Network Connections Research Articles

Visualizing the Influence of Social Networks on Recovery: A Mixed-Methods Social Identity Mapping Study with Recovering Adolescents.

Background: Social recovery capital (SRC) refers to resources and supports gained through relationships and is vital to adolescent addiction recovery. Much is known about how substance use relates to social networks, but little is known about how other dimensions of social networks influence recovery (e.g., network size/exposure, degree of conflict). Methods: This mixed-methods study sampled 28 adolescents who received treatment for alcohol and other drug (AOD) use disorder (14-19 yrs.: 71% male; M = 17.32 yrs., SD = 1.33; White 82%): 20 were recovery high school (RHS) students. Adolescents completed a social identity map for addiction recovery (SIM-AR), survey, and interview. Qualitative data were content analyzed and the data from the SIM-AR were quantified. Results: On average, participants reported belonging to five distinct groups within their network (Range, 2-9; SD = 1.63; M = 27.89 people, SD = 20.09). Of their social network connections, 51% drank alcohol and 46% used other substances, on average. Larger networks involved more conflict (r = 0.57). Participants were more likely to spend more time with groups that had greater proportions of non-substance-using members. These linkages were stronger for RHS than for non-RHS students. Qualitative analyses revealed that youth reported their recovery-oriented groups as supportive, but some reported that their substance-using friends also supported their recovery. Discussion: SIM-AR was a useful measurement tool, and, through qualitative interviews, we identified unique aspects of youths' social networks important for further examination. Research with recovering youth should examine SRC-related elements within their networks including relationship quality, belonging, and conflict, alongside the substance use behaviors of network members.

DEVELOPMENT OF NETWORK SIMULATION MODEL FOR EVALUATING THE EFFICIENCY OF DISTRIBUTED CONSENSUS TAKING INTO ACCOUNT THE INSTABILITY OF NETWORK CONNECTIONS

The dynamic and unpredictable nature of network environments poses a significant challenge for distributed systems, particularly those relying on consensus algorithms for state management and fault tolerance. To address this challenge, this article introduces a novel simulation model designed to study the impact of unstable network connections on clusters running consensus algorithms. The model is engineered to mimic varying degrees of network instability, including latency fluctuations and connection disruptions, which are characteristic of real-world distributed systems. Our proposed model represents a significant advancement in the simulation of distributed networks. It employs a sophisticated network emulation layer capable of generating a wide spectrum of unstable network conditions. The core of the model is a highly configurable consensus mechanism simulator that allows for the adjustment of key parameters such as heartbeat intervals, election timeouts, and message loss rates. This level of configurability enables a comprehensive analysis of consensus behaviors under different network scenarios. The article focuses on the methodology behind the development of the model, detailing the theoretical underpinnings and the implementation strategies used to ensure a realistic representation of network instability. We also discuss the potential applications of the model, which extend beyond academic research into practical domains where distributed ledger technologies and distributed databases are prevalent. Through the deployment of this model, researchers and system architects can gain deeper insights into the resilience and adaptability of consensus algorithms. The model serves as a tool for preemptively identifying and addressing potential issues in distributed systems, facilitating the development of more robust and reliable technologies. In summary, the article showcases the design and capabilities of a new model that enables an in-depth understanding of the delicate interplay between network instability and consensus efficiency. By focusing on the model itself, the article aims to lay a foundation for future studies and improvements in the field of distributed systems.

Optimized Python library for reconstruction of ensemble-based gene co-expression networks using multi-GPU

AbstractGene co-expression networks are valuable tools for discovering biologically relevant information within gene expression data. However, analysing large datasets presents challenges due to the identification of nonlinear gene–gene associations and the need to process an ever-growing number of gene pairs and their potential network connections. These challenges mean that some experiments are discarded because the techniques do not support these intense workloads. This paper presents pyEnGNet, a Python library that can generate gene co-expression networks in High-performance computing environments. To do this, pyEnGNet harnesses CPU and multi-GPU parallel computing resources, efficiently handling large datasets. These implementations have optimised memory management and processing, delivering timely results. We have used synthetic datasets to prove the runtime and intensive workload improvements. In addition, pyEnGNet was used in a real-life study of patients after allogeneic stem cell transplantation with invasive aspergillosis and was able to detect biological perspectives in the study.

