Network Stack Research Articles

A coupling model of multi-feature fusion and multi-machine learning model integration for defect recognition

As Oil and gas pipelines are vulnerable to physical defects such as dents, cracks and corrosion leading to the risk of pipeline leakage. In this context, the recognition of these pipeline defects by using magnetic flux leakage (MFL) signal can provide a reliable reference and a good evaluation standard for predicting the remaining life of in-service pipelines. Nevertheless, the complexity of the MFL signal brings severe challenges to the recognition accuracy. This study, therefore, proposes a new coupling model for defect recognition based on multi-feature fusion and multi-machine learning model integration. This model is divided into three analysis phase, namely feature extraction phase, feature fusion phase and defect recognition phase. In the first phase, three kinds of features are extracted to obtain as much defect MFL signal information as possible. In the second phase, a multi-feature fusion method based on Dempster-Shafer (DS) evidence theory and Apriori algorithm is proposed, eliminating redundant features and realizing information complementation between different feature sets. In the third phase, we introduce a multi-machine learning model integration network (Stacking) to improve the defect recognition accuracy, which is inputted by the feature subset obtained from multi-feature fusion. By combining multi-feature fusion method with the Stacking mechanism, this coupling defect recognition model realizes the recognition of defect MFL signals. Experimental work shows that the proposed model improves the recognition accuracy and has the advantages of strong anti-jamming ability.

Node Intrusion Tendency Recognition Using Network Level Features Based Deep Learning Approach

Adhoc network is highly susceptible for intrusion attacks due to the simplified accesscontrol and compacted network stack. Malicious node recognition in Mobile adhocnetwork (MANET) is challengeable due to nodes mobility and limited coverageof nodes. Thus, link may keep fluctuating throughout the communication period.In this paper, deep analytic model is made for extracting attacker node behaviorsfrom networking point of view. Attributed such as link durations, re-healing timeand number of received packets (by attacker) was the main features of this work.Later, deep learning paradigm is integrated to perform attacker node recognition. Dataobtained from network analytical model is used to train three different models namelyFeed forward neural network (FFNN), Cascade backpropagation neural network(CBPNN) and Convolutional neural network (CNN). Attacker node recognitionaccuracy of 85.5

Performance Evaluation of Co-Channel Interference on Wireless Networks

ABSTRACT Over the past few years, a large number of mobile devices are being used in real life with the advancement of wireless technology. The explosive increase in the number of wireless mobile devices makes it impossible to avoid the co-channel interference (CCI) or adjacent channel interference (ACI) phenomenon. Therefore, this interference phenomenon has been recognized as an important problem as it causes network performance degradation. In this paper, we conducted a CCI experiment in an outdoor environment where a Wi-Fi signal is not detected and in the ns-3 simulator, and compared the CCI phenomenon with the experiment results and simulation results. As we evaluated network performance between real network and simulation, we analyzed the performance impact at each network stack how packet errors propagate to upper layers in wireless ad-hoc network and propose a theoretical maximum throughput considering error rate in the data link layer and TCP layer.

A General Approach for Traffic Classification in Wireless Networks Using Deep Learning

Traffic Classification (TC) systems allow inferring the application that is generating the traffic being analyzed. State-of-the-art TC algorithms are based on Deep Learning (DL) and have outperformed traditional methods in complex and modern scenarios, even if traffic is encrypted. Most of the works on TC assume the traffic flows on a wired network under the same network management domain. This assumption limits the capabilities of TC systems in wireless networks since users’ traffic on one network domain can be negatively impacted by undetected users’ traffic from other network domains or detected ones but with no traffic context in a shared spectrum. To solve this problem, we introduce a novel framework to achieve TC at any layer on the radio network stack. We propose a spectrum-based procedure that uses a DL-based classifier to realize this framework. We design two DL-based classifiers, a novel Convolutional Neural Network (CNN) spectrum-based TC and a Recurrent Neural Networks (RNN) as baseline architecture, and benchmark their performance on three TC tasks at different radio stack layers. The datasets were generated by combining packet traces from real transmissions with an 802.11 standard-compliant waveform generator. Performance evaluations show that the best model can achieve an accuracy above 92% in the most demanding TC task, a drop of only 4.37% in accuracy compared to a byte-based DL approach, with micro-second per-packet prediction time, which is very promising for delivering real-time spectrum-based traffic analyzers.

