Efficient Network Research Articles

Multi‐scale feature extraction for energy‐efficient object detection in remote sensing images

AbstractObject detection in remote sensing images aims to interpret images to obtain information on the category and location of potential targets, which is of great importance in traffic detection, marine supervision, and space reconnaissance. However, the complex backgrounds and large scale variations in remote sensing images present significant challenges. Traditional methods relied mainly on image filtering or feature descriptor methods to extract features, resulting in underperformance. Deep learning methods, especially one‐stage detectors, for example, the Real‐Time Object Detector (RTMDet) offers advanced solutions with efficient network architectures. Nevertheless, difficulty in feature extraction from complex backgrounds and target localisation in scale variations images limits detection accuracy. In this paper, an improved detector based on RTMDet, called the Multi‐Scale Feature Extraction‐assist RTMDet (MRTMDet), is proposed which address limitations through enhancement feature extraction and fusion networks. At the core of MRTMDet is a new backbone network MobileViT++ and a feature fusion network SFC‐FPN, which enhances the model's ability to capture global and multi‐scale features by carefully designing a hybrid feature processing unit of CNN and a transformer based on vision transformer (ViT) and poly‐scale convolution (PSConv), respectively. The experiment in DIOR‐R demonstrated that MRTMDet achieves competitive performance of 62.2% mAP, balancing precision with a lightweight design.

RRBM-YOLO: Research on Efficient and Lightweight Convolutional Neural Networks for Underground Coal Gangue Identification.

Coal gangue identification is the primary step in coal flow initial screening, which mainly faces problems such as low identification efficiency, complex algorithms, and high hardware requirements. In response to the above, this article proposes a new "hardware friendly" coal gangue image recognition algorithm, RRBM-YOLO, which is combined with dark light enhancement. Specifically, coal gangue image samples were customized in two scenarios: normal lighting and simulated underground lighting with poor lighting conditions. The images were preprocessed using the dim light enhancement algorithm Retinexformer, with YOLOv8 as the backbone network. The lightweight module RepGhost, the repeated weighted bi-directional feature extraction module BiFPN, and the multi-dimensional attention mechanism MCA were integrated, and different datasets were replaced to enhance the adaptability of the model and improve its generalization ability. The findings from the experiment indicate that the precision of the proposed model is as high as 0.988, the mAP@0.5(%) value and mAP@0.5:0.95(%) values increased by 10.49% and 36.62% compared to the original YOLOv8 model, and the inference speed reached 8.1GFLOPS. This indicates that RRBM-YOLO can attain an optimal equilibrium between detection precision and inference velocity, with excellent accuracy, robustness, and industrial application potential.

The Role of Sorghum in Enhancing Food Security Among Smallholder Farmers in Makueni County, Kenya

In the wake of climate change and prevailing food insecurity, there has been increased attention on crops that can withstand harsh climatic conditions and have the potential to sustain livelihoods. Sorghum (<i>Sorghum bicolor)</i> is among the cereal crops with the potential to address these unprecedented challenges. It grows in arid and semi-arid regions characterized by unpredictable weather patterns, rising poverty levels, and food insecurity. In Kenya, sorghum ranks third in terms of production and importance. Nevertheless, there is prevailing food insecurity in Makueni County, where sorghum thrives well. Hence, the purpose of this study was to assess the role of sorghum in enhancing food security among smallholder farmers by establishing the potential factors influencing sorghum production and income from sorghum. A multistage sampling method was used to select a sample of 96 respondents. Data analysis involved the use of multiple linear regression model and gross margin analysis. The results indicated that experience, household size, and extension service influence sorghum production positively, while distance to all-weather roads and off-farm income have a negative effect. Gross margin results revealed sorghum is a profitable enterprise with an average net farm income of about 10,760 KES per acre. This suggests that sorghum production improves the income of sorghum-producing households and consequently enhances food security. The study, therefore, proposes strategies such as developing appropriate training facilities and strengthening extension services to boost sorghum production and thus promote food security among smallholder farmers. Furthermore, national and county governments should develop efficient road networks and provide incentives to sorghum producers to enhance access to services and markets, and foster specialization in sorghum enterprise.

