Long Range Wide Area Network (LoRaWAN) provides a promising solution for long-range, low-power wireless communication in Internet of Things (IoT) applications. However, energy consumption remains a critical challenge that significantly impacts network lifetime and scalability. Traditional LoRaWAN implementations rely on automatic and continuous transmission parameter allocation schemes managed by centralized gateways, which fail to adapt to dynamic network conditions such as varying link quality, node mobility, and fluctuating energy levels, leading to excessive energy consumption and reduced network performance. In this work, we propose Adaptive Energy Efficient Routing Protocol (AEERP), a reinforcement learning-based framework that dynamically optimizes transmission parameters in LoRaWAN network. Our approach leverages Expected State-Action-Reward-State-Action (SARSA) to enable intelligent adaptation of spreading factor, transmission power, and gateway selection based on real-time conditions. Key innovations include: (1) a hybrid Q-value initialization strategy combining domain knowledge with exploration, (2) adaptive discount factor and learning rate mechanisms, and (3) joint optimization of transmission parameters based on residual energy, distance, and Packet Delivery Ratio (PDR). Extensive simulations demonstrate that AEERP significantly outperforms state-of-the-art methods, achieving substantial energy conservation, superior PDR, enhanced signal-to-noise ratios, and reduced bit error rates. Results show that AEERP effectively balances energy efficiency, and communication reliability for sustainable LoRaWAN deployments.

Underwater Optical Wireless Sensor Network (UOWSN) is a promising technology as it can achieve high-speed communication in underwater environment. However, affected by the uncertainty of complex underwater environment, the network topology of UOWSN is highly dynamic, making it difficult to quantify flexibility or further optimize the topological structure. Additionally, node mobility and energy constraints pose significant challenges to reliable communication. In this paper, we propose a mobility-aware and energy-efficient flexibility-based network topology evaluation model (ME-FEM) for UOWSNs. Then, a reinforcement learning model, termed ME-FEM-DRL, for optimizing the network topology based on ME-FEM is developed, which enables UOWSN to maintain an optimal topology when working in harsh underwater environments. Theoretical analysis proves the NP-hardness of the optimization problem and demonstrates that our algorithm achieves an approximation ratio of$O(\log N)$with optimal parameter boundaries. Simulation results demonstrate that the proposed method can significantly improve the network flexibility. Compared with the five baseline algorithms in simulations, ME-FEM-DRL reduces normalized topology optimization time cost by 64% and extends network lifetime by 95% on average. Test-bed experiments verify the applicability and effectiveness in practical applications for detecting emergent events.

Underwater Optical Wireless Sensor Networks (UOWSNs) have emerged as a promising solution for high-speed underwater communication. However, these networks face a critical challenge of mutual interference among optical nodes, which occurs when the directional optical beams intersect or coverage areas overlap due to node mobility in dynamic underwater environments. Existing interference management approaches demonstrate limited effectiveness due to their reliance on simplified channel models and inability to handle rapid topology changes, resulting in significant network performance degradation. This paper presents a novel framework that systematically addresses interference management in UOWSNs through two key innovations. First, we propose a Sparse Bayesian Learning-based Interference Detection (SBL-ID) algorithm that enables real-time identification and characterization of interference patterns under complex underwater channel conditions. Second, we develop an Adaptive Interference Alignment and Delay Compensation (AIADC) algorithm that projects interference signals into a reduced-dimensional subspace, thereby enhancing the signal-to-interference ratio and facilitating accurate detection of desired signals amid interference. Our framework transforms the NP-hard interference management problem into tractable optimizations, achieving near-optimal solutions with polynomial time complexity. Extensive simulations demonstrate that our approach reduces BER by 95% and improves network throughput by 67% compared to state-of-the-art techniques. Testbed experiments conducted in both pool and lake further validate our framework's effectiveness, maintaining consistent performance improvements under diverse underwater conditions.

Underwater Optical Wireless Sensor Networks (UOWSNs) play important roles in resource exploration and maritime rescue. However, they face significant challenges in real-time data transmission due to the limited propagation range of optical signals (typically 10-100 m), frequent link disconnections caused by node mobility, and the extended distances to onshore servers. Traditional cloud computing solutions, designed for stable terrestrial networks with stationary edge servers and continuous connectivity, experience high latency (3-15 s) in UOWSNs, rendering them unsuitable for real-time applications in underwater environments. To address this issue, we propose a cloud-edge-end architecture tailored for UOWSNs, which can not only combat unique underwater environmental interference on link connection and topological changes but also guarantee robust and real-time communication. We develop a dynamic link-stability-based task offloading path selection (DLS-TOPS) algorithm for maximizing network resource profits. Afterward, we propose an online primal-dual task offloading (OPD-TO) algorithm for minimizing task completion time. Simulation results indicate that the proposed method significantly improves the real-time performance and resource profits of the network, reducing the total task completion time by more than 50% compared to baseline algorithms. We implemented a UOWSN with a cloud-edge-end architecture using commercial off-the-shelf and verified the applicability and effectiveness of the proposed scheme in emergency detection through testbed experiments.

