Brain lesions,such as those caused by stroke or traumatic brain injury(TBI),frequently result in persistent motor and cognitive impairments that significantly affect the individual patient's quality of life.Despit...Brain lesions,such as those caused by stroke or traumatic brain injury(TBI),frequently result in persistent motor and cognitive impairments that significantly affect the individual patient's quality of life.Despite differences in the mechanisms of injury,both conditions share a high prevalence of motor and cognitive impairments.These deficits show only limited natural recovery.展开更多
Central Asia is characterized by an arid climate and widespread desert distribution,with its sustainable development severely constrained by dust events.An objective understanding of the spatiotemporal patterns and dr...Central Asia is characterized by an arid climate and widespread desert distribution,with its sustainable development severely constrained by dust events.An objective understanding of the spatiotemporal patterns and driving forces of dust weather is highly important in this area.Based on the meteorological observations from 2000 to 2020,we examined the spatiotemporal characteristics of dust weather in the five Central Asian countries(Kazakhstan,Uzbekistan,Kyrgyzstan,Turkmenistan,and Tajikistan)via Theil-Sen trend analysis and Geodetector modeling method,quantitatively revealing the influence of environmental factors,such as temperature,precipitation,and vegetation,on the frequency of dust weather.The results showed that:(1)dust weather in Central Asia was mainly distributed in a large''dust belt''extending from west to east from northern part of the Caspian lowland desert,and concentrated in basins,plains,and other low-altitude areas.Strong dust weather mainly occurred in northern areas of the Aral Sea and southern edge of Central Asia,with a maximum annual frequency of 21.9%;(2)strong dust weather in Central Asia has fluctuated and slightly decreased since 2001.The highest frequency(1.1%)occurred in spring(from March to June);(3)from 2000 to 2020,changes such as spot shifting and shrinking occurred in the four main source areas(north of the Aral Sea,Kyzylkum Desert,Karakum Desert,and Garabogazköl Bay region),where sandstorms occurred in Central Asia,and northern Caspian lowland desert became the most important low-emission dust source in Central Asia;and(4)the combined effect of soil moisture and air temperature has the most significant influence on dust weather in Central Asia.This study provides a theoretical basis for sand prevention and sand control in Central Asia.In the future,Central Asia should focus on the rational utilization of land and water resources,and implement human interventions such as vegetation restoration and optimization of irrigation methods to curb further desertification in this area.展开更多
End-to-end Temporal Action Detection(TAD)has achieved remarkable progress in recent years,driven by innovations in model architectures and the emergence of Video Foundation Models(VFMs).However,existing TAD methods th...End-to-end Temporal Action Detection(TAD)has achieved remarkable progress in recent years,driven by innovations in model architectures and the emergence of Video Foundation Models(VFMs).However,existing TAD methods that perform full fine-tuning of pretrained video models often incur substantial computational costs,which become particularly pronounced when processing long video sequences.Moreover,the need for precise temporal boundary annotations makes data labeling extremely expensive.In low-resource settings where annotated samples are scarce,direct fine-tuning tends to cause overfitting.To address these challenges,we introduce Dynamic LowRank Adapter(DyLoRA),a lightweight fine-tuning framework tailored specifically for the TAD task.Built upon the Low-Rank Adaptation(LoRA)architecture,DyLoRA adapts only the key layers of the pretrained model via low-rank decomposition,reducing the number of trainable parameters to less than 5%of full fine-tuning methods.This significantly lowers memory consumption and mitigates overfitting in low-resource settings.Notably,DyLoRA enhances the temporal modeling capability of pretrained models by optimizing temporal dimension weights,thereby alleviating the representation misalignment of temporal features.Experimental results demonstrate that DyLoRA-TAD achieves impressive performance,with 73.9%mAP on THUMOS14,39.52%on ActivityNet-1.3,and 28.2%on Charades,substantially surpassing the best traditional feature-based methods.展开更多
Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The prese...Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The present article outlines the TransCarbonNet,a novel hybrid deep learning framework with self-attention characteristics added to the bidirectional Long Short-Term Memory(Bi-LSTM)network to forecast the carbon intensity of the grid several days.The proposed temporal fusion model not only learns the local temporal interactions but also the long-term patterns of the carbon emission data;hence,it is able to give suitable forecasts over a period of seven days.TransCarbonNet takes advantage of a multi-head self-attention element to identify significant temporal connections,which means the Bi-LSTM element calculates sequential dependencies in both directions.Massive tests on two actual data sets indicate much improved results in comparison with the existing results,with mean relative errors of 15.3 percent and 12.7 percent,respectively.The framework has given explicable weights of attention that reveal critical periods that influence carbon intensity alterations,and informed decisions on the management of carbon sustainability.The effectiveness of the proposed solution has been validated in numerous cases of operations,and TransCarbonNet is established to be an effective tool when it comes to carbon-friendly optimization of the grid.展开更多
Accurate precipitation estimation in semiarid,topographically complicated areas is critical for water resource management and climate risk monitoring.This work provides a detailed,multi-scale evaluation of four major ...Accurate precipitation estimation in semiarid,topographically complicated areas is critical for water resource management and climate risk monitoring.This work provides a detailed,multi-scale evaluation of four major satellite precipitation products(CHIRPS,PERSIANN-CDR,IMERG-F v07,and GSMaP)over Isfahan province,Iran,over a 9-year period(2015-2023).The performance of these products was benchmarked against a dense network of 98 rain gauges using a suite of continuous and categorical statistical metrics,following a two-stage quality control protocol to remove outliers and false alarms.The results revealed that the performance of all products improves with temporal aggregation.At the daily level,GSMaP performed marginally better,although all products were linked with considerable uncertainty.At the monthly and annual levels,the GPM-era products(IMERG and GSMaP)clearly beat the other two,establishing themselves as dependable tools for long-term hydro-climatological studies.Error analysis revealed that topography is the dominant regulating factor,creating a systematic elevationdependent bias,largely characterized by underestimation from most products in high-elevation areas,though the PERSIANN-CDR product exhibited a contrasting overestimation tendency.Finally,the findings highlight the importance of implementing local,elevation-dependent calibration before deploying these products in hydrological modeling.展开更多
