检索结果-南通市图书馆

Exploring the effect of fingertip aero-haptic feedforward cues in directing eyes-free target acquisition in VR

在线全文

学校读者我要写书评

暂无评论

虚拟现实与智能硬件（中英文） 2024年第2期6卷 113-131页

作者： Xiaofei REN Jian HE Teng HAN Songxian LIU Mengfei LV Rui ZHOU Faculty of information technology Beijing University of TechnologyBeijing 100124China Institute of Software Chinese Academy of SciencesBeijing 100190China beijing Engineering research center for IoT Software and Systems Beijing University of TechnologyBeijing 100124China

Background The sense of touch plays a crucial role in interactive behavior within virtual spaces,particularly when visual attention is absent.Although haptic feedback has been widely used to compensate for the lack of visual cues,the use of tactile information as a predictive feedforward cue to guide hand movements remains unexplored and lacks theoretical understanding.Methods This study introduces a fingertip aero-haptic rendering method to investigate its effectiveness in directing hand movements during eyes-free spatial interactions.The wearable device incorporates a multichannel micro-airflow chamber to deliver adjustable tactile effects on the fingertips.Results The first study verified that tactile directional feedforward cues significantly improve user capabilities in eyes-free target acquisition and that users rely heavily on haptic indications rather than spatial memory to control their hands.A subsequent study examined the impact of enriched tactile feedforward cues on assisting users in determining precise target positions during eyes-free interactions,and assessed the required learning efforts.Conclusions The haptic feedforward effect holds great practical promise in eyeless design for virtual reality.We aim to integrate cognitive models and tactile feedforward cues in the future,and apply richer tactile feedforward information to alleviate users'perceptual deficiencies.

关键词： Haptic Feedforward Virtual reality Aero-haptic

Review of the application of in-situ sensing techniques to address the tea growth characteristics from leaf to field

在线全文

学校读者我要写书评

暂无评论

International Journal of Agricultural and Biological Engineering 2024年第1期17卷 1-11页

作者： Qiong Cao Chunjiang Zhao Ze Xu Ping Jiang Haibin Yang Xiangyu Meng Guijun Yang information technology research center Beijing Academy of Agriculture and Forestry SciencesBeijing 100097China College of Machnical and Electrical Engineering Hunan Agricultural UniversityChangsha 410125China Tea research Institute of Chongqing Academy of Agricultural Sciences Chongqing 400000China

The tea plant is a valuable and evergreen crop that is extensively cultivated in China and many other countries.Currently,there is growing research interest in this plant.For the tea industry,it is crucial to develop rapid and non-invasive methods to evaluate tea plants in their natural environment.This article provides a comprehensive overview of non-invasive sensing techniques used for in-situ detection of tea plants.The topics covered include leaf,canopy,and field-level assessments,as well as statistical analysis techniques and characteristics specific to the research.Non-invasive testing technology is primarily used for monitoring and predicting tea pests and diseases,monitoring quality,and nutrients,determining tenderness and grade,identifying tea plant varieties,automatically detecting,and identifying tea buds,monitoring tea plant growth,and extracting tea garden areas through remote sensing.It also helps to evaluate planting suitability,assess disasters,and estimate yields.Additionally,the article examines the challenges and prospects of emerging techniques aimed at resolving the in-situ detection problem for tea plants.It can assist researchers and producers in comprehensively understanding the tea environment,quality characteristics,and growth process,thereby enhancing tea production quality,and fostering tea industry development.

关键词： non-destructive in-situ detection tea plants growth characteristics sensors

Multi-modal knowledge graph inference via media convergence and logic rule

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence technology 2024年第1期9卷 211-221页

作者： Feng Lin Dongmei Li Wenbin Zhang Dongsheng Shi Yuanzhou Jiao Qianzhong Chen Yiying Lin Wentao Zhu School of information Science and technology Beijing Forestry UniversityBeijingChina Engineering research center for Forestry-oriented Intelligent information Processing National Forestry and Grassland AdministrationBeijingChina Michigan Technological University HoughtonMichiganUSA

Media convergence works by processing information from different modalities and applying them to different domains.It is difficult for the conventional knowledge graph to utilise multi-media features because the introduction of a large amount of information from other modalities reduces the effectiveness of representation learning and makes knowledge graph inference less effective.To address the issue,an inference method based on Media Convergence and Rule-guided Joint Inference model(MCRJI)has been pro-posed.The authors not only converge multi-media features of entities but also introduce logic rules to improve the accuracy and interpretability of link prediction.First,a multi-headed self-attention approach is used to obtain the attention of different media features of entities during semantic synthesis.Second,logic rules of different lengths are mined from knowledge graph to learn new entity representations.Finally,knowledge graph inference is performed based on representing entities that converge multi-media features.Numerous experimental results show that MCRJI outperforms other advanced baselines in using multi-media features and knowledge graph inference,demonstrating that MCRJI provides an excellent approach for knowledge graph inference with converged multi-media features.

