Expansion Module Research Articles

Research on Fire Smoke Traceability Based on Emotional Intelligence Jaya Algorithm

To timely detect fire smoke in the early stages and trace the gas generated, thereby reducing the loss of human life and property and the damage to the ecological environment, this paper proposes a fire smoke tracing method based on the Emotional Intelligence Jaya algorithm (EIJaya). The algorithm assigns an anthropomorphic mental state to the Unmanned Aerial Vehicle (UAV) in the traceability task to realize its self-evaluation and social evaluation. In the simulation concentration field, the EIJaya algorithm, the basic Jaya algorithm, and the PSO algorithm were used for the simulation verification of gas traceability, and the simulation results proved the advantages of the EIJaya algorithm in terms of the success rate and the iteration times. In this paper, the TT UAV is chosen as an experimental tool to utilize the functions of its expansion module fully, and the experimental hardware system was constructed by combining it with the corresponding sensors. The corresponding experimental scene was built in the indoor environment, and the EIJaya algorithm was used to make multiple UAVs cooperate and carry out traceability experiments, which verified the algorithm's feasibility in practical applications and proved that the algorithm could quickly and accurately trace the fire smoke.

An enhanced key expansion module based on 2D hyper chaotic map and Galois field

Key expansion is an essential component in block cryptography, which serves the round function. By analyzing key expansion module of AES, it is found that the round-keys are highly correlated, and current round-key can be derived from its previous or the next round-key. To address these weaknesses, first, a 2D exponential chaotic map (2D-ECM) that exhibits ergodicity and superior randomness was constructed. Then, the Lyapunov exponents (LEs) were calculated based on the singular value decomposition (SVD) method. In addition, TestU01 test results showed that the sequences generated by 2D-ECM have better randomness. Further, an enhanced key expansion module was designed utilizing 2D-ECM and primitive polynomial over GF(2n), which has irreversibility and parallelism, and the round-keys are independent of each other. Simulation results and performance analysis demonstrated the effectiveness of the proposed enhanced key expansion module.

Measuring and Extracting the Complex Permittivity of Porous Ceramic Materials in the Y-Band

ABSTRACT Porous ceramics find extensive applications in aerospace and other fields, and the measurement of their electromagnetic parameters is helpful in optimization of material properties and device designs. In this paper, a free-space 8f quasi-optical measurement system consisting of a vector network analyzer, a 325–500 GHz frequency expansion module, and four off-axis parabolic mirrors have been established to measure the transmission parameter S21 of porous ceramics. The complex permittivity was extracted according to the Newton-Raphson iterative method utilizing its measured S21 parameters based on flat mode. The porous ceramics with different porosity and density were measured and the relationships between their permittivity and porosity and density was established, respectively. These results are beneficial to the quality evaluation and application design of porous ceramic materials in the aerospace field.

Development of active and passive reactivity control systems for a fast spectrum small modular reactor

This paper presents the development of active and passive reactivity control systems implemented in a fast-spectrum small modular reactor (SMR). The design of the control assembly serving as an active system still relies on a conventional rod-typed geometry. To enhance its worth, a thermalizing ZrH1.6 pin is introduced, which softens the neutrons around the control assembly, leading to increased neutron absorption in the absorber material. Additionally, a control assembly with a partial-length absorber is strategically placed at a certain location to mitigate high peak power levels. Two passive systems have been developed to enhance reactor safety: the gas expansion module (GEM) aimed to mitigate the unprotected loss of flow (ULOF), and the liquid lithium-6 absorber intended to address unprotected transient overpower (UTOP) and unprotected loss of heat sink (ULOSH) scenarios. With a total of 24 GEMs and 18 lithium-6 channels installed, they provide negative reactivity ranging from about 932 to 693 pcm (1.17$ to 1.03$) and 521 to 602 pcm (0.65$ to 0.89$), respectively.