The latitudinal diversity gradient(LDG)is one of the most notable biodiversity patterns in biogeography.The metabolic theory of ecology(MTE)explains ecological patterns,including the LDG.However,little is known about ...The latitudinal diversity gradient(LDG)is one of the most notable biodiversity patterns in biogeography.The metabolic theory of ecology(MTE)explains ecological patterns,including the LDG.However,little is known about whether the LDG remains stable over time as climate warming progresses and whether MTE remains applicable to clarify this pattern.In this study,forest data spanning temperate,subtropical,and tropical zones across China were used to analyze long-term changes in the LDG of tree species over 2005-2020.Based on the MTE framework,spatial scales were considered to assess temperature dependence of typical forest trees species.Our results show that species richness decreased with increasing latitude,and that temperature was the primary driver of this change.Although temperature in China has significantly increased over the past two decades,the LDG of tree species has remained stable.However,there was a decrease in species richness in tropical regions over time.With predictions of the MTE,the logarithm of typical forest tree species richness exhibited negative linear relationships with the inverse of ambient temperature,indicating temperature dependence of species richness.However,the relationship remained stable and was strongly influenced by spatial scale,intensifying as spatial scale increased.The findings emphasize the important role of temperature in shaping the LDG.The effects of spatial scale,in particular,should be considered when biodiversity management plans are developed for future climate change.展开更多
Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating In...Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating Interactive Dynamic Graph Convolution Network(IDGCN)with Temporal Multi-Head Trend-Aware Attention.Its core innovation lies in IDGCN,which uniquely splits sequences into symmetric intervals for interactive feature sharing via dynamic graphs,and a novel attention mechanism incorporating convolutional operations to capture essential local traffic trends—addressing a critical gap in standard attention for continuous data.For 15-and 60-min forecasting on METR-LA,AIDGCN achieves MAEs of 0.75%and 0.39%,and RMSEs of 1.32%and 0.14%,respectively.In the 60-min long-term forecasting of the PEMS-BAY dataset,the AIDGCN out-performs the MRA-BGCN method by 6.28%,4.93%,and 7.17%in terms of MAE,RMSE,and MAPE,respectively.Experimental results demonstrate the superiority of our pro-posed model over state-of-the-art methods.展开更多
With the increasing complexity of industrial automation,planetary gearboxes play a vital role in largescale equipment transmission systems,directly impacting operational efficiency and safety.Traditional maintenance s...With the increasing complexity of industrial automation,planetary gearboxes play a vital role in largescale equipment transmission systems,directly impacting operational efficiency and safety.Traditional maintenance strategies often struggle to accurately predict the degradation process of equipment,leading to excessive maintenance costs or potential failure risks.However,existing prediction methods based on statistical models are difficult to adapt to nonlinear degradation processes.To address these challenges,this study proposes a novel condition-based maintenance framework for planetary gearboxes.A comprehensive full-lifecycle degradation experiment was conducted to collect raw vibration signals,which were then processed using a temporal convolutional network autoencoder with multi-scale perception capability to extract deep temporal degradation features,enabling the collaborative extraction of longperiod meshing frequencies and short-term impact features from the vibration signals.Kernel principal component analysis was employed to fuse and normalize these features,enhancing the characterization of degradation progression.A nonlinear Wiener process was used to model the degradation trajectory,with a threshold decay function introduced to dynamically adjust maintenance strategies,and model parameters optimized through maximum likelihood estimation.Meanwhile,the maintenance strategy was optimized to minimize costs per unit time,determining the optimal maintenance timing and preventive maintenance threshold.The comprehensive indicator of degradation trends extracted by this method reaches 0.756,which is 41.2%higher than that of traditional time-domain features;the dynamic threshold strategy reduces the maintenance cost per unit time to 55.56,which is 8.9%better than that of the static threshold optimization.Experimental results demonstrate significant reductions in maintenance costs while enhancing system reliability and safety.This study realizes the organic integration of deep learning and reliability theory in the maintenance of planetary gearboxes,provides an interpretable solution for the predictive maintenance of complex mechanical systems,and promotes the development of condition-based maintenance strategies for planetary gearboxes.展开更多
High-precision optical frequency measurement serves as a cornerstone of modern science and technology,enabling advancements in fields ranging from fundamental physics to quantum information technologies.Obtaining prec...High-precision optical frequency measurement serves as a cornerstone of modern science and technology,enabling advancements in fields ranging from fundamental physics to quantum information technologies.Obtaining precise photon frequencies,especially in the ultraviolet or even extreme ultraviolet regimes,is a key goal in both light–matter interaction experiments and engineering applications.High-order harmonic generation(HHG)is an ideal light source for producing such photons.In this work,we propose an optical temporal interference model(OTIM)that establishes an analogy with multi-slit Fraunhofer diffraction(MSFD)to manipulate fine-frequency photon generation by exploiting the temporal coherence of HHG processes.Our model provides a unified physical framework for three distinct non-integer HHG generation schemes:single-pulse,shaped-pulse,and laser pulse train approaches,which correspond to single-MSFD-like,double-MSFD-like,and multi-MSFD-like processes,respectively.Arbitrary non-integer HHG photons can be obtained using our scheme.Our approach provides a new perspective for accurately measuring and controlling photon frequencies in fields such as frequency comb technology,interferometry,and atomic clocks.展开更多
Research on human motion prediction has made significant progress due to its importance in the development of various artificial intelligence applications.However,effectively capturing spatio-temporal features for smo...Research on human motion prediction has made significant progress due to its importance in the development of various artificial intelligence applications.However,effectively capturing spatio-temporal features for smoother and more precise human motion prediction remains a challenge.To address these issues,a robust human motion prediction method via integration of spatial and temporal cues(RISTC)has been proposed.This method captures sufficient spatio-temporal correlation of the observable sequence of human poses by utilizing the spatio-temporal mixed feature extractor(MFE).In multi-layer MFEs,the channel-graph united attention blocks extract the augmented spatial features of the human poses in the channel and spatial dimension.Additionally,multi-scale temporal blocks have been designed to effectively capture complicated and highly dynamic temporal information.Our experiments on the Human3.6M and Carnegie Mellon University motion capture(CMU Mocap)datasets show that the proposed network yields higher prediction accuracy than the state-of-the-art methods.展开更多
