A novel framework is proposed for quality of experience driven deployment and dynamic movement multiple unmanned aerial vehicles (UAVs). The problem joint non-convex three-dimensional (3-D) the UAVs formulated maximizing sum mean opinion score ground users, which proved to be NP-hard. In aim solving this pertinent problem, a three-step approach attaining 3-D UAVs. First, genetic algorithm based K-means (GAK-means) utilized obtaining cell partition users. Second, Q-learning proposed, in each...

A reconfigurable intelligent surface (RIS)-assisted multi-user downlink communication system over fading channels is investigated, where both non-orthogonal multiple access (NOMA) and orthogonal (OMA) schemes are employed. In particular, the time overhead for configuring RIS reflective elements at beginning of each channel considered. The optimization goal maximizing effective throughput entire transmission period by jointly optimizing phase shift power allocation AP block. an effort to...

A novel framework is proposed for cellular offloading with the aid of multiple unmanned aerial vehicles (UAVs), while non-orthogonal access (NOMA) technique employed at each UAV to further improve spectrum efficiency wireless network. The optimization problem joint three-dimensional (3D) trajectory design and power allocation formulated maximizing throughput. Since ground mobile users are considered as roaming continuously, UAVs need be re-deployed timely based on movement users. In an...

The effective trajectory design of multiple unmanned aerial vehicles (UAVs) is investigated for improving the capacity communication system. aim maximizing real-time downlink under coverage constraint by reaping mobility benefits UAVs. problem three-dimension (3D) dynamic movement UAVs formulated as a Constrained Markov Decision Process (CMDP) problem, while constrained Deep Q-Network (cDQN) algorithm proposed solving problem. In cDQN model, each UAV acts an agent to explore and learn its 3D...

Traffic prediction constitutes a pivotal facet within the purview of Intelligent Transportation Systems (ITS), and attainment highly precise predictions holds profound significance for efficacious traffic management. The precision prevailing deep learning-driven models typically sees an upward trend with rise in volume training data. However, procurement comprehensive spatiotemporal datasets is often fraught challenges, primarily stemming from substantial costs associated data collection...

This paper develops an intelligent grid-interactive building controller, which optimizes operation during both normal hours and demand response (DR) events. To avoid costly on-demand computation to adapt non-linear models, the controller utilizes reinforcement learning (RL) makes real-time decisions based on a near-optimal control policy. Learning such policy typically amounts solving hard non-convex optimization problem. We propose address this problem with novel <italic...

Soft robotics are robotic systems made of materials that similar in softness to human soft tissues. Recent medical robot designs, including rehabilitation, surgical, and diagnostic robots, categorized by application reviewed for functionality. Each design is analyzed engineering characteristics clinical significance. Current technical challenges fabrication, sensor integration, control discussed. Future directions portable robust actuation power sources, adoptability, regulatory issues summarized.

A novel framework for Quality of experience (QoE)-driven deployment and movement multiple unmanned aerial vehicles (UAVs) is proposed. The problem joint non-concave 3D dynamic maximizing the sum mean opinion score (MOS) users formulated, which proved to be NP-hard. In an effort solve this problem, we proposed a three-step approach obtain UAVs. More specifically, in first step, GAK-means algorithm invoked cell partitioning ground users. Secondly, Q-learning based proposed, each UAV considered...

Extreme weather has an adverse effect on the stable operation of power system. In order to improve grid balance problem considering extreme in medium /long-term time scale, this paper proposes electrical and energy method weather. Firstly, influence hydropower renewable energy, random multi-scenario is adopted model renewble energy. On basis, medium/long-term system established. At same time, IEEERTS-79 taken as example verify feasibility proposed method. The results show that can better...

Three-dimensional (3D) printed tissue engineered bone was used to repair the defects in oral and maxillofacial (OMF) region of experimental dogs. Canine marrow stromal cells (BMSCs) were obtained from 9 male Beagle dogs vitro cultured for osteogenic differentiation. The OMF scanned 3D surgical guide plate mold by ProJet1200 high-precision printer using implant materials followed sintering at 1250 °C. bones co-cultured with BASCs 2 or 8 d. cell scaffold composite placed fixed 3 groups....