Thermodynamic and economic analysis of a novel compressed air energy storage system coupled with solar energy and liquid piston energy storage and release

Compressed air energy storage (CAES) is one of the important means to solve the instability of power generation in renewable energy systems. To further improve the output power of the CAES system and the stability of the double-chamber liquid piston expansion module (LPEM) a new CAES coupled with liquid piston energy storage and release (LPSR-CAES) is proposed. The coupled LPEM conducts suction stage B at the end of the expansion stage, ensuring stable exhaust pressure and temperature for the module. By establishing the thermodynamic and economic models of LPSR-CAES, the effect laws of key node parameters on the system performance are investigated. The results show that the heat transfer between liquid droplets and air dominates the heat transfer in LPEM. The proposed LPEM exhibits excellent isothermal performance and stability, with a maximum temperature difference of about 20 K during the cycle, and stable exhaust temperature changes within 10 K. Under the design conditions, the converted electrical efficiency, round-trip efficiency, exergy efficiency and net present value of the system are 68.31 %, 58.86 %, 66.99 % and 12.25 M$ respectively. The higher the solar supplement temperature, the more outstanding the thermal and economic performance of the system. The short-term energy storage system performance of the proposed system is more prominent. Based on the actual light data, the system can achieve 72.09 % and 69.41 % of converted electrical efficiency and exergy efficiency, respectively, at the 219th day. The results of this study provide theoretical support for the engineering application of the proposed system.

Domain expansion fusion single-domain generalization framework for mechanical fault diagnosis under unknown working conditions

In real industrial scenarios, mechanical systems often adjust working conditions based on specific tasks, leading to challenges in collecting data for all possible machine states in advance. Consequently, applying deep learning models trained on data from a single working condition directly to other unknown working condition poses a significant challenge. To tackle this issue, a novel domain expansion fusion single-domain generalization framework is proposed for machinery fault diagnosis under unknown working conditions. Firstly, a domain expansion module that can be controlled via a constraint function is developed to create expanded domains that generate samples with controlled differences from the source domain. Subsequently, a dual-branch feature fusion network is proposed in the feature extraction module. It combines two distinct feature extractors and employs a weighted average fusion strategy to extract discriminative features. Additionally, a state recognition module is implemented through a multi-classifier ensemble strategy to enhance the robustness and accuracy of health state identification. Lastly, an adversarial contrastive training strategy is employed to optimize the network and enhance its generalization capabilities and fault diagnosis performance. Through case studies conducted on two mechanical fault datasets, the proposed method demonstrates good diagnosis performance on single-domain generalized diagnosis tasks with an average accuracy of 87.53%. Its generalization effect is validated. Furthermore, the comparison and ablation experiment results confirm the effectiveness and superior performance of the proposed intelligent fault diagnosis method in scenarios with unknown working conditions with an average accuracy improvement of at least 3.94%.

Which is better? Taxonomy induction with learning the optimal structure via contrastive learning

A taxonomy represents a hierarchically structured knowledge graph that forms the infrastructure for various downstream applications, including recommender systems, web search, and question answering. The exploration of automated induction from text corpora has yielded notable taxonomies such as CN-probase, CN-DBpedia, and Zhishi.schema. Despite these efforts, existing taxonomies still face two critical issues that result in sub-optimal hierarchical structures. On the one hand, commonly observed taxonomies exhibit a coarse-grained and “flat” structure, stemming from a noticeable lack of diversity in both nodes and edges. This limitation primarily originates from the biased and homogeneous data distribution. On the other hand, the semantic granularity among “siblings” within these taxonomies remains inconsistent, presenting a challenge in accurately and comprehensively identifying hierarchical relations. To address these issues, this study introduces a novel taxonomy induction framework composed of three meticulously designed components. Initially, we established a seed schema by leveraging statistical information from external data sources as distant supervision to append nodes and edges containing “generic semantics”, thereby rectifying biased data distributions. Subsequently, a clustering algorithm is employed to group the nodes based on their similarities, followed by a refinement operation of the hierarchical relations among these nodes. Building on this seed schema, we propose a fine-grained contrastive learning method in the expansion module to strengthen the utilization of taxonomic structures, consequently boosting the precision of query-anchor matching. Finally, we meticulously scrutinized the hierarchical relations between each query and its siblings to ensure the integrity of the constructed taxonomy. Extensive experiments on real-world datasets validated the efficacy of our proposed framework for constructing well-structured taxonomies.