Brain functional network changes in patients with juvenile myoclonic epilepsy: a study based on graph theory and Granger causality analysis

Many resting-state functional magnetic resonance imaging (rs-fMRI) studies have shown that the brain networks are disrupted in adolescent patients with juvenile myoclonic epilepsy (JME). However, previous studies have mainly focused on investigating brain connectivity disruptions from the perspective of static functional connections, overlooking the dynamic causal characteristics between brain network connections. In our study involving 37 JME patients and 35 Healthy Controls (HC), we utilized rs-fMRI to construct whole-brain functional connectivity network. By applying graph theory, we delved into the altered topological structures of the brain functional connectivity network in JME patients and identified abnormal regions as key regions of interest (ROIs). A novel aspect of our research was the application of a combined approach using the sliding window technique and Granger causality analysis (GCA). This method allowed us to delve into the dynamic causal relationships between these ROIs and uncover the intricate patterns of dynamic effective connectivity (DEC) that pervade various brain functional networks. Graph theory analysis revealed significant deviations in JME patients, characterized by abnormal increases or decreases in metrics such as nodal betweenness centrality, degree centrality, and efficiency. These findings underscore the presence of widespread disruptions in the topological features of the brain. Further, clustering analysis of the time series data from abnormal brain regions distinguished two distinct states indicative of DEC patterns: a state of strong connectivity at a lower frequency (State 1) and a state of weak connectivity at a higher frequency (State 2). Notably, both states were associated with connectivity abnormalities across different ROIs, suggesting the disruption of local properties within the brain functional connectivity network and the existence of widespread multi-functional brain functional networks damage in JME patients. Our findings elucidate significant disruptions in the local properties of whole-brain functional connectivity network in patients with JME, revealing causal impairments across multiple functional networks. These findings collectively suggest that JME is a generalized epilepsy with localized abnormalities. Such insights highlight the intricate network dysfunctions characteristic of JME, thereby enriching our understanding of its pathophysiological features.

Competence vs. Independence: Auditors’ Connections with Members of their Clients’ Business Community*

Prior research finds that auditors’ social connections with their clients harms audit quality. We examine auditors’ social connections with members of their clients’ business community, a setting in which auditors’ connections may improve audit quality. While social ties within a client’s business community should improve auditor competency, they also threaten auditor independence. We test the effects of auditors’ network connections on audit quality using data from China, where data on social connections and individual auditors are available. Auditors’ business connections should be particularly beneficial in a relational economy like China, where clients heavily rely on social networks for contracting. We find that auditors with strong local business and government connections deliver higher quality audits as evidenced by fewer financial irregularities among their clients. Our findings are consistent with the improved competency that arises from auditors’ business connections outweighing the potential costs of impaired auditor independence.

Algorithmic approach to discrete fracture network flow modeling in consideration of realistic connections in large-scale fracture networks

Analyzing rock mass seepage using the discrete fracture network (DFN) flow model poses challenges when dealing with complex fracture networks. This paper presents a novel DFN flow model that incorporates the actual connections of large-scale fractures. Notably, this model efficiently manages over 20,000 fractures without necessitating adjustments to the DFN geometry. All geometric analyses, such as identifying connected fractures, dividing the two-dimensional domain into closed loops, triangulating arbitrary loops, and refining triangular elements, are fully automated. The analysis processes are comprehensively introduced, and core algorithms, along with their pseudo-codes, are outlined and explained to assist readers in their programming endeavors. The accuracy of geometric analyses is validated through topological graphs representing the connection relationships between fractures. In practical application, the proposed model is employed to assess the water-sealing effectiveness of an underground storage cavern project. The analysis results indicate that the existing design scheme can effectively prevent the stored oil from leaking in the presence of both dense and sparse fractures. Furthermore, following extensive modification and optimization, the scale and precision of model computation suggest that the proposed model and developed codes can meet the requirements of engineering applications.