This study examined the influence of the built environment surrounding rail stations on rail transit ridership and its spatiotemporal variations,aiming to enhance rail transit operational efficiency and inform station...This study examined the influence of the built environment surrounding rail stations on rail transit ridership and its spatiotemporal variations,aiming to enhance rail transit operational efficiency and inform station planning and development.Data from 159 metro stations in Nanjing,collected over a 14-d period,were analyzed to identify changes in weekday and weekend ridership patterns.The analysis included explanatory variables grouped into three categories:urban spatial variables,socioeconomic vari-ables,and transit service variables.A geographically and temporally weighted regression(GTWR)model was developed,and its performance was compared with that of ordinary least squares(OLS)and geographically weighted regression(GWR)models.The results demonstrated that the GTWR model outperformed others in analyzing the relationship between rail transit ridership and the built environment.In addition,the coefficients of explanatory variables showed significant variation across spatiotemporal dimensions,revealing distinct patterns.Notably,the influence of commuter flows led to more pronounced temporal heterogeneity in the coefficients observed on weekdays.These findings offer valuable insights for optimizing urban public transportation systems and advancing integrated urban rail development.展开更多
The Yellow River Basin in Sichuan Province(YRS)is undergoing severe soil erosion and exacerbated ecological vulnerability,which collectively pose formidable challenges for regional water conservation(WC)and sustainabl...The Yellow River Basin in Sichuan Province(YRS)is undergoing severe soil erosion and exacerbated ecological vulnerability,which collectively pose formidable challenges for regional water conservation(WC)and sustainable development.While effectively enhancing WC necessitates a comprehensive understanding of its driving factors and corresponding intervention strategies,existing studies have largely neglected the spatiotemporal heterogeneity of both natural and socio-economic drivers.Therefore,this study explored the spatiotemporal heterogeneity of WC drivers in YRS using multi-scale geographically weighted regression(MGWR)and geographically and temporally weighted regression(GTWR)models from an eco-hydrological perspective.We discovered that downstream regions,which are more developed,achieved significantly better WC than upstream regions.The results also demonstrated that the influence of temperature and wind speed is consistently dominant and temporally stable due to climate stability,while the influence of vegetation shifted from negative to positive around 2010,likely indicating greater benefits from understory vegetation.Economic growth positively impacted WC in upstream regions but had a negative effect in the more developed downstream regions.These findings highlight the importance of targeted water conservation strategies,including locally appropriate revegetation,optimization of agricultural and economic structures,and the establishment of eco-compensation mechanisms for ecological conservation and sustainable development.展开更多
The optical chirality of vortex structured light has attracted more and more attention in recent years due to its fascinating properties and wide potential applications.Such an issue is typically studied in a spatial ...The optical chirality of vortex structured light has attracted more and more attention in recent years due to its fascinating properties and wide potential applications.Such an issue is typically studied in a spatial medium.This work is devoted to the study of the optical chirality of vortex structured light in the temporal medium with timevarying permittivity.A full vector theoretical model is developed to describe the optical chirality of LaguerreGaussian(LG)vortex light beams that undergo the temporal reflection and transmission.展开更多
Action recognition,a fundamental task in the field of video understanding,has been extensively researched and applied.In contrast to an image,a video introduces an extra temporal dimension.However,many existing action...Action recognition,a fundamental task in the field of video understanding,has been extensively researched and applied.In contrast to an image,a video introduces an extra temporal dimension.However,many existing action recognition networks either perform simple temporal fusion through averaging or rely on pre-trained models from image recognition,resulting in limited temporal information extraction capabilities.This work proposes a highly efficient temporal decoding module that can be seamlessly integrated into any action recognition backbone network to enhance the focus on temporal relationships between video frames.Firstly,the decoder initializes a set of learnable queries,termed video-level action category prediction queries.Then,they are combined with the video frame features extracted by the backbone network after self-attention learning to extract video context information.Finally,these prediction queries with rich temporal features are used for category prediction.Experimental results on HMDB51,MSRDailyAct3D,Diving48 and Breakfast datasets show that using TokShift-Transformer and VideoMAE as encoders results in a significant improvement in Top-1 accuracy compared to the original models(TokShift-Transformer and VideoMAE),after introducing the proposed temporal decoder.The introduction of the temporal decoder results in an average performance increase exceeding 11%for TokShift-Transformer and nearly 5%for VideoMAE across the four datasets.Furthermore,the work explores the combination of the decoder with various action recognition networks,including Timesformer,as encoders.This results in an average accuracy improvement of more than 3.5%on the HMDB51 dataset.The code is available at https://github.com/huangturbo/TempDecoder.展开更多
The online version of the original article can be found at:https://www.sciopen.com/article/10.26599/JOTO.2025.9540018 Erratum to Journal of Otology,2025,20(2):123-126.https://doi.org/10.26599/JOTO.2025.9540018 The sur...The online version of the original article can be found at:https://www.sciopen.com/article/10.26599/JOTO.2025.9540018 Erratum to Journal of Otology,2025,20(2):123-126.https://doi.org/10.26599/JOTO.2025.9540018 The surnames and given names of these authors are reversed:Saro-Buendía Miguel,Andresen-Lorca Belén,Pérez-García Alberto,Llópez Carratala Nacho,Carreres Polo Joan,Armengot Carceller Miguel,Perolada Valmaña Jose María.It should be Miguel Saro-Buendía,Belén Andresen-Lorca,Alberto Pérez-García,Nacho Llópez Carratala,Joan Carreres Polo,Miguel Armengot Carceller,Jose María Perolada Valmaña.展开更多
Osteoradionecrosis of the temporal bone(ORN-TB)is usually controlled with conservative measures.However,a temporal bone resection may be required in unresponsive cases.The reconstruction of the resulting defects may b...Osteoradionecrosis of the temporal bone(ORN-TB)is usually controlled with conservative measures.However,a temporal bone resection may be required in unresponsive cases.The reconstruction of the resulting defects may be challenging because of the radiation damage to regional tissues.As a result,distant free flaps may be an optimal choice.For instance,the gracilis muscular free flap(GMFF)has consistent vascular anatomy and can be used to reconstruct small defects.We report three cases of uncontrolled ORN-TB requiring an extensive temporal bone resection followed by vascularized obliteration with a GMFF.The patients reported complete control of the main otologic symptoms(otorrhea,otalgia,and aural fullness)and optimal functional and aesthetic outcomes.Finally,the patients reported significant improvement in quality of life despite early postoperative complications.To our knowledge,the GMFF had not been used to obliterate temporal bone defects in patients with ORN-TB.展开更多