Research on Deep Learning Detection Model for Pedestrian Objects in Complex Scenes Based on Improved YOLOv7.

Pedestrian detection is very important for the environment perception and safety action of intelligent robots and autonomous driving, and is the key to ensuring the safe action of intelligent robots and auto assisted driving. In response to the characteristics of pedestrian objects occupying a small image area, diverse poses, complex scenes and severe occlusion, this paper proposes an improved pedestrian object detection method based on the YOLOv7 model, which adopts the Convolutional Block Attention Module (CBAM) attention mechanism and Deformable ConvNets v2 (DCNv2) in the two Efficient Layer Aggregation Network (ELAN) modules of the backbone feature extraction network. In addition, the detection head is replaced with a Dynamic Head (DyHead) detector head with an attention mechanism; unnecessary background information around the pedestrian object is also effectively excluded, making the model learn more concentrated feature representations. Compared with the original model, the log-average miss rate of the improved YOLOv7 model is significantly reduced in both the Citypersons dataset and the INRIA dataset. The improved YOLOv7 model proposed in this paper achieved good performance improvement in different pedestrian detection problems. The research in this paper has important reference significance for pedestrian detection in complex scenes such as small, occluded and overlapping objects.

Topological organization of the brain network in thyroid-associated ophthalmopathy using graph theoretical analysis.

Mounting neuroimaging evidence indicates that patients with thyroid-associated ophthalmopathy (TAO) demonstrate altered brain function and structure. Nonetheless, the alterations in the topological properties of the functional brain connectome in TAO patients are not yet fully understood. This study aimed to investigate the topological organization of the functional brain connectome in TAO patients using graph-theoretic methods. Twenty-five TAO patients (10 males and 15 females) and 25 age-, sex-, and education-matched healthy controls (HCs) (10 males and 15 females) (the TAO and HC data are from the same dataset in previous studies) underwent resting-state MRI scans. Graph-theoretic analysis was used to study the global, nodal, and edge topological properties of the brain's functional connectome. Both the TAO and HC groups exhibited high-efficiency small-world networks in their brain functional networks. However, there were no significant differences in small-world properties (Cp, γ, λ, Lp, and σ) and network efficiency [global and local efficiencies (Eloc)] between the two groups. In addition, the TAO group demonstrated reduced betweenness centrality in the right fusiform and increased nodal Eloc in the right intraparietal sulcus (P < 0.05, Bonferroni-corrected). Furthermore, the TAO group displayed altered functional connections among the default-mode network (DMN), visual network (VN), sensorimotor network (SMN), and cingulo-opercular network (CON). Patients with TAO exhibited abnormal topological organization of the human brain connectome, including decreased betweenness centrality and increased nodal Eloc. Moreover, the TAO group displayed altered functional connections primarily within the DMN, VN, SMN, and CON. These findings provide crucial insights into the neural mechanisms underlying visual loss, abnormal emotion regulation, and cognitive deficits in TAO patients.

A framework for measuring the training efficiency of a neural architecture

Measuring Efficiency in neural network system development is an open research problem. This paper presents an experimental framework to measure the training efficiency of a neural architecture. To demonstrate our approach, we analyze the training efficiency of Convolutional Neural Networks and Bayesian equivalents on the MNIST and CIFAR-10 tasks. Our results show that training efficiency decays as training progresses and varies across different stopping criteria for a given neural model and learning task. We also find a non-linear relationship between training stopping criteria, training Efficiency, model size, and training Efficiency. Furthermore, we illustrate the potential confounding effects of overtraining on measuring the training efficiency of a neural architecture. Regarding relative training efficiency across different architectures, our results indicate that CNNs are more efficient than BCNNs on both datasets. More generally, as a learning task becomes more complex, the relative difference in training efficiency between different architectures becomes more pronounced.

