检索结果-内蒙古大学图书馆

Collaborative Learning of Gesture Recognition and 3D Hand Pose Estimation with Multi-order Feature Analysis 16th

学校读者我要写书评

暂无评论

Collaborative Learning of Gesture Recognition and 3D Hand Po...

16th European Conference on computer Vision, ECCV 2020

作者： Yang, Siyuan Liu, Jun Lu, Shijian Er, Meng Hwa Kot, Alex C. Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore Singapore School of Computer Science and Engineering Nanyang Technological University Singapore Singapore

ISBN: (纸本)9783030585792

Gesture recognition and 3D hand pose estimation are two highly correlated tasks, yet they are often handled separately. In this paper, we present a novel collaborative learning network for joint gesture recognition and 3D hand pose estimation. The proposed network exploits joint-aware features that are crucial for both tasks, with which gesture recognition and 3D hand pose estimation boost each other to learn highly discriminative features. In addition, a novel multi-order multi-stream feature analysis method is introduced which learns posture and multi-order motion information from the intermediate feature maps of videos effectively and efficiently. Due to the exploitation of joint-aware features in common, the proposed technique is capable of learning gesture recognition and 3D hand pose estimation even when only gesture or pose labels are available, and this enables weakly supervised network learning with much reduced data labeling efforts. Extensive experiments show that our proposed method achieves superior gesture recognition and 3D hand pose estimation performance as compared with the state-of-the-art. © 2020, Springer Nature Switzerland AG.

关键词： Gesture recognition

Deep Learning Based Approach for Fresh Produce Market Price Prediction

学校读者我要写书评

暂无评论

Deep Learning Based Approach for Fresh Produce Market Price ...

International Joint Conference on Neural Networks (IJCNN)

作者： Lobna Nassar Ifeanyi Emmanuel Okwuchi Muhammad Saad Fakhri Karray Kumaraswamy Ponnambalam Electrical and Computer Engineering Department University of Waterloo Canada Systems Design Engineering Department University of Waterloo Canada

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

Building highly precise prediction models for Fresh Produce (FP) market price is crucial to protect retailers from overpriced FP. In this paper we are comparing the price prediction models performance of deep learning (DL) models with statistical as well as standard machine learning (ML) models. Five types of FP are considered in performance testing. It is found that the conventional ML models outperform the statistical models such as ARIMA. On the other hand, the winning model among the conventional ML models (the Gradient Boosting model) proves to be less performant as compared with the simple or compound DL models. Moreover, the simple DL models, such as the Long Short-Term Memory (LSTM), are outperformed by the compound one, the Convolutional Long Short-Term Memory Recurrent Neural Network (CNN-LSTM), whose performance improves by adding attention. The model is capable of precisely predicting FP prices for up to three weeks ahead.

关键词： Predictive models Autoregressive processes Boosting Forecasting Logic gates Time series analysis

Robust Semi-supervised Federated Learning for Images Automatic Recognition in Internet of Drones

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Zhe Ma, Shiyao Yang, Zhaohui Xiong, Zehui Kang, Jiawen Wu, Yi Zhang, Kejia Niyato, Dusit The School of Data Science and Technology Heilongjiang University China The College of Information and Communication Engineering Dalian Minzu University China The Department of Electronic and Electrical Engineering University College London LondonWC1E 6BT United Kingdom The Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore The Automation School Guangdong University of Technology China The School of Mathematical Science Heilongjiang University China School of Computer Science and Engineering Nanyang Technological University Singapore