Systemic steroid treatment can modify the histological features of a temporal artery biopsy,leading to debate about the value of performing the biopsy after 2 weeks of steroid use.The aim of this study was to examine ...Systemic steroid treatment can modify the histological features of a temporal artery biopsy,leading to debate about the value of performing the biopsy after 2 weeks of steroid use.The aim of this study was to examine the results of temporal artery biopsies in patients who have been on systemic steroids for over two weeks.In this observational study,a retrospective review of patients who underwent temporal artery biopsy between January 2018 and October 2023 at Royal Shrewsbury Hospital was performed,with scrutiny of the histology reports for features of giant cell arteritis.Patients who were on systemic steroids for more than 2 weeks at the time of performing the temporal artery biopsy were studied with histological evaluation of temporal artery biopsy specimens was performed by consultant histopathologists experienced in vasculitis diagnosis.Descriptive statistics were used for data analysis.A total of 60 patients were identified to have signs in keeping with or suggestive of giant cell arteritis on histological examination of temporal artery specimens.Mean duration of steroid treatment before performing the temporal artery biopsy was 2.7 weeks(range,0 days to 13 weeks).Nineteen(31%)patients had received more than 2 weeks of steroid treatment at the time of temporal biopsy.In our study,histological features in temporal artery biopsy specimens from patients who had received more than 2 weeks of steroid therapy showed similarities to classical features noted in untreated patients,but with some differences,such as a milder and patchier inflammatory cell infiltrate,fewer histiocytes,and residual scarring.Therefore,in patients posing a diagnostic dilemma due to equivocal clinical features,a temporal artery biopsy can still be considered,even if they have been on long-term steroids,if the treating clinicians feel that it will aid the diagnosis and management.展开更多
Temporal optics,which enables lossless manipulation of ultrafast pulses,offers a new dimension for the regulation of quantum optical fields.In this paper,we established a temporal Fourier transform(TF)system based on ...Temporal optics,which enables lossless manipulation of ultrafast pulses,offers a new dimension for the regulation of quantum optical fields.In this paper,we established a temporal Fourier transform(TF)system based on a four-wave mixing(FWM)time lens and constructed a full quantum theoretical model for the resulting temporal SU(1,1)interferometer.This interferometer has high temporal resolution,can impose interference in both time and frequency domains,and is sensitive to the phase derivative.By introducing linear time-varying phase modulation,we achieved sub-picosecond precision in temporal autocorrelation measurements and generatedan optical frequency comb with a fixed interval based on a feedback iteration mechanism.Theoretical analysis revealsthe crucial regulatory role of time-frequency coupling in quantum interference,providing novel solutions for ultrafast quantum imaging,temporal mode encoding,and the generation of optical frequency quantization.展开更多
Background Lip reading uses lip images for visual speech recognition.Deep-learning-based lip reading has greatly improved performance in current datasets;however,most existing research ignores the significance of shor...Background Lip reading uses lip images for visual speech recognition.Deep-learning-based lip reading has greatly improved performance in current datasets;however,most existing research ignores the significance of short-term temporal dependencies of lip-shape variations between adjacent frames,which leaves space for further improvement in feature extraction.Methods This article presents a spatiotemporal feature fusion network(STDNet)that compensates for the deficiencies of current lip-reading approaches in short-term temporal dependency modeling.Specifically,to distinguish more similar and intricate content,STDNet adds a temporal feature extraction branch based on a 3D-CNN,which enhances the learning of dynamic lip movements in adjacent frames while not affecting spatial feature extraction.In particular,we designed a local–temporal block,which aggregates interframe differences,strengthening the relationship between various local lip regions through multiscale convolution.We incorporated the squeeze-and-excitation mechanism into the Global-Temporal Block,which processes a single frame as an independent unitto learn temporal variations across the entire lip region more effectively.Furthermore,attention pooling was introduced to highlight meaningful frames containing key semantic information for the target word.Results Experimental results demonstrated STDNet's superior performance on the LRW and LRW-1000,achieving word-level recognition accuracies of 90.2% and 53.56%,respectively.Extensive ablation experiments verified the rationality and effectiveness of its modules.Conclusions The proposed model effectively addresses short-term temporal dependency limitations in lip reading,and improves the temporal robustness of the model against variable-length sequences.These advancements validate the importance of explicit short-term dynamics modeling for practical lip-reading systems.展开更多
As the demand for advanced computational systems capable of handling large data volumes rises,nano-electronic devices,such as memristors,are being developed for efficient data processing,especially in reservoir comput...As the demand for advanced computational systems capable of handling large data volumes rises,nano-electronic devices,such as memristors,are being developed for efficient data processing,especially in reservoir computing(RC).RC enables the processing of temporal information with minimal training costs,making it a promising approach for neuromorphic computing.However,current memristor devices of-ten suffer from limitations in dynamic conductance and temporal behavior,which affects their perfor-mance in these applications.In this study,we present a multilayered indium-tin-oxide(ITO)/ZnO/indium-gallium-zinc oxide(IGZO)/ZnO/ITO memristor fabricated via radiofrequency sputtering to explore its fil-amentary and nonfilamentary resistive switching(RS)characteristics.High-resolution transmission elec-tron microscopy confirmed the polycrystalline structure of the ZnO/IGZO/ZnO active layer.Dual-switching modes were demonstrated by controlling the current compliance(I_(CC)).In the filamentary mode,the memristor exhibited a large memory window(10^(3)),low-operating voltages(±2 V),excellent cycle-to-cycle stability,and multilevel switching with controlled reset-stop voltages,making it suitable for high-density memory applications.Nonfilamentary switching demonstrated stable on/off ratios above 10,en-durance up to 102 cycles,and retention suited for short-term memory.Key synaptic behaviors,such as paired-pulse facilitation(PPF),post-tetanic potentiation(PTP),and spike-rate dependent plasticity(SRDP)were successfully emulated by modulating pulse amplitude,width,and interval.Experience-dependent plasticity(EDP)was also demonstrated,further replicating biological synaptic functions.These tempo-ral properties were utilized to develop a 4-bit reservoir computing system with 16 distinct conductance states,enabling efficient information encoding.For image recognition tasks,convolutional neural net-work(CNN)simulations achieved a high accuracy of 98.45%after 25 training epochs,outperforming the accuracy achieved following artificial neural network(ANN)simulations(87.79%).These findings demon-strate that the multilayered memristor exhibits high performance in neuromorphic systems,particularly for complex pattern recognition tasks,such as digit and letter classification.展开更多
基金supported by the Defitech Foundation(Morges,CH)to FCHthe Bertarelli Foundation-Catalyst program(Gstaad,CH)to FCH+2 种基金the Wyss Center for Bio and Neuroengineering the Lighthouse Partnership for AI-guided Neuromodulation to FCHthe Fonds de recherche du Quebec-Sante(FRQS#342969)to CEPthe Neuro X Postdoctoral Fellowship Program to CEP。
文摘Brain lesions,such as those caused by stroke or traumatic brain injury(TBI),frequently result in persistent motor and cognitive impairments that significantly affect the individual patient's quality of life.Despite differences in the mechanisms of injury,both conditions share a high prevalence of motor and cognitive impairments.These deficits show only limited natural recovery.
