Accurate sizing of colorectal polyps is essential for malignancy risk assessment and surveillance planning. However, both visual estimation and current instrument-based aids often suffer from variability or workflow disruption. Recent AI-based approaches typically rely on reference objects, camera calibration, or depth networks with suboptimal accuracy in endoscopic imagery. We present a calibration-free pipeline that segments the polyp and then couples ViTCAN-Depth, a monocular metric-depth model that fuses parallel CNN and Vision-Transformer encoders via channel-attention gating, with Depth–Pixel Linear (DPL), a lightweight module that converts pixel diameter and depth into real-world diameter using a learned scalar, eliminating camera calibration and reference objects. ViTCAN-Depth outperforms state-of-the-art CNN- or ViT-based metric-depth networks on the C3VD synthetic benchmark, and yields higher-fidelity depth maps on real colonoscopy images. Across 78 polyps from five independent cohorts, the system achieves a mean absolute error of 0.67mm (RMSE=0.88mm), suggesting its potential for integration into clinical workflows.

Face aging tasks aim to simulate changes in the appearance of faces over time. However, due to the lack of data on different ages under the same identity, existing models are commonly trained using mapping between age groups. This makes it difficult for most existing aging methods to accurately capture the correspondence between individual identities and aging features, leading to generating faces that do not match the real aging appearance. In this paper, we re-annotate the CACD2000 dataset and propose a consensus-agent deep reinforcement learning method to solve the aforementioned problem. Specifically, we define two agents, the aging process agent and the aging personalization agent, and model the task of matching aging features as a Markov decision process. The aging process agent simulates the aging process of an individual, while the aging personalization agent calculates the difference between the aging appearance of an individual and the average aging appearance. The two agents iteratively adjust the matching degree between the target aging feature and the current identity through a form of synergistic cooperation. Extensive experimental results on four face aging datasets show that our model achieves convincing performance compared to the current state-of-the-art methods.

A pragmatic distributed algorithm (PDA) is proposed for supporting the efficient spectral access of multiple Primary Users (PUs) and Cognitive Users (CUs) in cooperative Cognitive Radio (CR) networks. The novelty of our PDA is that the PUs negotiate with the CUs concerning the specific amount of relaying and transmission time, the CU is granted, which the CU will either accept or decline. The CUs may serve as relay nodes for relaying the signal received from the PUs to their destinations, while both the PUs' and the CUs' minimum rate requirements are satisfied. This will reduce the required transmission power and/or increase the transmission rate of the PU. Our results show that the proposed scheme performs better than the benchmarker, despite its significantly lower overhead and complexity. Moreover, we show that the cooperative spectral access based on our PDA reaches an equilibrium, when it is repeated for a sufficiently long duration. These benefits are achieved, because the PUs are motivated to cooperate by the incentive of achieving a higher PU rate, whilst non-cooperation can be discouraged with the aid of a limited-duration punishment. Furthermore, we invoke an attractive practical adaptive Turbo Trellis Coded Modulation (ATTCM) scheme, which appropriately adjusts the code rate and the modulation mode according to the near-instantaneous channel conditions. It was found that the joint design of coding, modulation and user-cooperation may lead to significant mutual benefits for all the PUs and the CUs.

A cooperative Medium Access Control (MAC) protocol employing auction-style relay selection combined with superposition coding is designed. In our proposed scheme, the source achieves its target throughput with the aid of cooperation. The potential candidate relays carry out autonomous decisions concerning whether to contend for a transmission opportunity to convey their traffic in the light of their individual energy requirements. Simulation results demonstrate that our scheme is capable of providing both considerable energy savings, as well as substantial throughput improvements for both the source and the relay in a 'win-win' cooperation regime.

In this paper, we design an energy-efficient cooperative Medium Access Control (MAC) protocol combined with physical layer power / rate control in order to minimize the energy consumption. Based on the Channel State Information (CSI) and relay-to-destination distance, the potential candidate relays carry out autonomous decisions for minimizing the transmission power required for forwarding their data, when relying on their cooperation. Simulation results demonstrate that our scheme is capable of providing considerable energy savings, while maintaining the target Frame Error Ratio (FER), which is achieved at the cost of introducing a modest additional MAC overhead.

This paper proposes a channel error adaptive FEC algorithm to balance the conflict between the QoS of video transmission and the bandwidth utilization ratio in wireless IP networks. Two analytic models are derived, one is playable frame rate in MPEG video stream, another is effective utilization ratio of FEC. Based on these analytic models, quality of video stream and effective utilization ratio of FEC under different network conditions (presented by packet loss probability in this paper) are predicted. Then optimal amount of redundant packets is calculated and decided, which makes both the quality of video stream and the effective utilization ratio of FEC approximate their maximum. The simulation results show that the proposed algorithm improves system performance in both the QoS of wireless video transmission and the utilization of bandwidth.

Based on a combination of non-linear grad-contrast operator and multi-resolution wavelet analysis, a kind of image enhancement processing algorithm for useful tiny characters is presented. The algorithm can enhance the tiny characters while confine amplifying the noise. Low-contrast structure can be found in many kinds of digital images, which makes the images vague and uncertainly, especially in X-ray images. The analysis of the results shows that local regions of the image are enhanced by using the concept of the grad contrast to make image clearer adaptively. Experiments were conducted on real pictures, and the results show that the algorithm is flexible and convenient.