprehensive network weights and trust weights.In the process of consensus improvement:A feedback mechanism with four identification and two direction rules is designed to guide the consensus of the improvement process.Based on the trust relationship among DMs,the preferences are modified,and the corresponding social network is updated to accelerate the consensus.Compared with the previous research,the proposedmodel not only allows the subgroups to be reconstructed and updated during the adjustment process,but also improves the accuracy of the adjustment by the feedbackmechanism.Finally,an example analysis is conducted to verify the effectiveness and flexibility of the proposed method.Moreover,compared with previous studies,the superiority of the proposed method in solving the LGDM problem is highlighted.展开更多
Quantized training has been proven to be a prominent method to achieve deep neural network training under limited computational resources.It uses low bit-width arithmetics with a proper scaling factor to achieve negli...Quantized training has been proven to be a prominent method to achieve deep neural network training under limited computational resources.It uses low bit-width arithmetics with a proper scaling factor to achieve negligible accuracy loss.Cambricon-Q is the ASIC design proposed to efficiently support quantized training,and achieves significant performance improvement.However,there are still two caveats in the design.First,Cambricon-Q with different hardware specifications may lead to different numerical errors,resulting in non-reproducible behaviors which may become a major concern in critical applications.Second,Cambricon-Q cannot leverage data sparsity,where considerable cycles could still be squeezed out.To address the caveats,the acceleration core of Cambricon-Q is redesigned to support fine-grained irregular data processing.The new design not only enables acceleration on sparse data,but also enables performing local dynamic quantization by contiguous value ranges(which is hardware independent),instead of contiguous addresses(which is dependent on hardware factors).Experimental results show that the accuracy loss of the method still keeps negligible,and the accelerator achieves 1.61×performance improvement over Cambricon-Q,with about 10%energy increase.展开更多
●AIM:To determine the teaching effects of a real-time three dimensional(3D)visualization system in the operating room for early-stage phacoemulsification training.●METHODS:A total of 10 ophthalmology residents of th...●AIM:To determine the teaching effects of a real-time three dimensional(3D)visualization system in the operating room for early-stage phacoemulsification training.●METHODS:A total of 10 ophthalmology residents of the first-year postgraduate were included.All the residents were novices to cataract surgery.Real-time cataract surgical observations were performed using a custom-built 3D visualization system.The training lasted 4wk(32h)in all.A modified International Council of Ophthalmology’s Ophthalmology Surgical Competency Assessment Rubric(ICO-OSCAR)containing 4 specific steps of cataract surgery was applied.The self-assessment(self)and expert-assessment(expert)were performed through the microsurgical attempts in the wet lab for each participant.●RESULTS:Compared with pre-training assessments(self 3.2±0.8,expert 2.5±0.6),the overall mean scores of posttraining(self 5.2±0.4,expert 4.7±0.6)were significantly improved after real-time observation training of 3D visualization system(P<0.05).Scores of 4 surgical items were significantly improved both self and expert assessment after training(P<0.05).●CONCLUSION:The 3D observation training provides novice ophthalmic residents with a better understanding of intraocular microsurgical techniques.It is a useful tool to improve teaching efficiency of surgical education.展开更多
The human brain is highly plastic.Cognitive training is usually used to modify functional connectivity of brain networks.Moreover,the structures of brain networks may determine its dynamic behavior which is related to...The human brain is highly plastic.Cognitive training is usually used to modify functional connectivity of brain networks.Moreover,the structures of brain networks may determine its dynamic behavior which is related to human cognitive abilities.To study the effect of functional connectivity on the brain dynamics,the dynamic model based on functional connections of the brain and the Hindmarsh–Rose model is utilized in this work.The resting-state fMRI data from the experimental group undergoing abacus-based mental calculation(AMC)training and from the control group are used to construct the functional brain networks.The dynamic behavior of brain at the resting and task states for the AMC group and the control group are simulated with the above-mentioned dynamic model.In the resting state,there are the differences of brain activation between the AMC group and the control group,and more brain regions are inspired in the AMC group.A stimulus with sinusoidal signals to brain networks is introduced to simulate the brain dynamics in the task states.The dynamic characteristics are extracted by the excitation rates,the response intensities and the state distributions.The change in the functional connectivity of brain networks with the AMC training would in turn improve the brain response to external stimulus,and make the brain more efficient in processing tasks.