Semantic communications offer promising prospects for enhancing data transmission efficiency. However, existing schemes have predominantly concentrated on point-to-point transmissions. In this paper, we aim to investi...
详细信息
In this paper, we propose two algorithms based on iterative optimization for UAV path planning. In the first one, a nonlinear programming (NLP) problem of unmanned aerial vehicle (UAV) path planning is transformed int...
详细信息
Transfer learning(TL)utilizes data or knowledge from one or more source domains to facilitate learning in a target *** is particularly useful when the target domain has very few or no labeled data,due to annotation ex...
详细信息
Transfer learning(TL)utilizes data or knowledge from one or more source domains to facilitate learning in a target *** is particularly useful when the target domain has very few or no labeled data,due to annotation expense,privacy concerns,***,the effectiveness of TL is not always *** transfer(NT),i.e.,leveraging source domain data/knowledge undesirably reduces learning performance in the target domain,and has been a long-standing and challenging problem in *** approaches have been proposed in the literature to address this ***,there does not exist a systematic *** paper fills this gap,by first introducing the definition of NT and its causes,and reviewing over fifty representative approaches for overcoming NT,which fall into three categories:domain similarity estimation,safe transfer,and NT *** areas,including computer vision,bioinformatics,natural language processing,recommender systems,and robotics,that use NT mitigation strategies to facilitate positive transfers,are also ***,we give guidelines on NT task construction and baseline algorithms,benchmark existing TL and NT mitigation approaches on three NT-specific datasets,and point out challenges and future research *** ensure reproducibility,our code is publicized at https://***/chamwen/NT-Benchmark.
In this paper,multi-UAV trajectory planning and resource allocation are jointly investigated to improve the information freshness for vehicular networks,where the vehicles collect time-critical traffic information by ...
详细信息
In this paper,multi-UAV trajectory planning and resource allocation are jointly investigated to improve the information freshness for vehicular networks,where the vehicles collect time-critical traffic information by on-board sensors and upload to the UAVs through their allocated spectrum *** adopt the expected sum age of information(ESAoI)to measure the network-wide information *** is jointly affected by both the UAVs trajectory and the resource allocation,which are coupled with each other and make the analysis of ESAoI *** tackle this challenge,we introduce a joint trajectory planning and resource allocation procedure,where the UAVs firstly fly to their destinations and then hover to allocate resource blocks(RBs)during a *** on this procedure,we formulate a trajectory planning and resource allocation problem for ESAoI *** solve the mixed integer nonlinear programming(MINLP)problem with hybrid decision variables,we propose a TD3 trajectory planning and Round-robin resource allocation(TTPRRA).Specifically,we exploit the exploration and learning ability of the twin delayed deep deterministic policy gradient algorithm(TD3)for UAVs trajectory planning,and utilize Round Robin rule for the optimal resource *** TTP-RRA,the UAVs obtain their flight velocities by sensing the locations and the age of information(AoI)of the vehicles,then allocate the RBs to the vehicles in a descending order of AoI until the remaining RBs are not sufficient to support another successful *** results demonstrate that TTP-RRA outperforms the baseline approaches in terms of ESAoI and average AoI(AAoI).
For real-time measurement of crystal size distribution(CSD) by in-situ captured crystal images,a deep-learning based image analysis method is proposed to improve measurement accuracy and efficiency,based on the well r...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
For real-time measurement of crystal size distribution(CSD) by in-situ captured crystal images,a deep-learning based image analysis method is proposed to improve measurement accuracy and efficiency,based on the well recognized maskregional convolutional neural network(Mask R-CNN).An automatic dataset labelling algorithm is established to facilitate preparing the training dataset that is required to include a large number of crystal image samples for effective deep ***,an image thresholding segmentation algorithm is introduced to extract the region of interest(ROI) in each crystal image sample for training the Mask R-CNN,such that improved segmentation accuracy and efficiency could be obtained for online image analysis to measure CSD during a crystallization *** results on measuring the crystallization process of β form L-glutamic acid(β-LGA) are shown to verify the effectiveness and advantage of the proposed method.
With the development of intelligent agents pursuing humanisation,artificial intelligence must consider emotion,the most basic spiritual need in human *** emotional dialogue systems usually use an external emotional di...
详细信息
With the development of intelligent agents pursuing humanisation,artificial intelligence must consider emotion,the most basic spiritual need in human *** emotional dialogue systems usually use an external emotional dictionary to select appropriate emotional words to add to the response or concatenate emotional tags and semantic features in the decoding step to generate appropriate ***,selecting emotional words from a fixed emotional dictionary may result in loss of the diversity and consistency of the *** propose a semantic and emotion-based dual latent variable generation model(Dual-LVG)for dialogue systems,which is able to generate appropriate emotional responses without an emotional *** from previous work,the conditional variational autoencoder(CVAE)adopts the standard transformer ***,Dual-LVG regularises the CVAE latent space by introducing a dual latent space of semantics and *** content diversity and emotional accuracy of the generated responses are improved by learning emotion and semantic features ***,the average attention mechanism is adopted to better extract semantic features at the sequence level,and the semi-supervised attention mechanism is used in the decoding step to strengthen the fusion of emotional features of the *** results show that Dual-LVG can successfully achieve the effect of generating different content by controlling emotional factors.
Underwater magnetic induction(MI)-assisted acoustic cooperative multiple-input-multipleoutput(MIMO) has been recently proposed as a promising technique for underwater wireless sensor networks(UWSNs).For the more,the e...
详细信息
Underwater magnetic induction(MI)-assisted acoustic cooperative multiple-input-multipleoutput(MIMO) has been recently proposed as a promising technique for underwater wireless sensor networks(UWSNs).For the more,the energy utilization of energy-constrained sensor nodes is one of the key issues in UWSNs,and it relates to the network *** this paper,we present an energy-efficient data collection for underwater MI-assisted acoustic cooperative MIMO wireless sensor networks(WSNs),including the formation of cooperative MIMO and relay link ***,the cooperative MIMO is formed by considering its expected transmission range and the energy balance of nodes with ***,from the perspective of the node’s energy consumption,the expected cooperative MIMO size and the selection of master node(MN) are ***,to improve the coverage of the networks and prolong the network lifetime,relay links are established by relay selection algorithm that using matching ***,the simulation results show that the proposed data collection improves its efficiency,reduces the energy consumption of the master node,improves the networks’ coverage,and extends the network lifetime.
To address the challenges of insufficient spectral feature extraction and feature redundancy in hyperspectral image (HSI) classification, this paper proposes a Multi-Path Fusion Transformer Network (MPFT) that integra...
详细信息
To improve the safety of stage lifts' operation and reduce the failure rate, a digital-twin assisted fault prediction method is proposed here. Signals such as vibration and temperature are collected from the virtu...
详细信息
Virtual Reality Head-Mounted Display (HMD), also known as VR glasses, is a typical amusement device that provides an immersive viewing experience based on virtual reality technology in cultural tourism equipment. Vari...
详细信息
暂无评论