Maximizing energy efficiency in HetNets through centralized and distributed sleep strategies under QoS constraint

This research addresses the critical need to optimize the Energy Efficiency (EE) for Ultra-Dense HetNets amid the ever-increasing demands for high-speed data networks. The rapid increase in high-speed devices highlights the urgent necessity for a transformative change in upcoming 5G cellular networks. According to Ericsson's 2022 report, mobile data traffic volume is expected to double by 2027, with mobile video traffic anticipated to rise by nearly 30% each year. In response to these challenges, researchers have identified essential technologies that facilitate 5G networks, including massive Multiple-input-Multiple-output (m-MIMO) systems and HetNets. Although both promise enhanced coverage and throughput, HetNets emerges as a cost-effective solution, surpassing m-MIMO in implementation cost and coverage. However, achieving maximum EE in HetNets necessitates careful consideration of various constraints, including delay, coverage probability, and Signal-to-Interference-plus-Noise Ratio (SINR) thresholds. This research marks a significant milestone in adopting the Distributed Dynamic Opportunistic Sleep Strategy (D-DOSS) approach. The D-DOSS method organizes small clusters throughout the network and evaluates key Quality of Service (QoS) parameters including Energy Utilization Efficiency (EUE), Coverage Probability, Data Throughput, and Success Probability using Monte Carlo simulations. This research analyzes Distributed Sleep (DS) and Centralized Schemes (CS) concerning given QoS parameters. While DS methodologies often exhibit performance trade-offs compared to CS, they provide significant advantages in terms of ease of implementation and management. CS, though representing the most commonly used method in ultra-dense HetNets involves high computational costs that complicate its management. By integrating the D-DOSS and addressing various constraints, this research not only advances HetNet technologies but also makes a significant contribution to optimizing EE while preserving network performance and QoS. The innovative D-DOSS approach offers a promising solution to the challenges of energy efficiency in wireless communication networks and paves the way for future advancements in HetNet deployments. The results and analysis show that D-DOSS effectively addresses the limitations of DS and outperforms existing CS techniques.

Rethinking max-min planning on energy-efficient software-defined networking for 5G networks.

Energy efficiency plays an important role in intelligent networking for 5G networks, which concerns environmental, financial, and performance aspects of intelligent networking for 5G networks. To this end, network designers propose energy-efficient approaches to reduce energy consumption of networks and to raise network performance by switching off the links/nodes with low loads or at idle status. The existing energy-efficient approaches can be formulated as a max-min optimal problem, namely maximizing network/node/port throughput via minimum energy consumption. The max-min planning investigates energy efficiency only from the links/nodes perspective. The max-min planning for energy-efficient networking, if not carefully designed from the network-wide standpoint, can lead to lower energy efficiency for the whole network due to lack of global planning, which in turn results in the degraded performance due to network un-connectivity after closing the nodes/links. In this paper we rethink the max-min planning framework on energy-efficient software-defined networking for intelligent networking of 5G networks, which takes in account combining network connectivity and maximum network flow with minimum energy consumption. Our framework aims at how to deliver dynamic end-to-end traffic demands with the appropriate network topology by building data forwarding plane with maximum network flow and control plane with network connectivity. We discuss the associated challenges and implementation issues. A dynamic max-min planning framework depending on dynamic end-to-end traffic demands is presented to achieve network-wide energy efficiency. Numerical results show the improved energy efficiency performance for the whole network.

