Federated learning (FL) is crucial in edge computing for next-generation wireless networks because it enables collaborative learning among devices while protecting data privacy. However, marine edge networks encounter complex issues, including frequent network disruptions, highly dynamic network topologies, and stringent bandwidth limitations, compared to traditional FL environments. Additionally, the heterogeneity of devices and unconventional data distribution complicate model training further. Moreover, due to the broadcast nature and dynamic vulnerability of wireless medium, edge nodes are susceptible to interference or malicious attacks, such as information theft and poisoning attacks, leading to inaccurate or even failed learning outcomes. Many distributed learning algorithms assume stable node environments, overlooking security and communication bottlenecks, which reduces learning efficiency and model performance. Therefore, researching privacy protection and defenses against poisoning attacks in federated learning within edge computing networks is of significant importance and value. To address this, we propose the Differential Evolution Edge-Partially Federated Learning framework, which aims to secure gradient communication by leveraging the characteristics of heterogeneous devices and non-independent and identically distributed (Non-IID) data, thereby reducing the risk of information leakage during gradient communication and effectively mitigating the impact of data heterogeneity in edge environments. Additionally, we have designed a Partial Layer Mean Detection method based on this framework to detect and defend against poisoning attacks. This algorithm protects the security of gradient information without significantly increasing computational and communication overhead. Experimental results demonstrate that, in marine edge computing environments, this framework improves privacy protection performance by 20% and increases poisoning attack defense rates by 10% without adding extra computational costs.

Global warming is a prominent problem in the world, and a lot of research has been done on how to stop or slow it down. The main cause of global warming is pollution, especially the four main pollutants–carbon monoxide, ozone, nitrogen dioxide, and sulfur dioxide.1 With the use of AI, models can be built that provide insight into pollutant levels across regions of the US. In this project, linear regression models were built that predicted these four pollutant levels across four regions of the US. Pollution levels were studied and used to determine the impact of each pollutant in each region. Results showed that ozone in the west was predicted to have the worst pollutant levels, suggesting resources can be allocated to this region over others to lessen the harmful effects of pollution.

Vehicle-to-vehicle dynamic wireless charging (V2V-DWC) is a contemporary electrified transportation technology in which a dedicated charging vehicle supplies power to a user vehicle. This technology is gaining popularity due to the slow progress in energy storage technology and the limited availability of plug-in charging stations. The concept of V2V wireless power transfer offers a means for EVs to replenish their batteries during a journey. Literature shows that the concept has been empirically validated through analysis and experimentation, however, the issue of misalignment has not been addressed from this perspective yet. For optimal power transfer in V2V, the coils need to be in perfect alignment. Lateral Misalignment (LTM) arises when these coils are not properly aligned which results in undesirable energy loss. Furthermore, there is still a deficiency in the development of appropriate controllers for V2V misalignment problem solution. This paper aims to develop Neural Network based Adaptive Fuzzy Logic Controller (ANFIS), to mitigate the misalignment problem of V2V-DWC system. The paper delves into a comparative analysis of the proposed controller with the existing Fuzzy Logic Controller (FLC) to assess their effectiveness for different degrees of LTMs. The effectiveness of the proposed ANFIS controller has been assessed using simulations in MATLAB/Simulink alongside experimental tests. Results show that proposed ANFIS outperforms the FLC in both simulated and experimental scenarios in solving the V2V misalignment issue.

Iterative thresholding-type algorithm, as one of the typical methods of compressed sensing (CS) theory, is widely used in sparse recovery field, because of its simple computational process. However, the estimation accuracy and convergence speed achieved by this type of algorithm with a nonconvex regularization, e.g., iterative half thresholding (IHalfT) algorithm, are not satisfactory, which limits its practical application. To improve the performance, a modified algorithm is proposed in this paper. Firstly, a novel non-negative expression is introduced in the algorithm to reduce the gap between the relaxation function and the objective function, which can bring tens of dB estimation accuracy improvement, and the convergence of the modified algorithm is verified. Secondly, the fundamental reasons for the remarkable improvement of performance are discussed and analyzed through theoretical derivation. Thirdly, the applicable conditions are elaborated for the modified algorithm. Finally, extensive experimental results demonstrate the effectiveness of the modified iterative thresholding-type algorithm with nonconvex regularization. Keywords-compressed sensing (CS), iterative hard thresholding (IHT), iterative soft thresholding (IST), iterative half thresholding (IHalfT), fast iterative shrinkage-thresholding algorithm (FISTA), normalized iterative hard thresholding (NIHT), alternating direction method of multipliers (ADMM).

This manuscript summarizes work on the Capsule Vision Challenge 2024 by MISAHUB. To address the multi-class disease classification task, which is challenging due to the complexity and imbalance in the Capsule Vision challenge dataset, this paper proposes CASCRNet (Capsule endoscopy-Aspp-SCR-Network), a parameter-efficient and novel model that uses Shared Channel Residual (SCR) blocks and Atrous Spatial Pyramid Pooling (ASPP) blocks. Further, the performance of the proposed model is compared with other well-known approaches. The experimental results yield that proposed model provides better disease classification results. The proposed model was successful in classifying diseases with an F1 Score of 78.5% and a Mean AUC of 98.3%, which is promising given its compact architecture.

