Heterogeneous Network Data Research Articles

ABBR: An augmented BBR for collaborative intelligent transmission over heterogeneous networks in IIoT

In the era of Industry 5.0, with the deep convergence of Industrial Internet of Things (IIoT) and 5G technology, stable transmission of massive data in heterogeneous networks becomes crucial. This is not only the key to improving the efficiency of human–machine collaboration, but also the basis for ensuring system continuity and reliability. The arrival of 5G has brought new challenges to the communication of IIoT in heterogeneous environments. Due to the inherent characteristics of wireless networks, such as random packet loss and network jitter, traditional transmission control schemes often fail to achieve optimal performance. In this paper we propose a novel transmission control algorithm, aBBR. It is an augmented algorithm based on BBRv3. aBBR dynamically adjusts the sending window size through real-time analysis to enhance the transmission performance in heterogeneous networks. Simulation results show that, compared to traditional algorithms, aBBR demonstrates the best comprehensive performance in terms of throughput, latency, and retransmission. When random packet loss exists in the link, aBBR improves the throughput by an average of 29.3% and decreases the retransmission rate by 18.5% while keeping the transmission delay at the same level as BBRv3.

Research on the Ddissemination Mechanism of Excellent Traditional Culture in New Media Environment based on Petri Network

To act inside and out study and investigation on the cooperation and correspondence of traditional culture, this article utilizes the Web combination advanced media strategy. The prerequisites for the Web might be communicated and depicted utilizing this primary data. The quantity of items in the network and its intricacy are developing alongside the interest for Web applications, so we can configuration proper bunching calculations to get more precise network structure data by using different kinds of semantic data in the heterogeneous data network. As a result of China s 5000-year history, the country has a variety of wonderful traditional cultures. We must thus improve the transmission of traditional culture and its legacy. Chinese traditional poetry is one of them and represents Chinese traditional culture, which has to be passed down to future generations. Our research focuses on the issues of packet loss, communication delays, and quantization errors in network-controlled systems (NCS). Regardless of the way that NCS offers a worldview for changing in accordance with the successive changes in the assembling area, displaying and overseeing tasks are testing issues due to the confounded cooperation s between framework substances and the effect of the network-prompted defer on the shut circle framework.

A heterogeneous network structure publishing security framework based on cloud-edge collaboration

With the integration of different fields, a large amount of heterogeneous data converges into a heterogeneous network with different types of nodes and edges. Then it is published by the cloud platform for applications such as recommendation services and public opinion analysis. However, in traditional cloud platform data publishing, one is privacy leakage due to the long transmission delay to the cloud platform, and the other is privacy leakage due to privacy attacks during cloud platform data publishing. In addition, there is an imbalance between privacy and availability in the privacy protection of the network structure between heterogeneous nodes. To address these issues, we propose a heterogeneous network structure publishing security framework based on cloud-edge collaboration. In this framework, we design a non-interactive edge privacy protection center and provide a heterogeneous network data publishing privacy protection model (HNPP). First, the network between heterogeneous nodes is transformed into an equivalent homogeneous network based on trivial closure. Then, we use differential privacy and random perturbations to achieve the homogeneous network structure reconstruction. Finally, we only rely on generation rules and reconstructed equivalent homogeneous networks to generate the heterogeneous network structure. We conducted extensive experimental analysis on real datasets, and the results show that the original edge retention rate of the network after privacy protection is above 0.88, and the clustering precision is above 0.92. It shows that the HNPP model is able to balance the privacy and availability of heterogeneous network structure publishing.

Data + pilot biases in modern GNSS signals

While traditional GNSS signals are always modulated with navigation data, various modern signals provide a distinct pilot channel without data modulation to support long coherent integration times. Intra-signal biases between the data and pilot components of such signals are evaluated for satellites of the GPS, Galileo, BeiDou-3, and QZSS constellations using measurements from a dedicated set of receivers. Peak values of about 2 ns are obtained for the GPS L5 signal, while slightly smaller values of up to 1 ns apply for the B1C and B2a signals of BeiDou-3 as well as the QZSS L1C signal. For Galileo E1 and E5a/b, data + pilot biases are confined to less than 0.1–0.3 ns, which is typically less than other pseudorange errors for these signals. Fully negligible values of < 0.05 ns are obtained for the L1C and L2C signals of GPS as well as the L2C signal of QZSS in accord with expectations for time-multiplexed or interlaced modulations. To support consistent processing of multi-GNSS data in heterogeneous networks, biases between combined data + pilot tracking and pilot-only tracking are derived in a dedicated zero-baseline receiver test bed. The analysis confirms the general understanding that biases between combined and pilot-only pseudoranges amount to a fixed fraction of the corresponding data + pilot biases. This fraction depends on the power sharing of the data and pilot component in the respective signals and amounts to 50% in most cases. The results of this study are expected to remove the prevailing problem of two distinct receiver groups in the generation of satellite clock and bias products by the International GNSS Service and to enable a rigorous and consistent use of these products by multi-GNSS users.