基金funded by the National Natural Science Foundation of China(42571311).
文摘Central Asia is characterized by an arid climate and widespread desert distribution,with its sustainable development severely constrained by dust events.An objective understanding of the spatiotemporal patterns and driving forces of dust weather is highly important in this area.Based on the meteorological observations from 2000 to 2020,we examined the spatiotemporal characteristics of dust weather in the five Central Asian countries(Kazakhstan,Uzbekistan,Kyrgyzstan,Turkmenistan,and Tajikistan)via Theil-Sen trend analysis and Geodetector modeling method,quantitatively revealing the influence of environmental factors,such as temperature,precipitation,and vegetation,on the frequency of dust weather.The results showed that:(1)dust weather in Central Asia was mainly distributed in a large''dust belt''extending from west to east from northern part of the Caspian lowland desert,and concentrated in basins,plains,and other low-altitude areas.Strong dust weather mainly occurred in northern areas of the Aral Sea and southern edge of Central Asia,with a maximum annual frequency of 21.9%;(2)strong dust weather in Central Asia has fluctuated and slightly decreased since 2001.The highest frequency(1.1%)occurred in spring(from March to June);(3)from 2000 to 2020,changes such as spot shifting and shrinking occurred in the four main source areas(north of the Aral Sea,Kyzylkum Desert,Karakum Desert,and Garabogazköl Bay region),where sandstorms occurred in Central Asia,and northern Caspian lowland desert became the most important low-emission dust source in Central Asia;and(4)the combined effect of soil moisture and air temperature has the most significant influence on dust weather in Central Asia.This study provides a theoretical basis for sand prevention and sand control in Central Asia.In the future,Central Asia should focus on the rational utilization of land and water resources,and implement human interventions such as vegetation restoration and optimization of irrigation methods to curb further desertification in this area.
基金supported by the National Natural Science Foundation of China(Grant No.62266054)the Major Science and Technology Project of Yunnan Province(Grant No.202402AD080002)the Scientific Research Fund of the Yunnan Provincial Department of Education(Grant No.2025Y0302).
文摘End-to-end Temporal Action Detection(TAD)has achieved remarkable progress in recent years,driven by innovations in model architectures and the emergence of Video Foundation Models(VFMs).However,existing TAD methods that perform full fine-tuning of pretrained video models often incur substantial computational costs,which become particularly pronounced when processing long video sequences.Moreover,the need for precise temporal boundary annotations makes data labeling extremely expensive.In low-resource settings where annotated samples are scarce,direct fine-tuning tends to cause overfitting.To address these challenges,we introduce Dynamic LowRank Adapter(DyLoRA),a lightweight fine-tuning framework tailored specifically for the TAD task.Built upon the Low-Rank Adaptation(LoRA)architecture,DyLoRA adapts only the key layers of the pretrained model via low-rank decomposition,reducing the number of trainable parameters to less than 5%of full fine-tuning methods.This significantly lowers memory consumption and mitigates overfitting in low-resource settings.Notably,DyLoRA enhances the temporal modeling capability of pretrained models by optimizing temporal dimension weights,thereby alleviating the representation misalignment of temporal features.Experimental results demonstrate that DyLoRA-TAD achieves impressive performance,with 73.9%mAP on THUMOS14,39.52%on ActivityNet-1.3,and 28.2%on Charades,substantially surpassing the best traditional feature-based methods.
基金funded by the Deanship of Scientific Research and Libraries at Princess Nourah bint Abdulrahman University,through the“Nafea”Program,Grant No.(NP-45-082).
文摘Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The present article outlines the TransCarbonNet,a novel hybrid deep learning framework with self-attention characteristics added to the bidirectional Long Short-Term Memory(Bi-LSTM)network to forecast the carbon intensity of the grid several days.The proposed temporal fusion model not only learns the local temporal interactions but also the long-term patterns of the carbon emission data;hence,it is able to give suitable forecasts over a period of seven days.TransCarbonNet takes advantage of a multi-head self-attention element to identify significant temporal connections,which means the Bi-LSTM element calculates sequential dependencies in both directions.Massive tests on two actual data sets indicate much improved results in comparison with the existing results,with mean relative errors of 15.3 percent and 12.7 percent,respectively.The framework has given explicable weights of attention that reveal critical periods that influence carbon intensity alterations,and informed decisions on the management of carbon sustainability.The effectiveness of the proposed solution has been validated in numerous cases of operations,and TransCarbonNet is established to be an effective tool when it comes to carbon-friendly optimization of the grid.
文摘Accurate precipitation estimation in semiarid,topographically complicated areas is critical for water resource management and climate risk monitoring.This work provides a detailed,multi-scale evaluation of four major satellite precipitation products(CHIRPS,PERSIANN-CDR,IMERG-F v07,and GSMaP)over Isfahan province,Iran,over a 9-year period(2015-2023).The performance of these products was benchmarked against a dense network of 98 rain gauges using a suite of continuous and categorical statistical metrics,following a two-stage quality control protocol to remove outliers and false alarms.The results revealed that the performance of all products improves with temporal aggregation.At the daily level,GSMaP performed marginally better,although all products were linked with considerable uncertainty.At the monthly and annual levels,the GPM-era products(IMERG and GSMaP)clearly beat the other two,establishing themselves as dependable tools for long-term hydro-climatological studies.Error analysis revealed that topography is the dominant regulating factor,creating a systematic elevationdependent bias,largely characterized by underestimation from most products in high-elevation areas,though the PERSIANN-CDR product exhibited a contrasting overestimation tendency.Finally,the findings highlight the importance of implementing local,elevation-dependent calibration before deploying these products in hydrological modeling.
