Edge intelligence has emerged as a promising paradigm to accelerate DNN inference by model partitioning, which is particularly useful for intelligent scenarios that demand high accuracy and low latency. However, the dynamic nature of the edge environment and the diversity of end devices pose a significant challenge for DNN model partitioning strategies. Meanwhile, limited resources of the edge server make it difficult to manage resource allocation efficiently among multiple devices. In addition, most of the existing studies disregard the different service requirements of the DNN inference tasks, such as its high accuracy-sensitive or high latency-sensitive. To address these challenges, we propose a Multi-Compression Scale DNN Inference Acceleration (MCIA) based on cloud-edge-end collaboration. We model this problem as a mixed-integer multi-dimensional optimization problem, jointly optimizing the DNN model version choice, the partitioning choice, and the allocation of computational and bandwidth resources to maximize the tradeoff between inference accuracy and latency depending on the property of the tasks. Initially, we train multiple versions of DNN inference models with different compression scales in the cloud, and deploy them to end devices and edge server. Next, a deep reinforcement learning-based algorithm is developed for joint decision making of adaptive collaborative inference and resource allocation based on the current multi-compression scale models and the task property. Experimental results show that MCIA can adapt to heterogeneous devices and dynamic networks, and has superior performance compared with other methods.

Wireless Sensor Network (WSN) has been widely used with its main characteristics of resilience, scalability, and mobility. However, the node battery capacity in WSN is limited. In addition, in scenes with emergencies such as forest ecological monitoring, data packets of wildfire emergencies have higher real‐time requirements than periodic normal data. Therefore, this paper proposes an energy‐efficient MAC protocol based on Receiver initiation and Multi‐Priority Backoff (RMP‐MAC). RMP‐MAC adopts the wake‐up matching mechanism initiated by the receiver. The sender adjusts its schedule according to the wake‐up information of the receiver to match the receiver, which reduces the energy consumption of idle listening. In addition, RMP‐MAC proposes a multi‐priority factor adaptive backoff mechanism based on event priority, node remaining energy level, and the number of data packets waiting in the transmission queue, ensuring the transmission of emergency data in the actual situation of forest ecological monitoring. Simulation experiments show that compared with PB‐MAC, AP‐MAC, and MPQ‐MAC, RMP‐MAC can reduce energy consumption by 20.22%, 12.47%, and 6.62% respectively. In addition, it has improved in the average collisions, network throughput, and average delay of packets.

In an Ad hoc sensor network, nodes have characteristics of limited battery energy, self-organization and low mobility. Due to the mobility and heterogeneity of the energy consumption in the hierarchical network, the cluster head and topology are changed dynamically. Therefore, topology control and energy consumption are growing to be critical in enhancing the stability and prolonging the lifetime of the network. In order to improve the survivability of Ad hoc network effectively, this paper proposes a new algorithm named the robust, energy-efficient weighted clustering algorithm (RE²WCA). For the homogeneous of the energy consumption; the proposed clustering algorithm takes the residual energy and group mobility into consideration by restricting minimum iteration times. In addition, a distributed fault detection algorithm and cluster head backup mechanism are presented to achieve the periodic and real-time topology maintenance to enhance the robustness of the network. The network is analyzed and the simulations are performed to compare the performance of this new clustering algorithm with the similar algorithms in terms of cluster characteristics, lifetime, throughput and energy consumption of the network. The result shows that the proposed algorithm provides better performance than others.

Network-assisted full-duplex (NAFD) cell-free (CF) massive MIMO systems enable simultaneous uplink and downlink transmissions, where interference suppression and beamforming are critical for improving spectral efficiency and system performance. However, the asymmetric time-varying properties of current network traffic, coupled with the interference problems associated with complex network topologies, make existing resource allocation and interference management strategies difficult to handle, and unable to satisfy the low-latency, high-reliability Quality-of-Service (QoS) requirements of the growing number of terminal devices (TDs). To address these challenges, we propose a novel access method based on decoupled uplink-downlink multi-connectivity transmission to achieve flexible access selection and formulate an optimization problem that maximizes the cumulative fair spectral efficiency by simultaneously optimizing power allocation and link scheduling. To solve this mixed-integer nonlinear programming (MINLP) problem, we propose an optimized transfer scheme that reduces the dimensionality of the action and constraint spaces. Then, we characterize the network states as heterogeneous graph structures and employ node-level and metapath-level attention mechanisms for message passing and aggregation, and obtain graph-level scheduling policy via the heterogeneous graph neural network (HGNN). Finally, in light of the superior performance of Deep Reinforcement Learning (DRL) in exploration-based tasks, we design a holistic updating mechanism using environmental feedback and advantage state-action function, named as HGN-DRL for this end-to-end learning framework. Simulation results demonstrated the effectiveness and scalability of HGN-DRL in large-scale cell-free scenarios.

Task offloading has attracted widespread attention in accelerating applications and reducing energy consumption. However, in areas with surging traffic (nucleic acid testing, concerts, etc.), the limited resources of fixed-base stations cannot meet user requirements. Unmanned aerial vehicles (UAVs) can effectively serve as temporary-base stations or aerial access points for mobile devices (MDs). In the UAV-assisted MEC system, we intend to jointly optimize the trajectory and user association to maximize computational efficiency. This problem is a non-convex fractional problem; therefore, it is not feasible to use only a traditional method, such as Dinkelbach’s method, for solving a fractional problem. Therefore, to facilitate online decision making for this joint optimization problem, we introduce deep reinforcement learning (DRL) and propose a double-layer cycle algorithm for maximizing computation efficiency (DCMCE). Specifically, in the outer loop, we model the trajectory planning problem as a Markov decision process, and use deep reinforcement learning to output the best trajectory. In the inner loop, we use Dinkelbach’s method to simplify the fraction problem, and propose a priority function to optimize user association to maximize computational efficiency. Simulation results show that DCMCE achieves higher computational efficiency than the baseline scheme.

Effective clinical trials are necessary for understanding medical advances but early termination of trials can result in unnecessary waste of resources. Survival models can be used to predict survival probabilities in such trials. However, survival data from clinical trials are sparse, and DeepSurv cannot accurately capture their effective features, making the models weak in generalization and decreasing their prediction accuracy. In this paper, we propose a survival prediction model for clinical trial completion based on the combination of denoising autoencoder (DAE) and DeepSurv models. The DAE is used to obtain a robust representation of features by breaking the loop of raw features after autoencoder training, and then the robust features are provided to DeepSurv as input for training. The clinical trial dataset for training the model was obtained from the ClinicalTrials.gov dataset. A study of clinical trial completion in pregnant women was conducted in response to the fact that many current clinical trials exclude pregnant women. The experimental results showed that the denoising autoencoder and deep survival regression (DAE‐DSR) model was able to extract meaningful and robust features for survival analysis; the C‐index of the training and test datasets were 0.74 and 0.75 respectively. Compared with the Cox proportional hazards model and DeepSurv model, the survival analysis curves obtained by using DAE‐DSR model had more prominent features, and the model was more robust and performed better in actual prediction.