An Efficient Blockchain-Based IoT System …

177

Fig. 2 Traditional KNN confusion matrix

5

Conclusion

Blockchain, the Internet of Things, and artificial intelligence most especially machine

learning are all technologies that may be merged in many ways. It was contended

that these advancements will converge because the combination of these technologies

will boost business models, goods, and services. This study delivers a comprehensive

study on the use of machine learning to make Blockchain-based IoT network smart

applications more robust to attacks. To examine attacks on a blockchain-based IoT

network, an improved K-Nearest Neighbor (KNN) classifier has been presented.

With 96.7% and 81.6%, respectively, the improved KNN algorithm outperformed

the traditional KNN method. Accuracy and performance are both improved when

the false-positive rate is reduced. In this work, the limitations of various approaches

of accuracy, such as false-positive rates, are discussed [23].