Analysis of the Quality of Licensing Management through the Online Single Submission Risk Based Approach (OSS-RBA) System at the Investment Office and One-Stop Integrated Services of Central Maluku Regency

This research have two purposes: 1. to learn and explain the quality analysis of licensing management through the Online Single Submission Risk Based Approach (OSS-RBA) system at Dinas Penanaman Modal dan Pelayanan Terpadu Satu Pintu Kabupaten Maluku Tengah and 2. to know and explain what the supportive and impeding factors in the management of licences through the Online Single Submission Risk Based Approach (OSS - RBA) at Dinas Penanaman Modal dan Pelayanan Terpadu Satu Pintu Kabupaten Maluku Tengah. The method used in this research is qualitative with a descriptive approach, using five dimensions of quality according to Parasuraman, Zeithaml, and Berry: tangibles, reliability, responsiveness, assurance, and empathy. In this research, there were 22 respondents, consisting of 7 (seven) officers at Dinas Penanaman Modal dan Pelayanan Terpadu Satu Pintu Kabupaten Maluku Tengah and 15 entrepreneurs (14 UMK and 1 non-UMK). In this research, data collection techniques are carried out with observations, structured interviews, and documentation. Based on the results of the quality analysis of licensing management through the Online Single Submission Risk Based Approach (OSS-RBA) system at Dinas Penanaman Modal dan Pelayanan Terpadu Satu Pintu Kabupaten Maluku Tengah. The researcher concluded the following categories of results: 1. tangibles with a good category; 2. reliability with a good category; 3. responsiveness with an excellent category; 4. assurance with an excellent category; and 5. empathy with an excellent category. In addition, there are factors that support the process of licensing management through this OSS-RBA system: ease of requirements, accessibility, rapidity of handling time, and fee/cost setting. While the factors that hinder the process of licensing management through this OSS-RBA system are: network and system connections, compliance with requirements, has not made changes to the AHU for the enterprise/AHU blocked, the entrepreneur forgot their OSS access rights, incorrectly entered KBLI, still exists the brokering practice, Identity Card Number (NIK) and Taxpayer Identification Number (NPWP) having problems and invalid

Tool Wear Prediction Based on Residual Connection and Temporal Networks

Since tool wear accumulates in the cutting process, the condition of the cutting tool shows a degradation trend, which ultimately affects the surface quality. Tool wear monitoring and prediction are of significant importance in intelligent manufacturing. The cutting signal shows short-term randomness due to non-uniform materials in the workpiece, making it difficult to accurately monitor tool condition by relying on instantaneous signals. To reduce the impact of transient fluctuations, this paper proposes a novel network based on deep learning to monitor and predict tool wear. Firstly, a CNN model based on residual connection was designed to extract deep features from multi-sensor signals. After that, a temporal model based on an encoder and decoder was built for short-term monitoring and long-term prediction. It captured the instantaneous features and long-term trend features by mining the temporal dependence of the signals. In addition, an encoder and decoder-based temporal model is proposed for smoothing correction to improve the estimation accuracy of the temporal model. To validate the performance of the proposed model, the PHM dataset was used for wear monitoring and prediction and compared with other deep learning models. In addition, CFRP milling experiments were conducted to verify the stability and generalization of the model under different machining conditions. The experimental results show that the model outperformed other deep learning models in terms of MAE, MAPE, and RMSE.