Air access networks have been recognized as a significant driver of various Internet of Things (IoT) services and applications. In particular, the aerial computing network infrastructure centered on the Internet of Drones has set off a new revolution in automatic image recognition. This emerging technology relies on sharing ground truth labeled data between Unmanned Aerial Vehicle (UAV) swarms to train a high-quality automatic image recognition model. However, such an approach will bring data privacy and data availability challenges. To address these issues, we first present a Semi-supervised Federated Learning (SSFL) framework for privacy-preserving UAV image recognition. Specifically, we propose model parameters mixing strategy to improve the naive combination of FL and semi-supervised learning methods under two realistic scenarios (labels-at-client and labels-at-server), which is referred to as Federated Mixing (FedMix). Furthermore, there are significant differences in the number, features, and distribution of local data collected by UAVs using different camera modules in different environments, i.e., statistical heterogeneity. To alleviate the statistical heterogeneity problem, we propose an aggregation rule based on the frequency of the client’s participation in training, namely the FedFreq aggregation rule, which can adjust the weight of the corresponding local model according to its frequency. Numerical results demonstrate that the performance of our proposed method is significantly better than those of the current baseline and is robust to different non-IID levels of client data. Copyright © 2022, The Authors. All rights reserved.

关键词： Drones

Variational and phase response analysis for limit cycles with hard boundaries, with applications to neuromechanical control problems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Yangyang Gill, Jeffrey P. Chiel, Hillel J. Thomas, Peter J. Department of Mathematics The University of Iowa Iowa CityIA52242 United States Department of Biology Case Western Reserve University ClevelandOH44106 United States Departments of Biology Neurosciencesand Biomedical Engineering Case Western Reserve University ClevelandOH44106 United States Departments of Mathematics Applied Mathematics and StatisticsBiologyCognitive ScienceData and Computer Scienceand Electrical Control and Systems Engineering Case Western Reserve University ClevelandOH44106 United States

Motor systems show an overall robustness, but because they are highly nonlinear, understanding how they achieve robustness is difficult. In many rhythmic systems, robustness against perturbations involves response of both the shape and the timing of the trajectory. This makes the study of robustness even more challenging. To understand how a motor system produces robust behaviors in a variable environment, we consider a neuromechanical model of motor patterns in the feeding apparatus of the marine mollusk Aplysia californica (Shaw et al., 2015;Lyttle et al., 2017). We established in (Wang et al., 2021) the tools for studying combined shape and timing responses of limit cycle systems under sustained perturbations and here apply them to study robustness of the neuromechanical model against increased mechanical load during swallowing. Interestingly, we discover that nonlinear biomechanical properties confer resilience by immediately increasing resistance to applied loads. In contrast, the effect of changed sensory feedback signal is significantly delayed by the firing rates’ hard boundary properties. Our analysis suggests that sensory feedback contributes to robustness in swallowing primarily by shifting the timing of neural activation involved in the power stroke of the motor cycle (retraction). This effect enables the system to generate stronger retractor muscle forces to compensate for the increased load, and hence achieve strong robustness. The approaches that we are applying to understanding a neuromechanical model in Aplysia, and the results that we have obtained, are likely to provide insights into the function of other motor systems that encounter changing mechanical loads and hard boundaries, both due to mechanical and neuronal firing *** Codes 34C07, 34C15, 58E25, 49J52, 92B20, 93C73 Copyright © 2022, The Authors. All rights reserved.

关键词： Activation analysis

DenseNet for Breast Tumor Classification in Mammographic Images 1st

学校读者我要写书评

暂无评论

DenseNet for Breast Tumor Classification in Mammographic Ima...

1st International Conference on Bioengineering and Biomedical Signal and Image Processing, BIOMESIP 2021

作者： Jiménez Gaona, Yuliana Rodriguez-Alvarez, María José Espino-Morato, Hector Castillo Malla, Darwin Lakshminarayanan, Vasudevan Departamento de Química y Ciencias Exactas Universidad Técnica Particular de Loja San Cayetano Alto s/n CP1101608 Loja Ecuador Valencia46022 Spain Theoretical and Experimental Epistemology Lab School of Optometry and Vision Science Waterloo Canada Department of Systems Design Engineering Physics and Electrical and Computer Engineering University of Waterloo WaterlooONN2L3G1 Canada Valencia46022 Spain

ISBN: (纸本)9783030881627

Breast cancer screening is an efficient method to detect breast lesions early. The common screening techniques are tomosynthesis and mammography images. However, the traditional manual diagnosis requires an intense workload for pathologists, and hence is prone to diagnostic errors. Thus, the aim of this study was to build a deep convolutional neural network method for automatic detection, segmentation, and classification of breast lesions in mammography images. Based on deep learning the Mask-CNN (RoIAlign) method was developed to automate RoI segmentation. Then feature extraction, selection and classification were carried out by the DenseNet architecture. Finally, the precision and accuracy of the model was evaluated by the AUC, accuracy and precision metrics. To summarize, the findings of this study show that the methodology may improve the diagnosis and efficiency in automatic tumor localization through medical image classification. © 2021, Springer Nature Switzerland AG.

