Comparison of KNN and DNN Classifiers Performance in Predicting Mobile Phone Price Ranges

Abstract

The aim of this study was to compare the classification performances of K-nearest neighbors (KNN) and Deep Neural Networks (DNN) models in a dataset. For this purpose, the “mobile price forecast" dataset has been selected. It includes 20 different features of mobile phones such as battery power, Bluetooth function, memory capacity, screen size. The problem presented in the dataset is to determine the price range class before the mobile phones are released. Such a forecast will help companies that manufacture mobile devices to estimate the price of their mobile phones in a more convenient method to compete against their competitors in the market. In the implementation phase of the study, the KNN and DNN models were created in Python 3.6 with the Sklearn and Keras libraries. The classification performances of the models were determined using F-1 score, accuracy, recall and accuracy measurements. As a result of the study, validation data was classified with 92% accuracy using the trained DNN model. In addition, at another stage of the study, the price range for 1000 devices with different features was determined by using a test dataset that was not labeled, and the results produced by both models were compared.

Keywords

• Classification
• Deep Neural Networks
• KNN
• Mobile Phone Prices

References

1. Guo J., Wang X., "Image Classification Based on SURF and KNN", International Conference on Computer and Information Science (ICIS), Beijing, China, 2019.
2. Öztürk A., Durak U., and Badıllı F., "Twitter Verilerinden Doğal Dil İşleme ve Makine Öğrenmesi ile Hastalık Tespiti", Konya Mühendislik Bilimleri Dergisi, vol 8(4), pp. 839 - 852, 2020.
3. Uğuz S., Oral O., and Çağlayan N., "PV Güç Santrallerinden Elde Edilecek Enerjinin Makine Öğrenmesi Metotları Kullanılarak Tahmin Edilmesi", Uluslararası Mühendislik Araştırma ve Geliştirme Dergisi , vol 11(3), pp. 769-799, 2019.
4. Manzak D., Çetinel G., and Manzak A., "Automated Classification of Alzheimer’s Disease using Deep Neural Network (DNN) by Random Forest Feature Elimination", The 14th International Conference on Computer Science & Education , Toronto, Canada, 2019.
5. Paltrinieri N., Comfort L., ve Reniers G., "Learning about risk: Machine learning for risk assessment", Safety Science , vol 118, pp. 475-486, 2019.
6. Maehashi K., and Shintani M., "Macroeconomic forecasting using factor models and machine learning: an application to Japan", Journal of the Japanese and International Economies, vol 58, 2020.
7. Pondhu L. N. and Kummari G., "Performance Analysis of Machine Learning Algorithms for Gender Classification", 2nd International Conference on Inventive Communication and Computational Technologies , 2018.
8. Aydoğan M. and Karci A., "Makine Öğrenmesi ve Transfer Öğrenme ile Türkçe Metin Sınıflandırma", International Conference on Artificial Intelligence and Data Processing , Malatya, Turkey, 2019.

