Rockburst is one of the most hazardous geological disasters in underground engineering due to its complex causes and destructive nature. To address this, there is an imperative for methodologies that can predict rockb...
详细信息
Rockburst is one of the most hazardous geological disasters in underground engineering due to its complex causes and destructive nature. To address this, there is an imperative for methodologies that can predict rockbursts quickly and effectively to mitigate preemptively the risks and damages. In this study, 259 rockburst instances were analyzed, employing six rockburst feature parameters: maximum tangential stress (sigma theta), uniaxial compressive strength of rock (sigma c), uniaxial tensile strength of rock (sigma t), stress coefficient (sigma theta/sigma t), rock brittleness coefficient (sigma c/sigma t), and elastic energy index (Wet) as inputs. By integrating three novel meta-heuristic algorithms-dingo optimizationalgorithm (DOA), osprey optimization algorithm (OOA), and rime-ice optimizationalgorithm (RIME)-with support vector machine (SVM), hybrid models for long-term rockburst trend prediction were constructed. Performance evaluations through fivefold cross-validation revealed that for the no rockbursts, DOA-SVM (Pop = 200) demonstrated superior predictive performance, achieving an accuracy of 0.9808, precision of 0.9231, recall of 1, and an F1-score of 0.96. For moderate rockbursts, OOA-SVM (Pop = 100) emerged as the most effective, registering an accuracy of 0.9808, precision of 0.9545, recall of 1, and an F1-score of 0.9767. For light and severe rockbursts, DOA-SVM, OOA-SVM, and RIME-SVM showcased comparable predictive outcomes. However, these hybrid models outperformed traditional SVM models optimized with conventional algorithms in terms of accuracy across all rockburst hazard levels. Moreover, the hybrid models underwent additional validation with a new dataset of 20 rockburst instances collected globally, confirming their robust efficacy and exceptional generalization capabilities. An ensuing analysis using local interpretable model-agnostic explanations (LIME) on the six key feature parameters revealed a significant positive correlation between s
The effectiveness of Transmission Control Protocol (TCP) connections is significantly impacted by congestion control (CC). Congestion occurs when the network cannot manage the level of traffic that arises when a large...
详细信息
The effectiveness of Transmission Control Protocol (TCP) connections is significantly impacted by congestion control (CC). Congestion occurs when the network cannot manage the level of traffic that arises when a large number of packets arrive at once. If congestion is anticipated, packet loss can be prevented by taking appropriate measures to lower the rate of packet production at the source. Many existing protocols are developed to control congestion on the other hand, the packet delivery ratio will not sufficiently be high and it lengthens the delay, which affects the performance of TCP. In order to improve TCP performance in MANET, the Packet Chaining Reservation Protocol (PCRP) using radial basis functional neural network (RBFNN) was developed. The initial message is transmitted by the transmitter, then waits for a reply. If the acknowledgement is received, the congestion prediction algorithm is executed to determine whether there is congestion or not on the data transmission line. Based on a few characteristics, RBFNN is used to estimate congestion in the transport layer. The best size of the cwnd is chosen using the osprey optimization algorithm (OOA), which is used for efficient data transfer. If the cwnd value above the threshold value signifies congestion avoidance phases are carried out in accordance with PCRP. This process is repeated until every message has been transmitted. The simulation analysis shows the proposed protocol has 89% packet delivery ratio, 2.5Mbps of throughput and 15 sec delay. Thus, the proposed approach is the better choice for enhancing the performance of TCP under MANET.
The Internet of Things (IoT) is basically about communication, which permits devices and circumstances to gather, share, and act on data. A transmission method called LoRa (Long Range) allows for the long-range transm...
详细信息
The Internet of Things (IoT) is basically about communication, which permits devices and circumstances to gather, share, and act on data. A transmission method called LoRa (Long Range) allows for the long-range transmission of data at a low delivery rate. The problems and the limitations of the IoT conception with a focus on LoRa technology are proposed in this study. This paper presents an analysis of the challenges and constraints associated with the Internet of Things (IoT) concept, with a specific emphasis on LoRa technology. A LoRaWAN (Long Range Wide Area Network) network consists of battery-operated devices that enable communication in both directions and is a form of Low Power Wide Area Network (LPWAN). However, various challenges present in IoT data transmission between sensor nodes due to its transmission rate that leads to high network collision. To overcome such challenges, Transmission Control Protocol (TCP) is used which is a transport layer protocol for efficient data transmission. However, existing work performs collision detection, collision avoidance, and resource allocation with limited parameters, which leads to inefficient collision avoidance. To leverage the existing issues, the proposed work adopts proper collision control and efficient resource allocation in the LoRaWAN network via TCP. In our proposed work, Multi-hop clustering is performed for LoRaWAN nodes and gateways using the Mini Batch K Means Clustering (MBKMC) algorithm to reduce the imbalance load among networks and computational complexities. Collision detection is performed using the Improved Gradient Boosting Decision Tree (IMPGBDT) algorithm. After that, collision avoidance is performed using the osprey optimization algorithm (OOA) based on channel transmission signal strength. The channel is allocated to the demanded resource request using the Deep Q Network (DQN) algorithm. Here, resource allocation is performed based on the Profit Maximization Multi Round Auction (PMMRA) algo
This study provides an in-depth exploration of the urban municipal solid waste (MSW) collection issue in the urban context, where there is a continuous rise in individual waste production levels and vulnerability to c...