DETECTION OF SPAM REVIEWS IN WEBSITES USING NET SPAM ALGORITHM

Now-a-days, people in general choose to purchase an online item depending on the reviews and feedback given in social media. The probability of leaving a scrutiny gives a glorious chance for person who writing a spam reviews regarding the product for individual reasons. Categorizing these kinds of spammers and the spam content create an interesting issue of analysis. Though a generous range of studies are done recently towards this, till date the methodologies used still hardly find the spam reviews. Here, propose an exclusive framework called Net-Spam that exploit spam options for creating review datasets as heterogeneous data networks to map spam detection procedure into further classifications. Maltreatment of spam options helps us to get the best output pertaining to various metrics experimented on realtime review datasets from Amazon and Yelp websites. The results show that Net-Spam outperforms the current ways from among the three classes of features namely detection of review, detection of user and detection of Spam Groupers.

Special invited paper: The SCORE normalization, especially for heterogeneous network and text data

SCORE was introduced as a spectral approach to network community detection. Since many networks have severe degree heterogeneity, the ordinary spectral clustering (OSC) approach to community detection may perform unsatisfactorily. SCORE alleviates the effect of degree heterogeneity by introducing a new normalization idea in the spectral domain and makes OSC more effective. SCORE is easy to use and computationally fast. It adapts easily to new directions and sees an increasing interest in practice. In this paper, we review the basics of SCORE, the adaption of SCORE to network mixed membership estimation and topic modeling, and the application of SCORE in real data, including two datasets on the publications of statisticians. We also review the theoretical “ideology” underlying SCORE. We show that in the spectral domain, SCORE converts a simplicial cone to a simplex and provides a simple and direct link between the simplex and network memberships. SCORE attains an exponential rate and a sharp phase transition in community detection, and achieves optimal rates in mixed membership estimation and topic modeling.

Multi-Modal Noise-Robust DDoS Attack Detection Architecture in Large-Scale Networks Based on Tensor SVD

Distributed Denial of Service (DDoS) attacks consumes the resources of traditional or cloud computing networks, resulting in the network unable to provide normal services. Therefore, accurate detection of DDoS attacks can avoid greater losses and provide an important guarantee for network space security. But with the rapid development of the Internet, the network scale is becoming larger and larger, and the structure is becoming more and more complex. Network data shows large-scale heterogeneous characteristics, which lead to data processing becomes more difficult and the traditional algorithms cannot accurately identify attack traffic. Therefore, how to accurately and efficiently detect DDoS attacks in large-scale networks has become a new challenge. To deal this problem, this paper proposes a novel DDoS attack detection framework. Which has mainly made three contributions: (i) Representation of large-scale heterogeneous network data by tensor; (ii) A multi-modal denoising algorithm based on tensor SVD is proposed; (iii) An efficient anomaly detection architecture suitable for large-scale networks is proposed, which combines (i), (ii) and XGBoost classification model. Experiments show that the framework can achieve a high detection rate of 98.84%, and has the characteristics of well extendable, strong noise-robust and fast detection speed.

Drug-target interaction prediction using high order nonlinear features via neural factorization machines

Medication design and repositioning are sped up by the prediction of drug-target interactions (DTIs). Two main kinds of prediction methods are commonly used, which are based on chemical structure feature extraction and deep learning methods. However, on the one hand, the DTI prediction approaches based on chemical structural feature extraction may not wholly explore the possible network characteristics in the data. On the other hand, many deep learning methods call for numerous layers of neural networks to be layered to learn higher-order feature interaction information. To sum up, the existing computation methods often have the limitations of gradient disappearance and overfitting. This study presents a novel method (JRD-NFM) by calculating Jaccard similarities, getting an eigenvector through Restarted random walk (RWR), and generating low-dimensional feature vectors by Disposition Component Analysis (DCA). Besides decoding the topological features and similarity information of target and drug node, it can also get the context information of a single network. Considering the advantages of Neural Factorization Machines (NFM) in extracting high-order nonlinear features and processing sparse data, this study use NFM to classifier the collection data to integrate drug and target biochemical structure information. The experimental results demonstrate that JRD-NFM can outperform widely used deep learning methods and conventional chemical structure approaches. It could provide fresh ideas for combining molecular structure and heterogeneous network data to predict DTIs.