关键词： logic rule media convergence multi-modal knowledge graph inference representation learning

The impact of water quality on the formation of halogenated benzoquinones and the adsorption efficiency by activated carbon

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2024年第1期135卷 693-702页

作者： Yongjing Wang Song Gao Xinyu Yan Songtao Wang Ruolin Zhang Yan Zhou Lianhai Ren Cheng Li State Environmental Protection Key Laboratory of Food Chain Pollution Control Beijing Technology and Business UniversityBeijing 100048China Institute of Scientific and Technical information of China Beijing 100038China Institute of Quality Standard and Testing technology Beijing Academy of Agriculture and Forestry SciencesBeijing 100097China Key Laboratory of Cleaner Production and Integrated Resource Utilization of China National Light Industry Beijing Technology and Business UniversityBeijing 100048China

Halogenated benzoquinones(HBQs)could cause bladder cancer,but there were few related studies on the generation and control.In this study,the impact of different precursors,pH,bromide concentration,and algae-derived organic matters on the formation of HBQs and the removal efficiency by activated carbon were investigated.It was found that the chlorination of bisphenol A produced the most 2,6-dichloro-1,4-benzoquinone(2,6-DCBQ),reaching 14.86μg/L at 1 hr,followed by tyrosine,2-chlorophenol,P-hydroxybenzoic acid,trichlorophenol,and N-methylaniline.The production of 2,6-DCBQ increased first and then decreased from 0 to 36 hr(chlorination doses 0-20 mg/L),indicating that HBQs were unstable in water.Trihalomethanes(THMs)were detected during chlorination,and the concentration increased with prolongation of reaction time.2,6-DCBQ production decreased and 2,6-dibromo-1,4-benzoquinone(2,6-DBBQ)production increased with increment bromide concentration and the bromide promoted the formation of tribromomethane.The production of 2,6-DCBQ decreased with increase of pH,and the maximum production was 141.38μg/L at pH of 5.Microcystis aeruginosa,Chlorella algae cells,and intracellular organic matters(IOM)could be chlorinated as potential precursors for HBQs.The most amount of 2,6-DCBQ was generated from algae cells of Microcystis aeruginosa,followed by Chlorella algae cells,Microcystis aeruginosa IOM,and Chlorella IOM.This study compared the removal efficiency of HBQs by granular activated carbon(GAC)and columnar activated carbon(CAC)under different carbon doses and initial concentrations of HBQs.It was found that the removal efficiency by GAC(80.1%)was higher than that by CAC(51.8%),indicating that GAC has better control for HBQs.

关键词： HBQS DBPS Drinking water Algae derived organic matters Activated carbon

Lensless opto-electronic neural network with quantum dot nonlinear activation

在线全文

学校读者我要写书评

暂无评论

Photonics research 2024年第4期12卷 682-690页

作者： WANXIN SHI XI JIANG ZHENG HUANG XUE LI YUYANG HAN SIGANG YANG HAIZHENG ZHONG HONGWEI CHEN beijing National research center for information Science and technology(BNRist) Department of Electronic EngineeringTsinghua UniversityBeijing 100084China China Mobile research Institute Beijing 100053China MIIT Key Laboratory for Low-dimensional Quantum Structure and Devices School of Materials Sciences&EngineeringBeijing Institute of TechnologyBeijing 100081China

With the swift advancement of neural networks and their expanding applications in many fields, optical neural networks have gradually become a feasible alternative to electrical neural networks due to their parallelism, high speed, low latency, and power consumption. Nonetheless, optical nonlinearity is hard to realize in free-space optics, which restricts the potential of the architecture.

关键词： network neural networks

A globally shared resource paradigm for encoded storage systems in the public cloud

在线全文

学校读者我要写书评

暂无评论

Fundamental research 2024年第3期4卷 642-650页

作者： Zhiyue Li Guangyan Zhang Department of Computer Science and technology Tsinghua UniversityBeijing 100084China beijing National research center for information Science and technology Tsinghua UniversityBeijing 100084China

Public clouds favor sharing of storage resources,in which many tenants acquire bandwidth and storage capacity from a shared storage pool.To provide high availability,data are often encoded to provide fault tolerance with low storage costs.Regarding this,efficiently organizing an encoded storage system for shared I/Os is critical for application performance.This is usually hard to achieve as different applications have different stripe configurations and fault tolerance levels.In this paper,we first study the block trace from the Alibaba cloud,and find that I/O patterns of modern applications prefer the resource sharing scheme.Based on this,we propose a globally shared resource paradigm for encoded storage system in the public cloud.The globally shared resource paradigm can provide balanced load and fault tolerance for numerous disk pool sizes and arbitrary application stripe configurations.Furthermore,we demonstrate with two case studies that our theory can help address the device-specific problems of HDD and SSD RAID arrays with slight modifications:comparing the existing resource partition and resource sharing methods,our theory can promote the rebuild speed of the HDD RAID arrays by 2.5,and reduce the P99 tail latency of the SSD arrays by up to two orders of magnitude.