SSL-LRN: A Lightweight Semi-Supervised-Learning-Based Approach for UWA Modulation Recognition

Due to the lack of sufficient valid labeled data and severe channel fading, the recognition of various underwater acoustic (UWA) communication modulation types still faces significant challenges. In this paper, we propose a lightweight UWA communication type recognition network based on semi-supervised learning, named the SSL-LRN. In the SSL-LRN, a mean teacher–student mechanism is developed to improve learning performance by averaging the weights of multiple models, thereby improving recognition accuracy for insufficiently labeled data. The SSL-LRN employs techniques such as quantization and small convolutional kernels to reduce floating-point operations (FLOPs), enabling its deployment on underwater mobile nodes. To mitigate the performance loss caused by quantization, the SSL-LRN adopts a channel expansion module to optimize the neuron distribution. It also employs an attention mechanism to enhance the recognition robustness for frequency-selective-fading channels. Pool and lake experiments demonstrate that the framework effectively recognizes most modulation types, achieving a more than 5% increase in recognition accuracy at a 0 dB signal-to-noise ratio (SNRs) while reducing FLOPs by 84.9% compared with baseline algorithms. Even with only 10% labeled data, the performance of the SSL-LRN approaches that of the fully supervised LRN algorithm.

AFE-YOLOv8: A Novel Object Detection Model for Unmanned Aerial Vehicle Scenes with Adaptive Feature Enhancement

Object detection in unmanned aerial vehicle (UAV) scenes is a challenging task due to the varying scales and complexities of targets. To address this, we propose a novel object detection model, AFE-YOLOv8, which integrates three innovative modules: the Multi-scale Nonlinear Fusion Module (MNFM), the Adaptive Feature Enhancement Module (AFEM), and the Receptive Field Expansion Module (RFEM). The MNFM introduces nonlinear mapping by exploiting the property that deformable convolution can dynamically adjust the shape of the convolution kernel according to the shape of the target, and it effectively enhances the feature extraction capability of the backbone network by integrating multi-scale feature maps from different mapping branches. Meanwhile, the AFEM introduces an adaptive fusion factor, and through the fusion factor, it adaptively integrates the small-target features contained in the feature maps of different detection branches into the small-target detection branch, thus enhancing the expression of the small-target features contained in the feature maps of the small-target detection branch. Furthermore, the RFEM expands the receptive field of the feature maps of the large- and medium-scale target detection branches through stacked convolution, so as to make the model’s receptive field cover the whole target, and thereby learn more rich and comprehensive features of the target. The experimental results demonstrate the superior performance of the proposed model compared to the baseline in detecting objects of various scales. On the VisDrone dataset, the proposed model achieves a 4.5% enhancement in mean average precision (mAP) and a 5.45% improvement in average precision at an IOU threshold of 0.5 (AP50). Additionally, ablation experiments conducted on the challenging DOTA dataset showcase the model’s robustness and generalization capabilities.

Radiological image analysis using effective channel extension and fusion network based on COVID CT images

Attention mechanisms demonstrate significant capabilities in improving the performance of COVID CT image classification networks. Existing strategies often employ global pooling to acquire feature vectors, overlooking local feature information. Complex attention modules are then applied to enhance network performance, inevitably leading to increased model complexity. To address these issues, this paper introduces an Effective Channel Expansion and Fusion (ECEF) module specifically designed to enhance the performance of medical COVID CT image classification. The module represents a simple yet effective convolutional neural network module. In the channel direction of the given feature map, the module performs segmentation, conducts global pooling operations separately on the segmented and overall feature maps to obtain corresponding attention vectors, and merges them to produce high-dimensional attention vectors. Channel attention feature vectors are derived along the two pooling operation directions and dynamically fused. The resulting attention vectors are multiplied by the input feature map for adaptive feature refinement. Through these operations, the ECEF module adeptly captures local features in COVID CT images, enhancing the classification performance of medical COVID CT images. As a lightweight and versatile module, ECEF seamlessly integrates into any CNN architecture with negligible overhead. It can undergo end-to-end training alongside basic CNNs. ResNet is selected as the backbone network for empirical studies conducted on COVID CT images, including the COVID-CT dataset. Experimental results indicate that, compared to current advanced channel attention mechanisms, the ECEF module exhibits superior performance in COVID CT image classification tasks. The successful application of the ECEF module establishes a foundation for its widespread use in areas such as COVID CT medical image segmentation and object detection.

