Efficient Network Research Articles

Revolutionizing automated pear picking using Mamba architecture

With the emergence of the new generation vision architecture Vmamba and the further demand for agricultural yield and efficiency, we propose an efficient and high-accuracy target detection network for automated pear picking tasks based on Vmamba, aiming to address the issue of low efficiency in current Transformer architectures. The proposed network, named SRSMamba, employs a Reward and Punishment Mechanism (RPM) to focus on important information while minimizing redundancy interference. It utilizes 3D Selective Scan (SS3D) to extend scanning dimensions and integrates global information across channel dimensions, thereby enhancing the model's robustness in complex agricultural environments and effectively adapting to the extraction of complex features in pear orchards and farmlands. Additionally, a Stacked Feature Pyramid Network (SFPN) is introduced to enhance semantic information during the feature fusion stage, particularly improving the detection capability for small targets. Experimental results show that SRSMamba has a low parameter count of 21.1 M, GFLOPs of 50.4, mAP of 72.0%, mAP50 reaching 94.8%, mAP75 at 68.1%, and FPS at 26.9. Compared with other state-of-the-art (SOTA) object detection methods, it achieves a good trade-off between model efficiency and detection accuracy.

UAVs Revolutionizing Efficiency: Integrating DRL and Random Walrus for Enhanced Energy and Spectral Resource Management

The improvement of energy efficiency and spectral efficiency in networks is achieved by seamlessly integrating energy harvesting, cognitive radio technologies, and Non-Orthogonal Multiple Access (NOMA) techniques. These complementary strategies optimize resource usage and address challenges related to energy consumption. Additionally, the adaptability and versatility of Unmanned Aerial Vehicles (UAVs) offer innovative solutions for enhancing coverage performance, thereby improving connectivity, efficiency, and reliability. We introduce a novel approach called the Deep Reinforcement Learning-Random Walrus (DRL-RW) algorithm, which combines Deep Reinforcement Learning (DRL) with the Random Walrus optimization (RWO) technique for efficient spectrum resource allocation and energy harvesting management in dynamic environments. The DRL-RW algorithm enables UAVs to learn optimal spectrum-sharing strategies and energy harvesting policies, while the RWO enhances the algorithm's adaptability and speed in exploring diverse solutions. Simulation results demonstrate the effectiveness of the DRL-RW algorithm, showing significant improvements in several performance metrics, including reduced energy consumption, enhanced computation time, improved convergence, increased signal-to-noise ratio, higher throughput, extended network lifetime, and increased harvested energy. These findings underscore the efficacy of the DRL-RW approach in addressing challenges associated with energy management in cognitive radio networks. The integration of UAVs, NOMA networks, and this novel algorithm represents a promising direction for developing energy-efficient communication systems.

Decision-making optimization for post-disaster restoration of multimodal transport networks in terms of resilience

IntroductionPublic health emergencies can have a ripple effect on the resilience of multimodal transport network, which will lead to problems such as route disruptions or blockages, route selection change and information transmission delay spreading to the whole network, further hindering the transportation planning and operational efficiency of the network. MethodsThis study constructs a multimodal transport route optimization model under uncertainty with the objective of the sum of transportation cost, transshipment cost, penalty cost and carbon emission cost. To enhance the computational efficiency of the model, a novel invasive weed optimization with memory and encoding value clustering capabilities is proposed. In addition, by fusing the Q-learning algorithm in reinforcement learning with the novel invasive weed algorithm, the action-value function table obtained from the training facilitates the selection of optimal routes. Based on empirical data, explore the sensitivity analysis of node disruptions, time windows, and fuzzy demand on route decision-making under public health emergencies. ResultsThe transport network is affected by public health emergencies, which makes the optimal route deviate from the expected goal, resulting in an increase in the total cost. The proportion of total cost is determined by the position of nodes in the network, with critical nodes suffering more losses than ordinary nodes. Reasonable setting of time windows and fuzzy demand intervals is an effective way to improve the resilience and transportation efficiency of multimodal transport network. ConclusionsThis study provides more applicable decision-making references for enterprises to prevent the risk of supply chain disruptions caused by public health emergencies.