Classification Algorithm for Heterogeneous Network Data Streams Based on Big Data Active Learning

Data classification is one of the main tasks in the current data mining field, and the existing network data triage algorithms have problems such as too small a proportion of labeled samples, a large amount of noise, and redundant data, which lead to low classification accuracy of data stream implementation. Network embedding can effectively improve these problems, but the network embedding itself has problems such as capturing relational honor and ambiguity. This study proposes a SNN-RODE based LapRLS heterogeneous network data classification algorithm to achieve deep embedding of structure and semantics among nodes by constructing a multitask SNN and selecting dead song datasets to perform mining tasks to train the neural network. Then a semisupervised learning classifier based on Laplace regular least squares regression model is designed to use the relative support difference function as the decision method and optimize the function. The simulation experimental results show that the SNN-RODE-LapRLS algorithm improves the performance by 14%-51% over the mainstream classification algorithms, and the consumption time meets the demand of real-time classification.

Cyber Threat Intelligence Sharing Scheme Based on Federated Learning for Network Intrusion Detection

The uses of machine learning (ML) technologies in the detection of network attacks have been proven to be effective when designed and evaluated using data samples originating from the same organisational network. However, it has been very challenging to design an ML-based detection system using heterogeneous network data samples originating from different sources and organisations. This is mainly due to privacy concerns and the lack of a universal format of datasets. In this paper, we propose a collaborative cyber threat intelligence sharing scheme to allow multiple organisations to join forces in the design, training, and evaluation of a robust ML-based network intrusion detection system. The threat intelligence sharing scheme utilises two critical aspects for its application; the availability of network data traffic in a common format to allow for the extraction of meaningful patterns across data sources and the adoption of a federated learning mechanism to avoid the necessity of sharing sensitive users’ information between organisations. As a result, each organisation benefits from the intelligence of other organisations while maintaining the privacy of its data internally. In this paper, the framework has been designed and evaluated using two key datasets in a NetFlow format known as NF-UNSW-NB15-v2 and NF-BoT-IoT-v2. In addition, two other common scenarios are considered in the evaluation process; a centralised training method where local data samples are directly shared with other organisations and a localised training method where no threat intelligence is shared. The results demonstrate the efficiency and effectiveness of the proposed framework by designing a universal ML model effectively classifying various benign and intrusive traffic types originating from multiple organisations without the need for inter-organisational data exchange.

Multisource Target Data Fusion Tracking Method for Heterogeneous Network Based on Data Mining

This research is on heterogeneous network fusion method of multisource target data based on data mining. Firstly, it is a distributed storage structure model for building heterogeneous network multisource target data. Then, using the phase space reconstruction method, a grid distribution structure model for data fusion tracking is constructed, and realize visual scheduling and automatic monitoring of multisource target data. Finally, according to the feature extraction results, analyze the statistical characteristics of multisource target data in heterogeneous networks, combined with the fuzzy tomographic analysis method, multilevel fusion, and adaptive mining of multisource target data, extract the associated feature quantities in it, and realize the fusion tracking of data. The simulation results show that, in relatively simple heterogeneous networks, the feature mining error of the proposed method is nearly 2.11% lower than the two traditional methods. In relatively complex heterogeneous networks, the feature mining error of the proposed method is nearly 6.48% lower than the two traditional methods. It can be seen that this method has better adaptability for fusion tracking of heterogeneous network multisource target data, the anti-interference ability is strong, and the tracking accuracy in the data fusion tracking process is also improved.

Digital-Media-Based Interaction and Dissemination of Traditional Culture Integrating Using Social Media Data Analytics.