LIDON: Loopback interconnect datacenter optical network

A loopback interconnect datacenter optical network (LIDON) is proposed for switching in datacenters with commercial devices. The intra- and inter-Pod switching in datacenters is accomplished with the Rack Expansion Module (REM) and the Loopback Interconnect Module (LIM) operating collectively. By developing the new functions of diagnostic ports of a wavelength selective switch, LIDON boasts several features, such as high path diversity and robust tolerance. Moreover, the scale of LIDON can be expanded by the proposed scheme to support the flexible switching volume. The feasibility of dividing intra- and inter-Pod signals was demonstrated by the filtering performance experiments. The simulations of the task completion time (TCT) for different services bore witness to the robust fault tolerance of LIDON.

Jellyfish detection algorithm based on multi-gradient flow feature fusion

Jellyfish detection is a challenge in the field of underwater biological identification. Although early works have solved some of the problems of jellyfish detection, there are still shortcomings. Earlier jellyfish datasets were not as extensive, necessitating heavy reliance on data augmentation. Moreover, the detection capability is limited, especially in scenarios involving jellyfish gatherings and occlusions. To overcome these limitations, we establish a high-quality dataset with more jellyfish species and propose a more robust real-time detection algorithm. Our algorithm primarily consists of a multi-gradient flow backbone and a feature fusion module GFPN. Additionally, we have designed a receptive field expansion module SPPFCSPC_G. The entire network employs the FReLU activation function, while the bounding box regression utilizes the WIOU loss function. Our methods demonstrate accuracy and run-time performance in comparison with the state-of-the-art yolo series algorithms. Results show that our algorithm achieves the highest Precision, Recall and mAP50, exceeding the baseline yolov5 by 1.1%, 4.1%, and 4.5%, and outperforming the latest yolov8 by 0.9%, 1.3%, and 2.5%. Importantly, our method effectively addresses aggregation, occlusion, and deformation issues commonly encountered in jellyfish detection.

Devignet: High-Resolution Vignetting Removal via a Dual Aggregated Fusion Transformer with Adaptive Channel Expansion

Vignetting commonly occurs as a degradation in images resulting from factors such as lens design, improper lens hood usage, and limitations in camera sensors. This degradation affects image details, color accuracy, and presents challenges in computational photography. Existing vignetting removal algorithms predominantly rely on ideal physics assumptions and hand-crafted parameters, resulting in the ineffective removal of irregular vignetting and suboptimal results. Moreover, the substantial lack of real-world vignetting datasets hinders the objective and comprehensive evaluation of vignetting removal. To address these challenges, we present VigSet, a pioneering dataset for vignetting removal. VigSet includes 983 pairs of both vignetting and vignetting-free high-resolution (over 4k) real-world images under various conditions. In addition, We introduce DeVigNet, a novel frequency-aware Transformer architecture designed for vignetting removal. Through the Laplacian Pyramid decomposition, we propose the Dual Aggregated Fusion Transformer to handle global features and remove vignetting in the low-frequency domain. Additionally, we propose the Adaptive Channel Expansion Module to enhance details in the high-frequency domain. The experiments demonstrate that the proposed model outperforms existing state-of-the-art methods. The code, models, and dataset are available at https://github.com/CXH-Research/DeVigNet.

Particle Image Velocimetry and Total Temperature Characterization of Arc-Heated Mach 4.5 Free Jet

Particle image velocimetry (PIV) measurements were conducted in the Arc-Heated Combustion Tunnel (ACT-II) on a high-enthalpy Mach 4.5 nozzle flow. The primary motivation for the current work is to establish the feasibility of PIV as a high-quality flow diagnostic technique in hypersonic arc-heated flows and produce a high-resolution hypersonic nozzle flow characterization, including nozzle free jet shear layer velocity profiles. Due to the uncertain nature of the gas composition in the flowfield of interest, PIV measurements of a supersonic wedge flow were used to couple the flow velocities to the oblique shock relations. This enabled a PIV-derived total temperature calculation that does not require a priori assumptions of the exact gas composition. A PIV expansion module was developed for this study, and proper seed sizing and material were selected for the present flow. An analysis of the seed particle response from the PIV measurements provided an initial validation of the seed performance while revealing potential issues with consistent seed sizing. These measurements and derived conditions represent a means of acquiring high-resolution velocimetry and temperature datasets that consider uncertainties in the experimental generation of hypersonic high-enthalpy flows.