展开更多
Electric power training is essential for ensuring the safety and reliability of the system.In this study,we introduce a novel Abnormal Action Recognition(AAR)system that utilizes a Lightweight Pose Estimation Network(...Electric power training is essential for ensuring the safety and reliability of the system.In this study,we introduce a novel Abnormal Action Recognition(AAR)system that utilizes a Lightweight Pose Estimation Network(LPEN)to efficiently and effectively detect abnormal fall-down and trespass incidents in electric power training scenarios.The LPEN network,comprising three stages—MobileNet,Initial Stage,and Refinement Stage—is employed to swiftly extract image features,detect human key points,and refine them for accurate analysis.Subsequently,a Pose-aware Action Analysis Module(PAAM)captures the positional coordinates of human skeletal points in each frame.Finally,an Abnormal Action Inference Module(AAIM)evaluates whether abnormal fall-down or unauthorized trespass behavior is occurring.For fall-down recognition,three criteria—falling speed,main angles of skeletal points,and the person’s bounding box—are considered.To identify unauthorized trespass,emphasis is placed on the position of the ankles.Extensive experiments validate the effectiveness and efficiency of the proposed system in ensuring the safety and reliability of electric power training.展开更多
基金supported by the Ministry of Trade,Industry & Energy(MOTIE,Korea) under Industrial Technology Innovation Program (No.10063424,'development of distant speech recognition and multi-task dialog processing technologies for in-door conversational robots')
文摘A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.
基金suppoited by an Alexander Graliam Bell Canada Graduate Scholarship-Doctoralsupported by an Ontario Graduate Scholarshipsupported by the Canada Research Chairs programme。
文摘Purpose:The aim of this umbrella review was to determine the impact of resistance training(RT)and individual RT prescription variables on muscle mass,strength,and physical function in healthy adults.Methods:Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses(PRISMA)guidelines,we systematically searched and screened eligible systematic reviews reporting the effects of differing RT prescription variables on muscle mass(or its proxies),strength,and/or physical function in healthy adults aged>18 years.Results:We identified 44 systematic reviews that met our inclusion criteria.The methodological quality of these reviews was assessed using A Measurement Tool to Assess Systematic Reviews;standardized effectiveness statements were generated.We found that RT was consistently a potent stimulus for increasing skeletal muscle mass(4/4 reviews provide some or sufficient evidence),strength(4/6 reviews provided some or sufficient evidence),and physical function(1/1 review provided some evidence).RT load(6/8 reviews provided some or sufficient evidence),weekly frequency(2/4 reviews provided some or sufficient evidence),volume(3/7 reviews provided some or sufficient evidence),and exercise order(1/1 review provided some evidence)impacted RT-induced increases in muscular strength.We discovered that 2/3 reviews provided some or sufficient evidence that RT volume and contraction velocity influenced skeletal muscle mass,while 4/7 reviews provided insufficient evidence in favor of RT load impacting skeletal muscle mass.There was insufficient evidence to conclude that time of day,periodization,inter-set rest,set configuration,set end point,contraction velocity/time under tension,or exercise order(only pertaining to hypertrophy)influenced skeletal muscle adaptations.A paucity of data limited insights into the impact of RT prescription variables on physical function.Conclusion:Overall,RT increased muscle mass,strength,and physical function compared to no exercise.RT intensity(load)and weekly frequency impacted RT-induced increases in muscular strength but not muscle hypertrophy.RT volume(number of sets)influenced muscular strength and hypertrophy.