HGLeNet DEEP LEARNING FOR SKIN CANCER DETECTION WITH SKIN LESION SEGMENTATION

Skin cancer is deemed to be the most dangerous type of cancer. It occurs due to the damage caused to the DNA and if left untreated can lead to death. Various methods have been devised over the last few years for skin cancer detection. However, their performance was affected by various challenges in image analysis, like color illumination variations, differences in shape, size, etc. Therefore, to tackle these issues the novel framework, deep learning (DL) technique for accurate skin cancer detection and lesion segmentation is developed. Primarily, the skin image is pre-processed by employing a weighted median filtering to eradicate the noises contained. Then, the segmentation of skin lesions is carried out by employing the efficient neural network (ENet). After that, augmentation is accomplished to avoid overfitting, and later, feature extraction is carried out. At last, skin cancer detection is effectuated with the help of hybrid GoogleNet-LeNet (HGLeNet), which is obtained by merging GoogleNet and LeNet, here layers are modified using the regression concept. Furthermore, the introduced framework is examined for its effectiveness through accuracy, sensitivity and specificity. Moreover, HGLeNet attained the highest accuracy of 0.922, sensitivity of 0.928, as well as specificity of 0.924.

CytoNet: an efficient dual attention based automatic prediction of cancer sub types in cytology studies

Computer-assisted diagnosis (CAD) plays a key role in cancer diagnosis or screening. Whereas, current CAD performs poorly on whole slide image (WSI) analysis, and thus fails to generalize well. This research aims to develop an automatic classification system to distinguish between different types of carcinomas. Obtaining rich deep features in multi-class classification while achieving high accuracy is still a challenging problem. The detection and classification of cancerous cells in WSI are quite challenging due to the misclassification of normal lumps and cancerous cells. This is due to cluttering, occlusion, and irregular cell distribution. Researchers in the past mostly obtained the hand-crafted features while neglecting the above-mentioned challenges which led to a reduction of the classification accuracy. To mitigate this problem we proposed an efficient dual attention-based network (CytoNet). The proposed network is composed of two main modules (i) Efficient-Net and (ii) Dual Attention Module (DAM). Efficient-Net is capable of obtaining higher accuracy and enhancing efficiency as compared to existing Convolutional Neural Networks (CNNs). It is also useful to obtain the most generic features as it has been trained on ImageNet. Whereas DAM is very robust in obtaining attention and targeted features while negating the background. In this way, the combination of an efficient and attention module is useful to obtain the robust, and intrinsic features to obtain comparable performance. Further, we evaluated the proposed network on two well-known datasets (i) Our generated thyroid dataset (ii) Mendeley Cervical dataset (Hussain in Data Brief, 2019) with enhanced performance compared to their counterparts. CytoNet demonstrated a 99% accuracy rate on the thyroid dataset in comparison to its counterpart. The precision, recall, and F1-score values achieved on the Mendeley Cervical dataset are 0.992, 0.985, and 0.977, respectively. The code implementation is available on GitHub. https://github.com/naveedilyas/CytoNet-An-Efficient-Dual-Attention-based-Automatic-Prediction-of-Cancer-Sub-types-in-Cytol.

Will new tram lines enhance the connectivity and walkability? A case study of Sakarya

&lt;p&gt;This study investigates the impact of planned tram lines on walkability and accessibility in Sakarya, utilizing Geographic Information Systems (GIS) for spatial analysis. The research evaluates the catchment areas of proposed tram stops, assessing their suitability and coverage, and examines how these areas integrate with existing public transport routes. By calculating time-oriented catchments for 5, 8, and 10-minute walking distances, the study identifies service gaps and redundancies in the public transport network. The findings reveal that the new tram lines will enhance accessibility by extending coverage to high-density areas and potentially reducing the demand on existing bus services. The analysis also highlights the overlap between bus transit lines and tram stops, suggesting optimizations to improve network efficiency. The results offer valuable insights for urban planners, aiming to optimize Sakarya’s public transport system to be more inclusive and sustainable. This study contributes to urban mobility planning by providing a detailed understanding of how new tram lines can improve connectivity and support sustainable urban development.&lt;/p&gt;

OSC-GOR: Optimal Security-Aware Cluster-Based Hybrid Geographical and Opportunistic Routing for Vehicular ad hoc Networks