This paper adopts the approach of the Internet fusion digital media to conduct in-depth research and analysis on the interaction and communication of traditional culture. This structural information can be used to express and describe the Internet requirements. With the increasing demand for the Internet applications, the number of objects in the network and the complexity of the structure are also growing, so we can design suitable clustering algorithms to obtain more reasonable network structure information by using different semantic information in the heterogeneous information network. Firstly, the caching scheme is transformed into a backpack problem, and the storage scheme is obtained recursively by using dynamic programming, after which the computational task is optimized based on this storage scheme by using the whale algorithm to make it the least costly. The exact balance between the connotation essence of traditional culture and the emotional resonance in modern life has not yet been found, and the visual language belonging to cultural aesthetics under the combination of traditional and modern aesthetics needs to be explored for a long time. From an objective point of view, the digital art communication of cultural elements still suffers from five problems: lack of communication cultivation and stratification of target audiences, low quality of transcription of digital artworks, unbalanced economic and cultural values, uneven development of digital art communication forms, and low degree of Internet adaptation. A ranking algorithm based on fusing multiple meta-paths is proposed to better reflect the ranking values of different object distributions of the Internet data in heterogeneous information networks, which can obtain better clustering, while better clustering can be calculated to obtain more reasonable rankings, and finally, the types of the Internet-oriented applications are divided into multiple reasonable clusters. The effects of selecting different meta-paths on the clustering algorithm and the effects of fused meta-paths versus single meta-paths on the clustering results are given in the experimental results section. Also compared with other clustering algorithms, the I-RankClus algorithm can better achieve the data clustering classification for the Internet application scenarios.

A Study on Information Classification and Storage in Cloud Computing Data Centers Based on Group Collaborative Intelligent Clustering

Internet of things (IoT) and cloud computing are combined to form a cloud computing data center, and cloud computing provides virtualization, storage, computing, and other support services for IoT applications. Data is the foundation and core of cloud IoT platform applications, and massive multisource heterogeneous IoT data aggregation and storage have basic requirements such as real-time, security, and scalability. This paper focuses on the aggregation and storage methods of massive heterogeneous cloud IoT data, solving the multisource data aggregation problem caused by inconsistent protocols and the heterogeneous data storage problem caused by inconsistent data types. A heterogeneous network protocol adaptation and data aggregation method is proposed for the multisource data aggregation problem caused by protocol inconsistency. A protocol adaptation layer is set up in the IoT virtual gateway to achieve compatibility with multiple types of data aggregation protocols, ensuring adaptive access to different types of IoT nodes, and on this basis, data is transmitted to the cloud IoT platform through a unified interface, shielding the variability of IoT sensing devices. Given the problems of device forgery and malicious tampering in the data aggregation process, we propose a fast authentication and data storage method for IoT devices based on “API key” and implant the device authentication API key into the protocol adaptation layer of the virtual gateway to realize the source authentication of IoT nodes and ensure the authenticity of data.

A Federated Deep Learning Empowered Resource Management Method to Optimize 5G and 6G Quality of Services (QoS)

The quality of service (QoS) in 5G/6G communication enormously depends upon the mobility and agility of the network architecture. An increase in the possible uses of 5G vehicular network simultaneously expands the scope of the network’s quality of service (QoS). To this end, a safety-critical real-time system has become one of the most demanding criteria for the vehicular network. Although different mathematical and computation methods have traditionally been used to optimize the allocation of resources, but the nonconvexity of optimization issues creates unique type of challenges. In recent years, machine learning (ML) has emerged as a valuable tool for dealing with computational complexity that involves large amounts of data in heterogeneous vehicular networks. By using optimization and cutting-edge machine learning techniques, this article gives readers an insight about how 5G vehicular network resources can be allocated to reinforce network communication. Furthermore, a new federated deep reinforcement learning- (FDRL-) based vehicle communication method is presented as a new insight. Finally, a UAV-aided vehicular communication system based on FDRL-based UAVs is proposed as a novel resource management technique to optimize 5G and 6G quality of services.

A Novel Robust-DEA Approach for Efficiency Measurement of Heterogeneous Hybrid Networks under Uncertainty

Over the past two decades, the use of network data envelopment analysis in real-world issues has attracted the attention of many researchers. This analysis is used when the output results of a decision unit are used as input to later units. Uncertainty in the inputs and outputs of each decision unit complicates the performance evaluation of such systems. In this paper, a new model of heterogeneous hybrid network data envelopment analysis is developed to measure the efficiency of decision units assuming the open structure of each decision unit, as well as the existence of interlayer relationships. In this model, constraints are defined in such a way that the number of units on the efficient boundary is limited. As a result, there is no need to use super-efficient models to determine overall performance. A robust approach has been used to deal with uncertainties in inputs, outputs and, interlayers. The application of the proposed model was studied to evaluate the performance of pistachio orchards in Yazd province, Iran, and the results were compared with traditional models. With the implementation of the proposed model, no unit was placed on the efficient boundary and there is no need for super-efficient models. The results were approved by agricultural experts.

