A GRU-based traffic situation prediction method in multi-domain software defined network.
Ontology highlight
ABSTRACT:
SUBMITTER: Sun W
PROVIDER: S-EPMC9299279 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Software defect prediction (SDP) can be used to produce reliable, high-quality software. The current SDP is practiced on program granular components (such as file level, class level, or function level), which cannot accurately predict failures. To solve this problem, we propose a new framework called DP-AGL, which uses attention-based GRU-LSTM for statement-level defect prediction. By using clang to build an abstract syntax tree (AST), we define a set of 32 statement-level metrics. We label each statement, then make a three-dimensional vector and apply it as an automatic learning model, and then use a gated recurrent unit (GRU) with a long short-term memory (LSTM). In addition, the Attention mechanism is used to generate important features and improve accuracy. To verify our experiments, we selected 119,989 C/C++ programs in Code4Bench. The benchmark tests cover various programs and variant sets written by thousands of programmers. As an evaluation standard, compared with the state evaluation method, the recall, precision, accuracy and F1 measurement of our well-trained DP-AGL under normal conditions have increased by 1%, 4%, 5%, and 2% respectively.
| S-EPMC7932164 | biostudies-literature
Project description:Network traffic prediction is an important network monitoring method, which is widely used in network resource optimization and anomaly detection. However, with the increasing scale of networks and the rapid development of 5-th generation mobile networks (5G), traditional traffic forecasting methods are no longer applicable. To solve this problem, this paper applies Long Short-Term Memory (LSTM) network, data augmentation, clustering algorithm, model compression, and other technologies, and proposes a Cluster-based Lightweight PREdiction Model (CLPREM), a method for real-time traffic prediction of 5G mobile networks. We have designed unique data processing and classification methods to make CLPREM more robust than traditional neural network models. To demonstrate the effectiveness of the method, we designed and conducted experiments in a variety of settings. Experimental results confirm that CLPREM can obtain higher accuracy than traditional prediction schemes with less time cost. To address the occasional anomaly prediction issue in CLPREM, we propose a preprocessing method that minimally impacts time overhead. This approach not only enhances the accuracy of CLPREM but also effectively resolves the real-time traffic prediction challenge in 5G mobile networks.
| S-EPMC10984461 | biostudies-literature
Project description:In the era of Internet of Things and 5G networks, handling real time network traffic with the required Quality of Services and optimal utilization of network resources is a challenging task. Traffic Engineering provides mechanisms to guide network traffic to improve utilization of network resources and meet requirements of the network Quality of Service (QoS). Traditional networks use IP based and Multi-Protocol Label Switching (MPLS) based Traffic Engineering mechanisms. Software Defined Networking (SDN) have characteristics useful for solving traffic scheduling and management. Currently the traditional networks are not going to be replaced fully by SDN enabled resources and hence traffic engineering solutions for Hybrid IP/SDN setups have to be explored. In this paper we propose a new Termite Inspired Optimization algorithm for dynamic path allocation and better utilization of network links using hybrid SDN setup. The proposed bioinspired algorithm based on Termite behaviour implemented in the SDN Controller supports elastic bandwidth demands from applications, by avoiding congestion, handling traffic priority and link availability. Testing in both simulated and physical test bed demonstrate the performance of the algorithm with the support of SDN. In cases of link failures, the algorithm in the SDN Controller performs failure recovery gracefully. The algorithm also performs very well in congestion avoidance. The SDN based algorithm can be implemented in the existing traditional WAN as a hybrid setup and is a less complex, better alternative to the traditional MPLS Traffic Engineering setup.