A novel feature integration and entity boundary detection for named entity recognition in cybersecurity

Owing to continuous cyberattacks, a large amount of threat intelligence is generated online every day. However, threat intelligence is mostly unstructured and multisource heterogeneous text. It is difficult for security analysts to understand the implicit threat in time. Knowledge Graph (KG) is an important research topic in recent years, which can perform automated and real-time analysis of threat intelligence in cybersecurity. As one of the critical technologies of KG, named entity recognition (NER) can identify cyberattack-related entities. It has been proved that long-distance structured information captured by dependency trees provides a rich semantic expression for the neural network. However, existing research works are more focused on the simple linear stack of neural networks when utilizing structured features. The interaction between different types of neural networks is vague. In addition, the existing models are insensitive to the boundaries of complex entity terms in cybersecurity. In this study, we propose a new feature integration and entity boundary detection (FIEBD) model. In our model, a new pretrained language model, PERT, is applied to obtain word embedding of cyber texts. Moreover, a novel neural network cell, namely GARU, is developed to incorporate different types of features extracted from graph neural networks and recurrent neural networks. It combines the graph encoder with the gate mechanism, aiming to obtain better hidden representation by explicit interaction. Furthermore, considering a large number of complex entities in cybersecurity, we contribute an entity boundary detection module to perform entity head and tail prediction as an augmentation task. We conduct extensive experiments on cybersecurity datasets. The results demonstrate that the proposed model achieves better performance than existing baseline methods.

Just-in-time updating soft sensor model of endpoint carbon content and temperature in BOF steelmaking based on deep residual supervised autoencoder

The key of Basic oxygen furnace (BOF) endpoint control is to achieve accurate forecast of the endpoint carbon content and temperature. Due to the highly nonlinear and complex distribution characteristics of process data, the predictions of these two indicators are inaccurate. Although deep learning can extract abstract features of complex data, existing methods are pre-trained in an unsupervised manner. For soft sensor applications, the key is to highlight important information and extract features related to the target variables for prediction. Thus, this paper proposes a feature extraction model based on deep residual supervised autoencoder (DRSupAE). By incorporating important information in the feature of previous hidden layers into deeper feature learning in the form of residual connection, and each residual supervised autoencoder (RSupAE) utilizes the target variables to guide feature extraction. In this way, the stacking of new deep networks not only enhances the impact of important target-related information in layer-wise training, but also captures features related to target variables. Moreover, for the time-varying phenomenon of the BOF steelmaking process, a strategy of just-in-time updating regression network (JITRN) is proposed, which is used to solve the problem that the static regression model cannot adapt to the frequent changes of sample characteristics and causes the prediction performance to decline. An experimental study on BOF steelmaking process data is provided to demonstrate the effectiveness of the proposed method.

TEGRAS: An Efficient Tegra Embedded GPU-Based RSA Acceleration Server

Industrial Internet of Things (IIoT) has strict requirements on the performance and security of devices. Public-key cryptography, as a kind of computing resource-consuming algorithm, is widely used in the digital signature, key exchange, and so on. The embedded graphics processing units (GPUs) are now rapidly achieving extraordinary computing power, such as NVIDIA Tegra K1/X1/X2/Xavier, which are also treated as edge computing devices. They are widely used in IIoT environments, such as intelligent manufacturing, smart cities, and vehicle-mounted systems. The performance advantages endow embedded GPUs with the possibility of accelerating cryptography that also requires high-density computing. This article implements an efficient Tegra-based embedded GPU RSA acceleration server-oriented IIoT, named TEGRAS. Various optimization methods are employed to promote efficiency, including multithreaded Montgomery multiplication and Chinese Remainder Theorem implementation on the resource-constricted embedded GPUs. With about 40–50 W of power consumption, TEGRAS can deliver 34 kops/s of RSA2048 signature generation and 1007 kops/s of RSA signature verification, which outperforms implementations in the desktop GPUs and embedded CPUs in the perspective of performance-to-power ratio. To evaluate TEGRAS in real-world scenarios, we additionally build a network stack to deliver digital signature services, which can provide more than 34 and 978 kops of signature generation and signature verification, respectively. In a word, based on the embedded GPU, we provide a high-throughput, low-latency, and ready-to-use RSA accelerator-oriented IIoT.