基金supported by the Key Program of National Science of China(Grant No.:42030509 and 42141005)。
文摘The latitudinal diversity gradient(LDG)is one of the most notable biodiversity patterns in biogeography.The metabolic theory of ecology(MTE)explains ecological patterns,including the LDG.However,little is known about whether the LDG remains stable over time as climate warming progresses and whether MTE remains applicable to clarify this pattern.In this study,forest data spanning temperate,subtropical,and tropical zones across China were used to analyze long-term changes in the LDG of tree species over 2005-2020.Based on the MTE framework,spatial scales were considered to assess temperature dependence of typical forest trees species.Our results show that species richness decreased with increasing latitude,and that temperature was the primary driver of this change.Although temperature in China has significantly increased over the past two decades,the LDG of tree species has remained stable.However,there was a decrease in species richness in tropical regions over time.With predictions of the MTE,the logarithm of typical forest tree species richness exhibited negative linear relationships with the inverse of ambient temperature,indicating temperature dependence of species richness.However,the relationship remained stable and was strongly influenced by spatial scale,intensifying as spatial scale increased.The findings emphasize the important role of temperature in shaping the LDG.The effects of spatial scale,in particular,should be considered when biodiversity management plans are developed for future climate change.
文摘Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating Interactive Dynamic Graph Convolution Network(IDGCN)with Temporal Multi-Head Trend-Aware Attention.Its core innovation lies in IDGCN,which uniquely splits sequences into symmetric intervals for interactive feature sharing via dynamic graphs,and a novel attention mechanism incorporating convolutional operations to capture essential local traffic trends—addressing a critical gap in standard attention for continuous data.For 15-and 60-min forecasting on METR-LA,AIDGCN achieves MAEs of 0.75%and 0.39%,and RMSEs of 1.32%and 0.14%,respectively.In the 60-min long-term forecasting of the PEMS-BAY dataset,the AIDGCN out-performs the MRA-BGCN method by 6.28%,4.93%,and 7.17%in terms of MAE,RMSE,and MAPE,respectively.Experimental results demonstrate the superiority of our pro-posed model over state-of-the-art methods.
基金funded by scientific research projects under Grant JY2024B011.
文摘With the increasing complexity of industrial automation,planetary gearboxes play a vital role in largescale equipment transmission systems,directly impacting operational efficiency and safety.Traditional maintenance strategies often struggle to accurately predict the degradation process of equipment,leading to excessive maintenance costs or potential failure risks.However,existing prediction methods based on statistical models are difficult to adapt to nonlinear degradation processes.To address these challenges,this study proposes a novel condition-based maintenance framework for planetary gearboxes.A comprehensive full-lifecycle degradation experiment was conducted to collect raw vibration signals,which were then processed using a temporal convolutional network autoencoder with multi-scale perception capability to extract deep temporal degradation features,enabling the collaborative extraction of longperiod meshing frequencies and short-term impact features from the vibration signals.Kernel principal component analysis was employed to fuse and normalize these features,enhancing the characterization of degradation progression.A nonlinear Wiener process was used to model the degradation trajectory,with a threshold decay function introduced to dynamically adjust maintenance strategies,and model parameters optimized through maximum likelihood estimation.Meanwhile,the maintenance strategy was optimized to minimize costs per unit time,determining the optimal maintenance timing and preventive maintenance threshold.The comprehensive indicator of degradation trends extracted by this method reaches 0.756,which is 41.2%higher than that of traditional time-domain features;the dynamic threshold strategy reduces the maintenance cost per unit time to 55.56,which is 8.9%better than that of the static threshold optimization.Experimental results demonstrate significant reductions in maintenance costs while enhancing system reliability and safety.This study realizes the organic integration of deep learning and reliability theory in the maintenance of planetary gearboxes,provides an interpretable solution for the predictive maintenance of complex mechanical systems,and promotes the development of condition-based maintenance strategies for planetary gearboxes.
基金supported by the National Natural Science Foundation of China(Grant No.12304379)the Natural Science Foundation of Liaoning Province(Grant No.2024BS-269)the Guangdong Basic and Applied Basic Research Foundation(Grant No.025A1515011117)。
文摘High-precision optical frequency measurement serves as a cornerstone of modern science and technology,enabling advancements in fields ranging from fundamental physics to quantum information technologies.Obtaining precise photon frequencies,especially in the ultraviolet or even extreme ultraviolet regimes,is a key goal in both light–matter interaction experiments and engineering applications.High-order harmonic generation(HHG)is an ideal light source for producing such photons.In this work,we propose an optical temporal interference model(OTIM)that establishes an analogy with multi-slit Fraunhofer diffraction(MSFD)to manipulate fine-frequency photon generation by exploiting the temporal coherence of HHG processes.Our model provides a unified physical framework for three distinct non-integer HHG generation schemes:single-pulse,shaped-pulse,and laser pulse train approaches,which correspond to single-MSFD-like,double-MSFD-like,and multi-MSFD-like processes,respectively.Arbitrary non-integer HHG photons can be obtained using our scheme.Our approach provides a new perspective for accurately measuring and controlling photon frequencies in fields such as frequency comb technology,interferometry,and atomic clocks.
基金supported by the National Key R&D Program of China(No.2018YFB1305200)the Natural Science Foundation of Zhejiang Province(No.LGG21F030011)。
文摘Research on human motion prediction has made significant progress due to its importance in the development of various artificial intelligence applications.However,effectively capturing spatio-temporal features for smoother and more precise human motion prediction remains a challenge.To address these issues,a robust human motion prediction method via integration of spatial and temporal cues(RISTC)has been proposed.This method captures sufficient spatio-temporal correlation of the observable sequence of human poses by utilizing the spatio-temporal mixed feature extractor(MFE).In multi-layer MFEs,the channel-graph united attention blocks extract the augmented spatial features of the human poses in the channel and spatial dimension.Additionally,multi-scale temporal blocks have been designed to effectively capture complicated and highly dynamic temporal information.Our experiments on the Human3.6M and Carnegie Mellon University motion capture(CMU Mocap)datasets show that the proposed network yields higher prediction accuracy than the state-of-the-art methods.
