Machine Learning-Based Malicious User Detection in Energy Harvested Cognitive Radio-Internet of Things

The COVID-19 outbreak resulted in preventative measures and restrictions for Bangladesh during the summer of 2020—these unstable and stressful times led to multiple social problems (e.g., domestic violence and divorce). Globally, researchers, policymakers, governments, and civil societies have been concerned about the increase in domestic violence against women and children during the ongoing COVID-19 pandemic. In Bangladesh, domestic violence against women and children has increased during the COVID-19 pandemic. In this article, we investigated family violence among 511 families during the COVID-19 outbreak. Participants were given questionnaires to answer, for a period of over ten days; we predicted family violence using a machine learning-based model. To predict domestic violence from our data set, we applied random forest, logistic regression, and Naive Bayes machine learning algorithms to our model. We employed an oversampling strategy named the Synthetic Minority Oversampling Technique (SMOTE) and the chi-squared statistical test to, respectively, solve the imbalance problem and discover the feature importance of our data set. The performances of the machine learning algorithms were evaluated based on accuracy, precision, recall, and F-score criteria. Finally, the receiver operating characteristic (ROC) and confusion matrices were developed and analyzed for three algorithms. On average, our model, with the random forest, logistic regression, and Naive Bayes algorithms, predicted family violence with 77%, 69%, and 62% accuracy for our data set. The findings of this study indicate that domestic violence has increased and is highly related to two features: family income level during the COVID-19 pandemic and education level of the family members.

show abstract

“…It is a binary classification model. The LR model is performed based on a logistical function that is defined as follows [23]:…”

Section: Logistic Regressionmentioning

confidence: 99%

Prediction on Domestic Violence in Bangladesh during the COVID-19 Outbreak Using Machine Learning Methods

Hossain

Asadullah

Rahaman

et al. 2021

ASI

Self Cite

View full text Add to dashboard Cite

show abstract

“…For the more complicated tasks, usually deep learning is used, which is a subset of the machine learning field, and consists of layered structures known as artificial neural networks inspired by the human brain [13]. Examples of machine learning-based techniques are proposed in [14][15][16][17][18][19][20][21] and summarized in Table 1. For MUs detection, the authors in [14] implemented a new support vector machine (SVM) algorithm to separate MUs from SUs under a three class hypothesis.…”

Section: Introductionmentioning

confidence: 99%

“…The proposed algorithm is evaluated in terms of accuracy, receiver operating characteristic (ROC), probability of detection (P d ), and false alarm (P f a ). In [15], the authors used three individual classifiers, namely logistic regression (LR), k-nearest neighbors (k-NN), and SVM to detect MUs in energy harvested CR-IoT networks. The proposed LR algorithm gives better performance results in terms of accuracy, sum rate, and network lifetime.…”

Section: Introductionmentioning

confidence: 99%

“…. Table3represents the comparative results in terms of accuracy and classification time between the different proposed CNN models, using a batch size equal to 5 and a number of epochs equal to15. As one can see, the RMSProp-based simple CNN achieves the highest performance results in terms of both accuracy and time, with 100% training accuracy and testing accuracy, and a faster classification time of 132 s; followed by an Adam-based simple CNN with very close results and a training accuracy of 99.74%, a testing accuracy of 100%, and a classification time of 135 s. The SGD-based simple CNN reaches a training accuracy of 95.55%, a testing accuracy of 98.18%, and a classification time of 137 s. For the transfer learning-based models, the EfficientNetB0-based model C is much faster than the other models (model A, model B, and model D), with a classification time of 165 sec, and it also achieves an acceptable accuracy performance, with 95.06% training accuracy and 96.36% testing accuracy.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Novel Prediction Model for Malicious Users Detection and Spectrum Sensing Based on Stacking and Deep Learning

Benazzouza

Ridouani²,

Salahdine³

et al. 2022

Sensors

View full text Add to dashboard Cite

Cooperative network is a promising concept for achieving a high-accuracy decision of spectrum sensing in cognitive radio networks. It enables a collaborative exchange of the sensing measurements among the network users to monitor the primary spectrum occupancy. However, the presence of malicious users leads to harmful interferences in the system by transmitting incorrect local sensing observations.To overcome this security related problem and to improve the accuracy decision of spectrum sensing in cooperative cognitive radio networks, we proposed a new approach based on two machine learning solutions. For the first solution, a new stacking model-based malicious users detection is proposed, using two innovative techniques, including chaotic compressive sensing technique-based authentication for feature extraction with a minimum of measurements and an ensemble machine learning technique for users classification. For the second solution, a novel deep learning technique is proposed, using scalogram images as inputs for the primary user spectrum’s classification. The simulation results show the high efficiency of both proposed solutions, where the accuracy of the new stacking model reaches 97% in the presence of 50% of malicious users, while the new scalogram technique-based spectrum sensing is fast and achieves a high probability of detection with a lower number of epochs and a low probability of false alarm.

show abstract

Support vector machine approach of malicious user identification in cognitive radio networks

Arshid

Zhang²,

Hussain³

et al. 2022

Wireless Netw

View full text Add to dashboard Cite

Machine Learning-Based Malicious User Detection in Energy Harvested Cognitive Radio-Internet of Things

Abstract: Our simulation data is generated from energy vector using ED technique.

Cited by 3 publications

References 22 publications

Prediction on Domestic Violence in Bangladesh during the COVID-19 Outbreak Using Machine Learning Methods

Prediction on Domestic Violence in Bangladesh during the COVID-19 Outbreak Using Machine Learning Methods

A Novel Prediction Model for Malicious Users Detection and Spectrum Sensing Based on Stacking and Deep Learning

Support vector machine approach of malicious user identification in cognitive radio networks

Contact Info

Product

Resources

About