关键词： Public cloud Encoded storage Load balancing RAID reconstruction Tail latency

Lactiplantibacillus plantarum FRT4 attenuates high-energy low-protein dietinduced fatty liver hemorrhage syndrome in laying hens through regulating gut-liver axis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Animal Science and Biotechnology 2024年第3期15卷 1292-1311页

作者： Daojie Li Hongying Cai Guohua Liu Yunsheng Han Kai Qiu Weiwei Liu Kun Meng Peilong Yang Key Laboratory of Feed Biotechnology of Ministry of agriculture and Rural Affairs Institute of Feed ResearchChinese Academy of Agricultural SciencesBeijing 100081China National Engineering research center of Biological Feed Beijing 100081China

Background Fatty liver hemorrhage syndrome(FLHS)becomes one of the most major factors resulting in the laying hen death for caged egg production.This study aimed to investigate the therapeutic effects of Lactiplantibacillus plan-tarum(Lp.plantarum)FRT4 on FLHS model in laying hen with a focus on liver lipid metabolism,and gut microbiota.Results The FLHS model of laying hens was established by feeding a high-energy low-protein(HELP)diet,and the treatment groups were fed a HELP diet supplemented with differential proportions of Lp.plantarum FRT4.The results indicated that Lp.plantarum FRT4 increased laying rate,and reduced the liver lipid accumulation by regulating lipid metabolism(lipid synthesis and transport)and improving the gut microbiota composition.Moreover,Lp.plan-tarum FRT4 regulated the liver glycerophospholipid metabolism.Meanwhile,“gut-liver”axis analysis showed that there was a correlation between gut microbiota and lipid metabolites.Conclusions The results indicated that Lp.plantarum FRT4 improved the laying performance and alleviated FLHS in HELP diet-induced laying hens through regulating“gut-liver”axis.Our findings reveal that glycerophospholipid metabolism could be the underlying mechanism for the anti-FLHS effect of Lp.plantarum FRT4 and for future use of Lp.plantarum FRT4 as an excellent additive for the prevention and mitigation of FLHS in laying hens.

关键词： Fatty liver hemorrhage syndrome Gut microbiota Lactiplantibacillus plantarum FRT4 Laying hens Lipid metabolism

维普期刊数据库博看期刊

Transfer Learning in Motor Imagery Brain Computer Interface: A Review

在线全文

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 2024年第1期29卷 37-59页

作者：李明爱许冬芹 Faculty of information technology Beijing University of TechnologyBeijing 100124China beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing 100124China Engineering research center of Digital Community Ministry of EducationBeijing 100124China

Transfer learning,as a new machine learning methodology,may solve problems in related but different domains by using existing knowledge,and it is often applied to transfer training data from another domain for model training in the case of insuficient training data.In recent years,an increasing number of researchers who engage in brain-computer interface(BCI),have focused on using transfer learning to make most of the available electroencephalogram data from different subjects,effectively reducing the cost of expensive data acquisition and labeling as well as greatly improving the learning performance of the model.This paper surveys the development of transfer learning and reviews the transfer learning approaches in BCI.In addition,according to the"what to transfer"question in transfer learning,this review is organized into three contexts:instance-based transfer learning,parameter-based transfer learning,and feature-based transfer learning.Furthermore,the current transfer learning applications in BCI research are summarized in terms of the transfer learning methods,datasets,evaluation performance,etc.At the end of the paper,the questions to be solved in future research are put forward,laying the foundation for the popularization and in-depth research of transfer learning in BCI.

关键词： transfer learning brain-computer interface(BCI) electroencephalogram machine learning

FSCIL-EACA: Few-Shot Class-Incremental Learning Network Based on Embedding Augmentation and Classifier Adaptation for Image Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第1期33卷 139-152页

作者： Ruru ZHANG Haihong E Meina SONG School of Computer Science Beijing University of Posts and Telecommunications Education Department information Network Engineering research center Beijing University of Posts and Telecommunications

The ability to learn incrementally is critical to the long-term operation of AI systems. Benefiting from the power of few-shot class-incremental learning(FSCIL), deep learning models can continuously recognize new classes with only a few samples. The difficulty is that limited instances of new classes will lead to overfitting and exacerbate the catastrophic forgetting of the old classes. Most previous works alleviate the above problems by imposing strong constraints on the model structure or parameters, but ignoring embedding network transferability and classifier adaptation(CA), failing to guarantee the efficient utilization of visual features and establishing relationships between old and new classes. In this paper, we propose a simple and novel approach from two perspectives: embedding bias and classifier bias. The method learns an embedding augmented(EA) network with cross-class transfer and class-specific discriminative abilities based on self-supervised learning and modulated attention to alleviate embedding bias. Based on the adaptive incremental classifier learning scheme to realize incremental learning capability,guiding the adaptive update of prototypes and feature embeddings to alleviate classifier bias. We conduct extensive experiments on two popular natural image datasets and two medical datasets. The experiments show that our method is significantly better than the baseline and achieves state-of-the-art results.

关键词： Few-shot class-incremental learning Embedding augmentation Classifier adaptation Image classification