Development of a robotic cluster for automated and scalable cell therapy manufacturing

Background aimsThe production of commercial autologous cell therapies such as chimeric antigen receptor T cells requires complex manual manufacturing processes. Skilled labor costs and challenges in manufacturing scale-out have contributed to high prices for these products. MethodsWe present a robotic system that uses industry-standard cell therapy manufacturing equipment to automate the steps involved in cell therapy manufacturing. The robotic cluster consists of a robotic arm and customized modules, allowing the robot to manipulate a variety of standard cell therapy instruments and materials such as incubators, bioreactors, and reagent bags. This system enables existing manual manufacturing processes to be rapidly adapted to robotic manufacturing, without having to adopt a completely new technology platform. Proof-of-concept for the robotic cluster's expansion module was demonstrated by expanding human CD8+ T cells. ResultsThe robotic cultures showed comparable cell yields, viability, and identity to those manually performed. In addition, the robotic system was able to maintain culture sterility. ConclusionsSuch modular robotic solutions may support scale-up and scale-out of cell therapies that are developed using classical manual methods in academic laboratories and biotechnology companies. This approach offers a pathway for overcoming manufacturing challenges associated with manual processes, ultimately contributing to the broader accessibility and affordability for personalized immunotherapies.

Backtranslate what you are saying and I will tell who you are

AbstractWith this work, we hypothesize that semantically enriching a user's text corpus using backtranslation and expansion modules can improve performance for author profiling tasks. To perform this textual enrichment, we translate an author's representative text. Translations are made from one language—the source language—into another—the target language—and then back to the original one. Finally, we expand an author's text by integrating the original version with the back‐translated one. Our framework includes these backtranslation and expansion modules followed by a SOTA classifier successfully employed for text classification. The framework is tested on three author profiling datasets from the last three years’ shared tasks on fake news, hate speech, irony and stereotypes detection hosted at the CLEF conference for the PAN Lab. This work is an extension of our previous one where we just presented our main idea. Here we improve our framework, and we also investigate more languages and more datasets. Finally, a qualitative analysis is provided. The results confirm that the backtranslation and expansion add‐on modules improve model performance on all three datasets evaluated.

Quo vadis, smallholder forest landscape? An introduction to the LPB-RAP model.

The impacts of the Anthropocene on climate and biodiversity pose societal and ecological problems that may only be solved by ecosystem restoration. Local to regional actions are required, which need to consider the prevailing present and future conditions of a certain landscape extent. Modeling approaches can be of help to support management efforts and to provide advice to policy making. We present stage one of the LaForeT-PLUC-BE model (Landscape Forestry in the Tropics-PCRaster Land Use Change-Biogeographic & Economic model; in short: LPB) and its thematic expansion module RAP (Restoration Areas Potentials). LPB-RAP is a high-resolution pixel-based scenario tool that relies on a range of explicit land use types (LUTs) to describe various forest types and the environment. It simulates and analyzes future landscape configurations under consideration of climate, population and land use change long-term. Simulated Land Use Land Cover Change (LULCC) builds on dynamic, probabilistic modeling incorporating climatic and anthropogenic determinants as well as restriction parameters to depict a sub-national regional smallholder-dominated forest landscape. The model delivers results for contrasting scenario settings by simulating without and with potential Forest and Landscape Restoration (FLR) measures. FLR potentials are depicted by up to five RAP-LUTs. The model builds on user-defined scenario inputs, such as the Shared Socioeconomic Pathways (SSP) and Representative Concentration Pathways (RCP). Model application is here exemplified for the SSP2-RCP4.5 scenario in the time frame 2018-2100 on the hectare scale in annual resolution using Esmeraldas province, Ecuador, as a case study area. The LPB-RAP model is a novel, heuristic Spatial Decision Support System (SDSS) tool for smallholder-dominated forest landscapes, supporting near-time top-down planning measures with long-term bottom-up modeling. Its application should be followed up by FLR on-site investigations and stakeholder participation across all involved scales.