Transcriptomic analysis of epicardial adipose tissue reveals the potential crosstalk genes and immune relationship between type 2 diabetes mellitus and atrial fibrillation

BackgroundThe complex relationship between atrial fibrillation (AF) and type 2 diabetes mellitus (T2DM) suggests a potential role for epicardial adipose tissue (EAT) that requires further investigation. This study employs bioinformatics and experimental approaches to clarify EAT's role in linking T2DM and AF, aiming to unravel the biological mechanisms involved. MethodBioinformatics analysis initially identified common differentially expressed genes (DEGs) in EAT from T2DM and AF datasets. Pathway enrichment and network analyses were then performed to determine the biological significance and network connections of these DEGs. Hub genes were identified through six CytoHubba algorithms and subsequently validated biologically. Experimentally, db/db mice were utilized to establish a T2DM model. AF induction was executed via programmed transesophageal electrical stimulation and burst pacing, focusing on comparing the incidence and duration of AF. Frozen sections and Hematoxylin and Eosin (H&E) staining were utilized to illuminate the structures of the heart and EAT. Moreover, quantitative PCR (qPCR) measured the expression of hub genes. ResultsThe study identified 106 DEGs in EAT from T2DM and AF datasets, underscoring significant pathways in energy metabolism and immune regulation. Three hub genes, CEBPZ, PAK1IP1, and BCCIP, emerged as pivotal in this context. In db/db mice, a marked predisposition towards AF induction and extended duration was observed, with HE staining verifying the presence of EAT. Additionally, qPCR validated significant changes in hub genes expression in db/db mice EAT. In-depth analysis identified 299 miRNAs and 33 TFs as potential regulators, notably GRHL1 and MYC. GeneMANIA analysis highlighted the hub genes' critical roles in stress responses and leukocyte differentiation, while immune profile correlations highlighted their impact on mast cells and neutrophils, emphasizing the genes' significant influence on immune regulation within the context of T2DM and AF. ConclusionThis investigation reveals the molecular links between T2DM and AF with a focus on EAT. Targeting these pathways, especially EAT-related ones, may enable personalized treatments and improved outcomes.

Influence of glass-phase structure on the degradation of rare-earth (Y2O3, La2O3)-doped CaO-Al2O3-SiO2-B2O3 glass-ceramics in citric acid solution

Liquid-phase sintering anorthite (LSA) glass-ceramics with degradation in citric-acid solution have been prepared from CaO-Al2O3-SiO2-B2O3 low-melting compositions. By means of the chemical corrosion of the glass phases, LSA glass-ceramics are effectively degraded in the citric acid solution. Then, the influence of B2O3 and rare-earth (RE) on the structures of glass phases, the degradation of LSA glass-ceramics in the citric-acid solutions, and the dielectric properties are investigated systematically. The results suggest that when the B2O3 molar ratio in the composition CaO-Al2O3-SiO2-B2O3 is 0.5, doping LSA glass-ceramics with RE can reduce the quantity of bridging oxygen and [BO4] units in the glass phase, as well as the degree of network connection of [AlO4] units in the glass network. Conversely, when the B2O3 molar ratio is decreased down to 0.3, doping RE into LSA glass-ceramics increases the quantity of bridging oxygen and [BO4] units for glass phase. This improvement in chemical stability effectively impedes the degradation of LSA glass-ceramics in citric-acid solutions. Concurrently, the degradation mechanism of LSA glass-ceramics in citric acid solution is analyzed and explained in terms of classical glass corrosion theory, while the microstructural characteristics of LSA glass-ceramics are utilized to investigate their dielectric properties. It indicates that the dielectric loss and dielectric constant of LSA glass-ceramics are significantly lowered as a result of the existence of the glass phase. Especially when the B2O3 molar ratio in the composition CaO-Al2O3-SiO2-B2O3 is 0.3, and the La2O3 doping percentage into LSA glass-ceramics is 0.5wt.%, the LSA glass-ceramics exhibit the lowest dielectric loss value of 3.13×10-3 and εr=4.17. Developing the LSA glass-ceramic with degradation in organic acids can provide a new idea for the recycling and disposal of e-waste.

Information and immigrant settlement

We study a randomly-assigned program providing information on U.S. settlement for new Filipino immigrants. The intervention, a 2.5-hour pre-departure training and an accompanying paper handbook, has no effect on employment, settlement, and subjective wellbeing, but leads immigrants to acquire substantially fewer social network connections. We rationalize these findings with a simple model, showing that information and social network links are substitutes under reasonable assumptions. Consistent with the model, the treatment reduces social network links more when costs of acquiring network links are lower. Offsetting reductions in the acquisition of social network connections can hence reduce the effectiveness of information interventions.