Conventional vascular interventional surgery (VIS) is performed under fluoroscopic guidance by surgeons. In order to reduce X-ray irradiation the radiologists, catheter operating systems have been developed assist This paper proposed an active supporting medical manipulator, which can neatly adjust and accurately position system. Forward kinematics inverse were solved based on analysis. Quintic polynomial interpolation was adopted in trajectory planning for smooth motion of manipulator. The...

Abstract In light of the increasing hydrogen permeability in distribution networks as a means to cope with extreme events and improve network resilience, this paper introduces novel strategy for enhancing power resilience. It outlines comprehensive approach that focuses on dispatching storage (HS) vehicle (HV) within penetrated systems (HPDS), segmenting into pre‐disaster post‐disaster stages. Firstly, stage, models HS HVs are established gather operational data facilitate rapid response,...

The Robbins-Monro stochastic approximation algorithm is a foundation of many algorithmic frameworks for reinforcement learning (RL), and often an efficient approach to solving (or approximating the solution to) complex optimal control problems. However, in cases practitioners are unable apply these techniques because inherent high variance. This paper aims provide general "quasistochastic approximation," which all processes under consideration deterministic, much like quasi-Monte-Carlo...

Reinforcement learning is of vital significance in machine and also a promising approach for traffic signal control urban road networks with assistance deep neural networks. However, large scale network, the centralized reinforcement beset difficulties due to extremely high dimension joint action space. The multi-agent (MARL) overcomes problem by employing distributed local agents whose space much smaller. Even though, MARL introduces another issue that multiple interact environment...

P2A (Power to ammonia) is one of the important ways large-scale consumption renewable energy, and technological routes for chemical industry realize low-carbon clean development. The new off-grid energy power hydrogen ammonia system lacks support large grids due complex mathematical model system, more variables, cumbersome constraints, which leads solving difficulties, production simulation results obtained suffer from problems low economic efficiency high abandonment rate. To address...

A novel framework is proposed for enhancing the driving safety and fuel economy of autonomous vehicles (AVs) with aid vehicle-to-infrastructure (V2I) communication networks. To solve this pertinent problem, a double deep Q-network (DDQN) algorithm making collision-free decisions. Thus, trajectory velocity AV are determined by receiving real-time traffic information from base stations (BSs). Compared to conventional algorithm, DDQN capable overcoming large overestimation action values...

Driven by the unprecedented high throughput and low latency requirements in next-generation wireless networks, this paper introduces an artificial intelligence (AI) enabled framework which unmanned aerial vehicles (UAVs) use non-orthogonal multiple access (NOMA) mobile edge computing (MEC) techniques to service terrestrial users (MUs). The proposed enables MUs offload their computational tasks simultaneously, intelligently, flexibly, thus enhancing connectivity as well reducing transmission...

In order to meet the real-time performance requirements, intelligent decisions in many IoT applications must take place right here now at network edge. The conventional cloud-based learning approach would not be able keep up with demands achieving edge intelligence these applications. Nevertheless, pushing artificial (AI) frontier achieve is highly nontrivial due constrained computing resources and limited training data To tackle challenges, we develop a distributionally robust optimization...

Conventional vascular interventional surgery (VIS) is performed by surgeons under fluoroscopic X-ray guidance. Catheter operating systems have been developed to reduce physical stress and irradiation the radiologists. However, catheter are all attached surgical bed or fixed at tip of passive manipulator, which inconvenient adjust position orientation system. Therefore, a novel active supporting medical manipulator was accurately firmly hold The structure synthesized optimized according...

A novel framework is proposed for quality of experience (QoE)-driven deployment and dynamic movement multiple unmanned aerial vehicles (UAVs). The problem joint non-convex three-dimensional (3D) the UAVs formulated maximizing sum mean opinion score (MOS) ground users, which proved to be NP-hard. In aim solving this pertinent problem, a three-step approach attaining 3D UAVs. Firstly, genetic algorithm based K-means (GAK-means) utilized obtaining cell partition users. Secondly, Q-learning...