| S-EPMC7924724 | biostudies-literature
Project description:In the context of the proliferated evolution of network service types and the expeditious augmentation of network resource deployment, the requisition for copious labeled datasets to facilitate superior performance in traffic classification methods, particularly those hinging on deep learning, is imperative. Nonetheless, the procurement and annotation of such extensive datasets necessitate considerable temporal and human resource investments. In response to this predicament, this work introduces a methodology, termed MTEFU, leveraging a deep learning model-based multi-task learning algorithm, strategically designed to mitigate the reliance on substantial labeled training samples. Multiple classification tasks, encompassing duration, bandwidth size, and business traffic category, are incorporated, with a shared parameter strategy implemented amongst tasks to assure the transference of information across disparate tasks. Employing CNN, SAE, GRU, and LSTM as multi-task learning classification models, training validation and experimental testing were conducted on the QUIC dataset. A comparative analysis with single-task and ensemble learning methods reveals that, in the context of predicting network traffic types, the accuracy derived from the multi-task learning strategy, even with a mere 150 labeled samples, can emulate the 94.67% accuracy achieved through single-task learning with a fully labeled dataset of 6139 samples.
| S-EPMC10827795 | biostudies-literature
Project description:In this paper, to solve the problem of detecting network anomalies, a method of forming a set of informative features formalizing the normal and anomalous behavior of the system on the basis of evaluating the Hurst (H) parameter of the network traffic has been proposed. Criteria to detect and prevent various types of network anomalies using the Three Sigma Rule and Hurst parameter have been defined. A rescaled range (RS) method to evaluate the Hurst parameter has been chosen. The practical value of the proposed method is conditioned by a set of the following factors: low time spent on calculations, short time required for monitoring, the possibility of self-training, as well as the possibility of observing a wide range of traffic types. For new DPI (Deep Packet Inspection) system implementation, algorithms for analyzing and captured traffic with protocol detection and determining statistical load parameters have been developed. In addition, algorithms that are responsible for flow regulation to ensure the QoS (Quality of Services) based on the conducted static analysis of flows and the proposed method of detection of anomalies using the parameter Hurst have been developed. We compared the proposed software DPI system with the existing SolarWinds Deep Packet Inspection for the possibility of network traffic anomaly detection and prevention. The created software components of the proposed DPI system increase the efficiency of using standard intrusion detection and prevention systems by identifying and taking into account new non-standard factors and dependencies. The use of the developed system in the IoT communication infrastructure will increase the level of information security and significantly reduce the risks of its loss.
| S-EPMC7146318 | biostudies-literature
Project description:This data article contains information on a new intelligent bandwidth allocation model for future network (Smart Allocation). The included data describe the topology of the network testbed and the obtained results. Obtained data show the effectiveness of the proposed model in comparison with the MAM and RDM bandwidth allocation models. In relation to the performances evaluation, a variety of flows are used such as: voice over IP (VoIP), video, HTTP, and Internet Control Message Protocol (ICMP). The evaluation criteria are: VoIP latency and jitter, Peak Signal to Noise Ratio (PSNR) video, retransmission video, goodput, HTTP response page, and the Round-Trip Time (RTT) ICMP delay. The presented data are extracted based on simulation.
| S-EPMC6134167 | biostudies-literature
Project description:In recent years a number of calculative models based on protein-protein interaction (PPI) networks have been proposed successively. However, due to false positives, false negatives, and the incompleteness of PPI networks, there are still many challenges affecting the design of computational models with satisfactory predictive accuracy when inferring key proteins. This study proposes a prediction model called WPDINM for detecting key proteins based on a novel weighted protein-domain interaction (PDI) network. In WPDINM, a weighted PPI network is constructed first by combining the gene expression data of proteins with topological information extracted from the original PPI network. Simultaneously, a weighted domain-domain interaction (DDI) network is constructed based on the original PDI network. Next, through integrating the newly obtained weighted PPI network and weighted DDI network with the original PDI network, a weighted PDI network is further constructed. Then, based on topological features and biological information, including the subcellular localization and orthologous information of proteins, a novel PageRank-based iterative algorithm is designed and implemented on the newly constructed weighted PDI network to estimate the criticality of proteins. Finally, to assess the prediction performance of WPDINM, we compared it with 12 kinds of competitive measures. Experimental results show that WPDINM can achieve a predictive accuracy rate of 90.19, 81.96, 70.72, 62.04, 55.83, and 51.13% in the top 1%, top 5%, top 10%, top 15%, top 20%, and top 25% separately, which exceeds the prediction accuracy achieved by traditional state-of-the-art competing measures. Owing to the satisfactory identification effect, the WPDINM measure may contribute to the further development of key protein identification.