关键词： Mammography

Semantic Communications for Future Internet: Fundamentals, Applications, and Challenges

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Wanting Du, Hongyang Liew, Zi Qin Lim, Wei Yang Bryan Xiong, Zehui Niyato, Dusit Chi, Xuefen Shen, Xuemin Sherman Miao, Chunyan The Department of Communications Engineering Jilin University Changchun130012 China Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore Singapore The School of Computer Science and Engineering The Energy Research Institute Ntu Interdisciplinary Nanyang Technological University Singapore Singapore Alibaba Group The Alibaba-NTU Joint Research Institute Nanyang Technological University Singapore Singapore School of Computer Science and Engineering Ntu Singapore Singapore The Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada The School of Computer Science and Engineering Nanyang Technological University Singapore Singapore The Alibaba-NTU Joint Research Institute Nanyang Technological University Singapore Singapore The Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly Nanyang Technological University Singapore Singapore

With the increasing demand for intelligent services, the sixth-generation (6G) wireless networks will shift from a traditional architecture that focuses solely on a high transmission rate to a new architecture that is based on the intelligent connection of everything. Semantic communication (SemCom), a revolutionary architecture that integrates user as well as application requirements and the meaning of information into data processing and transmission, is predicted to become a new core paradigm in 6G. While SemCom is expected to progress beyond the classical Shannon paradigm, several obstacles need to be overcome on the way to a SemCom-enabled smart wireless Internet. In this paper, we first highlight the motivations and compelling reasons of SemCom in 6G. Then, we provide an overview of SemCom-related theory development. After that, we introduce three types of SemCom, i.e., semantic-oriented communication, goal-oriented communication, and semantic-aware communication. Following that, we organize the design of the communication system into three dimensions, i.e., semantic information (SI) extraction, SI transmission, and SI metrics. For each dimension, we review existing techniques and discuss their benefits and limitation, as well as the remaining challenges. Then, we introduce the potential applications of SemCom in 6G and portray the vision of future SemCom-empowered network architecture. Finally, we outline future research opportunities. In a nutshell, this paper provides a holistic review of the fundamentals of SemCom, its applications in 6G networks, and the existing challenges and open issues with insights for further in-depth investigations. Copyright © 2022, The Authors. All rights reserved.

关键词： Network architecture

3D-printed liquid metal polymer composites as NIR-responsive 4D printing soft robot

学校读者我要写书评

暂无评论

Nature Communications 2023年第1期14卷 7815页

作者： Zhang, Liwen Huang, Xumin Cole, Tim Lu, Hongda Hang, Jiangyu Li, Weihua Tang, Shi-Yang Boyer, Cyrille Davis, Thomas P. Qiao, Ruirui Australian Institute of Bioengineering & Nanotechnology The University of Queensland Brisbane 4072 QLD Australia Department of Electronic Electrical and Systems Engineering University of Birmingham Birmingham United Kingdom School of Mechanical Materials Mechatronic and Biomedical Engineering University of Wollongong Wollongong 2522 NSW Australia School of Electronics and Computer Science University of Southampton Southampton SO17 1BJ United Kingdom Cluster for Advanced Macromolecular Design School of Chemical Engineering The University of New South Wales Sydney 2052 NSW Australia

4D printing combines 3D printing with nanomaterials to create shape-morphing materials that exhibit stimuli-responsive functionalities. In this study, reversible addition-fragmentation chain transfer polymerization agents grafted onto liquid metal nanoparticles are successfully employed in ultraviolet light-mediated stereolithographic 3D printing and near-infrared light-responsive 4D printing. Spherical liquid metal nanoparticles are directly prepared in 3D-printed resins via a one-pot approach, providing a simple and efficient strategy for fabricating liquid metal-polymer composites. Unlike rigid nanoparticles, the soft and liquid nature of nanoparticles reduces glass transition temperature, tensile stress, and modulus of 3D-printed materials. This approach enables the photothermal-induced 4D printing of composites, as demonstrated by the programmed shape memory of 3D-printed composites rapidly recovering to their original shape in 60 s under light irradiation. This work provides a perspective on the use of liquid metal-polymer composites in 4D printing, showcasing their potential for application in the field of soft robots. © 2023, The Author(s).