Construction of a Prediction Model for Distance Education Quality Assessment Based on Convolutional Neural Network.

This paper introduces the principles and operation steps of convolution and pooling of convolutional neural networks in detail. In view of the shortcomings of fixed sampling points and single receptive field in traditional convolution and pooling forms, deformable convolution and deformable pooling are introduced to enhance the network's ability to adapt to image details and large displacement problems. The concepts of warp, loop optimization, and network stack are introduced. In order to improve the optimization performance of the algorithm, three subnetwork structures and stack models are designed, and various methods are used to improve the prediction accuracy of distance education quality assessment. In order to improve the accuracy and timeliness of education quality assessment, this paper proposes a distance education quality assessment model based on mining algorithms. The prediction index is selected by the improved BP neural network. It is required to establish the input layer node as the input vector based on the number of data sources since the input layer is used for data input. The neural network is trained with a quarter of the mining data, and the mining algorithm is further trained with network error trials. A fuzzy relationship matrix is created based on the assessment of teaching quality's hierarchical structure. This leads to the conclusion of the fuzzy thorough evaluation of the effectiveness of distant learning. Experiments show that the proposed model has an average accuracy of 96%, the average teaching quality modeling time is 25.44 ms, and the evaluation speed is fast.

What happens next? Combining enhanced multilevel script learning and dual fusion strategies for script event prediction

Script event prediction (SEP), aiming at predicting next event from context event sequences (i.e., scripts), has played an important role in many real-world applications such as government decision-making. While most of the existing research only depend on the top-level event prediction, they ignore the influence of other bottom levels or other relationship modeling manners. In this paper, we focus on the problem of SEP via multilevel script learning where the goal of is to explore a multistage, multiprediction and multilevel information fusion model for SEP. This is challenging in (1) simultaneously modeling of the multilevel event relationship semantic information and (2) effectively designing multilevel information fusion strategies. In this paper, we propose a new script event prediction model based on Enhanced Multilevel script learning and Dual Fusion strategies, named EMDF-Net. Specifically, EMDF-Net designs the multilevel (event/chain/segment level) script learning to model both temporal and casual information as well as the rich structural relevance via neural stacking of self-attention mechanism and graph neural networks. Then it proposes dual fusion strategies to fully integrate different-level information by nonlinear feature composition and weighted score fusion. Finally, a deep supervision strategy is utilized to end-to-end train the whole model and provide a good initialization for information fusion. Experimental results on the popular NYT corpus demonstrate the effectiveness and superiority of EMDF-Net.

Learning-Based Resource Management for Low-Power and Lossy IoT Networks

Internet of Things (IoT) networks are key to the realization of modern industries and societies. A key application of IoT is in smart-grid communications. Smart-grid networks are resource constrained in terms of computing power and energy capacity. Similarly, the wireless links between devices are typically associated with high packet-loss rates, low throughput, and instability. To provide a sustainable communication mechanism, an IoT network stack is proposed for these devices. However, each network stack layer has its own constraints. For example, to facilitate the operation of these low-power and lossy network (LLN) devices, the international engineering task force (IETF) standardized a network-layer protocol called a routing protocol for low-power and lossy networks (RPLs). RPL often creates an inefficient network in densely deployed and varying traffic load conditions. Future dense IoT-based networks are expected to automatically optimize the reliability and efficiency of communication by inferring the diverse features of both the environments and actions of the devices. Machine learning (ML) provides a promising framework for such a dense network environment. In this study, we examine the underlying perspective of ML for such systems. We utilize the multiarmed bandit (MAB)-based expected energy count (BEEX) technique, which provides nodes the ability to effectively optimize their operation. Using the proposed mechanism, nodes can intelligently adapt their network-layer behavior. The performance of the proposed (BEEX) algorithm is evaluated through a Contiki 3.0 Cooja simulation. The proposed method improves the energy consumption and packet delivery ratio and produces a lower control overhead than other state-of-the-art mechanisms.