基金The National Key Research and Development Program of China(No.2022YFC3800201).
文摘This study examined the influence of the built environment surrounding rail stations on rail transit ridership and its spatiotemporal variations,aiming to enhance rail transit operational efficiency and inform station planning and development.Data from 159 metro stations in Nanjing,collected over a 14-d period,were analyzed to identify changes in weekday and weekend ridership patterns.The analysis included explanatory variables grouped into three categories:urban spatial variables,socioeconomic vari-ables,and transit service variables.A geographically and temporally weighted regression(GTWR)model was developed,and its performance was compared with that of ordinary least squares(OLS)and geographically weighted regression(GWR)models.The results demonstrated that the GTWR model outperformed others in analyzing the relationship between rail transit ridership and the built environment.In addition,the coefficients of explanatory variables showed significant variation across spatiotemporal dimensions,revealing distinct patterns.Notably,the influence of commuter flows led to more pronounced temporal heterogeneity in the coefficients observed on weekdays.These findings offer valuable insights for optimizing urban public transportation systems and advancing integrated urban rail development.
基金supported by the funding provided by the State Key Laboratory of Hydraulics and Mountain River Engineering(SKHL2210)National Natural Science Foundation of China(42171304)+1 种基金the Sichuan Science and Technology Program(2023YFS0380)Natural Science Foundation of Jiangsu Province of China(BK20242018)。
文摘The Yellow River Basin in Sichuan Province(YRS)is undergoing severe soil erosion and exacerbated ecological vulnerability,which collectively pose formidable challenges for regional water conservation(WC)and sustainable development.While effectively enhancing WC necessitates a comprehensive understanding of its driving factors and corresponding intervention strategies,existing studies have largely neglected the spatiotemporal heterogeneity of both natural and socio-economic drivers.Therefore,this study explored the spatiotemporal heterogeneity of WC drivers in YRS using multi-scale geographically weighted regression(MGWR)and geographically and temporally weighted regression(GTWR)models from an eco-hydrological perspective.We discovered that downstream regions,which are more developed,achieved significantly better WC than upstream regions.The results also demonstrated that the influence of temperature and wind speed is consistently dominant and temporally stable due to climate stability,while the influence of vegetation shifted from negative to positive around 2010,likely indicating greater benefits from understory vegetation.Economic growth positively impacted WC in upstream regions but had a negative effect in the more developed downstream regions.These findings highlight the importance of targeted water conservation strategies,including locally appropriate revegetation,optimization of agricultural and economic structures,and the establishment of eco-compensation mechanisms for ecological conservation and sustainable development.
基金National Natural Science Foundation of China(12374273,12421005,92464205)Hunan Provincial Major Sci-Tech Program(2023ZJ1010)+2 种基金Key Laboratory Foundation of Complex Environment Optoelectronic Information Perception of Ministry of EducationFundamental Research Funds for the Central Universities(YJSJ25020)Innovation Fund of Xidian University。
文摘The optical chirality of vortex structured light has attracted more and more attention in recent years due to its fascinating properties and wide potential applications.Such an issue is typically studied in a spatial medium.This work is devoted to the study of the optical chirality of vortex structured light in the temporal medium with timevarying permittivity.A full vector theoretical model is developed to describe the optical chirality of LaguerreGaussian(LG)vortex light beams that undergo the temporal reflection and transmission.
基金Shanghai Municipal Commission of Economy and Information Technology,China (No.202301054)。
文摘Action recognition,a fundamental task in the field of video understanding,has been extensively researched and applied.In contrast to an image,a video introduces an extra temporal dimension.However,many existing action recognition networks either perform simple temporal fusion through averaging or rely on pre-trained models from image recognition,resulting in limited temporal information extraction capabilities.This work proposes a highly efficient temporal decoding module that can be seamlessly integrated into any action recognition backbone network to enhance the focus on temporal relationships between video frames.Firstly,the decoder initializes a set of learnable queries,termed video-level action category prediction queries.Then,they are combined with the video frame features extracted by the backbone network after self-attention learning to extract video context information.Finally,these prediction queries with rich temporal features are used for category prediction.Experimental results on HMDB51,MSRDailyAct3D,Diving48 and Breakfast datasets show that using TokShift-Transformer and VideoMAE as encoders results in a significant improvement in Top-1 accuracy compared to the original models(TokShift-Transformer and VideoMAE),after introducing the proposed temporal decoder.The introduction of the temporal decoder results in an average performance increase exceeding 11%for TokShift-Transformer and nearly 5%for VideoMAE across the four datasets.Furthermore,the work explores the combination of the decoder with various action recognition networks,including Timesformer,as encoders.This results in an average accuracy improvement of more than 3.5%on the HMDB51 dataset.The code is available at https://github.com/huangturbo/TempDecoder.
文摘The online version of the original article can be found at:https://www.sciopen.com/article/10.26599/JOTO.2025.9540018 Erratum to Journal of Otology,2025,20(2):123-126.https://doi.org/10.26599/JOTO.2025.9540018 The surnames and given names of these authors are reversed:Saro-Buendía Miguel,Andresen-Lorca Belén,Pérez-García Alberto,Llópez Carratala Nacho,Carreres Polo Joan,Armengot Carceller Miguel,Perolada Valmaña Jose María.It should be Miguel Saro-Buendía,Belén Andresen-Lorca,Alberto Pérez-García,Nacho Llópez Carratala,Joan Carreres Polo,Miguel Armengot Carceller,Jose María Perolada Valmaña.
文摘Osteoradionecrosis of the temporal bone(ORN-TB)is usually controlled with conservative measures.However,a temporal bone resection may be required in unresponsive cases.The reconstruction of the resulting defects may be challenging because of the radiation damage to regional tissues.As a result,distant free flaps may be an optimal choice.For instance,the gracilis muscular free flap(GMFF)has consistent vascular anatomy and can be used to reconstruct small defects.We report three cases of uncontrolled ORN-TB requiring an extensive temporal bone resection followed by vascularized obliteration with a GMFF.The patients reported complete control of the main otologic symptoms(otorrhea,otalgia,and aural fullness)and optimal functional and aesthetic outcomes.Finally,the patients reported significant improvement in quality of life despite early postoperative complications.To our knowledge,the GMFF had not been used to obliterate temporal bone defects in patients with ORN-TB.