基金supported by the Scientific Research Project of Xiang Jiang Lab(22XJ02003)the University Fundamental Research Fund(23-ZZCX-JDZ-28)+5 种基金the National Science Fund for Outstanding Young Scholars(62122093)the National Natural Science Foundation of China(72071205)the Hunan Graduate Research Innovation Project(ZC23112101-10)the Hunan Natural Science Foundation Regional Joint Project(2023JJ50490)the Science and Technology Project for Young and Middle-aged Talents of Hunan(2023TJ-Z03)the Science and Technology Innovation Program of Humnan Province(2023RC1002)。
文摘Traditional large-scale multi-objective optimization algorithms(LSMOEAs)encounter difficulties when dealing with sparse large-scale multi-objective optimization problems(SLM-OPs)where most decision variables are zero.As a result,many algorithms use a two-layer encoding approach to optimize binary variable Mask and real variable Dec separately.Nevertheless,existing optimizers often focus on locating non-zero variable posi-tions to optimize the binary variables Mask.However,approxi-mating the sparse distribution of real Pareto optimal solutions does not necessarily mean that the objective function is optimized.In data mining,it is common to mine frequent itemsets appear-ing together in a dataset to reveal the correlation between data.Inspired by this,we propose a novel two-layer encoding learning swarm optimizer based on frequent itemsets(TELSO)to address these SLMOPs.TELSO mined the frequent terms of multiple particles with better target values to find mask combinations that can obtain better objective values for fast convergence.Experi-mental results on five real-world problems and eight benchmark sets demonstrate that TELSO outperforms existing state-of-the-art sparse large-scale multi-objective evolutionary algorithms(SLMOEAs)in terms of performance and convergence speed.
基金support by the Open Project of Xiangjiang Laboratory(22XJ02003)the University Fundamental Research Fund(23-ZZCX-JDZ-28,ZK21-07)+5 种基金the National Science Fund for Outstanding Young Scholars(62122093)the National Natural Science Foundation of China(72071205)the Hunan Graduate Research Innovation Project(CX20230074)the Hunan Natural Science Foundation Regional Joint Project(2023JJ50490)the Science and Technology Project for Young and Middle-aged Talents of Hunan(2023TJZ03)the Science and Technology Innovation Program of Humnan Province(2023RC1002).
文摘Sparse large-scale multi-objective optimization problems(SLMOPs)are common in science and engineering.However,the large-scale problem represents the high dimensionality of the decision space,requiring algorithms to traverse vast expanse with limited computational resources.Furthermore,in the context of sparse,most variables in Pareto optimal solutions are zero,making it difficult for algorithms to identify non-zero variables efficiently.This paper is dedicated to addressing the challenges posed by SLMOPs.To start,we introduce innovative objective functions customized to mine maximum and minimum candidate sets.This substantial enhancement dramatically improves the efficacy of frequent pattern mining.In this way,selecting candidate sets is no longer based on the quantity of nonzero variables they contain but on a higher proportion of nonzero variables within specific dimensions.Additionally,we unveil a novel approach to association rule mining,which delves into the intricate relationships between non-zero variables.This novel methodology aids in identifying sparse distributions that can potentially expedite reductions in the objective function value.We extensively tested our algorithm across eight benchmark problems and four real-world SLMOPs.The results demonstrate that our approach achieves competitive solutions across various challenges.
基金supported by Hong Kong Spinal Cord Injury Fund (HKSCIF),China (to HZ)。
文摘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.
文摘BACKGROUND Eighty percent of stroke patients develop upper limb dysfunction,especially hand dysfunction,which has a very slow recovery,resulting in economic burden to families and society.AIM To investigate the impact of task-oriented training based on acupuncture therapy on upper extremity function in patients with early stroke.METHODS Patients with early stroke hemiplegia who visited our hospital between January 2021 and October 2022 were divided into a control group and an observation group,each with 50 cases.The control group underwent head acupuncture plus routine upper limb rehabilitation training(acupuncture therapy).In addition to acupuncture and rehabilitation,the observation group underwent upper limb task-oriented training(30 min).Each group underwent treatment 5 d/wk for 4 wk.Upper extremity function was assessed in both groups using the Fugl-Meyer Assessment-Upper Extremity(FMA-UE),Wolf Motor Function Rating Scale(WMFT),modified Barthel Index(MBI),and Canadian Occupational Performance Measure(COPM).Quality of life was evaluated using the Short-Form 36-Item Health Survey(SF-36).Clinical efficacy of the interventions was also evaluated.RESULTS Before intervention,no significant differences were observed in the FMA-UE,MBI,and WMFT scores between the two groups(P>0.05).After intervention,the FMA-UE,WMFT,MBI,COPM-Functional Mobility and Satisfaction,and SF-36 scores increased in both groups(P<0.05),with even higher scores in the observation group(P<0.05).The observation group also obtained a higher total effective rate than the control group(P<0.05).CONCLUSION Task-oriented training based on acupuncture rehabilitation significantly enhanced upper extremity mobility,quality of life,and clinical efficacy in patients with early stroke.
