Intelligent personal assistants play a pivotal role in in-vehicle systems,significantly enhancing life efficiency,driving safety,and decision-making support.In this study,the multi-modal design elements of intelligent...Intelligent personal assistants play a pivotal role in in-vehicle systems,significantly enhancing life efficiency,driving safety,and decision-making support.In this study,the multi-modal design elements of intelligent personal assistants within the context of visual,auditory,and somatosensory interactions with drivers were discussed.Their impact on the driver’s psychological state through various modes such as visual imagery,voice interaction,and gesture interaction were explored.The study also introduced innovative designs for in-vehicle intelligent personal assistants,incorporating design principles such as driver-centricity,prioritizing passenger safety,and utilizing timely feedback as a criterion.Additionally,the study employed design methods like driver behavior research and driving situation analysis to enhance the emotional connection between drivers and their vehicles,ultimately improving driver satisfaction and trust.展开更多
The multi-mode integrated railway system,anchored by the high-speed railway,caters to the diverse travel requirements both within and between cities,offering safe,comfortable,punctual,and eco-friendly transportation s...The multi-mode integrated railway system,anchored by the high-speed railway,caters to the diverse travel requirements both within and between cities,offering safe,comfortable,punctual,and eco-friendly transportation services.With the expansion of the railway networks,enhancing the efficiency and safety of the comprehensive system has become a crucial issue in the advanced development of railway transportation.In light of the prevailing application of artificial intelligence technologies within railway systems,this study leverages large model technology characterized by robust learning capabilities,efficient associative abilities,and linkage analysis to propose an Artificial-intelligent(AI)-powered railway control and dispatching system.This system is elaborately designed with four core functions,including global optimum unattended dispatching,synergetic transportation in multiple modes,high-speed automatic control,and precise maintenance decision and execution.The deployment pathway and essential tasks of the system are further delineated,alongside the challenges and obstacles encountered.The AI-powered system promises a significant enhancement in the operational efficiency and safety of the composite railway system,ensuring a more effective alignment between transportation services and passenger demands.展开更多
Aiming at the needs of different lighting applications, combined with the characteristics of LED dimming and color control, and using MSP430 digital control technology, a novel LED intelligent dimming and color contro...Aiming at the needs of different lighting applications, combined with the characteristics of LED dimming and color control, and using MSP430 digital control technology, a novel LED intelligent dimming and color control system was designed. The system integrated Bluetooth remote, human infrared sensor, voice/gesture control and other control modes, which could achieve LED multi-mode dimming and color intelligent control. System hardware and software were designed to develop a prototype to experimental verification. The designed method proposes new ideas and information for LED control.展开更多
A novel heuristic search algorithm called seeker op- timization algorithm (SOA) is proposed for the real-parameter optimization. The proposed SOA is based on simulating the act of human searching. In the SOA, search...A novel heuristic search algorithm called seeker op- timization algorithm (SOA) is proposed for the real-parameter optimization. The proposed SOA is based on simulating the act of human searching. In the SOA, search direction is based on empir- ical gradients by evaluating the response to the position changes, while step length is based on uncertainty reasoning by using a simple fuzzy rule. The effectiveness of the SOA is evaluated by using a challenging set of typically complex functions in compari- son to differential evolution (DE) and three modified particle swarm optimization (PSO) algorithms. The simulation results show that the performance of the SOA is superior or comparable to that of the other algorithms.展开更多
Image captioning refers to automatic generation of descriptive texts according to the visual content of images.It is a technique integrating multiple disciplines including the computer vision(CV),natural language proc...Image captioning refers to automatic generation of descriptive texts according to the visual content of images.It is a technique integrating multiple disciplines including the computer vision(CV),natural language processing(NLP)and artificial intelligence.In recent years,substantial research efforts have been devoted to generate image caption with impressive progress.To summarize the recent advances in image captioning,we present a comprehensive review on image captioning,covering both traditional methods and recent deep learning-based techniques.Specifically,we first briefly review the early traditional works based on the retrieval and template.Then deep learning-based image captioning researches are focused,which is categorized into the encoder-decoder framework,attention mechanism and training strategies on the basis of model structures and training manners for a detailed introduction.After that,we summarize the publicly available datasets,evaluation metrics and those proposed for specific requirements,and then compare the state of the art methods on the MS COCO dataset.Finally,we provide some discussions on open challenges and future research directions.展开更多
