By considering the different cumulant combinations of 2FSK, 4FSK, 2PSK, 4PSK, 2ASK, and 4ASK, this paper established new identification parameters to achieve recognition those digital modulations. The deep neural network (DNN) was also employed improve rate, which designed classify signal based on distinct feature each type that extracted with high order cumulants. extensive simulations demonstrated exceptional classification performance for key features overall success rate proposed...

Vehicular edge computing (VEC) effectively reduces the load of vehicles by offloading tasks from vehicle terminals to servers. However, increase in quantity transmission time and energy network. In order reduce servers improve system response, a shared strategy based on deep reinforcement learning is proposed for complex environment Internet Vehicles (IoVs). The exploits commonality task requests, similar coming different can share results former submitted. be adapted scenarios IoVs. Each...

Multi-agent reinforcement learning (MARL) has made significant progress, largely fueled by the development of specialized testbeds that enable systematic evaluation algorithms in controlled yet challenging scenarios. However, existing often focus on purely virtual simulations or limited robot morphologies such as robotic arms, quadrupeds, and humanoids, leaving high-mobility platforms with real-world physical constraints like drones underexplored. To bridge this gap, we present VolleyBots, a...

In this paper, we investigate the secrecy outage performance of a typical cooperative downlink non-orthogonal multiple access (NOMA) system over Nakagami-m fading channel, in which base station transmits superimposed signal to two users via relay. First, behavior considered Nakagami-$m$ channel under three wiretapping cases, e.g., one eavesdropper (Eve), non-colluding and colluding eavesdroppers, are studied, both analytical asymptotic expressions for probability derived. Next, by...

To reduce the pilot overhead of cascaded channel estimation for RIS-aided Massive MIMO communication system, we proposed a deep compressed sensing-based scheme, where U-shaped network (U-Net), an encoder-decoder with skip connection, is used to recover high-dimensional matrix from limited overhead. The connections between encoder and decoder can fuse features different scales semantic by concatenating feature map, which enhance reconstruction performance channel. further improve extraction...

This letter investigates a jammer-aided cooperative non-orthogonal multiple access (NOMA) system, where one relay is used to deliver information and other relays are acted as jammers. Two simple selection (RS) strategies, e.g., random RS max-min RS, considered in this letter. Analytical asymptotical expressions for secrecy outage probability (SOP) under both schemes developed. Simulation results show that NOMA system with jammer achieves lower SOP than the without moderate high SNR range....

In this letter, we propose a novel time switching (TS) transmission scheme for intelligent reflecting surface (IRS)-assisted unmanned aerial vehicle (UAV)-enabled wireless powered communication network (WPCN). the energy harvesting (EH) phase, operation of IRS is switched between and to improve transfer. information transmitting (IT) assisted unassisted IT avoid deficient duration phase when starved. We formulate an achievable sum-rate maximization problem by jointly optimizing resource...

In this paper, we consider the secrecy outage probability (SOP) of a cooperative non-orthogonal multiple access (NOMA) vehicular communication (VC) system, where relay is working in either half-duplex (HD) or full-duplex (FD) mode. We assume that all these links experience Nakagami-m fading. Some closed-form analytical expressions for SOP performance FD/HD NOMA-VC system are derived. Results show FD-based superior than HD-based low signal noise ratio (SNR) region, and can be further improved...

In this letter, we propose a multi-task learning (MTL)-based joint channel estimation scheme for reconfigurable intelligent surface (RIS) assisted millimeter-wave communication system, where the direct (DC) and cascaded (CC) are estimated at same coherence time by feature of shared pilots. Since dimension CC is much larger than DC, design learnable loss function based on homoscedastic task uncertainty to balance training two subtasks. Meanwhile, residual shrinkage blocks introduced into...

The dissolved gas analysis (DGA) is an effective technique for detecting incipient faults in oil-immersed power transformers. So the paper investigates DGA methods, while employ ANSI/IEEE C57.104 standards and Japan Electric Association - " Gas pattern diagnosis Specific rules as based on to develop a fast transformer fault method practice. We designed report's form which was so easy understand that we can accurate of what up body by MATLAB programmed. user only keys measured data main gases...

In view of a hit-and-run traffic affair, we design novel multi-sensor intelligent transportation monitoring system (MITMS) based on information fusion technology, which has an architecture covering the various roads city. Unlike single sensor system, MITMS takes infrared detector, CCD camera and microprocessor as hardware foundation, integrated with vehicle body color recognition, logo recognition type software module. Thus it can reduce environmental interference in process feature...

Abstract In order to improve the performance of mobile edge computing (MEC) system, intelligent reflecting surface (IRS) has recently been included. This paper investigates computation an IRS‐aided MEC where access point services multi‐MEC devices by utilizing two distributed IRSs operate a partial offloading strategy. Through collaboratively constructing cooperative passive beamforming at IRSs, central processing unit (CPU) frequency, time allocation, and transmit power users, optimization...

In view of a hit-and-run traffic affair, we design novel multi-sensor intelligent transportation monitoring system (MITMS) based on information fusion technology, which has an architecture covering the various roads city. Unlike single sensor system, MITMS takes infrared detector, CCD camera and microprocessor as hardware foundation, integrated with vehicle body color recognition, logo recognition type software module. Thus it can reduce environmental interference in process feature...

The distributed spectrum sensing, in which multiple secondary users (SUs) cooperatively perform has been shown to be beneficial improving the spectrum-hole detection performance significantly. This paper hence considers model of sensing. In addition, this focuses on hybrid strategy, combines underlay and interweave approaches. also scenario, each SU is presence co-channel interference when performing sensing data transmission. Based conducted analysis considered model, studies transmit power...

Dissolved gas analysis (DGA) is an effective tool for detecting incipient faults in power transformers. The ANSI/IEEE C57.104 standards, the most popular guides interpretation of gases generated oil-immersed transformers, and IEC-Duval triangle method are integrated to develop proposed transformer fault diagnosis method. key dissolved gases, including H 2 , CH 4 C 6 total combustible (TCG), suggested by ASTM D3612s instruction DGA investigated. tested data oil were taken from substations...

In this work, we introduce OmniDrones, an efficient and flexible platform tailored for reinforcement learning in drone control, built on Nvidia's Omniverse Isaac Sim. It employs a bottom-up design approach that allows users to easily experiment with various application scenarios top of GPU-parallelized simulations. also offers range benchmark tasks, presenting challenges ranging from single-drone hovering over-actuated system tracking. summary, propose open-sourced simulation platform,...