文摘Assessment of past-climate simulations of regional climate models(RCMs)is important for understanding the reliability of RCMs when used to project future regional climate.Here,we assess the performance and discuss possible causes of biases in a WRF-based RCM with a grid spacing of 50 km,named WRFG,from the North American Regional Climate Change Assessment Program(NARCCAP)in simulating wet season precipitation over the Central United States for a period when observational data are available.The RCM reproduces key features of the precipitation distribution characteristics during late spring to early summer,although it tends to underestimate the magnitude of precipitation.This dry bias is partially due to the model’s lack of skill in simulating nocturnal precipitation related to the lack of eastward propagating convective systems in the simulation.Inaccuracy in reproducing large-scale circulation and environmental conditions is another contributing factor.The too weak simulated pressure gradient between the Rocky Mountains and the Gulf of Mexico results in weaker southerly winds in between,leading to a reduction of warm moist air transport from the Gulf to the Central Great Plains.The simulated low-level horizontal convergence fields are less favorable for upward motion than in the NARR and hence,for the development of moist convection as well.Therefore,a careful examination of an RCM’s deficiencies and the identification of the source of errors are important when using the RCM to project precipitation changes in future climate scenarios.
文摘Accurate positioning is one of the essential requirements for numerous applications of remote sensing data,especially in the event of a noisy or unreliable satellite signal.Toward this end,we present a novel framework for aircraft geo-localization in a large range that only requires a downward-facing monocular camera,an altimeter,a compass,and an open-source Vector Map(VMAP).The algorithm combines the matching and particle filter methods.Shape vector and correlation between two building contour vectors are defined,and a coarse-to-fine building vector matching(CFBVM)method is proposed in the matching stage,for which the original matching results are described by the Gaussian mixture model(GMM).Subsequently,an improved resampling strategy is designed to reduce computing expenses with a huge number of initial particles,and a credibility indicator is designed to avoid location mistakes in the particle filter stage.An experimental evaluation of the approach based on flight data is provided.On a flight at a height of 0.2 km over a flight distance of 2 km,the aircraft is geo-localized in a reference map of 11,025 km~2using 0.09 km~2aerial images without any prior information.The absolute localization error is less than 10 m.
基金supported by the State Grid Science&Technology Project(5100-202114296A-0-0-00).
文摘This article introduces the concept of load aggregation,which involves a comprehensive analysis of loads to acquire their external characteristics for the purpose of modeling and analyzing power systems.The online identification method is a computer-involved approach for data collection,processing,and system identification,commonly used for adaptive control and prediction.This paper proposes a method for dynamically aggregating large-scale adjustable loads to support high proportions of new energy integration,aiming to study the aggregation characteristics of regional large-scale adjustable loads using online identification techniques and feature extraction methods.The experiment selected 300 central air conditioners as the research subject and analyzed their regulation characteristics,economic efficiency,and comfort.The experimental results show that as the adjustment time of the air conditioner increases from 5 minutes to 35 minutes,the stable adjustment quantity during the adjustment period decreases from 28.46 to 3.57,indicating that air conditioning loads can be controlled over a long period and have better adjustment effects in the short term.Overall,the experimental results of this paper demonstrate that analyzing the aggregation characteristics of regional large-scale adjustable loads using online identification techniques and feature extraction algorithms is effective.
