A model for intrusion detection system using hidden Markov and variational Bayesian model for IoT based wireless sensor network

Kalnoor, Gauri; Gowrishankar, S.

doi:10.1007/s41870-021-00748-1

Cited by 29 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most unstructured data exists in text, and the information extraction for text data requires the completion of entity extraction [23]. In order to extract entities from text, the locations of entities have to be determined first, and other entities are determined to be placed in predefined categories by using the HMM(Hidden Markov Models) [24] method for the entity extraction. It focuses on transforming entity extraction problems into feature labeling problems for processing.…”

Section: Information Extraction For Unstructured Datamentioning

confidence: 99%

Design of agricultural question answering information extraction method based on improved LSTM algorithm

Tang,

Aridas,

Talip

2024

Preprint

View full text Add to dashboard Cite

With the rapid growth of the agricultural information and the need for data analysis, how to accurately extract useful information from massive data has become an urgent first step in agricultural data mining and application. In this study, an agricultural question-answering information extraction method based on the IM-BILSTM (Improved Bidirectional Long Short-Term Memory) algorithm is designed. Firstly, it uses Python's Scrapy crawler framework to obtain the imformation of soil types, crop diseases and pests, and agricultural trade information, and remove abnormal values. Secondly, the information extraction converts the semi-structured data by using entity extraction methods. Thirdly, the BERT(Bidirectional Encoder Representations from Transformers) algorithm is introduced to improve the performance of the BILSTM algorithm. After comparing with the BERT-CRF(Conditional Random Field) and BILSTM algorithm, the result shows that the IM-BILSTM algorithm has better information extraction performance than the other two algorithms. This study improves the accuracy of the agricultural information recommendation system from the perspective of information extraction. Compared with other work that is done from the perspective of recommendation algorithm optimization, it is more innovative; it helps to understand the semantics and contextual relationships in agricultural question and answer, so as to Improve the accuracy of agricultural information recommendation systems. By gaining a deeper understanding of farmers' needs and interests, the system can better recommend relevant and practical information.

show abstract

Section: Information Extraction For Unstructured Datamentioning

confidence: 99%

Design of agricultural question answering information extraction method based on improved LSTM algorithm

Tang,

Aridas,

Talip

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Then coming onto studies work stated in paper [7], precise type of cyber hazard data is the time collection of cyber attacks discovered via a cyber defense device referred to as honeypots, which passively display the incoming Internet connections, alongwith algorithms Bayesian method, hidden Markov model, seasonal ARIMA Model, FARIMA version , FARIMA+GARCH model, marked factor method, vine copula model with parameters as degree of prediction accuracy, to forecast or are expecting Cyber assaults. As per the examine cited in paper [8] datasets used are "Alert Dataset, 'LLDDoS1.Zero DARPA'dataset", and algorithms is Hidden Markov Model with parameters inclusive of IDS database, National Vulnerabilities Database (NVD), assault garph datasources, HMM parameters. Profiles, metrics,statistical models, and procedures for evaluating logs were all part of the concept [9].…”

Section: Literature Surveymentioning

confidence: 99%

Empirical Analysis of Machine Learning Techniques for Intrusion Detection in Network System

Singh¹,

Bansal²

2023

IJSREM

View full text Add to dashboard Cite

Abstract—Increasing network resource usage creates security risks with it. Malwares and other sources may disrupt the system operations and inadequate security holes in systems. Intrusion Detection System(IDS) is invented to alert admins in case of such security breaches. In order to enhance IDS systems, artificial intelligence as well as . In this research, literature studies employing CSE-CIC IDS- 2018, UNSW-NB15, ISCX-2012, NSLKDD and CIDDS-001 data sets, frequently used to design IDS systems, updated in detail. In addition, max-min normalisation was done on these data sets and classed created utilising ,K NN algo, vector support machine (SVM), Decision Tree (DT) algorithms, which among the most ancient ML approaches. As a result, some genuinely good results have been analyzed. Index Terms—Intrusion, Machine Learning, Security

show abstract

“…For the measurement of a trust value, a weighted score product or more complex characteristics such as the inference of Bayes [7,22] or regression analysis [23] can be involved.…”

Section: International Journal On Recent and Innovation Trends In Com...mentioning

confidence: 99%

Intelligent Trust based Security Framework for Internet of Things

Rana¹,

Singh²,

Vijaya

2022

IJRITCC

View full text Add to dashboard Cite

Trust models have recently been proposed for Internet of Things (IoT) applications as a significant system of protection against external threats. This approach to IoT risk management is viable, trustworthy, and secure. At present, the trust security mechanism for immersion applications has not been specified for IoT systems. Several unfamiliar participants or machines share their resources through distributed systems to carry out a job or provide a service. One can have access to tools, network routes, connections, power processing, and storage space. This puts users of the IoT at much greater risk of, for example, anonymity, data leakage, and other safety violations. Trust measurement for new nodes has become crucial for unknown peer threats to be mitigated. Trust must be evaluated in the application sense using acceptable metrics based on the functional properties of nodes. The multifaceted confidence parameterization cannot be clarified explicitly by current stable models. In most current models, loss of confidence is inadequately modeled. Esteem ratings are frequently mis-weighted when previous confidence is taken into account, increasing the impact of harmful recommendations. In this manuscript, a systematic method called Relationship History along with cumulative trust value (Distributed confidence management scheme model) has been proposed to evaluate interactive peers trust worthiness in a specific context. It includes estimating confidence decline, gathering & weighing trust parameters and calculating the cumulative trust value between nodes. Trust standards can rely on practical contextual resources, determining if a service provider is trustworthy or not and does it deliver effective service? The simulation results suggest that the proposed model outperforms other similar models in terms of security, routing and efficiency and further assesses its performance based on derived utility and trust precision, convergence, and longevity.

show abstract

A model for intrusion detection system using hidden Markov and variational Bayesian model for IoT based wireless sensor network

Cited by 29 publications

References 11 publications

Design of agricultural question answering information extraction method based on improved LSTM algorithm

Design of agricultural question answering information extraction method based on improved LSTM algorithm

Empirical Analysis of Machine Learning Techniques for Intrusion Detection in Network System

Intelligent Trust based Security Framework for Internet of Things

Contact Info

Product

Resources

About