9. Taneja S., and Gupta C., "An Enhanced K-Nearest Neighbor Algorithm Using Information Gain and Clustering", Fourth International Conference on Advanced Computing & Communication Technologies, 2014.
10. Li H., Jiang H., Wang D., and Han B., "An Improved KNN Algorithm for Text Classification", Eighth International Conference on Instrumentation and Measurement, Computer, Communication and Control, 2018.
11. Sarma M. S., Srinivas Y., Abhiram M., Prasanthi M. S. and Ramya M. S. L., "KNN File Classification for Securing Cloud Infrastructure", 2nd IEEE International Conference On Recent Trends In Electronics Information & Communication Technology, India, 2017.
12. Manjusha M., and Harikumar R., "Performance Analysis of KNN Classifier and K-Means Clustering for Robust Classification of Epilepsy from EEG Signals", International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET) , 2016.
13. Ser G., and C. T. Bati, "Derin Sinir Ağları ile En iyi Modelin Belirlenmesi: Mantar Verileri Üzerine Keras Uygulaması", Yüzüncü Yıl Üniversitesi Tarım Bilimleri Dergisi , vol 29(3), pp. 406-417, 2019.
14. Paseddula C. and Gansgashetty S. V., "DNN based Acoustic Scene Classification using Score Fusion of MFCC and Inverse MFCC", IEEE 13th International Conference on Industrial and Information Systems (ICIIS), 2018.
15. Mobile Price Prediction | Kaggle, [Online]. Available: https://www.kaggle.com/iabhishekofficial/ mobile-price-classification. [Accessed: 5 10 2020].
16. Cai Y. L., Ji D. and Chai D., "A KNN Research Paper Classification Method Based on Shared Nearest Neighbor", NTCIR, 2010.
17. Padraig C. and Delany S. J., k-Nearest Neighbour Classifiers, 2007.
18. Guo G., Wang H., Bi Y. and Greer K., "KNN Model-Based Approach in Classification", Lecture Notes in Computer Science, vol 2888, pp. 986-996, 2003.
19. Atallah D., Badawy M., El-Sayed A. and Ghoneim M., "Predicting kidney transplantation outcome based on hybrid feature selection and KNN classifier", Multimedia Tools and Applications, vol 78, p. 20383–2040, 2019.
20. Cover T. and Hart P., "Nearest neighbor pattern classification", IEEE Transactions on Information Theory, vol 13(1), pp. 21-27, 1967.
21. Yu L. H., Huang M. W., S. W. Ke and Tsai C. F., "The distance function effect on k-nearest neighbor classification for medical datasets", SprigerPlus, vol 5, 2016.
22. Bhattacharya G., Ghosh K. and Chowdhury A., "kNN Classification with an Outlier Informative Distance Measure", International Conference on Pattern Recognition and Machine Intelligence, 2017.
23. Mishra M. and Srivastava M., "A view of Artificial Neural Network", International Conference on Advances in Engineering & Technology Research (ICAETR), 2014.
24. Brian R., "Pattern Recognition and Neural Networks", Cambridge University Press, 1996.
25. Kustrin S. and Beresford R., "Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research", Journal of pharmaceutical and biomedical analysi, vol 22, pp. 717-727, 2000.
26. Ion R. M., Munteanu D. and Cocina G. C., "Concept of artificial neural network (ANN) and its application in cerebral aneurism with multi walls carbon nanotubes (MWCNT)", Materials Science, 2009.
27. Sarvepalli S. K., "Deep Learning in Neural Networks: The science behind an Artificial Brain", Liverpool Hope University, Liverpool, 2015.
28. Imran S., Jamil A., Shah S. and Kashif F. "Impact of Varying Neurons and Hidden Layers in Neural Network Architecture for a Time Frequency Application", IEEE International Multitopic Conference, Islamabad, 2006.
29. Wilamowski B. M., Chen Yixin and Malinowski A., "Efficient algorithm for training neural networks with one hidden layer", International Joint Conference on Neural Networks., Washington, DC, USA, 1999.
30. Bayraci S. and Susuz O., "Deep Neural Network (DNN) Based Classification Model In Application To Loan Default Prediction", Theoretical and Applied Economics , vol 26(621), pp. 75-84, 2018.
31. Serre T., Kreiman G. and Kouh M., "A quantitative theory of immediate visual recognition", Progress in Brain Research, vol 165, pp. 33-56, 2007.
32. Glorot X. and Bengio Y., "Understanding the difficulty of training deep feedforward neural networks. Journal of Machine Learning Research", Proceedings Track, vol 9, pp. 249-256, 2010.
33. Sze V., Chen Y., Yang T. and Emer J. S., "Efficient Processing of Deep Neural Networks: A Tutorial and Survey", Proceedings of the IEEE, vol 105(12), pp. 2295 - 2329, 2017.
34. Rumelhart D E., Hinton G. E. and Williams R. J., "Learning representations by back-propagating errors", Nature, vol 323(6088), p. 533–536, 1986.
35. Huang Y., Shiyu S, Xiusheng D and Zhigang C, "A study on Deep Neural Networks framework", IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), 2016.