SASE and the future of IoT security

Secure Access Service Edge (SASE) is starting to become mainstream. And this approach promises unified policies that improve agility, fortify security and simplify the network stack – especially when it comes to the Internet of Things (IoT).

Restoring Application Traffic of Latency-Sensitive Networked Systems Using Adversarial Autoencoders

The Internet of Things (IoT), coupled with the edge computing paradigm, is enabling several pervasive networked applications with stringent real-time requirements, such as telemedicine and haptic telecommunications. Recent advances in network virtualization and artificial intelligence are helping solve network latency and capacity problems, learning from several states of the network stack. However, despite such advances, a network architecture able to meet the demands of next-generation networked applications with stringent real-time requirements still has untackled challenges. In this paper, we argue that only using network (or transport) layer information to predict traffic evolution and other network states may be insufficient, and a more holistic approach that considers predictions of application-layer states is needed to repair the inefficiencies of the TCP/IP architecture. Based on this intuition, we present the design and implementation of Reparo. At its core, the design of our solution is based on the detection of a packet loss and its restoration using a Hidden Markov Model (HMM) empowered with adversarial autoencoders. In our evaluation, we considered a telemedicine use case, specifically a telepathology session, in which a microscope is controlled remotely in real-time to assess histological imagery. Our results confirm that the use of adversarial autoencoders enhances the accuracy of the prediction method satisfying our telemedicine application’s requirements with a notable improvement in terms of throughput and latency perceived by the user.

Имитационная модель беспроводной ad-hoc сети для исследования алгоритмов маршрутизации трафика

Communication network simulators are software designed to model, explore, test and debug network technologies, including wireless decentralized self-organizing networks or ad-hoc networks. They greatly simplify the research, development and optimization of routing protocols in these networks. However, the well-known simulators have a number of disadvantages, including the difficulty of adding custom extensions to ad-hoc network routing protocols, the lack of the necessary network stack, the lack of routing algorithm visualization modes, low performance, and difficulty in debugging communication protocols. The purpose of this work is to create a simulation model of a wireless network that would allow us to explore, debug and evaluate the developed algorithms and routing protocols for ad-hoc networks. At the same time, the requirements for interface ergonomics and the ability to visualize the operation of algorithms, ensure the collection of statistics, and create various scenarios for the operation of the network come to the fore. The article proposes the structure of the simulation model, which includes the modules of the network subscriber, application software, network layer of the OSI data transmission model, radio module, radio transmission environment, statistics collection, visualization and scenario management. To solve the tasks set, the approach of discrete-event modeling was used. To create a simulator of wireless decentralized networks and routing algorithms, a set of classes was developed that implement the modules of the simulation model. Based on the proposed structure, module classes and discrete event simulation algorithm, a software implementation of the simulation model was created using the C++ programming language and the Qt framework. The developed simulation model was used in the course of an experimental study of the effectiveness of the network routing algorithm. The proposed software will simplify the development and debugging of algorithms and routing protocols for ad-hoc networks.