Semi-Supervised Intrusion Detection System for In-Vehicle Networks Based on Variational Autoencoder and Adversarial Reinforcement Learning

Despite the affordability, simplicity, and efficiency of controller area network (CAN) protocols, the security vulnerability remains a major challenge. Currently, a machine learning-based intrusion detection system (IDS) is considered an effective approach for improving security in CAN by identifying malicious attacks. However, earlier studies that relied on supervised learning methods required considerable amounts of labeled data. Data collection from vehicles is time-consuming and expensive. Furthermore, the obtained data exhibited a class imbalance, which presents further challenges in the analysis and model training. Thus, we propose a semi-supervised learning-based IDS that combines variational autoencoder (VAE) and adversarial reinforcement learning for the multi-class classification of both known and unknown attacks. The proposed system capitalizes on the diverse patterns inherent in unlabeled data, transforming this data space into one that is more conducive to classification. Concurrently, adversarial agents in the reinforcement learning algorithm interact competitively, progressively enhancing their ability to intelligently classify and select samples. To reduce the reliance on labeled data and effectively exploit them, we utilize a pseudo-labeling process for pre-training. Experimental results indicate that the proposed model achieves more effective classification while requiring less labeled data compared to other baseline models for known attacks. By inheriting the advantages of VAE, promising results demonstrate that the proposed system detects unknown attacks containing similar or completely different characteristics with high F1 scores exceeding 0.9 and 0.84, respectively. Finally, the proposed system was demonstrated to be a lightweight model for the expeditious detection of malevolent messages introduced into in-vehicle networks to ensure minimal latency.

Joint Pruning and Channel-Wise Mixed-Precision Quantization for Efficient Deep Neural Networks

Joint Pruning and Channel-Wise Mixed-Precision Quantization for Efficient Deep Neural Networks

PreAlgPro: Prediction of allergenic proteins with pre-trained protein language model and efficient neutral network

Allergy is a prevalent phenomenon, involving allergens such as nuts and milk. Avoiding exposure to allergens is the most effective preventive measure against allergic reactions. However, current homology-based methods for identifying allergenic proteins encounter challenges when dealing with non-homologous data. Traditional machine learning approaches rely on manually extracted features, which lack important protein functional characteristics, including evolutionary information. Consequently, there is still considerable room for improvement in existing methods. In this study, we present PreAlgPro, a method for identifying allergenic proteins based on pre-trained protein language models and deep learning techniques. Specifically, we employed the ProtT5 model to extract protein embedding features, replacing the manual feature extraction step. Furthermore, we devised an Attention-CNN neural network architecture to identify potential features that contribute to the classification of allergenic proteins. The performance of our model was evaluated on four independent test sets, and the experimental results demonstrate that PreAlgPro surpasses existing state-of-the-art methods. Additionally, we collected allergenic protein samples to validate the robustness of the model and conducted an analysis of model interpretability.

A complex network analysis of groundwater wells in and around the Doñana Natural Space, Spain

This paper proposes the use of Complex Network Analysis tools to study the spatial distribution and temporal evolution of groundwater abstraction wells within a region of interest. To that end a weighted undirected network connecting wells within a certain distance was built. The edge weights take into account the distance between the wells as well as their corresponding abstraction volumes. In addition to the conventional complex network metrics, two specific abstraction-based centrality indexes are proposed, based on the total impact of a groundwater abstraction well on its surrounding wells and on the total impact of surrounding wells on a specific location. The proposed approach has been applied to the area of the Doñana Natural Space, one of the most important wetlands in Europe. The topology of the network reveals a large number of small, disconnected components and a few large components. This is reflected also in the degree distribution, which follows a Power Law distribution. The network has a large average clustering coefficient, a small average path length and a low level of centralisation. Global and average local network efficiency are also high. The network is assortative in terms of degree-degree and strength-strength correlations. Eigenvector centrality of the nodes reveals the location of influential wells.

