Network Data Mining Research Articles

Peptide hemolytic activity analysis using visual data mining of similarity-based complex networks

Peptides are promising drug development frameworks that have been hindered by intrinsic undesired properties including hemolytic activity. We aim to get a better insight into the chemical space of hemolytic peptides using a novel approach based on network science and data mining. Metadata networks (METNs) were useful to characterize and find general patterns associated with hemolytic peptides, whereas Half-Space Proximal Networks (HSPNs), represented the hemolytic peptide space. The best candidate HSPNs were used to extract various subsets of hemolytic peptides (scaffolds) considering network centrality and peptide similarity. These scaffolds have been proved to be useful in developing robust similarity-based model classifiers. Finally, using an alignment-free approach, we reported 47 putative hemolytic motifs, which can be used as toxic signatures when developing novel peptide-based drugs. We provided evidence that the number of hemolytic motifs in a sequence might be related to the likelihood of being hemolytic.

Machine Learning, Data Mining, and IoT Applications in Smart and Sustainable Networks

The smart and sustainable networks require highly connected systems that can improve their operational performance, reduce environmental impact, and increase functional efficiency [...]

Research on classified prediction algorithm of platform customer value based on "tree" concept

The concept of "trees," representing decision trees, random forests, and XGBoost algorithms, has gained increasing attention in the field of classification prediction in recent years. These tree-based machine learning algorithms have been widely applied in the e-commerce sector. This paper discusses the decision tree, random forest, and XGBoost algorithms individually, and extracts useful classification rules from large volumes of online customer data to provide intelligent decision support for computer network customer management. The study finds that algorithms related to the "tree" concept can integrate a customers current value (such as purchasing behavior) with potential value (such as customer interest inferred from online reviews) through detailed classification criteria, thereby constructing a customer value measurement model. The evolution from decision trees to random forest and XGBoost algorithms has effectively promoted research on customer value hierarchy prediction, improving the efficiency of data mining in computer networks.

Deep neural networks and conventional machine learning classifiers to analyze thoracic survival data

Lung cancer is a prevalent global health concern and most prevalent malignancy in Indonesian hospitals. Following thoracic surgery, patients were categorized into two classes: individuals who experienced mortality within a year and those who achieved survival. Despite being about socks, the dataset for the deceased category consisted of 70 data samples, while the dataset for the final group comprised 400 samples. Data calculation involves the utilization of both deep neural networks and standard machine learning algorithms. The study use the Python programming language to evaluate the algorithms, and it measures their performance using metrics such as accuracy, F1-Score, precision, recall, receiver operating characteristic (ROC), and area under curve (AUC). The test results indicate that the deep neural network method achieves an accuracy of 95,56%, an F1 score of 79,24%, a precision of 91,96%, a recall of 85,52%, and an AUC of 85,52%. This study suggests that utilizing deep neural network data mining techniques, specifically with a cross-validation fold of 10, variations of six hidden layer encoder-decoder, relu, sigmoid activation function, optimizer Adam, and learning rate of 0,01, dropout rate of 0,2. Employing the Synthetic Minority Over-sampling Technique data preprocessing method, can effectively analyze thoracic patient survival data sets.

On Efficient Large Sparse Matrix Chain Multiplication

Sparse matrices are often used to model the interactions among different objects and they are prevalent in many areas including e-commerce, social network, and biology. As one of the fundamental matrix operations, the sparse matrix chain multiplication (SMCM) aims to efficiently multiply a chain of sparse matrices, which has found various real-world applications in areas like network analysis, data mining, and machine learning. The efficiency of SMCM largely hinges on the order of multiplying the matrices, which further relies on the accurate estimation of the sparsity values of intermediate matrices. Existing matrix sparsity estimators often struggle with large sparse matrices, because they suffer from the accuracy issue in both theory and practice. To enable efficient SMCM, in this paper we introduce a novel row-wise sparsity estimator (RS-estimator), a straightforward yet effective estimator that leverages matrix structural properties to achieve efficient, accurate, and theoretically guaranteed sparsity estimation. Based on the RS-estimator, we propose a novel ordering algorithm for determining a good order of efficient SMCM. We further develop an efficient parallel SMCM algorithm by effectively utilizing multiple CPU threads. We have conducted experiments by multiplying various chains of large sparse matrices extracted from five real-world large graph datasets, and the results demonstrate the effectiveness and efficiency of our proposed methods. In particular, our SMCM algorithm is up to three orders of magnitude faster than the state-of-the-art algorithms.