详细信息
Power converters are widely used in renewable energy conversion systems such as photovoltaics. Their main role is to adapt the output voltage to a desired voltage *** study proposes a highly efficient Single-Ended Pri...
详细信息
Power converters are widely used in renewable energy conversion systems such as photovoltaics. Their main role is to adapt the output voltage to a desired voltage *** study proposes a highly efficient Single-Ended Primary Inductor Converter (SEPIC) to enhance the utilization of PV arrays by ensuring a continuous flow of current. To minimize DC voltage ripples, a Proportional-Integral (PI) controller is presented to continuously monitor the High power extracted from the PV array. The PI controller parameters are optimized using the osprey optimization algorithm (OOA), which mimics the hunting behavior of ospreys in nature. The OOA draws inspiration from the hunting strategy of ospreys when they hunt fish in the seas. The osprey first detects the position of its prey and then captures it, carrying it to a suitable location to consume it. Similarly, the OOA iteratively optimizes the PI controller parameters to advance the SEPIC converter and achieve a DC-link voltage for steady-state at the converter's output. Then it is fed into a voltage source inverter (VSI), which connects the system to a single-phase utility grid. A fuzzy logic tuned PI controller is employed to synchronize the inverter's output with the grid. The performance is evaluated by analyzing the harmonic content in the grid current. To validate the proposed approach, a Simulink model is developed and compared against a hardware prototype. The proposed results achieved an effectiveness of performance and efficient power conversion in the system.
An adaptive metaheuristic optimization-based QoS-aware, Energy-balancing, Secure Routing Protocol (AQoSESRP) is proposed in this article. The network is modelled as a biconcentric hexagon (BiCon-HexA), and the cluster...
详细信息
An adaptive metaheuristic optimization-based QoS-aware, Energy-balancing, Secure Routing Protocol (AQoSESRP) is proposed in this article. The network is modelled as a biconcentric hexagon (BiCon-HexA), and the clusters are formed within the BiCon-HexA network. The BiCon-HexA is divided into six sectors to support effective data aggregation, and then clusters are formed within all sectors. The optimal cluster head (CH) selection mechanism is modelled by an Adaptive Hunter-Prey optimization (AdapH-PO) algorithm considering QoS parameters. Data aggregation is then done securely with an enhanced encryption approach. Here, upgraded elliptic curve cryptography (UEllip-CC) is used to encode data in CH. This UEllip-CC approach provides security improvements in data transmission. Furthermore, in this study, CHs are combined in the multi-hop routing of data packets to reduce the power consumption problems of wireless sensor networks (WSN). To determine the optimal route for data transmission, an energy-balanced multi-path routing algorithm called improved convolutional osprey network (ICON) is presented. Nevertheless, the data transmission nodes can be overloaded in the data routing phase. Here, the congestion problem can be solved by applying an improved version of the Random Early Detection (RED) congestion control model to discard the data packets more noticeably. The simulation of AQoS-ESRP is done with Matlab, and the performance is evaluated using different metrics. When compared to existing systems, the simulation results clearly indicate a significantly higher throughput and delay. Thus, the AQoS ESRP model is employed to maximize the overall data transfer in the WSN.
Accurately estimating the state of health (SOH) of lithium batteries is a critical and challenging task in battery management systems. Data-driven models are widely used for SOH estimation but still suffer from the di...
详细信息
Accurately estimating the state of health (SOH) of lithium batteries is a critical and challenging task in battery management systems. Data-driven models are widely used for SOH estimation but still suffer from the difficulty of balancing speed, accuracy, and adaptability. Therefore, this study constructs the dung beetle optimizationalgorithm to optimize the kernel extreme learning machine model. This paper addresses the issues of long iteration time and mismatches in kernel function mapping in data-driven models. To improve the model's generality, an adaptive learning kernel function is designed to complement the polynomial kernel function and form a joint function. This joint function is then introduced into a single implicit-layer extreme learning machine, which achieves fast speed and strong adaptive capability. To enhance the algorithmic parameter search capability, the optimal Latin hypercube idea, and the ospreyalgorithm's global exploration strategy are introduced, which effectively improves the algorithm's global search capability. Additionally, it successfully regulated the positional update through the design of the logarithmic weighting factor, which improved the local search and convergence capabilities of the algorithm. The experiment validates the effectiveness and rationality of the proposed model for advancing battery management system applications.
Introduction: The crucial transition toward carbon neutrality is developing and adopting low-carbon buildings and communities to achieve the recycling and reuse of resources and to minimize the damage to the natural e...