Disruptions in segregation mechanisms in fMRI-based brain functional network predict the major depressive disorder condition

This study investigates the functional brain network in major depressive disorder using network theory and a consensus network approach. At the macroscopic level, we found significant differences in connectivity measures such as node strength and clustering coefficient, with healthy controls exhibiting higher values. This is consistent with disruptions in functional brain network segregation in patients with major depressive disorder. Consensus network analysis revealed that the central executive and salience networks were predominant in healthy controls, whereas depressed patients showed greater overlap with the default mode network. No differences were found in network efficiency measures, indicating comparable brain network integration between healthy controls and major depressive disorder groups. Importantly, the clustering coefficient emerged as an effective diagnostic biomarker for depression, achieving high sensitivity (90%), specificity (92%), and overall precision (90%). Further analysis at the mesoscale level uncovered unique functional connections distinguishing healthy controls and major depressive disorder groups. Our findings underscore the utility of analyzing functional networks from the macroscale to the mesoscale, and provide insight into overcoming the challenges associated with intersubject variability and the multiple comparisons problem in network analysis.

Fault Detection in Transmission Line

Abstract: This project focuses on the design and implementation of an advanced fault detection system for overhead transmission lines, utilizing key components such as the ESP 8266 microcontroller, current sensors, a GPS module, and IoT integration. The system is capable of detecting and classifying four major fault types: single line to ground (L-G), line to line (LL), double line to ground (L-L-G), and three-phase faults (L-L-LG). By placing current sensors at the transmission line's sending end, the system identifies faults and accurately determines their location through GPS coordinates .Simulations using protect us software were conducted to verify the system’s performance prior to building a hardware prototype. Upon fault detection, the system provides alerts via an LCD display and a buzzer, while real-time fault data is transmitted to an Android app and web server through the arduino IoT cloud. Testing confirmed the system’s precision in fault identification and location tracking, ensuring timely notifications for control room and remote device operators. This successful implementation highlights the system's potential for improving safety and efficiency in power transmission networks. the project lays the groundwork for further exploration into advanced fault detection and real-time monitoring solutions in electrical engineering.

Random-Coupled Neural Network

Improving the efficiency of current neural networks and modeling them on biological neural systems have become prominent research directions in recent years. The pulse-coupled neural network (PCNN) is widely used to mimic the computational characteristics of the human brain in computer vision and neural network fields. However, PCNN faces limitations such as limited neural connections, high computational costs, and a lack of stochastic properties. This study proposes a random-coupled neural network (RCNN) to address these limitations. RCNN employs a stochastic inactivation process, selectively inactivating neural connections using a random inactivation weight matrix. This method reduces the computational burden and allows for extensive neural connections. RCNN encodes constant stimuli as periodic spike trains and periodic stimuli as chaotic spike trains, reflecting the information encoding characteristics of biological neural systems. Our experiments applied RCNN to image segmentation and fusion tasks, demonstrating its robustness, efficiency, and high noise resistance. Results indicate that RCNN surpasses traditional methods in performance across these applications.

MIMO-Uformer: A Transformer-Based Image Deblurring Network for Vehicle Surveillance Scenarios

Motion blur is a common problem in the field of surveillance scenarios, and it obstructs the acquisition of valuable information. Thanks to the success of deep learning, a sequence of CNN-based architecture has been designed for image deblurring and has made great progress. As another type of neural network, transformers have exhibited powerful deep representation learning and impressive performance based on high-level vision tasks. Transformer-based networks leverage self-attention to capture the long-range dependencies in the data, yet the computational complexity is quadratic to the spatial resolution, which makes transformers infeasible for the restoration of high-resolution images. In this article, we propose an efficient transformer-based deblurring network, named MIMO-Uformer, for vehicle-surveillance scenarios. The distinct feature of the MIMO-Uformer is that the basic-window-based multi-head self-attention (W-MSA) of the Swin transformer is employed to reduce the computational complexity and then incorporated into a multi-input and multi-output U-shaped network (MIMO-UNet). The performance can benefit from the operation of multi-scale images by MIMO-UNet. However, most deblurring networks are designed for global blur, while local blur is more common under vehicle-surveillance scenarios since the motion blur is primarily caused by local moving vehicles. Based on this observation, we further propose an Intersection over Patch (IoP) factor and a supervised morphological loss to improve the performance based on local blur. Extensive experiments on a public and a self-established dataset are carried out to verify the effectiveness. As a result, the deblurring behavior based on PSNR is improved at least 0.21 dB based on GOPRO and 0.74 dB based on the self-established datasets compared to the existing benchmarks.