Underwater Optical Wireless Sensor Network (UOWSN) is a promising technology as it can achieve high-speed communication in underwater environment. However, affected by the uncertainty of complex underwater environment, the network topology of UOWSN is highly dynamic, making it difficult to quantify flexibility or further optimize the topological structure. In this paper, we propose a flexibility-based network topology evaluation model (FEM) for UOWSNs. Then, a reinforcement learning model, termed FEM-DRL, for optimizing the network topology based on FEM is developed, which enables UOWSN to maintain an optimal topology when working in harsh underwater environments. Simulation results demonstrate that the proposed method can significantly improve the network flexibility and reduces the time cost for constructing network topology by 41.8% compared with baseline algorithms. Test-bed experiments verify the applicability and effectiveness in practical applications for detecting emergent events.

Degraded images commonly exist in the general sources of character images, leading to unsatisfactory character recognition results. Existing methods have dedicated efforts to restoring degraded character images. However, the denoising results obtained by these methods do not appear to improve character recognition performance. This is mainly because current methods only focus on pixel-level information and ignore critical features of a character, such as its glyph, resulting in character-glyph damage during the denoising process. In this paper, we introduce a novel generic framework based on glyph fusion and attention mechanisms, i.e., CharFormer, for precisely recovering character images without changing their inherent glyphs. Unlike existing frameworks, CharFormer introduces a parallel target task for capturing additional information and injecting it into the image denoising backbone, which will maintain the consistency of character glyphs during character image denoising. Moreover, we utilize attention-based networks for global-local feature interaction, which will help to deal with blind denoising and enhance denoising performance. We compare CharFormer with state-of-the-art methods on multiple datasets. The experimental results show the superiority of CharFormer quantitatively and qualitatively.

The locality of reference is a well studied phenomenon in computer systems. As one special case, the network locality has been demonstrated to exist in the wired local area networks. Previous research suggests that the network traffic does not follow uniform distribution. In this paper, we explore the network locality in the wireless networks. We take a close look at wireless traces from wireless local area networks (WLANs) and wireless mesh network simulations with different routing protocols to analyze various network locality characteristics. We also measure a new network locality characteristic to explore the possible use of such property in the network coding. Our experiment validates the prevailing existence of network locality in wireless networks and shows how these network locality characteristics are different from those in the wired networks.

Network coding has been shown to improve the performance of the multi-hop wireless networks, by taking advantage of the "mix and broadcast" style communication. In this work, we explore coding-aware routing to further improve end-to-end throughput in the multi-hop wireless networks. A heuristic routing metric ETOX and a novel routing framework HyCare are proposed to route the packets when inter-session network coding protocol is incorporated. Using Network Locality as a heuristic, ETOX homogenizes coding opportunities with other measurements into routes selection. Different from previous attempts on such kind of design, e.g., ERC, ETOX is an unconditional link metric that can be used in many existing routing protocols. It is included in our proposed hybrid routing framework HyCare, which possesses both link-state routing and reverse forwarding functionality. While HyCare can work as an independent routing protocol, it can also collaborate with underlying network coding protocol so as to acquire more accurate ETOX values. Extensive performance evaluation shows significant enhancement for different settings, thereby validating our design methodology.

In this paper, we introduce a new framework for network coding in a multi-radio multi-channel wireless mesh network. Our proposed protocol called Murco, is the first practical work in this area that embraces a distributed solution of network coding in a multi-radio multi-channel network. Murco has been fully implemented and evaluated as a high performance mesh backbone. Experiments indicate very promising results not just on throughput, but also on end-to-end delay. Murco does not depend on any special channel assignment algorithm or routing protocol. Therefore, it offers a total compatibility with existing technologies.

In this paper, we explore two specific Wireless Sensor Network applications of environmental monitoring and motion capturing, where the traditional methods of energy-balanced data propagation are not ideally suited. These solutions are either too generic to exploit the specific characteristic of our application or are too complex to be implemented for simplistic requirements of our application. We propose and analyse a simple, energy efficient and energy balanced algorithm for the propagation of data in our specific application which can be used in other Wireless Sensor Networks with similar characteristics and requirements. We first model our problem using Integer Programming to find an optimal solution which is NP hard to solve. Subsequently, we also provide a heuristic solution that prolongs the lifetime of our network to near the optimal value.