文摘Objective:Transurethral resection of bladder tumor is one of the most common everyday urological procedures.This kind of surgery demands a set of skills that need training and experience.In this review,we aimed to investigate the current literature to find out if simulators,phantoms,and other training models could be used as a tool for teaching urologists.Methods:A systematic review was performed according to the Preferred Reporting Items for Systematic reviews and Meta-Analyses statement and the recommendations of the European Association of Urology guidelines for conducting systematic reviews.Fifteen out of 932 studies met our inclusion criteria and are presented in the current review.Results:The UroTrainer(Karl Storz GmbH,Tuttlingen,Germany),a virtual reality training simulator,achieved positive feedback and an excellent face and construct validity by the participants.The inspection of bladder mucosa,blood loss,tumor resection,and procedural time was improved after the training,especially for inexperienced urologists and medical students.The construct validity of UroSim®(VirtaMed,Zurich,Switzerland)was established.SIMBLA simulator(Samed GmbH,Dresden,Germany)was found to be a realistic and useful tool by experts and urologists with intermediate experience.The test objective competency model based on SIMBLA simulator could be used for evaluating urologists.The porcine model of the Asian Urological Surgery Training and Education Group also received positive feedback by the participants that tried it.The Simulation and Technology Enhanced Learning Initiative Project had an extraordinary face and content validity,and 60%of participants would like to use the simulators in the future.The 5-day multimodal training curriculum“Boot Camp”in the United Kingdom achieved an increase of the level of confidence of the participants that lasted months after the project.Conclusion:Simulators and courses or curricula based on a simulator training could be a valuable learning tool for any surgeon,and there is no doubt that they should be a part of every urologist's technical education.
基金supported in part by the National Natural Science Foundation of China(NSFC)under Grant 92267202in part by the Municipal Government of Quzhou under Grant 2023D027+2 种基金in part by the National Natural Science Foundation of China(NSFC)under Grant 62321001in part by the National Key Research and Development Program of China under Grant 2020YFA0711303in part by the Beijing Natural Science Foundation under Grant Z220004.
文摘Communicating on millimeter wave(mmWave)bands is ushering in a new epoch of mobile communication which provides the availability of 10 Gbps high data rate transmission.However,mmWave links are easily prone to short transmission range communication because of the serious free space path loss and the blockage by obstacles.To overcome these challenges,highly directional beams are exploited to achieve robust links by hybrid beamforming.Accurately aligning the transmitter and receiver beams,i.e.beam training,is vitally important to high data rate transmission.However,it may cause huge overhead which has negative effects on initial access,handover,and tracking.Besides,the mobility patterns of users are complicated and dynamic,which may cause tracking error and large tracking latency.An efficient beam tracking method has a positive effect on sustaining robust links.This article provides an overview of the beam training and tracking technologies on mmWave bands and reveals the insights for future research in the 6th Generation(6G)mobile network.Especially,some open research problems are proposed to realize fast,accurate,and robust beam training and tracking.We hope that this survey provides guidelines for the researchers in the area of mmWave communications.
基金supported by the Minas Gerais State University (UEMG/Brazil)a Research Productivity Scholarship Program (UEMG-PQ08/2021)+1 种基金a doctorate scholarship from the National Council of Technological and Scientific Development (CNPq/Brazil-Process140473/2020-3)a doctorate scholarship fromthe Coordination of Improvement of Higher Education Personnel (CAPES/Brazil-Code 001)。
文摘Purpose:This meta-analytical study aimed to explore the effects of resistance training(RT) volume on body adiposity,metabolic risk,and inflammation in postmenopausal and older females.Methods:A systematic search was performed for randomized controlled trials in PubMed,Scopus,Web of Science,and SciELO.Randomized controlled trials with postmenopausal and older females that compared RT effects on body adiposity,metabolic risk,and inflammation with a control group(CG) were included.Independent reviewers selected the studies,extracted the data,and performed the risk of bias and certainty of the evidence(Grading of Recommendations,Assessment,Development,and Evaluation(GRADE)) evaluations.Total body and abdominal adiposity,blood lipids,glucose,and C-reactive protein were included for meta-analysis.A random-effects model,standardized mean difference(Hedges’ g),and 95% confidence interval(95%CI) were used for meta-analysis.Results:Twenty randomized controlled trials(overall risk of bias:some concerns;GRADE:low to very low) with overweight/obese postmenopausal and older females were included.RT groups were divided into low-volume RT(LVRT,~44 sets/week) and high-volume RT(HVRT,~77 sets/week).Both RT groups presented improved body adiposity,metabolic risk,and inflammation when compared to CG.However,HVRT demonstrated higher effect sizes than LVRT for glucose(HVRT=-1.19;95%CI:-1.63 to-0.74;LVRT=-0.78;95%CI:-1.15 to-0.41) and C-reactive protein(HVRT=-1.00;95%CI:-1.32 to-0.67;LVRT=-0.34;95%CI,-0.63 to-0.04)) when compared to CG.Conclusion:Compared to CG,HVRT protocols elicit greater improvements in metabolic risk and inflammation outcomes than LVRT in overweight/obese postmenopausal and older females.