Vehicular ad hoc networks (VANETs) are crucial for infrastructure-less vehicular communication. The dynamic and complex nature of VANETs necessitates efficient routing strategies. This paper introduces an optimal security-aware cluster-based hybrid geographical and opportunistic routing (OSC-GOR) for VANETs. By utilizing the improved bald eagle optimization (IBEO) algorithm, we achieve optimal clustering that enhances energy efficiency. Cluster heads (CHs) are elected based on trust, calculated from metrics like energy consumption and signal strength. A Poplar optimization algorithm (POA) further refines these metrics. Subsequently, an optimal min–max recurrent neural network (OMM-RNN) determines the next forwarder nodes, facilitating data transfer in VANETs. Implemented using the NS-2 tool and SUMO traffic generator, OSC-GOR showcases optimized clustering and superior network efficiency. Comparative simulations reveal OSC-GOR’s advantages in energy use, latency, delivery ratio, goodput, and routing overhead, outperforming existing methods. Notably, OSC-GOR effectively counters VANET attacks such as GPS spoofing and Sybil threats.

A Classification and Segmentation Model for Diamond Abrasive Grains Based on Improved Swin-Unet-SAM

The detection of abrasive grain images in diamond tools serves as the foundation for assessing the overall condition of the tools, encompassing crucial aspects of diamond abrasive grains like the quantity, size, morphology, and distribution. Given the intricate background textures and reflective characteristics exhibited by diamond images, diamond detection and segmentation pose a significant challenge. Recently, numerous defect detection methods based on machine learning and deep learning have emerged. However, several issues persist, such as detection accuracy and the interference caused by intricate background textures. The present work demonstrates an efficient classification and segmentation network algorithm that combines Swin-Unet with SAM (Segment Anything Model) to alleviate the existing problems. Specifically, four embedding structures were devised to bridge the two models for iterative training. The transformer blocks within the Swin-Unet model were enhanced to facilitate classification and coarse segmentation, and the mask structure in SAM was refined to enable fine segmentation. The experimental results show that under a small sample dataset with complex background textures, the average index values of ACC (accuracy), SE (Sensitivity), and DSC (Dice Similarity Coefficient) for the classification and segmentation of diamond abrasive grains reached 98.7%, 92.5%, and 85.9%, respectively. Compared with the model before improvement, its ACC, SE and DSC increased by 1.2%, 15.9%, and 7.6%, respectively. The test results, based on four different datasets, consistently indicated that this model has excellent segmentation performance and robustness and has great application potential in the industrial field.

Analysis of Factors Affecting the Spatial Association Network of Food Security Level in China

Food security serves as the cornerstone of national security, intricately linked to social stability and economic progress. Currently, with the swift evolutions in social economy, logistics and transport, information dissemination, and technological advancements, there has been a marked increase in the cross-regional flow of food production, distribution, and consumption. Consequently, the spatial interdependence of food security across different regions has grown increasingly salient. This paper investigates the spatial interrelationship of food security levels in China through a network analysis framework, examining its determinants and network dynamics. The findings offer valuable insights for decision-makers aiming to optimize agricultural resource allocation and enhance national food security levels. This research establishes a comprehensive evaluation index system for assessing food security levels in China across four dimensions: production security, distribution security, supply security, and consumption security. Employing data from 30 provinces between 2008 and 2022, the entropy method quantifies food security levels, while a modified gravity model underpins the construction of a spatial association network. This framework subsequently examines the network’s structural characteristics and the factors influencing its formation. The results reveal that: (1) China’s food security levels demonstrate a consistent upward trajectory over the study period, though significant regional disparities persist. The central region surpasses the national average, while the eastern and western regions lag. Recently, the western region has shown accelerated improvements in food security, followed by the central area, with the eastern region maintaining steady growth. (2) A structurally robust spatial correlation network of food security has emerged, characterized by variations in the number of network relationships, fluctuations in network density, and a decline in network efficiency while still exhibiting pronounced small-world characteristics. (3) The network displays a clear core-periphery structure, with Shanghai, Beijing, and Jiangsu positioned centrally, playing pivotal intermediary roles, whereas remote provinces such as Gansu, Ningxia, and Liaoning occupy the periphery. (4) The four major regions demonstrate sparse internal connectivity yet robust inter-regional ties, resulting in pronounced spillover effects. (5) Various factors, including geographic distance, provincial proximity, disparities in economic development levels, variations in marketization, differences in agricultural human capital, and disparities in land productivity, significantly impact the establishment of spatial correlations in food security. The affirmative influences of geographic distance and neighboring relations, along with the beneficial shifts in economic development disparities, suggest that the flow of technology and resources plays a crucial role in reinforcing spatial connections.