Federated learning (FL) enables multiple parties to collaboratively train machine learning models while preserving data privacy. However, securing communication within FL frameworks remains a significant challenge due to potential vulnerabilities to data breaches and integrity attacks. This paper proposes a novel approach using Dilithium, a robust digital signature framework, to enhance data security in FL. By integrating Dilithium into FL protocols, this study demonstrates enhanced protection against data tampering and unauthorized access, thereby promoting safer and more efficient collaborative model training across distributed networks. Furthermore, our approach incorporates an optimized key distribution mechanism that reduces latency and ensures seamless synchronization among participants. Additionally, the proposed client selection algorithm aims to minimize the time and computational load on the system. Experimental results demonstrate that our system achieves a total processing time of 6.891 seconds, significantly outperforming the 10.24 seconds of normal FL and 12.32 seconds of FL-Dilithium systems on the same computing platforms. Additionally, the proposed model achieves an accuracy of 94%, surpassing the 93% of the normal FL and 92% of the FL-Dilithium models.

Our approach leverages the massive parallelism and computational power of a modern graphics processing unit (GPU) to accelerate CRYSTALS-Dilithium's key operations. While post-quantum cryptographic algorithms like Dilithium offer robust security, they face computational challenges in high-throughput scenarios. Dilithium's performance bottlenecks, particularly in polynomial arithmetic and random sampling, have limited its practical deployment. To address these challenges, we leverage GPU acceleration as a promising solution to enhance efficiency. Our approach develops novel GPU-centric algorithms and data structures tailored to Dilithium's requirements. We focus on optimizing number theoretic transforms (NTT), polynomial arithmetic, and random sampling, with an emphasis on batch processing and efficient memory management to maximize throughput. Experimental results demonstrate significant performance improvements over existing implementations. Our GPUaccelerated version consistently outperforms reference implementations, achieving speed-ups ranging from 53.7% to 59.9% for signature generation and 20.0% to 63.8% for verification across various security levels. These results highlight the potential of our approach in enabling efficient post-quantum cryptography for high-performance applications.

Generative Artificial Intelligence (AI) is revolutionizing educational technology by enabling highly personalized and adaptive learning environments within Intelligent Tutoring Systems (ITS). This report delves into the integration of Generative AI, particularly large language models (LLMs) like GPT-4, into ITS to enhance personalized education through dynamic content generation, real-time feedback, and adaptive learning pathways. We explore key applications such as automated question generation, customized feedback mechanisms, and interactive dialogue systems that respond to individual learner needs. The report also addresses significant challenges, including ensuring pedagogical accuracy, mitigating inherent biases in AI models, and maintaining learner engagement. Future directions highlight the potential advancements in multimodal AI integration, emotional intelligence in tutoring systems, and the ethical implications of AI-driven education. By synthesizing current research and practical implementations, this report underscores the transformative potential of Generative AI in creating more effective, equitable, and engaging educational experiences.

This study presents a novel chipless complementary split-ring resonator (CSRR) loaded substrate integrated waveguide (SIW) tag, coupled with an ultra-wideband coplanar antenna, for real-time monitoring of lubricant evaporation on lubricant-infused surfaces (LISs). The sensor introduces a new method for assessing the stability of the lubricant layer, a critical factor for the efficient operation of these coatings. Its design and functionality have been validated through simulations and measurements of the evaporation rate of two different lubricants with different vapor pressures, demonstrating high sensitivity in detecting lubricant evaporation. This sensor represents a significant advancement in biomaterial development and testing, providing a real-time solution to ensure the effectiveness of lubricant-infused coatings, which is essential for minimizing complications like non-specific adhesion of blood components and bacteria.

The principle of maximum entropy is a well-established technique for choosing a distribution that matches available information while minimizing bias. It finds broad use across scientific disciplines and in machine learning. However, the principle as defined by Jaynes (1957) is susceptible to noise and error in observations. This forces real-world practitioners to use relaxed versions of the principle in an ad hoc way, negatively impacting interpretation. To address this situation, we present a new principle we call uncertain maximum entropy that generalizes the classic principle and provides interpretable solutions irrespective of the observational methods in use. We introduce a convex approximation and expectationmaximization based algorithm for finding solutions to our new principle. Finally, we contrast this new technique with two simpler generally applicable solutions theoretically and experimentally show our technique provides superior accuracy.

This article explores the integration of weather balloons within non-terrestrial networks (NTNs) as a pioneering solution for smart cities, addressing both connectivity and security challenges. Weather balloons are proposed as a feasible alternative to satellites, offering seamless connectivity by overcoming terrestrial obstructions and reducing signal latency. Meanwhile, the application of Quantum Key Distribution (QKD), combined with AI optimization, ensures robust data security in high-speed transmission environments. This dual-layer approach forms a comprehensive end-to-end solution, where weather balloons and quantum security work in tandem to provide a resilient, scalable, and secure network infrastructure. The synergy of these technologies is discussed, highlighting their potential to revolutionize smart city infrastructure and set new standards for consumer electronics.