详细信息
Introduction: The crucial transition toward carbon neutrality is developing and adopting low-carbon buildings and communities to achieve the recycling and reuse of resources and to minimize the damage to the natural environment by humans. Energy saving for residential buildings is essential for enhancing cost-effectiveness and redundant energy drain. Considering the increasing attention to energy conservation and the accessibility of sustainable energy sources, common energy-saving solutions expose inherent inadequacies limiting their effectiveness. The ineffectual use of traditional energy sources can result in waste, greater operating costs, and excessive energy consumption in residential ***: Hence, a Multi-Objective Energy-Saving optimization Method (MOESOM) has been proposed to optimize energy use and conservation in residential buildings in southern Anhui, China. The proposed approach examines lower operational costs and carbon emissions by using green energy sources and encouraging effective energy consumption habits. The suggested Multi-Objective Energy-Saving optimization Method technique offers insight into energy saving by utilizing green energy sources and confining energy uses. The multi-objective turns around energy saving and resource usage for decreasing operational costs and averting carbon emissions. Thus, the suggested technique is verified utilizing the osprey optimization algorithm (OOA);the detailed goal is recognized utilizing the multiple objectives described. Based on the progress of low-carbon emissions and energy saving, the number of iterations for augmenting osprey agents is identified. This agent-based optimization is executed if the novel augmented agent fulfills any of the trailing progression. The emission control level and energy-saving factor are assessed considering the variance between new and old agent progression. This encourages the various objectives to be fulfilled under similar criteria balancing their outcom
Traditional methods for detecting soil microplastics include chemical digestion, density separation, staining, etc. These methods often only provide qualitative analysis of microplastics and are difficult to accuratel...
详细信息
Traditional methods for detecting soil microplastics include chemical digestion, density separation, staining, etc. These methods often only provide qualitative analysis of microplastics and are difficult to accurately quantify. To address this issue, laser induced fluorescence (LIF) technology is introduced, which can achieve high sensitivity, non-destructive, and rapid detection, and improve the accuracy and efficiency of qualitative and quantitative analysis of soil microplastics. Therefore, based on LIF technology, a qualitative prediction model for optimizing Extreme Learning Machine (ELM) using osprey optimization algorithm (OOA) and a quantitative prediction model combining Continuous Projection algorithm (SPA) with Partial Least Squares algorithm (PLS) were established. Qualitative analysis used eight types of microplastics, with AS, PA66, ABS, PS, POM, PBT, PET, and PVC as experimental samples. Initially, spectral data is obtained using LIF technology and the raw spectral data is pre-processed using polynomial smoothing algorithm (SG) and moving average (MA) methods. Subsequently, factor analysis (FA) and local linear embedding (LLE) techniques are applied to dimensionality reduction and then input into the ELM model. At the same time, the ELM parameter is optimized by using OOA algorithm. In the quantitative analysis, PA66 powder and soil are mixed in different proportions (10:0, 8:2, 5:5, 2:8, 0:10), SG and MA pre-processing are performed on the spectral data obtained by LIF technology, and SPA is used to select the spectral characteristic wavelength for the original data and the pre-processed spectral data, and then a linear regression model is established combined with PLS. In order to facilitate the comparison of data, the experimental results are reserved to 5 decimal places, the experimental results indicate that LIF technology is faster than traditional methods in extracting raw data. The convergence of the OOA-optimized ELM model is better than tha
One of the critical technologies to ensure cyberspace security is network traffic anomaly detection, which detects malicious attacks by analyzing and identifying network traffic behavior. The rapid development of the ...
详细信息
One of the critical technologies to ensure cyberspace security is network traffic anomaly detection, which detects malicious attacks by analyzing and identifying network traffic behavior. The rapid development of the network has led to explosive growth in network traffic, which seriously impacts the user's information security. Researchers have delved into intrusion detection as an active defense technology to address this challenge. However, traditional machine learning methods struggle to capture complex threats and attack patterns when dealing with large-scale network data. In contrast, deep learning methods have the advantages of automatically extracting features from network traffic data and strong generalization capabilities. Aiming to enhance the ability of network anomaly traffic detection, this paper proposes a network traffic anomaly detection based on Deep Residual Shrinkage Network (DRSN), namely "GSOOA-1DDRSN". This method uses an improved osprey optimization algorithm to select the most relevant and essential features in network traffic, reducing the features' dimensionality. For better detection performance of network traffic anomalies, a one-dimensional deep residual shrinkage network (1DDRSN) is designed as a classifier. Validation is performed using the NSL-KDD and UNSWNB15 datasets and compared with other methods. The experimental results show that GSOOA1DDRSN has improved multi-classification accuracy, precision, recall, and F1 Score by approximately 2 % and 3 %, respectively, compared to the 1DDRSN model on two datasets. Additionally, it reduces the time computation costs by 20 % and 30 % on these datasets. Furthermore, compared to other models, GSOOA-1DDRSN offers superior classification accuracy and effectively reduces the number of features.
暂无评论