| S-EPMC8010314 | biostudies-literature
Project description:Cutter wear is one of the key factors influencing construction efficiency during shield tunnelling. Prediction of cutter wear can improve construction efficiency by reducing the times of cutter inspections in engineering practice. Evaluation of cutter life is vital for cutter wear prediction, however, existing cutter life indices can only estimate the health condition of all cutters on cutterhead on a holistic basis. A new index was proposed to evaluate cutter wear located at a specific installation position on cutterhead. A deep learning model integrating the index was developed for the estimation of accumulated cutter wear during real time shield tunnelling. The new index can be obtained by monitored field parameters and can predict cutter wear with historical wear patterns. The input and output data samples were reshaped for multi-step prediction. A shield tunnelling section in Guangzhou weathered granite was used for validation. The proposed method can help reduce the cost of cutter replacement by reducing the times of machine interventions. The method article is a companion paper to the original article [1].• Proposed index for prediction of cutter wear rate.• Deep learning model of 1D-CNN and GRU.• Multi-step cutter wear prediction. Graphical abstract Image, graphical abstract
| S-EPMC9880237 | biostudies-literature
Project description:MotivationMost proteins consist of multiple domains, independent structural and evolutionary units that are often reshuffled in genomic rearrangements to form new protein architectures. Template-based modeling methods can often detect homologous templates for individual domains, but templates that could be used to model the entire query protein are often not available.ResultsWe have developed a fast docking algorithm ab initio domain assembly (AIDA) for assembling multi-domain protein structures, guided by the ab initio folding potential. This approach can be extended to discontinuous domains (i.e. domains with 'inserted' domains). When tested on experimentally solved structures of multi-domain proteins, the relative domain positions were accurately found among top 5000 models in 86% of cases. AIDA server can use domain assignments provided by the user or predict them from the provided sequence. The latter approach is particularly useful for automated protein structure prediction servers. The blind test consisting of 95 CASP10 targets shows that domain boundaries could be successfully determined for 97% of targets.Availability and implementationThe AIDA package as well as the benchmark sets used here are available for download at http://ffas.burnham.org/AIDA/.Contactadam@sanfordburnham.orgSupplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC4481839 | biostudies-literature
Project description:To "put oneself in the place of other road users" may improve understanding of the global traffic situation. It should be useful enabling drivers to anticipate and detect obstacles in time to prevent accidents to other road users, especially those most vulnerable. We created a pioneering Hazard Perception and Prediction test to explore this skill in different road users (pedestrians, cyclists and drivers), with videos recorded in naturalistic scenarios: walking, riding a bicycle and driving a car. There were 79 participants (30 pedestrians, 14 cyclists, 13 novice drivers and 22 experienced drivers). Sixty videos of hazardous traffic situations were presented, divided into 2 blocks of 30 videos each: 10 walking, 10 riding a bicycle, 10 driving a car. In each situation presented, we evaluated the performance of the participants carrying out the task of predicting the hazard and estimating the risk. In the second block, after they had carried out the task, we gave them feedback on their performance and let them see the whole video (i.e., checking what happened next). The results showed that the holistic test had acceptable psychometric properties (Cronbach's alpha = .846). The test was able to discriminate between the different conditions manipulated: a) between traffic hazards recorded from different perspectives: walking, riding a bicycle and driving a car; b) between participants with different user profiles: pedestrians, cyclists and drivers; c) between the two test blocks: the first evaluation only and the second combining evaluation with this complex intervention. We found modal bias effects in both Hazard Perception and Prediction; and in Risk Estimation.
| S-EPMC7567349 | biostudies-literature