文摘Systemic steroid treatment can modify the histological features of a temporal artery biopsy,leading to debate about the value of performing the biopsy after 2 weeks of steroid use.The aim of this study was to examine the results of temporal artery biopsies in patients who have been on systemic steroids for over two weeks.In this observational study,a retrospective review of patients who underwent temporal artery biopsy between January 2018 and October 2023 at Royal Shrewsbury Hospital was performed,with scrutiny of the histology reports for features of giant cell arteritis.Patients who were on systemic steroids for more than 2 weeks at the time of performing the temporal artery biopsy were studied with histological evaluation of temporal artery biopsy specimens was performed by consultant histopathologists experienced in vasculitis diagnosis.Descriptive statistics were used for data analysis.A total of 60 patients were identified to have signs in keeping with or suggestive of giant cell arteritis on histological examination of temporal artery specimens.Mean duration of steroid treatment before performing the temporal artery biopsy was 2.7 weeks(range,0 days to 13 weeks).Nineteen(31%)patients had received more than 2 weeks of steroid treatment at the time of temporal biopsy.In our study,histological features in temporal artery biopsy specimens from patients who had received more than 2 weeks of steroid therapy showed similarities to classical features noted in untreated patients,but with some differences,such as a milder and patchier inflammatory cell infiltrate,fewer histiocytes,and residual scarring.Therefore,in patients posing a diagnostic dilemma due to equivocal clinical features,a temporal artery biopsy can still be considered,even if they have been on long-term steroids,if the treating clinicians feel that it will aid the diagnosis and management.
文摘Temporal optics,which enables lossless manipulation of ultrafast pulses,offers a new dimension for the regulation of quantum optical fields.In this paper,we established a temporal Fourier transform(TF)system based on a four-wave mixing(FWM)time lens and constructed a full quantum theoretical model for the resulting temporal SU(1,1)interferometer.This interferometer has high temporal resolution,can impose interference in both time and frequency domains,and is sensitive to the phase derivative.By introducing linear time-varying phase modulation,we achieved sub-picosecond precision in temporal autocorrelation measurements and generatedan optical frequency comb with a fixed interval based on a feedback iteration mechanism.Theoretical analysis revealsthe crucial regulatory role of time-frequency coupling in quantum interference,providing novel solutions for ultrafast quantum imaging,temporal mode encoding,and the generation of optical frequency quantization.
基金Supported by the National Key Research and Development Program of China(2023YFC3306201)the National Natural Science Foundation of China(61772125)the Fundamental Research Funds for the Central Universities(N2317004).
文摘Background Lip reading uses lip images for visual speech recognition.Deep-learning-based lip reading has greatly improved performance in current datasets;however,most existing research ignores the significance of short-term temporal dependencies of lip-shape variations between adjacent frames,which leaves space for further improvement in feature extraction.Methods This article presents a spatiotemporal feature fusion network(STDNet)that compensates for the deficiencies of current lip-reading approaches in short-term temporal dependency modeling.Specifically,to distinguish more similar and intricate content,STDNet adds a temporal feature extraction branch based on a 3D-CNN,which enhances the learning of dynamic lip movements in adjacent frames while not affecting spatial feature extraction.In particular,we designed a local–temporal block,which aggregates interframe differences,strengthening the relationship between various local lip regions through multiscale convolution.We incorporated the squeeze-and-excitation mechanism into the Global-Temporal Block,which processes a single frame as an independent unitto learn temporal variations across the entire lip region more effectively.Furthermore,attention pooling was introduced to highlight meaningful frames containing key semantic information for the target word.Results Experimental results demonstrated STDNet's superior performance on the LRW and LRW-1000,achieving word-level recognition accuracies of 90.2% and 53.56%,respectively.Extensive ablation experiments verified the rationality and effectiveness of its modules.Conclusions The proposed model effectively addresses short-term temporal dependency limitations in lip reading,and improves the temporal robustness of the model against variable-length sequences.These advancements validate the importance of explicit short-term dynamics modeling for practical lip-reading systems.
基金supported by the National R&D Pro-gram through the National Research Foundation of Korea(NRF)funded by the Ministry of Science and ICT(Nos.RS-2024-00356939 and RS-2024-00405691).
文摘As the demand for advanced computational systems capable of handling large data volumes rises,nano-electronic devices,such as memristors,are being developed for efficient data processing,especially in reservoir computing(RC).RC enables the processing of temporal information with minimal training costs,making it a promising approach for neuromorphic computing.However,current memristor devices of-ten suffer from limitations in dynamic conductance and temporal behavior,which affects their perfor-mance in these applications.In this study,we present a multilayered indium-tin-oxide(ITO)/ZnO/indium-gallium-zinc oxide(IGZO)/ZnO/ITO memristor fabricated via radiofrequency sputtering to explore its fil-amentary and nonfilamentary resistive switching(RS)characteristics.High-resolution transmission elec-tron microscopy confirmed the polycrystalline structure of the ZnO/IGZO/ZnO active layer.Dual-switching modes were demonstrated by controlling the current compliance(I_(CC)).In the filamentary mode,the memristor exhibited a large memory window(10^(3)),low-operating voltages(±2 V),excellent cycle-to-cycle stability,and multilevel switching with controlled reset-stop voltages,making it suitable for high-density memory applications.Nonfilamentary switching demonstrated stable on/off ratios above 10,en-durance up to 102 cycles,and retention suited for short-term memory.Key synaptic behaviors,such as paired-pulse facilitation(PPF),post-tetanic potentiation(PTP),and spike-rate dependent plasticity(SRDP)were successfully emulated by modulating pulse amplitude,width,and interval.Experience-dependent plasticity(EDP)was also demonstrated,further replicating biological synaptic functions.These tempo-ral properties were utilized to develop a 4-bit reservoir computing system with 16 distinct conductance states,enabling efficient information encoding.For image recognition tasks,convolutional neural net-work(CNN)simulations achieved a high accuracy of 98.45%after 25 training epochs,outperforming the accuracy achieved following artificial neural network(ANN)simulations(87.79%).These findings demon-strate that the multilayered memristor exhibits high performance in neuromorphic systems,particularly for complex pattern recognition tasks,such as digit and letter classification.