Identifying and segmenting spacecraft components is vital in many on-orbit space missions,such as on-orbit maintenance and component recovery.Integrating depth maps with visual images has been proven effective in impr...Identifying and segmenting spacecraft components is vital in many on-orbit space missions,such as on-orbit maintenance and component recovery.Integrating depth maps with visual images has been proven effective in improving segmentation accuracy.However,existing methods ignore the noise and fallacy in collected depth maps,which interfere with the network to extract representative features,decreasing the final segmentation accuracy.To this end,this paper proposes a Filtering and Regret Network(FRNet)for spacecraft component segmentation.The FRNet incorporates filtering and regret mechanisms to suppress the abnormal depth response in shallow layers and selectively reuses the filtered cues in deep layers,avoiding the detrimental effects of low-quality depth information while preserving the semantic context inherent in depth maps.Furthermore,a two-stage feature fusion module is proposed,which involves information interaction and aggregation.This module effectively explores the feature correlation and unifies the multimodal features into a comprehensive representation.Finally,a large-scale spacecraft component recognition dataset is constructed for training and evaluating spacecraft component segmentation algorithms.Experimental results demonstrate that the FRNet achieves a state-of-the-art performance with a mean Intersection Over Union(mIOU)of 84.13%and an average inference time of 133.2 ms when tested on an NVIDIA RTX 2080 SUPER GPU.展开更多
目的比较不同算法对桂枝茯苓胶囊内容物吸湿性预测模型性能的影响,确定最优建模算法。方法以54个物理性质参数为输入,胶囊内容物吸湿性为输出,对比偏最小二乘算法(partial least squares,PLS)、决策树算法(classification and regressio...目的比较不同算法对桂枝茯苓胶囊内容物吸湿性预测模型性能的影响,确定最优建模算法。方法以54个物理性质参数为输入,胶囊内容物吸湿性为输出,对比偏最小二乘算法(partial least squares,PLS)、决策树算法(classification and regression tree,CART)、多元自适应回归样条算法(multivariate adaptive regression splines,MARS)和广义路径追踪算法(generalized path seeker,GPS)对建立吸湿性预测模型性能的影响。结果MARS算法建立的预测模型性能最佳,预测能力最强,模型的校正集决定系数(R2c)为0.843,预测集决定系数(R2p)为0.808,校正集均方根误差(root mean square error of calibration,RMSEC)为0.391,预测集均方根误差(root mean square error of prediction,RMSEP)为0.472,平均相对预测误差为2.69%,小于5%。结论MARS算法建立的吸湿性预测模型更适合桂枝茯苓胶囊的生产应用,该算法可嵌入在线控制系统,为生产过程的质量控制智能化提供技术支持。展开更多
π-Conjugated organic luminescent materials are essential components for modern optical and photoelectric research.This review mainly probes into the recent work in the progress of smart π-conjugated organic systems ...π-Conjugated organic luminescent materials are essential components for modern optical and photoelectric research.This review mainly probes into the recent work in the progress of smart π-conjugated organic systems in the form of cyanostilbene and its derivatives,which can regulate its excellent features in response to a variety of physical or chemical stimuli(e.g.viscosity,light,magnetism,electric field,polarity,pH and solvent environment).As a result of its extensive applicability and adaptability,cyanostilbene and its derivatives have been planted into different structural architectures such as polymers,functional nanoparticles,solid membranes,supramolecular systems and so on.This review will first give a general description of the preparation and characterization of cyanostilbenebased optoelectric luminophores and then focus on their peculiar functional properties in the need for advanced material applications,such as AIEE(aggregation-induced enhanced emission effect),solidstate emission,photovoltaics,photolithography and photochromism to be further processed afterwards.The purpose of this review is to give a platform of practical organic materials,mostly cyanostilbene and its derivatives,based on stable aromatic derivatives,to contribute to the booming of modern π-conjugated photoelectric materials that integrate with contemporary physics,material chemistry,bioengineering,medical science and aerospace altogether.展开更多
Visual representation learning is ubiquitous in various real-world applications,including visual comprehension,video understanding,multi-modal analysis,human-computer interaction,and urban computing.Due to the emergen...Visual representation learning is ubiquitous in various real-world applications,including visual comprehension,video understanding,multi-modal analysis,human-computer interaction,and urban computing.Due to the emergence of huge amounts of multimodal heterogeneous spatial/temporal/spatial-temporal data in the big data era,the lack of interpretability,robustness,and out-of-distribution generalization are becoming the challenges of the existing visual models.The majority of the existing methods tend to fit the original data/variable distributions and ignore the essential causal relations behind the multi-modal knowledge,which lacks unified guidance and analysis about why modern visual representation learning methods easily collapse into data bias and have limited generalization and cognitive abilities.Inspired by the strong inference ability of human-level agents,recent years have therefore witnessed great effort in developing causal reasoning paradigms to realize robust representation and model learning with good cognitive ability.In this paper,we conduct a comprehensive review of existing causal reasoning methods for visual representation learning,covering fundamental theories,models,and datasets.The limitations of current methods and datasets are also discussed.Moreover,we propose some prospective challenges,opportunities,and future research directions for benchmarking causal reasoning algorithms in visual representation learning.This paper aims to provide a comprehensive overview of this emerging field,attract attention,encourage discussions,bring to the forefront the urgency of developing novel causal reasoning methods,publicly available benchmarks,and consensus-building standards for reliable visual representation learning and related real-world applications more efficiently.展开更多
文摘Intelligent personal assistants play a pivotal role in in-vehicle systems,significantly enhancing life efficiency,driving safety,and decision-making support.In this study,the multi-modal design elements of intelligent personal assistants within the context of visual,auditory,and somatosensory interactions with drivers were discussed.Their impact on the driver’s psychological state through various modes such as visual imagery,voice interaction,and gesture interaction were explored.The study also introduced innovative designs for in-vehicle intelligent personal assistants,incorporating design principles such as driver-centricity,prioritizing passenger safety,and utilizing timely feedback as a criterion.Additionally,the study employed design methods like driver behavior research and driving situation analysis to enhance the emotional connection between drivers and their vehicles,ultimately improving driver satisfaction and trust.