Optimizing IOT Network Performance: A Study on Low-Power Wide-Area Network (LPWAN) Technologies for Smart City Applications

Abstract: This research explores with a specific focus on smart city applications, how to optimise the execution of Web of Things (IoT) networks by utilising breakthroughs in Low-Powered Wide Area Networks (LPWAN). As IoT devices proliferate and generate vast amounts of data, having a competent network becomes essential, especially when dealing with low device thickness and limited power availability. This analysis provides a detailed energy consumption model tailored to LoRaWAN, based on a deeper understanding of its functional components in Internet of Things scenarios. The review uses MATLAB for replication and looks at two clear scenarios: the standard allocation of spreading factors without optimisation and an improved method that uses particle swarm optimisation (PSO) for dynamic spreading factor work. The results show that the network energy consumption dropped significantly, from 6.3997×10^ (- 17) Joules to 2.5230×10^(- 17) Joules, along with increased throughput, decreased parcel misfortune, and decreased idleness. Through a detailed analysis of several parameters, such as network density and data transfer efficiency, this study demonstrates the feasibility of the suggested optimisation model in terms of improving battery efficiency and overall network performance. Finally, the findings demonstrate how efficient LPWAN systems may provide robust and useful IoT environments, which are essential for the successful implementation of smart city initiatives.

Metaheuristic optimized complex-valued dilated recurrent neural network for attack detection in internet of vehicular communications

The Internet of Vehicles (IoV) is a specialized iteration of the Internet of Things (IoT) tailored to facilitate communication and connectivity among vehicles and their environment. It harnesses the power of advanced technologies such as cloud computing, wireless communication, and data analytics to seamlessly exchange real-time data among vehicles, road-side infrastructure, traffic management systems, and other entities. The primary objectives of this real-time data exchange include enhancing road safety, reducing traffic congestion, boosting traffic flow efficiency, and enriching the driving experience. Through the IoV, vehicles can share information about traffic conditions, weather forecasts, road hazards, and other relevant data, fostering smarter, safer, and more efficient transportation networks. Developing, implementing and maintaining sophisticated techniques for detecting attacks present significant challenges and costs, which might limit their deployment, especially in smaller settings or those with constrained resources. To overcome these drawbacks, this article outlines developing an innovative attack detection model for the IoV using advanced deep learning techniques. The model aims to enhance security in vehicular networks by efficiently identifying attacks. Initially, data is collected from online databases and subjected to an optimal feature extraction process. During this phase, the Enhanced Exploitation in Hybrid Leader-based Optimization (EEHLO) method is employed to select the optimal features. These features are utilized by a Complex-Valued Dilated Recurrent Neural Network (CV-DRNN) to detect attacks within vehicle networks accurately. The performance of this novel attack detection model is rigorously evaluated and compared with that of traditional models using a variety of metrics.

Optimizing Open Radio Access Network Systems with LLAMA V2 for Enhanced Mobile Broadband, Ultra-Reliable Low-Latency Communications, and Massive Machine-Type Communications: A Framework for Efficient Network Slicing and Real-Time Resource Allocation

Optimizing Open Radio Access Network Systems with LLAMA V2 for Enhanced Mobile Broadband, Ultra-Reliable Low-Latency Communications, and Massive Machine-Type Communications: A Framework for Efficient Network Slicing and Real-Time Resource Allocation

Advanced Beamforming and Multi‐Access Edge Computing: Empowering Ultra‐Reliable and Low‐Latency Applications in 6G Networks

ABSTRACT6G technology is expected to transform communications by allowing the Internet of Everything, representing a huge advance in 2030. While B5G has not yet been established, various nations are actively working on 5G, but certain research groups are presently devoting their attention to the creation of 6G technologies. The upcoming 6G networks promise higher quality of service (QoS) features, including virtual reality and holographic communications. Multi‐Access Edge Computing (MEC) and, in particular, the offloading idea are key components of 6G innovation that enable resource‐intensive application design. If the wireless link used for computational offloading is inefficient, MEC's true potential can be impeded. Intelligent beamforming and MEC have garnered attention recently. Systematically optimizing the wireless communication environment, these developments improve connectivity between user equipment (UE) and base station (BS). By increasing the electrical charge of the reflectable signal, intelligent beamforming increases the range and efficacy of Back Communication. Particularly, this study assesses how well the MEC structure performs in urban microcellular settings when intelligent beamforming is used in communications. It has been demonstrated that the use of Intelligent Reflecting Surfaces (IRS) greatly reduces spectrum and energy usage. This study's results are implemented in Python software. Our suggested strategy shows better latency compared to other optimization methods and shorter task completion times than traditional methods. When compared to conventional techniques, the suggested MEC‐enabled network showcasing lower latency (4.9 ms) and efficient network congestion management and task completion time (30 ms) demonstrates a significant performance. These results highlight how intelligent beamforming and MEC have a lot of potential to shape the architecture of 6G networks in the future.