Multi-UAV Escape Target Search: A Multi-Agent Reinforcement Learning Method.

The multi-UAV target search problem is crucial in the field of autonomous Unmanned Aerial Vehicle (UAV) decision-making. The algorithm design of Multi-Agent Reinforcement Learning (MARL) methods has become integral to research on multi-UAV target search owing to its adaptability to the rapid online decision-making required by UAVs in complex, uncertain environments. In non-cooperative target search scenarios, targets may have the ability to escape. Target probability maps are used in many studies to characterize the likelihood of a target's existence, guiding the UAV to efficiently explore the task area and locate the target more quickly. However, the escape behavior of the target causes the target probability map to deviate from the actual target's position, thereby reducing its effectiveness in measuring the target's probability of existence and diminishing the efficiency of the UAV search. This paper investigates the multi-UAV target search problem in scenarios involving static obstacles and dynamic escape targets, modeling the problem within the framework of decentralized partially observable Markov decision process. Based on this model, a spatio-temporal efficient exploration network and a global convolutional local ascent mechanism are proposed. Subsequently, we introduce a multi-UAV Escape Target Search algorithm based on MAPPO (ETS-MAPPO) for addressing the escape target search difficulty problem. Simulation results demonstrate that the ETS-MAPPO algorithm outperforms five classic MARL algorithms in terms of the number of target searches, area coverage rate, and other metrics.

Noninvasive Deep Learning Analysis for Smith–Magenis Syndrome Classification

Smith–Magenis syndrome (SMS) is a rare, underdiagnosed condition due to limited public awareness of genetic testing and a lengthy diagnostic process. Voice analysis can be a noninvasive tool for monitoring and detecting SMS. In this paper, the cepstral peak prominence and mel-frequency cepstral coefficients are used as disease monitoring and detection metrics. In addition, an efficient neural network, incorporating synthetic data processes, was used to detect SMS in a cohort of individuals with the disease. Three study cases were conducted with a set of 19 SMS patients and 292 controls. The three study cases employed various oversampling and undersampling techniques, including SMOTE, random oversampling, NearMiss, random undersampling, and 16 additional methods, resulting in balanced accuracies ranging from 69% to 92%. This is the first study using a neural network model to focus on a rare genetic syndrome using phonation analysis data. By using synthetic data (oversampling and undersampling) and a CNN, it was possible to detect SMS with high levels of accuracy. Voice analysis and deep learning techniques have proven to be a useful and noninvasive method. This is a finding that may help in the complex identification of this syndrome as well as other rare diseases.

