Realizing digital-twin services is one of promising applications in 6 G mobile communication and network scenarios. In addition, the use of unmanned aerial vehicles (UAVs) is essential for enabling the services e...
详细信息
Realizing digital-twin services is one of promising applications in 6 G mobile communication and network scenarios. In addition, the use of unmanned aerial vehicles (UAVs) is essential for enabling the services even in the extreme areas where humans cannot reach. In this emerging scenario, it is necessary to design collaborative algorithms for autonomous UAV trajectory control and a centralized computing platform (e.g., cloud) in digital-twin networks. For this system, it is required to build energy-efficient algorithms due to the power-hungry nature in UAVs. Based on this requirements and system characteristics, this paper proposes autonomous UAV charging algorithms and systems where the UAVs are classified into two types, i.e., cluster UAVs (for main image recording operations in digital-twin services, and some of them take the roles of mobile edge computing) and charging UAVs (for charging the cluster UAVs). Our proposed charging should be (i) fully distributed for practical, scalable, and low-overhead operations and (ii) trustworthy for secure and privacy-preserving computation;where these are essential for collaborative operations. Therefore, a novel auction-based charging algorithm for UAV-based digital-twin networks is proposed in order to realize the distributed and truthful operations, which cannot be achieved by the convex optimization-based centralized algorithms in the literature. Our performance evaluation verifies that the proposed algorithm achieves performance improvements (at most 15.53%). IEEE
This study explores the potential of Mg/Carbon Nanotubes/Baghdadite composites as biomaterials for bone regeneration and repair while addressing the obstacles to their clinical *** powder was synthesized using the sol...
详细信息
This study explores the potential of Mg/Carbon Nanotubes/Baghdadite composites as biomaterials for bone regeneration and repair while addressing the obstacles to their clinical *** powder was synthesized using the sol-gel method to ensure a fine distribution within the Mg/CNTs ***/1.5 wt.%CNT composites were reinforced with BAG at weight fractions of 0.5,1.0,and 1.5 wt.%using spark plasma sintering at 450℃and 50 MPa after homogenization via ball *** cellular bioactivity of these nanocomposites was evaluated using human osteoblast-like cells and adipose-derived mesenchymal stromal *** proliferation and attachment of MG-63cells were assessed and visualized using the methylthiazol tetrazolium(MTT)assay and SEM,while AD-MSC differentiation was measured using alkaline phosphatase activity *** were also generated to visualize the diameter distributions of particles in SEM images using image processing *** Mg/CNTs/0.5 wt.%BAG composite demonstrated optimal mechanical properties,with compressive strength,yield strength,and fracture strain of 259.75 MPa,180.25 MPa,and 31.65%,*** learning models,including CNN,LSTM,and GRU,were employed to predict stress-strain relationships across varying BAG amounts,aiming to accurately model these curves without requiring extensive physical *** shown by contact angle measurements,enhanced hydrophilicity promoted better cell adhesion and ***,corrosion resistance improved with a higher BAG *** study concludes that Mg/CNTs composites reinforced with BAG concentrations below 1.0 wt.%offer promising biodegradable implant materials for orthopedic applications,featuring adequate load-bearing capacity and improved corrosion resistance.
Distance and size estimation of objects of interests is an inevitable task for many navigation and obstacle avoidance algorithms mainly used in autonomus and robotic systems. Stereo vision systems, inspired by human v...
详细信息
Issues regarding safety, circuit breaker reclosing, power quality, and regulatory compliance are identified when islanding is to be detected in a microgrid. In this paper, a novel communication-based, passive islandin...
详细信息
Federated learning is widely accepted as a privacy-preserving paradigm for training a shared global model across multiple client devices in a collaborative fashion. However, in practice, the significantly limited comp...
详细信息
Federated learning is widely accepted as a privacy-preserving paradigm for training a shared global model across multiple client devices in a collaborative fashion. However, in practice, the significantly limited computational power on client devices has been a major barrier when we wish to train large models with potentially hundreds of millions of parameters. In this paper, we propose a new architecture, referred to as Infocomm, that incorporates locally supervised learning in federated learning. With locally supervised learning, the disadvantages of split learning can be avoided by using a more flexible way to offload training from resource constrained clients to a more capable server. Infocomm enables parallel training of different modules of the neural network in both the server and clients in a gradient-isolated fashion. The efficacy in reducing both training time and communication time is supported by our theoretical analysis and empirical results. In the scenario involving larger models and fewer available local data, Infocomm has been observed to reduce the elapsed time per round by over 37% without sacrificing accuracy compared to both conventional federated learning or directly combining federated learning and split learning, which showcases the advantages of Infocomm under power-constrained IoT scenarios. IEEE
This paper presents a novel supervised learning framework for real-time optimization of multi-parametric mixed-integer quadratic programming (mp-MIQP) problems. The framework utilizes a multi-layer perceptron (MLP) mo...