基金supported in part by the Central Government Guides Local Science and TechnologyDevelopment Funds(Grant No.YDZJSX2021A038)in part by theNational Natural Science Foundation of China under(Grant No.61806138)in part by the China University Industry-University-Research Collaborative Innovation Fund(Future Network Innovation Research and Application Project)(Grant 2021FNA04014).
文摘The large-scale multi-objective optimization algorithm(LSMOA),based on the grouping of decision variables,is an advanced method for handling high-dimensional decision variables.However,in practical problems,the interaction among decision variables is intricate,leading to large group sizes and suboptimal optimization effects;hence a large-scale multi-objective optimization algorithm based on weighted overlapping grouping of decision variables(MOEAWOD)is proposed in this paper.Initially,the decision variables are perturbed and categorized into convergence and diversity variables;subsequently,the convergence variables are subdivided into groups based on the interactions among different decision variables.If the size of a group surpasses the set threshold,that group undergoes a process of weighting and overlapping grouping.Specifically,the interaction strength is evaluated based on the interaction frequency and number of objectives among various decision variables.The decision variable with the highest interaction in the group is identified and disregarded,and the remaining variables are then reclassified into subgroups.Finally,the decision variable with the strongest interaction is added to each subgroup.MOEAWOD minimizes the interactivity between different groups and maximizes the interactivity of decision variables within groups,which contributed to the optimized direction of convergence and diversity exploration with different groups.MOEAWOD was subjected to testing on 18 benchmark large-scale optimization problems,and the experimental results demonstrate the effectiveness of our methods.Compared with the other algorithms,our method is still at an advantage.
基金supported by the National Natural Science Foundation of China(No.U21B2003,62072250,62072250,62172435,U1804263,U20B2065,61872203,71802110,61802212)the National Key R&D Program of China(No.2021QY0700)+4 种基金the Key Laboratory of Intelligent Support Technology for Complex Environments(Nanjing University of Information Science and Technology),Ministry of Education,and the Natural Science Foundation of Jiangsu Province(No.BK20200750)Open Foundation of Henan Key Laboratory of Cyberspace Situation Awareness(No.HNTS2022002)Post Graduate Research&Practice Innvoation Program of Jiangsu Province(No.KYCX200974)Open Project Fund of Shandong Provincial Key Laboratory of Computer Network(No.SDKLCN-2022-05)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)Fund and Graduate Student Scientific Research Innovation Projects of Jiangsu Province(No.KYCX231359).
文摘In recent years,various adversarial defense methods have been proposed to improve the robustness of deep neural networks.Adversarial training is one of the most potent methods to defend against adversarial attacks.However,the difference in the feature space between natural and adversarial examples hinders the accuracy and robustness of the model in adversarial training.This paper proposes a learnable distribution adversarial training method,aiming to construct the same distribution for training data utilizing the Gaussian mixture model.The distribution centroid is built to classify samples and constrain the distribution of the sample features.The natural and adversarial examples are pushed to the same distribution centroid to improve the accuracy and robustness of the model.The proposed method generates adversarial examples to close the distribution gap between the natural and adversarial examples through an attack algorithm explicitly designed for adversarial training.This algorithm gradually increases the accuracy and robustness of the model by scaling perturbation.Finally,the proposed method outputs the predicted labels and the distance between the sample and the distribution centroid.The distribution characteristics of the samples can be utilized to detect adversarial cases that can potentially evade the model defense.The effectiveness of the proposed method is demonstrated through comprehensive experiments.