Implementation of Data Mining to Determine Public Interest in Automatic Motorcycles

Research on public interest in automatic motorbikes was carried out with the aim of understanding the factors that influence the decision to purchase an automatic motorbike. Using data mining methods, this research applies the K-Nearest Neighbor (KNN) and Neural Network techniques to identify and analyze people's interest patterns. The data used amounted to 139 samples, of which 127 showed interest in automatic motorbikes, while 12 others showed no interest. The research process begins with data analysis, the next stage is preprocessing, which includes data cleaning, in the model design stage in data mining, two models are built: one using KNN and the other using Neural Network. These two models are designed to classify sample data based on interest in automatic motorbikes. The next stage is model testing. Test results show that both models can classify interests accurately, with most of the sample data being classified correctly. Model evaluation was carried out to measure the effectiveness and accuracy of the two methods. The evaluation results show that both models provide very good performance, with results that almost reach a perfect score. This shows that both methods, KNN and Neural Network, are very effective in classifying and predicting people's interest in automatic motorbikes based on available data. In conclusion, this research not only shows the effectiveness of KNN and Neural Network in data mining for analyzing people's interests, but also provides valuable insights for automatic motorbike manufacturers and sellers about consumer preferences.

Intrusion detection system in cloud computing by utilizing VTR-HLSTM based on deep learning

<div>Cloud computing (CC) is a rapidly developing IT approach with intrusion detection system being a crucial tool for safeguarding virtual networks and machines from potential threats, thereby mitigating security concerns in the cloud environment. The intrusion detection system (IDS) system demands significant improvements, primarily based on optimizing performance and bolstering security measures. This research aims to implement an IDS in cloud computing utilizing deep learning (DL) method. The DL model is a promising technique and is widely used to detect intrusions. The implemented hierarchical long short-term memory (HLSTM) method’s performance is evaluated for feature selection through variance threshold-based regression (VTR) on two IDS network datasets: Bot-IoT and network security lab-knowledge discovery and data mining (NSL-KDD). This paper concludes the use of an intrusion detection network resulting in high security and performance. Moreover, the implemented method on the NSL-KDD and Bot-IoT datasets obtains respective accuracies of 99.50% and 0.995. It is compared with the existing methods namely, ensemble ID model for CC utilizing DL, LeNet, fuzzy deep neural network with a Honey Bader algorithm for privacy-preserving ID, and improved metaheuristics with a fuzzy logic-based IDS for cloud security, and beluga whale-tasmanian devil optimization based on deep convolutional neural network (CNN) with TL, chronological slap swarm algorithm-based deep belief network (DBN), and dragonfly improved invasive weed optimization-based Shepard CNN.</div>

A review on network representation learning with multi-granularity perspective

Network data is ubiquitous, such as telecommunication, transport systems, online social networks, protein-protein interactions, etc. Since the huge scale and the complexity of network data, former machine learning system tried to understand network data arduously. On the other hand, thought of multi-granular cognitive computation simulates the problem-solving process of human brains. It simplifies the complex problems and solves problems from the easier to harder. Therefore, the application of multi-granularity problem-solving ideas or methods to deal with network data mining is increasingly adopted by researchers either intentionally or unintentionally. This paper looks into the domain of network representation learning (NRL). It systematically combs the research work in this field in recent years. In this paper, it is discovered that in dealing with the complexity of the network and pursuing the efficiency of computing resources, the multi-granularity solution becomes an excellent path that is hard to go around. Although there are several papers about survey of NRL, to our best knowledge, we are the first to survey the NRL from the perspective of multi-granular computing. This paper proposes the challenges that NRL meets. Furthermore, the feasibility of solving the challenges of NRL with multi-granular computing methodologies is analyzed and discussed. Some potential key scientific problems are sorted out and prospected in applying multi-granular computing for NRL research.

MGATs: Motif-Based Graph Attention Networks

In recent years, graph convolutional neural networks (GCNs) have become a popular research topic due to their outstanding performance in various complex network data mining tasks. However, current research on graph neural networks lacks understanding of the high-order structural features of networks, focusing mostly on node features and first-order neighbor features. This article proposes two new models, MGAT and MGATv2, by introducing high-order structure motifs that frequently appear in networks and combining them with graph attention mechanisms. By introducing a mixed information matrix based on motifs, the generation process of graph attention coefficients is improved, allowing the model to capture higher-order structural features. Compared with the latest research on various graph neural networks, both MGAT and MGATv2 achieve good results in node classification tasks. Furthermore, through various experimental studies on real datasets, we demonstrate that the introduction of network structural motifs can effectively enhance the expressive power of graph neural networks, indicating that both high-order structural features and attribute features are important components of network feature learning.