DBMS annihilator

Modern DBMS engines can achieve unprecedented transaction processing speeds thanks to the invention of clever data structures, concurrency schemes, and improvements in CPU and memory subsystems. However, developing realistic and efficient networked clients to benchmark these systems remains daunting. Simply put, traditional client-side networking stacks present high overheads and thus cannot exercise the high performance that modern DBMSs can, in principle, provide. In this demo, we propose a different approach to benchmarking; we showcase a new framework that leverages hardware-software co-design. With our system, which we call the DBMS Annihilator, workloads are specified using a high-level language that is then converted into hardware (FPGA) for execution. The hardware we use is a commodity Smart NIC, allowing workloads to be fully reproducible to anyone using such hardware. A software console and dashboard provide real-time visibility and interactivity, which we explore in this demo.

NIR Photodetectors with Highly Efficient Detectivity Enabled by 2D Fluorinated Dithienopicenocarbazole‐Based Ultra‐Narrow Bandgap Acceptors

AbstractDeveloping non‐fullerene acceptors (NFAs) with strong absorption and optical response in near‐infrared region (NIR) is an imperative avenue for achieving efficient organic solar cells (OSCs) and NIR organic photodetectors (OPDs). Herein, four ultra‐narrow bandgap NFAs with different alkyl side chains and 2D fluorinated or non‐fluorinated phenyl substituents using dithienopyrrolecarbazole as electron‐rich core are designed and synthesized for photoelectric devices. The effect of 2D central core fluorination on molecular self‐assembly and optoelectronic properties is comprehensively explored. Due to the banana‐type molecular conformation of these NFAs, they can easily form honeycomb‐like 3D network stacking, and the central core fluorination is confirmed that can reduce ππ stacking distance and enhance intermolecular interaction, which result in smaller molecular stacking density. As a result, the 2D fluorinated acceptors based OSCs display more balanced and higher carrier mobilities, contributing to higher fill factor and efficiency. Moreover, the NIR OPD devices based on PTB7‐Th:FDTPC‐OD exhibit a superior responsivity of >0.4 A W−1 at 880 nm, a low dark current of ≈8 × 10–11 A, and an excellent specific detectivity (D*) of >2.5 × 1011 Jones. The NIR OPD also demonstrates excellent performance in photo‐plethysmography and shows great potential for application in monitoring heart rate.

Automated segmentation of head CT scans for computer-assisted craniomaxillofacial surgery applying a hierarchical patch-based stack of convolutional neural networks

PurposeComputer-assisted techniques play an important role in craniomaxillofacial surgery. As segmentation of three-dimensional medical imaging represents a cornerstone for these procedures, the present study was aiming at investigating a deep learning approach for automated segmentation of head CT scans.MethodsThe deep learning approach of this study was based on the patchwork toolbox, using a multiscale stack of 3D convolutional neural networks. The images were split into nested patches using a fixed 3D matrix size with decreasing physical size in a pyramid format of four scale depths. Manual segmentation of 18 craniomaxillofacial structures was performed in 20 CT scans, of which 15 were used for the training of the deep learning network and five were used for validation of the results of automated segmentation. Segmentation accuracy was evaluated by Dice similarity coefficient (DSC), surface DSC, 95% Hausdorff distance (95HD) and average symmetric surface distance (ASSD).ResultsMean for DSC was 0.81 ± 0.13 (range: 0.61 [mental foramen] – 0.98 [mandible]). Mean Surface DSC was 0.94 ± 0.06 (range: 0.87 [mental foramen] – 0.99 [mandible]), with values > 0.9 for all structures but the mental foramen. Mean 95HD was 1.93 ± 2.05 mm (range: 1.00 [mandible] – 4.12 mm [maxillary sinus]) and for ASSD, a mean of 0.42 ± 0.44 mm (range: 0.09 [mandible] – 1.19 mm [mental foramen]) was found, with values < 1 mm for all structures but the mental foramen.ConclusionIn this study, high accuracy of automated segmentation of a variety of craniomaxillofacial structures could be demonstrated, suggesting this approach to be suitable for the incorporation into a computer-assisted craniomaxillofacial surgery workflow. The small amount of training data required and the flexibility of an open source-based network architecture enable a broad variety of clinical and research applications.