基金This work was supported by the National Natural Science Foundation of China(Nos.62034006,92264201,and 91964105)the Natural Science Foundation of Shandong Province(Nos.ZR2020JQ28 and ZR2020KF016)the Program of Qilu Young Scholars of Shandong University.
文摘With the rapid development of machine learning,the demand for high-efficient computing becomes more and more urgent.To break the bottleneck of the traditional Von Neumann architecture,computing-in-memory(CIM)has attracted increasing attention in recent years.In this work,to provide a feasible CIM solution for the large-scale neural networks(NN)requiring continuous weight updating in online training,a flash-based computing-in-memory with high endurance(10^(9) cycles)and ultrafast programming speed is investigated.On the one hand,the proposed programming scheme of channel hot electron injection(CHEI)and hot hole injection(HHI)demonstrate high linearity,symmetric potentiation,and a depression process,which help to improve the training speed and accuracy.On the other hand,the low-damage programming scheme and memory window(MW)optimizations can suppress cell degradation effectively with improved computing accuracy.Even after 109 cycles,the leakage current(I_(off))of cells remains sub-10pA,ensuring the large-scale computing ability of memory.Further characterizations are done on read disturb to demonstrate its robust reliabilities.By processing CIFAR-10 tasks,it is evident that~90%accuracy can be achieved after 109 cycles in both ResNet50 and VGG16 NN.Our results suggest that flash-based CIM has great potential to overcome the limitations of traditional Von Neumann architectures and enable high-performance NN online training,which pave the way for further development of artificial intelligence(AI)accelerators.
基金The work was supported by Humanities and Social Sciences Fund of the Ministry of Education(No.22YJA630119)the National Natural Science Foundation of China(No.71971051)Natural Science Foundation of Hebei Province(No.G2021501004).
文摘With the development of big data and social computing,large-scale group decisionmaking(LGDM)is nowmerging with social networks.Using social network analysis(SNA),this study proposes an LGDM consensus model that considers the trust relationship among decisionmakers(DMs).In the process of consensusmeasurement:the social network is constructed according to the social relationship among DMs,and the Louvain method is introduced to classify social networks to form subgroups.In this study,the weights of each decision maker and each subgroup are computed by comprehensive network weights and trust weights.In the process of consensus improvement:A feedback mechanism with four identification and two direction rules is designed to guide the consensus of the improvement process.Based on the trust relationship among DMs,the preferences are modified,and the corresponding social network is updated to accelerate the consensus.Compared with the previous research,the proposedmodel not only allows the subgroups to be reconstructed and updated during the adjustment process,but also improves the accuracy of the adjustment by the feedbackmechanism.Finally,an example analysis is conducted to verify the effectiveness and flexibility of the proposed method.Moreover,compared with previous studies,the superiority of the proposed method in solving the LGDM problem is highlighted.
基金the National Key Research and Devecopment Program of China(No.2022YFB4501601)the National Natural Science Foundation of China(No.62102398,U20A20227,62222214,62002338,U22A2028,U19B2019)+1 种基金the Chinese Academy of Sciences Project for Young Scientists in Basic Research(YSBR-029)Youth Innovation Promotion Association Chinese Academy of Sciences。
文摘Quantized training has been proven to be a prominent method to achieve deep neural network training under limited computational resources.It uses low bit-width arithmetics with a proper scaling factor to achieve negligible accuracy loss.Cambricon-Q is the ASIC design proposed to efficiently support quantized training,and achieves significant performance improvement.However,there are still two caveats in the design.First,Cambricon-Q with different hardware specifications may lead to different numerical errors,resulting in non-reproducible behaviors which may become a major concern in critical applications.Second,Cambricon-Q cannot leverage data sparsity,where considerable cycles could still be squeezed out.To address the caveats,the acceleration core of Cambricon-Q is redesigned to support fine-grained irregular data processing.The new design not only enables acceleration on sparse data,but also enables performing local dynamic quantization by contiguous value ranges(which is hardware independent),instead of contiguous addresses(which is dependent on hardware factors).Experimental results show that the accuracy loss of the method still keeps negligible,and the accelerator achieves 1.61×performance improvement over Cambricon-Q,with about 10%energy increase.