基金supported by the National Key R&D Program of China(2022YFB4300500).
文摘The multi-mode integrated railway system,anchored by the high-speed railway,caters to the diverse travel requirements both within and between cities,offering safe,comfortable,punctual,and eco-friendly transportation services.With the expansion of the railway networks,enhancing the efficiency and safety of the comprehensive system has become a crucial issue in the advanced development of railway transportation.In light of the prevailing application of artificial intelligence technologies within railway systems,this study leverages large model technology characterized by robust learning capabilities,efficient associative abilities,and linkage analysis to propose an Artificial-intelligent(AI)-powered railway control and dispatching system.This system is elaborately designed with four core functions,including global optimum unattended dispatching,synergetic transportation in multiple modes,high-speed automatic control,and precise maintenance decision and execution.The deployment pathway and essential tasks of the system are further delineated,alongside the challenges and obstacles encountered.The AI-powered system promises a significant enhancement in the operational efficiency and safety of the composite railway system,ensuring a more effective alignment between transportation services and passenger demands.
文摘Aiming at the needs of different lighting applications, combined with the characteristics of LED dimming and color control, and using MSP430 digital control technology, a novel LED intelligent dimming and color control system was designed. The system integrated Bluetooth remote, human infrared sensor, voice/gesture control and other control modes, which could achieve LED multi-mode dimming and color intelligent control. System hardware and software were designed to develop a prototype to experimental verification. The designed method proposes new ideas and information for LED control.
基金supported by the National Natural Science Foundation of China(60870004)
文摘A novel heuristic search algorithm called seeker op- timization algorithm (SOA) is proposed for the real-parameter optimization. The proposed SOA is based on simulating the act of human searching. In the SOA, search direction is based on empir- ical gradients by evaluating the response to the position changes, while step length is based on uncertainty reasoning by using a simple fuzzy rule. The effectiveness of the SOA is evaluated by using a challenging set of typically complex functions in compari- son to differential evolution (DE) and three modified particle swarm optimization (PSO) algorithms. The simulation results show that the performance of the SOA is superior or comparable to that of the other algorithms.
基金supported by Beijing Natural Science Foundation of China(L201023)the Natural Science Foundation of China(62076030)。
文摘Image captioning refers to automatic generation of descriptive texts according to the visual content of images.It is a technique integrating multiple disciplines including the computer vision(CV),natural language processing(NLP)and artificial intelligence.In recent years,substantial research efforts have been devoted to generate image caption with impressive progress.To summarize the recent advances in image captioning,we present a comprehensive review on image captioning,covering both traditional methods and recent deep learning-based techniques.Specifically,we first briefly review the early traditional works based on the retrieval and template.Then deep learning-based image captioning researches are focused,which is categorized into the encoder-decoder framework,attention mechanism and training strategies on the basis of model structures and training manners for a detailed introduction.After that,we summarize the publicly available datasets,evaluation metrics and those proposed for specific requirements,and then compare the state of the art methods on the MS COCO dataset.Finally,we provide some discussions on open challenges and future research directions.