Minimisation of metabolic networks defines a new functional class of genes

Construction of minimal metabolic networks (MMNs) contributes both to our understanding of the origins of metabolism and to the efficiency of biotechnological processes by preventing the diversion of flux away from product formation. We have designed MMNs using a novel in silico synthetic biology pipeline that removes genes encoding enzymes and transporters from genome-scale metabolic models. The resulting minimal gene-set still ensures both viability and high growth rates. The composition of these MMNs has defined a new functional class of genes termed Network Efficiency Determinants (NEDs). These genes, whilst not essential, are very rarely eliminated in constructing an MMN, suggesting that it is difficult for metabolism to be re-routed to obviate the need for such genes. Moreover, the removal of NED genes from an MMN significantly reduces its global efficiency. Bioinformatic analyses of the NED genes have revealed that not only do these genes have more genetic interactions than the bulk of metabolic genes but their protein products also show more protein-protein interactions. In yeast, NED genes are predominantly single-copy and are highly conserved across evolutionarily distant organisms. These features confirm the importance of the NED genes to the metabolic network, including why they are so rarely excluded during minimisation.

Multipath Routing with Dynamic Load Balancing for Enhanced Energy Efficiency in Zone-Based Wireless Ad Hoc Networks

Mobile Ad hoc Networks (MANETs) consist of independent, self-organized mobile nodes capable of wirelessly communicating with each other in a reliable and secure manner. One of the major challenges in MANETs is energy consumption, as the lifetime of a node's battery is limited. This limitation can affect both network connectivity and the lifetime of individual nodes. Various protocols, proposed by the IETF and other solution providers, have aimed to optimize bandwidth, transmission quality, and power control, but none have significantly improved energy consumption. In response to these challenges, the proposed protocol is the Dynamic Load Balancing in Multipath Energy-Consuming Routing Protocol (DLB-MERP) for Wireless Ad hoc Networks. DLB-MERP can be viewed as an extension of the AOMDV protocol and is classified as a zone-based routing protocol, though it incorporates superior load balancing and energy management techniques. It introduces the concept of virtual zones to manage and distribute energy consumption in an organized way. The protocol selects communication paths based on the availability of node energy and power levels. A leader node is defined within each zone, chosen based on its energy level, load, and channel strength, to optimize energy usage. This method increases network resiliency through multipath routing, thereby enhancing overall network performance and extending network lifetime. DLB-MERP effectively addresses the limitations of existing energy-aware routing methodologies by balancing energy consumption, leading to prolonged network operation.

Machine learning-driven discovery of high-performance MEMS disk resonator gyroscope structural topologies

The design of the microelectromechanical system (MEMS) disc resonator gyroscope (DRG) structural topology is crucial for its physical properties and performance. However, creating novel high-performance MEMS DRGs has long been viewed as a formidable challenge owing to their enormous design space, the complexity of microscale physical effects, and time-consuming finite element analysis (FEA). Here, we introduce a new machine learning-driven approach to discover high-performance DRG topologies. We represent the DRG topology as pixelated binary matrices and formulate the design task as a path-planning problem. This path-planning problem is solved via deep reinforcement learning (DRL). In addition, we develop a convolutional neural network-based surrogate model to replace the expensive FEA to provide reward signals for DRL training. Benefiting from the computational efficiency of neural networks, our approach achieves a significant acceleration ratio of 4.03 × 105 compared with FEA, reducing each DRL training run to only 426.5 s. Through 8000 training runs, we discovered 7120 novel structural topologies that achieve navigation-grade precision. Many of these surpass traditional designs in performance by several orders of magnitude, revealing innovative solutions previously unconceived by humans.

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.