Intelligent residual film recovery machine monitoring and control system

Domestic residue recovery machines in China still follow the traditional towed mechanical model, lacking automation and intelligent features. Under the key R&D project of Xinjiang Autonomous Region, our team has developed integrated intelligent agricultural machinery for cotton straw crushing and residue recovery. This research covers the monitoring and control system, including PLC control and communication, working parameter monitoring and adjustment, algorithmic control of electro-hydraulic actuators, and human-machine interface display. Compared to traditional models, this machine replaces the conventional chain-driven mechanical structure and diesel tractor traction power with a fully hydraulic integrated suspension drive and power system. Sensors, PLC, and a touch screen are utilized for real-time monitoring and display of parameters. Hardware components like electromagnetic switch valves, electro-hydraulic proportional valves, hydraulic cylinders, and software elements such as PLC programs and intelligent control algorithms are employed for electro-hydraulic switching and proportional control of certain working parameters and mechanisms. All parameter information is consolidated in the PLC host and expansion modules and displayed and controlled on the human-machine interface. The system was installed on the first-generation machine for indoor testing, revealing that the monitoring and control system used on the first-generation machine achieves parameter detection and adjustment of the actuating mechanisms. It incorporates more advanced functions compared to traditional residue recovery machines. However, there is still ample room for improvement in the overall intelligence of the machine. The control system’s structure requires adjustment, and certain functionalities of the overall mechanical structure and working components need optimization or upgrading. Detailed enhancements to the entire system will be made in the next-generation machine.

Photoinduced Puffing with Large Volume Expansion and Photomechanical Motions induced by Topochemical [4+4] Reactions in Molecular Crystal Solvates.

In this work, we report the first example of two crystal solvates of an anthracene-benzhydrazide based molecule (Ant) that display very distinct photo-responsive behaviour when 365 or 405 nm or visible light is illuminated. For the first time, the crystal hydrate that has water molecule in the lattice (hereafter named as Ant-H2O) display fascinating puffing behavior with large volume expansion upto 50 % accompanied with surface modulation when illuminated with 405 nm light, a phenomenon very much similar to the rice or popcorn puffing by thermal treatment. Utilizing the properties of photoconverted Ant-H2O crystals, we have demonstrated their application in photoinduced enhanced liquid absorption using various liquids/solutions. The other crystal solvate having DMF in the crystal lattice (hereafter named as Ant-DMF) responds to 405 nm light by bending, twisting, chopping, jumping or splitting etc. The chopping of Ant-DMF crystal was also observed under ambient/white light but at a slower rate compared to 405 nm light. Single crystal X-ray diffraction study reveals that the photoinduced puffing and photomechanical effects of these materials are rooted to the topochemical [4+4] cycloaddition reaction between the anthracene moieties that facilitate molecular packing change assisted by the reconfiguration of intermolecular non-covalent interactions involving lattice trapped solvent molecules.

A simplified decision feedback Chebyshev function link neural network with intelligent initialization for underwater acoustic channel equalization

IntroductionIn shallow-water environments, the reliability of underwater communication links is often compromised by significant multipath effects. Some equalization techniques such as decision feedback equalizer, and deep neural network equalizer suffer from slow convergence and high computational complexity.MethodsTo address this challenge, this paper proposes a simplified decision feedback Chebyshev function link neural network equalizer (SDF-CFLNNE). The structure of the SDF-CFLNNE employs Chebyshev polynomial function expansion modules to directly and non-linearly transform the input signals into the output layer, without the inclusion of hidden layers. Additionally, it feeds the decision signal back to the input layer rather than the function expansion module, which significantly reduces computational complexity. Considering that, in the training phase of neural networks, the random initialization of weights and biases can substantially impact the training process and the ultimate performance of the network, this paper proposes a chaotic sparrow search algorithm combining the osprey optimization algorithm and Cauchy mutation (OCCSSA) to optimize the initial weights and thresholds of the proposed equalizer. The OCCSSA utilizes the Piecewise chaotic population initialization and combines the exploration strategy of the ospreywith the Cauchy mutation strategy to enhance both global and local search capabilities. RseultsSimulations were conducted using underwater multipath signals generated by the Bellhop Acoustic Toolbox. The results demonstrate that the performance of the SDFCFLNNE initialized by OCCSSA surpasses that of CFLNN-based and traditional nonlinear equalizers, with a notable improvement of 2-6 dB in terms of signal-to-noise ratio at a bit error rate (BER) of 10−4 and a reduced mean square error (MSE). Furthermore, the effectiveness of the proposed equalizer was validated using the lake experimental data, demonstrating lower BER and MSE with improved stability. DiscussionThis underscores thepromise of employing the SDFCFLNNE initialized by OCCSSA as a promising solution to enhance the robustness of underwater communication in challenging environments.