Measuring the dynamic balance of integration and segregation underlying consciousness, anesthesia, and sleep in humans

Consciousness requires a dynamic balance of integration and segregation in brain networks. We report an fMRI-based metric, the integration-segregation difference (ISD), which captures two key network properties: network efficiency (integration) and clustering (segregation). With this metric, we quantify brain state transitions from conscious wakefulness to unresponsiveness induced by the anesthetic propofol. The observed changes in ISD suggest a profound shift towards the segregation of brain networks during anesthesia. A common unimodal-transmodal sequence of disintegration and reintegration occurs in brain networks during, respectively, loss and return of responsiveness. Machine learning models using integration and segregation data accurately identify awake vs. unresponsive states and their transitions. Metastability (dynamic recurrence of non-equilibrium transient states) is more effectively explained by integration, while complexity (diversity of neural activity) is more closely linked with segregation. A parallel analysis of sleep states produces similar findings. Our results demonstrate that the ISD reliably indexes states of consciousness.

Latency‐Sensitive Service Function Chains Intelligent Migration in Satellite Communication Driven by Deep Reinforcement Learning

ABSTRACTSatellite communication technology solves the problem that the traditional wired network infrastructure is difficult to achieve global communication coverage. However, factors such as satellite orbits introduce frequent changes to the network topology, and challenges like satellite failures and communication link interruptions are prevalent. In the face of these issues, service function chain (SFC) migration becomes a crucial method for swiftly adjusting SFCs during faults, maintaining service continuity and availability. This article proposes a latency‐sensitive SFC migration algorithm tailored to satellite networks. The algorithm first models the satellite network as a multi‐domain virtual network, capturing the constraints faced during SFC migration. Subsequently, a deep reinforcement learning algorithm integrated attention mechanism is designed to more accurately capture and understand the complex network environment and dynamic satellite network topology and derive optimal SFC migration strategies for superior performance. Finally, through experimentation and evaluation of the deep reinforcement learning‐driven latency‐sensitive service function chain intelligent migration algorithm (LS‐SFCM) in satellite communication, this study validates the effectiveness and superior performance of the algorithm in latency‐sensitive scenarios. It provides a new avenue for enhancing the service quality and efficiency of satellite communication networks.

CoupNeRF: Property‐aware Neural Radiance Fields for Multi‐Material Coupled Scenario Reconstruction

AbstractNeural Radiance Fields (NeRFs) have achieved significant recognition for their proficiency in scene reconstruction and rendering by utilizing neural networks to depict intricate volumetric environments. Despite considerable research dedicated to reconstructing physical scenes, rare works succeed in challenging scenarios involving dynamic, multi‐material objects. To alleviate, we introduce CoupNeRF, an efficient neural network architecture that is aware of multiple material properties. This architecture combines physically grounded continuum mechanics with NeRF, facilitating the identification of motion systems across a wide range of physical coupling scenarios. We first reconstruct specific‐material of objects within 3D physical fields to learn material parameters. Then, we develop a method to model the neighbouring particles, enhancing the learning process specifically in regions where material transitions occur. The effectiveness of CoupNeRF is demonstrated through extensive experiments, showcasing its proficiency in accurately coupling and identifying the behavior of complex physical scenes that span multiple physics domains.

Human risk recognition and prediction in manned submersible diving tasks driven by deep learning models

The complexity of human cognition is increased by the multiple and interactive information clusters brought about by the application of advanced intelligent information technologies. Especially in systems operating in extreme regions far from society, human errors are more pronounced than ever before. Prolonged social isolation, extreme weightless or overweight environments, stressful atmospheres, and lack of situational awareness are all added potential elements contributing to human risk. Although the development of human reliability analysis methods and their variants continues to mature, accurately predicting the potential risk of dynamic human behavior from sparse and discrete events remains a great challenge. We focus on deep learning computational architectures that are similar to the cognitive processes and mechanisms of the brain, and build neural networks that match the perceptual activation and memory cycling of the cognitive features of the brain. This study focuses on investigating the ability of the joint SNN-ITLSTM network to predict human error behavior and the clusters of performance shaping factors that effectively characterize the far-social nature. Combining the bionic properties of SNN and the temporal update mechanism of LSTM in the form of hierarchical events constitutes a computationally efficient network architecture. Our results show that the joint model proposed in this study has the performance to strengthen temporal influences and characterize cognitive features of the brain.