Machine Learning: Algorithms, Real-World Applications and Research Directions

Sarker, Iqbal H.

doi:10.1007/s42979-021-00592-x

Cited by 1,776 publications

(889 citation statements)

References 120 publications

Supporting

Mentioning

860

Contrasting

Unclassified

Order By: Relevance

“…(2) Sensor Network and Embedded Technology. Wireless sensor network can be considered to be composed of three parts: data acquisition network, data distribution network, and control management center [25][26][27][28]. The main components are sensors, data processing unit, and communication module integrated node.…”

Section: Overview Of the Internet Of Things And Related Technologiesmentioning

confidence: 99%

Traffic State Detection Based on Multidimensional Data Fusion System of Internet of Things

Zhang

Zhu

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In recent years, the rapid development of cloud computing, mobile Internet, Internet of Things, and other technologies has accelerated the explosive growth of the number and types of data in various industries. As one of the current hot research fields, the multidimensional data fusion system has received widespread attention all over the world. Road traffic and traffic management involve a wide range of participants; a variety of traffic behavior and traffic management means have produced a huge volume of traffic management data and have a very high application value. Therefore, it is of great significance to study the application mode of the traffic management multidimensional data fusion system and realize the asset value transformation of the multidimensional data fusion system. Starting from the safety supervision service of operating vehicles, this paper elaborates the traffic management multidimensional data fusion system platform for the safety supervision service of operating vehicles around the application requirements and architecture of the traffic management multidimensional data fusion system and the results of this research team. Paper with city comprehensive transport hub as the research object uses the Internet of Things technology; establishes a set of BIM model-based intelligent Internet operation management platform, multidimensional collection personnel, and vehicles, such as traffic, equipment, and business data information; realizes the integration of data, correlation, and instructions issued by ability, to support the building intelligence operation management needs of the business; and realizes traffic and transportation status detection.

show abstract

Section: Overview Of the Internet Of Things And Related Technologiesmentioning

confidence: 99%

Traffic State Detection Based on Multidimensional Data Fusion System of Internet of Things

Zhang

Zhu

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…These models learn the discriminating features of benign traffic and malicious traffic using different architectures such as Random Forest (RF) [ 18 ], Support Vector Machine (SVM) [ 19 ], Deep Neural Network (DNN) [ 20 ], Recurrent Neural Network (RNN) [ 21 ], Long Short-Term Memory (LSTM) [ 22 ] and Gated Recurrent Unit (GRU) [ 23 ]. For an in-depth understanding, comprehensive reviews and surveys on the application of ML and DL in intrusion detection are presented in [ 24 , 25 , 26 , 27 , 28 , 29 ].…”

Section: Introductionmentioning

confidence: 99%

SMOTE-DRNN: A Deep Learning Algorithm for Botnet Detection in the Internet-of-Things Networks

Popoola

Adebisi

Ande

et al. 2021

Sensors

View full text Add to dashboard Cite

Nowadays, hackers take illegal advantage of distributed resources in a network of computing devices (i.e., botnet) to launch cyberattacks against the Internet of Things (IoT). Recently, diverse Machine Learning (ML) and Deep Learning (DL) methods were proposed to detect botnet attacks in IoT networks. However, highly imbalanced network traffic data in the training set often degrade the classification performance of state-of-the-art ML and DL models, especially in classes with relatively few samples. In this paper, we propose an efficient DL-based botnet attack detection algorithm that can handle highly imbalanced network traffic data. Specifically, Synthetic Minority Oversampling Technique (SMOTE) generates additional minority samples to achieve class balance, while Deep Recurrent Neural Network (DRNN) learns hierarchical feature representations from the balanced network traffic data to perform discriminative classification. We develop DRNN and SMOTE-DRNN models with the Bot-IoT dataset, and the simulation results show that high-class imbalance in the training data adversely affects the precision, recall, F1 score, area under the receiver operating characteristic curve (AUC), geometric mean (GM) and Matthews correlation coefficient (MCC) of the DRNN model. On the other hand, the SMOTE-DRNN model achieved better classification performance with 99.50% precision, 99.75% recall, 99.62% F1 score, 99.87% AUC, 99.74% GM and 99.62% MCC. Additionally, the SMOTE-DRNN model outperformed state-of-the-art ML and DL models.

show abstract

“…the topics from the abstracts of research papers. After that, we employed kmeans clustering algorithm [7] to cluster the similar topics. A greedy algorithm ATAC has been introduced to find the attribute driven temporal local active community with respect the given query Q, containing the query node u q over k-core connected subgraph, within h hops.…”

Section: Discussionmentioning

confidence: 99%

“…The proposed framework includes three stages layout as presented in Figure 2 to search attribute driven temporal active community (ATAC). First, the pre-processing is performed to eliminate irrelevant data or noises from the activity stream S. Second, topic modeling method has been applied, in our case, we applied LDA/BERTopic (Topic Modelling Approach) to the filtered data to recognize the latent topics from S. Then similar topics are being clustered by employing k-means clustering algorithm [7]. Finally, an algorithm is developed and applied to the processed activity streams to detect the desired community.…”

Section: Active Online Local Community Detection Approachmentioning

confidence: 99%

Attribute Driven Temporal Active Online Community Search

et al. 2021

Self Cite

View full text Add to dashboard Cite

Almost all of the existing approaches to determining online local community are typically deliberated likeminded users who have similar topical interests. However, such methodologies overlook the prospective temporality of users' interests as well as users' degree of topical activeness. As a result, the consequential communities might have extremely lower active users. This research investigates how online social users' behaviors and topical activeness vary over time and how these parameters can be employed in order to improve the quality of the detected local community. For a given input query, consisting a query node (user) and a set of attributes, this research intends to find densely-connected community in which community members are temporally similar in terms of their activities related to the query attributes. To address the proposed problem, we develop a temporal activity biased weight model which gives higher weight to users' recent activities and develop an algorithm to search an effective community. The effectiveness of the proposed methodology is justified using four benchmark datasets and compared with four other baseline methods. Experimental results demonstrate that our proposed framework yields better outcomes than the baseline methods for all four benchmark datasets.INDEX TERMS Online local Community, query attributes, temporal topical activeness.

show abstract

Machine Learning: Algorithms, Real-World Applications and Research Directions

Cited by 1,776 publications

References 120 publications

Traffic State Detection Based on Multidimensional Data Fusion System of Internet of Things

Traffic State Detection Based on Multidimensional Data Fusion System of Internet of Things

SMOTE-DRNN: A Deep Learning Algorithm for Botnet Detection in the Internet-of-Things Networks

Attribute Driven Temporal Active Online Community Search

Contact Info

Product

Resources

About