This paper presents a novel method for eigenvalue computation using a distributed cooperative neural network framework. Unlike traditional techniques that struggle with scalability in large systems, our decentralized algorithm enables multiple autonomous agents to collaboratively estimate the smallest eigenvalue of large matrices. Each agent uses a localized neural network model, refining its estimates through inter-agent communication. Our approach guarantees convergence to the true eigenvalue, even with communication failures or network disruptions. Theoretical analysis confirms the robustness and accuracy of the method, while empirical results demonstrate its better performance compared to some traditional centralized algorithms

The deterministic generation of robust soliton comb has significant meaning for the optical frequency combs to be widely used in various applications. As a novel form of microcomb, Soliton crystal holds the advantages of easy generation, high conversion efficiency, and excellent thermal robustness. Here, we report the turnkey deterministic generation of 'Palmlike' soliton crystal with a free-running scheme. The robustness of the turnkey soliton crystal generation is also investigated in multiple aspects, including the success rate, the thermal robustness, and the long-term stability. The experiment results reveal our turnkey soliton crystal can achieve nearly a 100% success rate with a power variation less than ±1.5 dB over one hundred trials of two samples, is insensitive to thermal effects, and is robust to the environment during four-hour laboratory time.

The binding of proteins and ligands is critically important in drug design. However, accurately and efficiently predicting binding affinity still remains a formidable challenge. Recent research has established that deep learning-based computational methods provide a more straightforward and effective solution for quantifying binding affinity compared to traditional experimental approaches. In this study, we introduce a novel sequence-based deep learning architecture, termed ALSRI-Net (Attention-based Long-Short-Range Interaction Network). ALSRI-Net employs self-attention and cross-attention mechanisms to distinctly capture long-range and short-range interaction features between proteins and ligands. By integrating these interaction features, ALSRI-Net delivers more precise and robust predictions. The performance of ALSRI-Net was rigorously evaluated using the PDBbind v2016 core set and PDBbind v2013 core set, which serve as benchmarks, demonstrating the superior performance of ALSRI-Net. Additionally, we conducted dimensionality reduction and visualization of the extracted long-range and short-range interaction features, as well as their integrated features, providing insights into the respective contributions of these interactions and elucidating why the integration of these features leads to enhanced predictive accuracy. Our code and models are publicly available at https://github.com/Funiverse/ ALSRI-Net.

The significance of collaboration and coordination in these systems cannot be overstated. They are fundamental to ensuring that individual agents, each with their unique capabilities and roles, can function together effectively. This paper delves into the theoretical foundations and practical mechanisms of collaboration and coordination within MAS, exploring their evolution, key concepts, and real-world applications.

Color space is introduced to discuss 3-coloring of a graph G(V,E). It is a 3x|V| lattice that every column expresses a vertex and every row expresses a color. A color space can provide with all the information of a colored graph that include the topology, coloring and coloring transformation. So, it reduces calculation in searching 3-uncolorable vertices, And, we may try to find a deterministic algorithm to search some 3-uncolorable by using the color space.

Existing control paradigms for lower-limb exoskeletons aim at replicating task-specific, subject-dependent reference kinematics, which overly constrain voluntary human motion. Individuals with voluntary control over their lower-extremities would likely benefit from the ability to choose their gait patterns freely while being assisted by exoskeletons during different activities. In this paper, we propose a novel control paradigm and its implementation to alter a human's Centroidal Momentum, i.e., a sum of projected limb momenta onto the human's center of mass, through tracking a dynamic reference Centroidal Momentum to provide consistent assistance across tasks. This reference Centroidal Momentum is defined based on the human's self-selected gaits with scaled anatomical parameters, rather than reference kinematics of specific locomotor tasks. The resulting control strategy does not prescribe any reference trajectories, providing flexibility for human users. We demonstrate simulation results on a human-like biped and experimental results on four human subjects wearing a bilateral hip exoskeleton performing various walking tasks under different speed and incline/decline conditions. These results show that the generated assistance/resistance can reduce/increase the subjects' muscle efforts, respectively, across the performed tasks.

To find more 3-uncolorable vertices recognizable in polynomial time, we consider mobile 3-uncolorable vertices. In color space, the transfer is expressed by shift of dot strings in alternate configurations. An alternate configuration is the union of a DJC and movable dot strings relative to the DJC. It has several FLC one of which is a WFLC. The movement of the movable dot string exchanges FLC with WFLC to ensure that WFLC exists always in the configuration. We prove that an additional dot string (ADS) to an alternate configuration may turn the configuration to be a triplet. So, 3-uncolorable vertices in the graph of alternate configurations in planar graph with degree more than 4 G(V,E) can be recognized in O(|V8|). We need to find more recognizable 3-uncolorable vertices in polynomial time for judging 3-coloring of planar graph.