The Role of Mining and Detection of Big Data Processing Techniques in Cybersecurity

Abstract The need for advanced detection methods has become more critical in light of the increasing prevalence of network security incidents. This study proposes a novel approach to network security detection using a fuzzy data mining algorithm, addressing the rising challenges in big data processing and network security. The paper outlines the evolution of big data analytics by exploring the integration of network security detection, data mining, and structural feature analysis. Data for this research was collected using a sniffer device and underwent extensive preprocessing to ensure diversity and applicability. To overcome the limitations of traditional data mining, such as the issue of sharp boundaries, this method combines fuzzy logic with data mining techniques, enhancing conventional network security protocols. Simulation experiments demonstrate the efficacy of this fuzzy mining-based approach, with results showing 987,238 predicted positive cases, 93,951 of which were accurate. The method achieves an impressive 93.65% accuracy and 92.55% recall rate, proving its capability to promptly identify and mitigate suspicious network activities.

Exploration of the molecular mechanism guiding Xinfeng capsule regulatory mechanism for rheumatoid arthritis inflammation.

Rheumatoid arthritis (RA) is an autoimmune disease characterized by chronic inflammation of the joint synovium. The traditional Chinese medicine Xinfeng capsule (XFC) has a remarkable alleviating effect on inflammatory symptoms, such as joint pain and swelling, in patients with RA. However, the underlying mechanism of action remains to be elucidated. This study intended to conduct network pharmacology, animal experiments, data mining, and molecular docking to explore the molecular mechanism through which XFC can improve the inflammatory symptoms of RA. The Apriori association rules and a random walk model were employed to evaluate the effect of XFC on the clinical inflammatory indexes of RA. The active ingredients and the potential target genes of XFC were obtained from public databases. Based on the search tool for recurring instances of neighboring genes (STRING) database, the Database for Annotation, Visualization and Integrated Discovery (DAVID) database, Cytoscape software, and molecular docking method, the molecular mechanism by which XFC acts on RA was also analyzed. Finally, an adjuvant arthritis rat model was established to verify the effects of XFC on inflammation-related signaling pathways and inflammatory factors. XFC significantly reduced the level of C-reactive protein (CRP), vascular endothelial growth factor (VEGF), and the erythrocyte sedimentation rate (ESR). The docking space structures of the active ingredients in XFC, namely triptolide and quercetin, and the key targets were stable. Inflammation-related biological processes were identified as the key factors involved in the development of RA, and the regulation of the toll-like receptor (TLR) signaling pathway may be the key link for XFC toward improving the inflammatory state of RA. The expression levels of toll-like receptor 4 (TLR4), myeloid differentiation primary response protein MyD88 (MyD88), interleukin-1 receptor-associated kinase 1 (IRAK1), TNF receptor-associated factor 6 (TRAF6), TGF-beta-activated kinase 1 (TAK1), phospho-Inhibitor of NF-κB kinaseβ (p-IKKβ), phospho-Nuclear factor-k-gene binding (p-NF-κB), and interleukin-1β (IL-1β) can all be decreased by XFC. XFC improves joint inflammation symptoms by lowering pro-inflammatory factors tumor necrosis factor-α (TNF-α), interleukin-6 (IL-6), and interferon-γ (INF-γ) levels. XFC could effectively improve the clinical inflammatory indexes of RA. The active ingredients of XFC improved the inflammatory state of RA by regulating the TLR-signaling pathway.

Research on Weibo marketing advertising push method based on social network data mining

Research on Weibo marketing advertising push method based on social network data mining

Prediction method of e-commerce consumers' purchase behaviour based on social network data mining

Prediction method of e-commerce consumers' purchase behaviour based on social network data mining

Research on Weibo marketing advertising push method based on social network data mining

Research on Weibo marketing advertising push method based on social network data mining

Online learning effectiveness evaluation for college students based on social network data mining

Online learning effectiveness evaluation for college students based on social network data mining

A Graph DB-Based Solution for Semantic Technologies in the Future Internet

With the progressive improvements in the power, effectiveness, and reliability of AI solutions, more and more critical human problems are being handled by automated AI-based tools and systems. For more complex or particularly critical applications, the level of knowledge, not just information, must be handled by systems where explicit relationships among objects are represented and processed. For this purpose, the knowledge representation branch of AI proposes Knowledge Graphs, widely used in the Semantic Web, where different online applications may interact by understanding the meaning of the data they process and exchange. This paper describes a framework and online platform for the Internet-based knowledge graph definition, population, and exploitation based on the LPG graph model. Its main advantages are its efficiency and representational power and the wide range of functions that it provides to its users beyond traditional Semantic Web reasoning: network analysis, data mining, multistrategy reasoning, and knowledge browsing. Still, it can also be mapped onto the SW.

Exploring traditional Chinese medicine as a potential treatment for sarcopenia: A network pharmacology and data mining analysis of drug selection and efficacy.