关键词：

Towards reliable UAV swarm communication in D2D-enhanced cellular network

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Han, Yitao Liu, Liang Duan, Lingjie Zhang, Rui Engineering Systems and Design Pillar Singapore University of Technology and Design Department of Electrical and Computer Engineering National University of Singapore Department of Electronic and Information Engineering Hong Kong Polytechnic University Department of Electrical and Computer Engineering National University of Singapore

In the existing cellular networks, it remains a challenging problem to communicate with and control an unmanned aerial vehicle (UAV) swarm with both high reliability and low latency. Due to the UAV swarm's high working altitude and strong ground-to-air channels, it is generally exposed to multiple ground base stations (GBSs), while the GBSs that are serving ground users (occupied GBSs) can generate strong interference to the UAV swarm. To tackle this issue, we propose a novel two-phase transmission protocol by exploiting cellular plus device-to-device (D2D) communication for the UAV swarm. In Phase I, one swarm head is chosen for ground-to-air channel estimation, and all the GBSs that are not serving ground users (available GBSs) transmit a common control message to the UAV swarm simultaneously, using the same cellular frequency band. Both the swarm head and other swarm members can utilize the high power gain from multiple available GBSs' transmission, to combat the strong interference from occupied GBSs, while some UAVs may fail to decode the message due to uncorrelated ground-to-air channels. In Phase II, all the UAVs that have decoded the common control message in Phase I further relay it to the other UAVs in the swarm via D2D communication, by exploiting the less interfered D2D frequency band and the proximity among UAVs. In this paper, we aim to characterize the reliability performance of the above two-phase protocol, i.e., the expected percentage of UAVs in the swarm that can decode the common control message, which is a non-trivial problem due to the complex system setup and the intricate coupling between the two transmission phases. Nevertheless, we manage to obtain an approximated expression of the reliability performance of interest, under reasonable assumptions and with the aid of the Pearson distributions. Numerical results validate the accuracy of our analytical results and show the effectiveness of our protocol over other benchmark protocols. We also s

关键词： Unmanned aerial vehicles (UAV)

Prediction of Strawberry Yield and Farm Price Utilizing Deep Learning

学校读者我要写书评

暂无评论

Prediction of Strawberry Yield and Farm Price Utilizing Deep...

International Joint Conference on Neural Networks (IJCNN)

作者： Lobna Nassar Ifeanyi Emmanuel Okwuchi Muhammad Saad Fakhri Karray Kumaraswamy Ponnambalam Prarabdha Agrawal Electrical and Computer Engineering Department University of Waterloo Canada Systems Design Engineering Department University of Waterloo Ontario Canada

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

The currently deployed prediction models for strawberry fresh produce (FP) are based on either conventional machine learning (ML) or on simple deep learning (DL) models that are mostly applied for yield prediction. In this paper, we propose more comprehensive DL models that are applied for the first time to predict strawberry yield. The strawberry price is predicted as well directly from weather input parameters and yield. The strawberry price prediction is achieved using compound DL models such as Convolutional Long Short-Term Memory Recurrent Neural Network (CNN-LSTM). It is found that by adding attention, the performance of the compound models usually improves. After utilizing an aggregated performance measure to find the best model, the Attention-CNN-LSTM model proved to be the best compared to the rest of the deployed conventional ML models as well as the compound and simple DL models. The aggregated measure shows that this model is capable of precisely predicting strawberry prices five weeks ahead while maintaining the lowest prediction error and the highest model correlation.

关键词： Predictive models Meteorology Machine learning Feature extraction Data models Neurons Compounds