Special Issue on Decision Making in Heterogeneous Network Data Scenarios and Applications

Special Issue on Decision Making in Heterogeneous Network Data Scenarios and Applications

Federated Matrix Factorization: Algorithm Design and Application to Data Clustering

Recent demands on data privacy have called for federated learning (FL) as a new distributed learning paradigm in massive and heterogeneous networks. Although many FL algorithms have been proposed, few of them have considered the matrix factorization (MF) model, which is known to have a vast number of signal processing and machine learning applications. Since the MF problem involves two blocks of variables and the variables are usually subject to constraints related to specific solution structure, it requires new FL algorithm designs to achieve communication-efficient MF in heterogeneous data networks. In this paper, we address the challenge by proposing two new federated MF (FedMF) algorithms, namely, FedMAvg and FedMGS, based on the model averaging and gradient sharing principles, respectively. Both FedMAvg and FedMGS adopt multiple steps of local updates per communication round to speed up convergence, and allow only a randomly sampled subset of clients to communicate with the server for reducing the communication cost. Convergence properties for the two algorithms are thoroughly analyzed, which delineate the impacts of heterogeneous data distribution, local update number, and partial client communication on the algorithm performance, and guide the design of proposed algorithms. By focusing on a data clustering task, extensive experiment results are presented to examine the practical performance of proposed algorithms, as well as demonstrating their efficacy over the existing distributed clustering algorithms.

Data transmitted encryption for clustering protocol in heterogeneous wireless sensor networks

In this paper, elliptic curves Diffie Hellman-Rivest Shamir Adleman algorithm (ECDH-RSA) is a novel encryption method was proposed, which based on ECDH and RSA algorithm to secure transmitted data in heterogeneous wireless sensor networks (HWSNs). The proposed encryption is built under cheesboard clustering routing method (CCRM). The CCRM used to regulate energy consumption of the nodes. To achieve good scalability and performance by using limited powerful max-end sensors besides a large powerful of min-end sensors. ECDH is used for the sharing of public and private keys because of its ability to provide small key size high protection. The proposed authentication key is generated by merging it with the reference number of the node, and distance to its cluster head (CH). Decreasing the energy intake of CHs, RSA encryption allows CH to compile the tha data which encrypted with no need to decrypt it. The results of the simulation show that the approach could maximize the life of the network by nearly (47%, and 35.7%) compare by secure low-energy adaptive clustering hierarchy (Sec-LEACH and SL-LEACH) approches respectively.

Novel Data Compression Algorithm for Transmission Line Condition Monitoring

For the problem of data accumulation caused by massive sensor data in transmission line condition monitoring system, this paper analyzes the type and amount of data in the transmission line sensor network, compares the compression algorithms of wireless sensor network data at home and abroad, and proposes an efficient lossless compression algorithm suitable for sensor data in transmission line linear heterogeneous networks. The algorithm combines the wavelet compression algorithm and the neighborhood index sequence algorithm. It displays a fast operation speed and requires a small amount of calculation. It is suitable for battery powered wireless sensor network nodes. By combining wavelet correlation analysis and neighborhood index sequence coding, the compression algorithm proposed in this paper can achieve a high compression rate, has strong robustness to packet loss, has high compression performance, and can help to reduce network load and the packet loss rate. Simulation results show that the proposed method achieves a high compression rate in the compression of the transmission line parameter dataset, is superior to the existing data compression algorithms, and is suitable for the compression and transmission of transmission line condition monitoring data.

Data transmitted encryption for clustering protocol in heterogeneous wireless sensor networks

In this paper, we propose a novel encryption schema (ECDH – RSA) based on Elliptic Curves Diffie – Hellman algorithm (ECDH) and RSA algorithm to secure transmitted data in Heterogeneous Wireless sensor networks (HWSNs). The proposed encryption is built under Cheesboard Clustering Routing Method (CCRM). The CCRM used to balancing node energy consumption. To achieve good scalability and performance by deploying a small number of powerful high-end sensors in addition to a large number of lowend sensors. ECDH is used to exchange public and private keys due to its ability to provide high security with small key size. The proposed encryption key is 176-bit and is produced by combining it’s key, node identification number, and distance to its cluster head (CH). To reduce energy consumption of CH, RSA encryption is used to allow CH to aggregate the encrypted data without having to decrypt them. We demonstrated that the proposed method is capable to work with different sensing environments that need to capture text data as well as images. The Simulation results demonstrated that our proposed method greatly improve the network performance in terms of energy consumption and highest paths.