Intrusion detection in machine learning based E-shaped structure with algorithms, strategies and applications in wireless sensor networks

In the everyday world of computer applications, from the cloud to the Internet of Things, distributed sensor networks are essential (IoT). These computer application devices are often connected to Arduino network connection and microcontrollers such sensors and actuators. Thus, a defensive network with an IDS serves as the need for contemporary networks. The intrusion detection system has unavoidably evolved throughout the years, but despite this, it remains a difficult study topic since the current intrusion detection system uses signature-based approaches rather than anomaly detection. Therefore, improving the current intrusion detection system is challenging since it is difficult to find zero-day attacks in IoT networks when dealing with varied data sources. Filtered Deep Learning Model for Intrusion Detection with a Data Communication Approach is presented in this study. The five steps that make up the suggested model are Initialization of Sensor Networks, Cluster Formation and Head Selection, Connectivity, Attack Detection, and Data Broker. It was discovered that the suggested model for intrusion detection outperformed both the current Deep Learning Neural Net and Artificial Neural Network. In comparison to the most popular algorithms, experimental findings revealed a superior result of 96.12 % accuracy. The E-shaped patch antenna is a brand-new single-patch wide-band microstrip antenna that is presented in this research. A microstrip antenna's patch has two parallel slots built into it to increase its bandwidth. Investigating the behaviour of the currents on the patch allows for the exploration of the wide-band mechanism. A broad bandwidth is achieved by optimising the slot's length, breadth, and location. Finally, a 40.3 % E-shaped patch antenna is developed, made, and tested to resonate at 7.5 and 8.5 GHz for wireless communications. Additionally displayed are the reflection coefficient, VSWR, radiation pattern and directivity.

A meta-weighted network equipped with uncertainty estimations for remaining useful life prediction of turbopump bearings

Uncertainty quantification and negative transfer characterization are significant challenges in the context of deep learning-based remaining useful life prediction with limited data. Conventional Bayesian methods lack scalability to deep learning algorithms for uncertainty quantification due to intricate network connections and extensive training parameters. Additionally, although transfer learning is a promising way to improve the generalization ability of prediction algorithms, its effectiveness is not always guaranteed when leveraging source data undesirably reduces the prediction performance, which is named negative transfer. This manuscript proposed a meta-weighted neural network equipped with uncertainty estimation to discern in-distribution from out-of-distribution data and an adaptive sample meta re-weighting strategy is designed by specifying the weighting function from prediction loss to sample weight according to the gradient direction. Performance evaluations on cryogenic bearings demonstrate that the proposed algorithm can quantitatively determine the weights of source data based on prediction error, ultimately leading to accurate interval remaining life prediction.

Research hotspots and evolving trends of barrier dysfunction in acute lung injury and acute respiratory distress syndrome

Endothelial and epithelial barrier dysfunction due to increased permeability and heightened inflammatory reactions influences the emergence of acute lung injury (ALI) and acute respiratory distress syndrome (ARDS). Nevertheless, bibliometric research comparing endothelial and epithelial barriers is limited. Therefore, this bibliometric study analyzed the Web of Science Core Collection (WoSCC) of the Science Citation Index Expanded literature to explore present research priorities and development tendencies within this field. We conducted a comprehensive search (October 18, 2023) on WoSCC from January 1, 2010, to October 18, 2023, focusing on articles related to endothelial and epithelial barriers in ALI and ARDS. Retrieved data were visualized and analyzed using R-bibliometrix, VOS viewer 1.6.19, and CiteSpace 6.2. R4. Functional enrichment analysis of gene targets identified in the keyword list using Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene ontology databases, and based on the STRING database to construct a PPI network to predict core genes. A total of 941 original articles and reviews were identified. The United States had the highest number of publications and citations and the highest H-index and G-index. According to the Collaboration Network Analysis graph, the United States and China had the strongest collaboration. Birukova AA had the most publications and citations among all authors, while eight of the top ten institutions with mediator centrality were located in the United States. The American Journal of Physiology-Lung Cellular and Molecular Physiology was the leading journal and had the most well-established publication on endothelial and epithelial barriers in ALI and ARDS. Bibliometric analysis revealed that the most frequently used keywords were acute lung injury, ARDS, activation, expression, and inflammation. RHOA appeared most frequently among gene-related keywords, and the PI3K-AKT signaling pathway had the highest count in KEGG pathway enrichment. Research on endothelial versus epithelial barriers in ALI and ARDS remains preliminary. This bibliometric study examined cooperative network connections among countries, authors, journals, and network associations in the cited references. Investigation of the functions of the endothelial and epithelial barriers in ALI/ARDS associated with COVID-19 has recently gained significant attention.