文摘Identifying and segmenting spacecraft components is vital in many on-orbit space missions,such as on-orbit maintenance and component recovery.Integrating depth maps with visual images has been proven effective in improving segmentation accuracy.However,existing methods ignore the noise and fallacy in collected depth maps,which interfere with the network to extract representative features,decreasing the final segmentation accuracy.To this end,this paper proposes a Filtering and Regret Network(FRNet)for spacecraft component segmentation.The FRNet incorporates filtering and regret mechanisms to suppress the abnormal depth response in shallow layers and selectively reuses the filtered cues in deep layers,avoiding the detrimental effects of low-quality depth information while preserving the semantic context inherent in depth maps.Furthermore,a two-stage feature fusion module is proposed,which involves information interaction and aggregation.This module effectively explores the feature correlation and unifies the multimodal features into a comprehensive representation.Finally,a large-scale spacecraft component recognition dataset is constructed for training and evaluating spacecraft component segmentation algorithms.Experimental results demonstrate that the FRNet achieves a state-of-the-art performance with a mean Intersection Over Union(mIOU)of 84.13%and an average inference time of 133.2 ms when tested on an NVIDIA RTX 2080 SUPER GPU.
文摘目的比较不同算法对桂枝茯苓胶囊内容物吸湿性预测模型性能的影响,确定最优建模算法。方法以54个物理性质参数为输入,胶囊内容物吸湿性为输出,对比偏最小二乘算法(partial least squares,PLS)、决策树算法(classification and regression tree,CART)、多元自适应回归样条算法(multivariate adaptive regression splines,MARS)和广义路径追踪算法(generalized path seeker,GPS)对建立吸湿性预测模型性能的影响。结果MARS算法建立的预测模型性能最佳,预测能力最强,模型的校正集决定系数(R2c)为0.843,预测集决定系数(R2p)为0.808,校正集均方根误差(root mean square error of calibration,RMSEC)为0.391,预测集均方根误差(root mean square error of prediction,RMSEP)为0.472,平均相对预测误差为2.69%,小于5%。结论MARS算法建立的吸湿性预测模型更适合桂枝茯苓胶囊的生产应用,该算法可嵌入在线控制系统,为生产过程的质量控制智能化提供技术支持。
基金the Research Grant for Talent Introduction of Fudan University(No.JIH1717006)National Program for Thousand Young Talents of China for financial support
文摘π-Conjugated organic luminescent materials are essential components for modern optical and photoelectric research.This review mainly probes into the recent work in the progress of smart π-conjugated organic systems in the form of cyanostilbene and its derivatives,which can regulate its excellent features in response to a variety of physical or chemical stimuli(e.g.viscosity,light,magnetism,electric field,polarity,pH and solvent environment).As a result of its extensive applicability and adaptability,cyanostilbene and its derivatives have been planted into different structural architectures such as polymers,functional nanoparticles,solid membranes,supramolecular systems and so on.This review will first give a general description of the preparation and characterization of cyanostilbenebased optoelectric luminophores and then focus on their peculiar functional properties in the need for advanced material applications,such as AIEE(aggregation-induced enhanced emission effect),solidstate emission,photovoltaics,photolithography and photochromism to be further processed afterwards.The purpose of this review is to give a platform of practical organic materials,mostly cyanostilbene and its derivatives,based on stable aromatic derivatives,to contribute to the booming of modern π-conjugated photoelectric materials that integrate with contemporary physics,material chemistry,bioengineering,medical science and aerospace altogether.
基金supported in part by National Natural Science Foundation of China(Nos.62002395,61976250 and U1811463)the National Key R&D Program of China(No.2021ZD0111601)the Guangdong Basic and Applied Basic Research Foundation,China(Nos.2021A15150123 and 2020B1515020048).
文摘Visual representation learning is ubiquitous in various real-world applications,including visual comprehension,video understanding,multi-modal analysis,human-computer interaction,and urban computing.Due to the emergence of huge amounts of multimodal heterogeneous spatial/temporal/spatial-temporal data in the big data era,the lack of interpretability,robustness,and out-of-distribution generalization are becoming the challenges of the existing visual models.The majority of the existing methods tend to fit the original data/variable distributions and ignore the essential causal relations behind the multi-modal knowledge,which lacks unified guidance and analysis about why modern visual representation learning methods easily collapse into data bias and have limited generalization and cognitive abilities.Inspired by the strong inference ability of human-level agents,recent years have therefore witnessed great effort in developing causal reasoning paradigms to realize robust representation and model learning with good cognitive ability.In this paper,we conduct a comprehensive review of existing causal reasoning methods for visual representation learning,covering fundamental theories,models,and datasets.The limitations of current methods and datasets are also discussed.Moreover,we propose some prospective challenges,opportunities,and future research directions for benchmarking causal reasoning algorithms in visual representation learning.This paper aims to provide a comprehensive overview of this emerging field,attract attention,encourage discussions,bring to the forefront the urgency of developing novel causal reasoning methods,publicly available benchmarks,and consensus-building standards for reliable visual representation learning and related real-world applications more efficiently.