详细信息
The increasing penetration of renewable energy resources with highly fluctuating outputs has placed increasing concern on the accuracy and timeliness of electric power system state estimation(SE).Meanwhile,we note tha...
详细信息
The increasing penetration of renewable energy resources with highly fluctuating outputs has placed increasing concern on the accuracy and timeliness of electric power system state estimation(SE).Meanwhile,we note that only a fraction of system states fluctuate at the millisecond level and require to be *** such,refreshing only those states with significant variation would enhance the computational efficiency of SE and make fast-continuous update of states ***,this is difficult to achieve with conventional SE methods,which generally refresh states of the entire system every 4–5 *** this context,we propose a local hybrid linear SE framework using stream processing,in which synchronized measurements received from phasor measurement units(PMUs),and trigger/timingmode measurements received from remote terminal units(RTUs)are used to update the associated local ***,the measurement update process efficiency and timeliness are enhanced by proposing a trigger measurement-based fast dynamic partitioning algorithm for determining the areas of the system with states requiring *** particular,non-iterative hybrid linear formulations with both RTUs and PMUs are employed to solve the local SE *** timeliness,accuracy,and computational efficiency of the proposed method are demonstrated by extensive simulations based on IEEE 118-,300-,and 2383-bus systems.
The rapid growth of digital data necessitates advanced natural language processing(NLP)models like BERT(Bidi-rectional Encoder Representations from Transformers),known for its superior performance in text ***,BERT’s ...
详细信息
The rapid growth of digital data necessitates advanced natural language processing(NLP)models like BERT(Bidi-rectional Encoder Representations from Transformers),known for its superior performance in text ***,BERT’s size and computational demands limit its practicality,especially in resource-constrained *** research compresses the BERT base model for Bengali emotion classification through knowledge distillation(KD),pruning,and quantization *** Bengali being the sixth most spoken language globally,NLP research in this area is *** approach addresses this gap by creating an efficient BERT-based model for Bengali *** have explored 20 combinations for KD,quantization,and pruning,resulting in improved speedup,fewer parameters,and reduced memory *** best results demonstrate significant improvements in both speed and *** instance,in the case of mBERT,we achieved a 3.87×speedup and 4×compression ratio with a combination of Distil+Prune+Quant that reduced parameters from 178 to 46 M,while the memory size decreased from 711 to 178 *** results offer scalable solutions for NLP tasks in various languages and advance the field of model compression,making these models suitable for real-world applications in resource-limited environments.
In this paper we show a polar coding scheme for the deletion channel with a probability of error that decays roughly like 2-√Λ, where Λ is the length of the codeword. That is, the same decay rate as that of seminal...
详细信息
The perception in most existing vision-based reinforcement learning(RL) models for robotic manipulation relies heavily on static third-person or hand-mounted first-person cameras. In scenarios with occlusions and limi...
详细信息
The perception in most existing vision-based reinforcement learning(RL) models for robotic manipulation relies heavily on static third-person or hand-mounted first-person cameras. In scenarios with occlusions and limited maneuvering space, these carefully positioned cameras often struggle to provide effective visual observations during manipulation. Taking inspiration from human capabilities, we introduce a novel RL-based dual-arm active visual-guided manipulation model(DAVMM), which simultaneously infers “eye” actions and “hand” actions for two separate robotic arms(referred to as the vision-arm and the worker-arm) based on current observations, empowering the robot with the ability to actively perceive and interact with its environment. To handle the extensive redundant observation-action space, we propose a decouplable target-centric reward paradigm to offer stable guidance for the training process. For making fine-grained manipulation action decisions, alongside a global scene image encoder, we utilize an independent encoder to extract local target texture features,enabling the simultaneous acquisition of both global and detailed local information. Additionally, we employ residual-RL and curriculum learning techniques to further enhance our model's sample efficiency and training stability. We conducted comparative experiments and analyses of DAVMM against a set of strong baselines on three occluded and narrow-space manipulation tasks. DAVMM notably improves the success rates across all manipulation tasks and showcases rapid learning capabilities.
暂无评论