NetKernel: Making Network Stack Part of the Virtualized Infrastructure

This paper presents a system called NetKernel that decouples the network stack from the guest virtual machine and offers it as an independent module. NetKernel represents a new paradigm where network stack can be managed as part of the virtualized infrastructure. It provides important efficiency benefits: By gaining control and visibility of the network stack, operators can perform network management more directly and flexibly, such as multiplexing VMs running different applications to the same network stack module to save CPU cores, and enforcing fair bandwidth sharing. Users also benefit from the simplified stack deployment and better performance: For example mTCP can be deployed without API change to support nginx natively, and shared memory networking can be readily enabled to improve performance of colocated VMs. Testbed evaluation using 100G NICs shows that NetKernel preserves the performance and scalability of both kernel and userspace network stacks, and provides the same isolation as the current architecture.

Predicting Pedestrian Crossing Intention With Feature Fusion and Spatio-Temporal Attention

Predicting vulnerableroad user behavior is an essential prerequisite for deploying Automated Driving Systems (ADS) in the real-world. Pedestrian crossing intention should be recognized in real-time, especially for urban driving. Recent works have shown the potential of using vision-based deep neural network models for this task. However, these models are not robust and certain issues still need to be resolved. First, the global spatio-temporal context that accounts for the interaction between the target pedestrian and the scene has not been properly utilized. Second, the optimal strategy for fusing different sensor data has not been thoroughly investigated. This work addresses the above limitations by introducing a novel neural network architecture to fuse inherently different spatio-temporal features for pedestrian crossing intention prediction. We fuse different phenomena such as sequences of RGB imagery, semantic segmentation masks, and ego-vehicle speed in an optimal way using attention mechanisms and a stack of recurrent neural networks. The optimal architecture was obtained through exhaustive ablation and comparison studies. Extensive comparative experiments on the JAAD and PIE pedestrian action prediction benchmarks demonstrate the effectiveness of the proposed method, where state-of-the-art performance was achieved. Our code is open-source and publicly available: <uri>https://github.com/OSU-Haolin/Pedestrian_Crossing_Intention_Prediction</uri>.

A Hybrid NDN-IP Architecture for Live Video Streaming: From Host-Based to Content-Based Delivery to Improve QoE

With live video streaming becoming accessible in various applications on all client platforms, it is imperative to create a seamless and efficient distribution system that is flexible enough to choose from multiple Internet architectures best suited for video streaming (live, on-demand, AR). In this paper, we highlight the benefits of such a hybrid system for live video streaming as well as present a detailed analysis with the goal to provide a high quality of experience (QoE) for the viewer. For our hybrid architecture, video streaming is supported simultaneously over TCP/IP and Named Data Networking (NDN)-based architecture via operating system and networking virtualization techniques to design a flexible system that utilizes the benefits of these varying Internet architectures. Also, to relieve users from the burden of installing a new protocol stack (in the case of NDN) on their devices, we developed a lightweight solution in the form of a container that includes the network stack as well as the streaming application. At the client, the required Internet architecture (TCP/IP versus NDN) can be selected in a transparent and adaptive manner. Based on a prototype, we have designed and implemented maintaining efficient use of network resources, we demonstrate that in the case of live streaming, NDN achieves better QoE per client than IP and can also utilize higher than allocated bandwidth through in-network caching. Even without caching, as opposed to IP-only, our hybrid setup achieves better average bitrate and better perceived visual quality (computed via VMAF metric) over live video streaming services. Furthermore, we present detailed analysis on ways adaptive video streaming with NDN can be further improved with respect to QoE.

Stack Operation of Tensor Networks

The tensor network, as a factorization of tensors, aims at performing the operations that are common for normal tensors, such as addition, contraction, and stacking. However, because of its non-unique network structure, only the tensor network contraction is so far well defined. In this study, we propose a mathematically rigorous definition for the tensor network stack approach that compresses a large number of tensor networks into a single one without changing their structures and configurations. We illustrate the main ideas with the matrix product states based on machine learning as an example. Our results are compared with the for-loop and the efficient coding method on both CPU and GPU.