Network Analysis of International Trade: Shocks, Connections, and Implications

This paper delves into the intricate interplay between idiosyncratic shocks, network connections among economic agents, and the ensuing implications for international trade dynamics. Drawing upon economic theory and empirical evidence, it scrutinizes how localized supply shocks, such as those induced by natural disasters, reverberate through global trade networks. Two models are deployed to elucidate the relationships between exogenous shocks and fluctuations in international trade, offering insights into the mechanisms through which shocks propagate or dissipate. By examining the distribution of suppliers and the network structures of various goods, the paper uncovers nuances in the transmission of shocks and their impact on aggregate outcomes. Moreover, it explores the evolving role of countries within the global trade network, particularly in the context of energy trade. The findings underscore the significance of network analysis in understanding the resilience of international trade amidst disruptions and underscore the policy implications for trade and exchange rate strategies. Future avenues for research are also delineated, emphasizing the need for deeper investigations into the dynamics of trade networks and policy responses to shocks.

Predictive Analysis Application for Academic Student Advancement in Secondary Education Institutions

The study developed a Predictive Analysis Application for Academic Student Advancement at Dr. Josefa Jara Martinez High School (DJJMHS) to manage school forms and data records centrally. This system offers real-time attendance tracking, academic progress reports, prediction, visualization, staff performance monitoring, and report generation. It ensures secure network connections and improved security measures while presenting all functions through a user-friendly interface. Developed using HTML5, CSS3, JavaScript, and Python-MySQL, the system facilitates the issuance and processing of various school forms. Through two testing cycles, it demonstrated functionality and reliability, receiving a "Very Good" rating from 30 respondents. This indicates accurate and dependable access to end users' data and services through the system.

Social Capital and Cross-Border Venture Capital Investments in China

In the context of the Chinese market, foreign cross-border venture capitalists have devised specific strategies to mitigate the challenges associated with the liabilities of foreignness, such as risks and information asymmetry. They have strategically leveraged social capital to not only decrease investment risk but also to influence their investment preferences and behaviors. To investigate the influence of different types of social capital on the investment decisions of cross-border venture capitalists, hypotheses are proposed and tested using regression analysis. Our research reveals several key findings in this regard. Firstly, cross-border venture capitalists with a robust structural social capital network exhibit a greater propensity to invest in early-stage companies. This suggests that well-established connections and partnerships within the Chinese entrepreneurial ecosystem provide a level of comfort and confidence when investing in ventures at their infancy. Interestingly, relational and cognitive social capital, though undoubtedly valuable, do not significantly impact the decision to make early-stage investments. Furthermore, we have observed that venture capitalists with higher levels of structural and cognitive social capital are more inclined to form syndications. Collaborative partnerships and shared knowledge networks seem to be crucial factors that drive syndication decisions. Lastly, venture capitalists endowed with substantial structural and relational social capital tend to allocate larger investment amounts, signifying the influence of business or personal relationships and network connections on the scale of their investments.

An Enhanced Computational Approach Using Multi-kernel Positive Unlabeled Learning for Predicting Drug-target Interactions.