基金Supported by research grants from the National Key Research and Development Program of China(No.2020YFE0204400)the National Natural Science Foundation of China(No.82271042+1 种基金No.52203191)the Zhejiang Province Key Research and Development Program(No.2023C03090).
文摘●AIM:To determine the teaching effects of a real-time three dimensional(3D)visualization system in the operating room for early-stage phacoemulsification training.●METHODS:A total of 10 ophthalmology residents of the first-year postgraduate were included.All the residents were novices to cataract surgery.Real-time cataract surgical observations were performed using a custom-built 3D visualization system.The training lasted 4wk(32h)in all.A modified International Council of Ophthalmology’s Ophthalmology Surgical Competency Assessment Rubric(ICO-OSCAR)containing 4 specific steps of cataract surgery was applied.The self-assessment(self)and expert-assessment(expert)were performed through the microsurgical attempts in the wet lab for each participant.●RESULTS:Compared with pre-training assessments(self 3.2±0.8,expert 2.5±0.6),the overall mean scores of posttraining(self 5.2±0.4,expert 4.7±0.6)were significantly improved after real-time observation training of 3D visualization system(P<0.05).Scores of 4 surgical items were significantly improved both self and expert assessment after training(P<0.05).●CONCLUSION:The 3D observation training provides novice ophthalmic residents with a better understanding of intraocular microsurgical techniques.It is a useful tool to improve teaching efficiency of surgical education.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.62276229 and 32071096).
文摘The human brain is highly plastic.Cognitive training is usually used to modify functional connectivity of brain networks.Moreover,the structures of brain networks may determine its dynamic behavior which is related to human cognitive abilities.To study the effect of functional connectivity on the brain dynamics,the dynamic model based on functional connections of the brain and the Hindmarsh–Rose model is utilized in this work.The resting-state fMRI data from the experimental group undergoing abacus-based mental calculation(AMC)training and from the control group are used to construct the functional brain networks.The dynamic behavior of brain at the resting and task states for the AMC group and the control group are simulated with the above-mentioned dynamic model.In the resting state,there are the differences of brain activation between the AMC group and the control group,and more brain regions are inspired in the AMC group.A stimulus with sinusoidal signals to brain networks is introduced to simulate the brain dynamics in the task states.The dynamic characteristics are extracted by the excitation rates,the response intensities and the state distributions.The change in the functional connectivity of brain networks with the AMC training would in turn improve the brain response to external stimulus,and make the brain more efficient in processing tasks.
基金supportted by Natural Science Foundation of Jiangsu Province(No.BK20230696).
文摘Electric power training is essential for ensuring the safety and reliability of the system.In this study,we introduce a novel Abnormal Action Recognition(AAR)system that utilizes a Lightweight Pose Estimation Network(LPEN)to efficiently and effectively detect abnormal fall-down and trespass incidents in electric power training scenarios.The LPEN network,comprising three stages—MobileNet,Initial Stage,and Refinement Stage—is employed to swiftly extract image features,detect human key points,and refine them for accurate analysis.Subsequently,a Pose-aware Action Analysis Module(PAAM)captures the positional coordinates of human skeletal points in each frame.Finally,an Abnormal Action Inference Module(AAIM)evaluates whether abnormal fall-down or unauthorized trespass behavior is occurring.For fall-down recognition,three criteria—falling speed,main angles of skeletal points,and the person’s bounding box—are considered.To identify unauthorized trespass,emphasis is placed on the position of the ankles.Extensive experiments validate the effectiveness and efficiency of the proposed system in ensuring the safety and reliability of electric power training.