Sarcopenia, as an increasingly pressing clinical issue, can be ameliorated through employment of traditional Chinese medicines. However, the current lack of specific pharmacological interventions for Sarcopenia necessitates further exploration of novel possibilities in traditional Chinese medicine for the treatment of this condition, utilizing advanced methodologies such as web pharmacology and data mining. Screening the essential targets of Sarcopenia, conducting matching between target and active molecules, as well as active molecules and herbs. Employing data mining techniques to analyze the screening outcomes, and molecular docking to compare the binding activities of active molecules with target proteins. The approach of using herbs for the treatment of Sarcopenia involves 13 targets, with 414 active compounds and 367 types of herbs. Data mining reveals that the herbs used in treating Sarcopenia are primarily characterized by their bitter taste, exerting their effects through dispelling dampness and promoting blood circulation. Moreover, 2 new formulas are postulated. Furthermore, molecular docking analysis indicates that the main active components of the herbs can be observed to tightly bind with the targets. Through network pharmacology and molecular docking, our findings reveal that herbs contain 15 key active components and 5 key targets, which correspond to 7 major herbs and 2 new formulas. Academically, these findings hold significant reference value for the development of novel drugs targeting Sarcopenia.

Network Pharmacological Study of Compound Kushen Injection in Esophageal Cancer.

To provide new methods and ideas for the clinical application of integrated traditional Chinese and Western medicine in the treatment of esophageal cancer. Traditional Chinese medicine compound Kushen injection (CKI) has been widely used in the clinic with adjuvant radiotherapy and chemotherapy. However, the mechanism of action of CKI as adjuvant therapy for esophageal cancer has not yet been described. This study is based on network pharmacology, data mining, and molecular docking technology to explore the mechanism of action of CKI in the treatment of esophageal cancer. We obtained the effective ingredients and targets of CKI from the traditional Chinese medicine system pharmacology database and analysis platform (TCMSP) and esophageal cancer-related genes from the Online Mendelian Inheritance in Man (OMIM) and GeneCards databases. CKI mainly contains 58 active components. Among them, the top 5 active ingredients are quercetin, luteolin, naringenin, formononetin, and beta-sitostero. The target protein of the active ingredient was matched with the genes associated with esophageal cancer. The active ingredients targeted 187 esophageal cancer target proteins, including AKT1, MAPK1, MAPK3, TP53, HSP90AA1, and other proteins. Then, we enriched and analyzed the Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) and used AutoDockVina to dock the core targets and compounds. Finally, PyMOL and Ligplot were used for data visualization. This study provides a new method and ideas for the clinical application of integrated traditional Chinese and Western medicine in the treatment of esophageal cancer.

Research on Optimization of Medical Waste Emergency Disposal Transportation Network for Public Health Emergencies in the Context of Intelligent Transportation

In order to build a more comprehensive emergency disposal and transportation network system for medical waste, it is necessary to consider various uncertain factors and data characteristics. Therefore, in the context of intelligent transportation, this article considers the uncertainty of the quantity and regional population density of infectious medical waste generation as well as the emergency disposal of infectious medical waste under multi-cycle and multi-objective conditions, and it constructs a multi-cycle emergency disposal logistics network optimization model for infectious medical waste under uncertain conditions. Through deterministic transformation of the model and data mining of the medical waste disposal logistics network in Wuhan, China, the multi-objective model under uncertain conditions was also solved and sensitivity analyzed using the MOPSO-NSGA2 intelligent algorithm, verifying the effectiveness and superiority of the algorithm.

Applied Techniques for Twitter Data Retrieval in an Urban Area: Insight for Trip Production Modeling

This paper presents methods of retrieving Twitter data, both streaming and archive data, using Application Programming Interfaces. Twitter data are a kind of Location Based Social Network Data that, nowadays, is emerging in transportation demand modeling. Data regarding the locations of trip makers represent the most crucial step in the modeling. No research article has specifically addressed this topic with an up-to-date method; hence, this paper aims to refresh methods for retrieving Twitter data that can capture relevant data. The method is unique as the data are gathered for trip production modeling in zonal urban areas. Python script programs were built for both data retrieving methods. The programs were run for streaming data from May 2020 to April 2021 and archive data from 2018. The data were collected within Serang City, which is the nearest provincial city to Jakarta, the capital of Indonesia. In order to gather streaming data with no loss, the program has been run with referencing on sub-district office coordinate locations. Retrieving the intended data produces 1,090,623 documents, of which 54,103 are geotagged data from 2495 users. The study concluded that streaming data produce more geolocation data, while historical data capture more Twitter user data with relatively very little geotagged data and greater textual data than the period covered in this research. Thus, both techniques of retrieving Twitter data for urban personal trip modeling are necessary. Obtaining sufficient data collection using data streaming retrieval resulted in the most effective data preprocessing. This research contributes to Location Based Social Network data mining knowledge, both geolocation and text mining, and is useful for insight into developing trip production modeling in passenger transportation demand modeling using Machine Learning. This study also aims to provide useful methods for transportation system researchers and data scientists in utilizing Location Based Social Network data.