In recent years, analyzing complex biological networks to predict future links in such networks has attracted the attention of many medical and computer science researchers. The discovery of new drugs is one of the application cases for predicting future connections in biological networks. The operation of drug-target interactions prediction (DTIP) can be considered a fundamental step in identifying potential interactions between drug and target to identify new drugs. The previous studies reveal that predictions are made based on known interactions using computational methods to solve the cost problem and avoid blind study of all interactions. But, there seem to be challenges such as the lack of confirmed negative samples and the low accuracy in some computational methods. Thus, we have proposed an efficient and hybrid approach called MKPUL-BLM to manage some of the aforementioned challenges for predicting drug-target interactions. The MKPUL-BLM combins multi-kernel and positive unlabeled learning (PUL) approaches. Our method uses more information to increase accuracy, in addition to minimizing small similarities using network information. Also, potential negative samples are produced using a PUL approach because of lacking negative laboratory samples. Finally, labels are expanded via a semi-supervised. Our method improved to 0.98 and 0.94 in the old interactions set for the ROCAUC and AUPR criteria, respectively. Also, this method enhanced ROCAUC and AUPR criteria by 0.89 and 0.77 for the new interactions set. The MKPUL-BLM can be considered an efficient alternative to achieve more reliable predictions in the field of DTIP.

Ship Network Traffic Engineering Based on Reinforcement Learning

This research addresses multiple challenges faced by ship networks, including limited bandwidth, unstable network connections, high latency, and command priority. To solve these problems, we used reinforcement learning-based methods to simulate traffic engineering in ship networks. We focused on three aspects—traffic balance, instruction priority, and complex network structure—to evaluate reinforcement learning performance in these scenarios. Performance: We developed a reinforcement learning framework for ship network traffic engineering that treats the routing policy as the state and the network state as the environment. The agent generates routing changes and uses actions to optimize traffic services. The experimental results show that reinforcement learning optimizes network traffic balance, reasonably arranges instruction priorities, and copes with complex network structures, greatly improving the network’s quality of service (QoS). Through an in-depth analysis of the experimental data, we noticed that network consumption was reduced by 9.1% under reinforcement learning. Reinforcement learning effectively implemented priority routing of high-priority instructions while reducing the occupancy rate of the edge with the highest occupancy rate in the network by 18.53%.

An ameliorated localization algorithm for compensating stratification effect based on improved underwater salp swarm optimization technique

SummaryThe underwater acoustic sensor network is a fundamental source for ocean exploration. The potential applications of underwater acoustic sensor network (UASN) include seismic imaging, disaster prevention, mine reconnaissance, pollution monitoring, exploration of natural resources, and military surveillance. To acquire accurate results, implementing all applications of underwater sensor networks requires an adequate network connection and communication technology. The precise placement of underwater sensor nodes needs to be identified in order to achieve effective communication. To accomplish the requirement, the paper presents an efficient localization algorithm to compensate the stratification effect based on an improved underwater salp swarm optimization technique (LAS‐IUSSOT). To compute the location of sensor nodes with high accuracy, the nodes are initially randomly deployed in three‐dimensional underwater acoustic sensor network (3D‐UASN). After that, the hybridization of centroid‐based localization and the ray theory technique is used, and then, the degree of coplanarity is analyzed among the underwater sensor nodes. Then, the computation of the location of unknown nodes is performed using improved underwater salp swarm optimization technique (IUSSOT) to obtain the optimized location and compensate the impact of the stratification. The comparison of the simulation results of the existing algorithm and the proposed algorithm is performed. The LAS‐IUSSOT achieves 40.46% and 28.00% accuracy in terms of localization of underwater sensor nodes for both the sparse and dense regions in 3D‐UASN. The LAS‐IUSSOT achieves 49.39% and 62.57% accuracy in terms of ranging of underwater sensor nodes for both the sparse and dense regions in 3D‐UASN. Simulation results illustrate that the proposed algorithm outperforms the existing algorithm in terms of localization and ranging accuracy in both sparse and dense regions in 3D‐UASN, root mean square error (RMSE), normalized localization error (NLE), computation time, and convergence rate.