COMPARISON OF CLASSIFICATION ALGORITHMS FOR ANOMALY DETECTION IN ENERGY OPTIMIZATION OF HIGH RACK STORAGE SYSTEMS

Öz

The production systems digitized by ensuring healthy data flow between the units and the smart factory structures that are automated in line with this digitization process find more and more places in the production industry. Although such systems have provided important developments and technological advances in production processes, they also bring with it various problems. One of these is the process of quickly detecting and resolving an abnormal situation occurring in autonomous production systems. In this context, various studies have been carried out recently for anomaly detection. One of the most studied areas for anomaly detection is machine learning algorithms. In this study, the performances of various machine learning algorithms were tested on two different data sets obtained from a prototype study on energy optimization of high storage systems. As a result, learning models created with Artificial Neural Networks, C4.5 Decision Tree, Random Forest and k Nearest Neighbor algorithms have achieved a high performance rate in detecting anomalies within the tested data sets. Among these algorithms, the Random Forest algorithm has attracted attention with its accuracy performance of approximately 98%.

Anahtar Kelimeler

• Anomaly Detection
• Classification
• Machine Learning
• Smart Factories

YÜKSEK RAFLI DEPOLAMA SİSTEMLERİNİN ENERJİ OPTİMİZASYONUNDA ANOMALİ TESPİTİ İÇİN SINIFLAMA ALGORİTMALARININ KARŞILAŞTIRILMASI

Öz

Birimler arasında sağlıklı veri akışının sağlanması ile dijitalleşen üretim sistemleri ve bu dijitalleşme süreci doğrultusunda otomatikleşen zeki fabrika yapıları gün geçtikçe üretim endüstrisinde kendisine daha fazla yer bulmaktadır. Bu tür sistemler, üretim önemli gelişmeler ve teknolojik ilerlemeler sağlamış olsa da çeşitli sorunları da beraberinde getirmektedir. Bunlardan bir tanesi de otonom çalışan üretim sistemlerinde gerçekleşen bir anormal durumun hızlı bir şekilde tespit edilerek, çözüme kavuşturulması sürecidir. Bu kapsamda son zamanlarda anomali tespiti için çeşitli çalışmalar yapılmaktadır. Anomali tespiti konusunda en çok destek alınan alanlardan bir tanesi de makine öğrenmesi algoritmalarıdır. Bu çalışmada, yüksek depolama sistemlerinin enerji optimizasyonu hakkında uygulanmış bir prototip çalışmadan elde edilmiş olan iki farklı veri seti üzerinde çeşitli makine öğrenmesi algoritmalarının performansları test edilmiştir. Sonuç olarak, Yapay Sinir Ağları, C4.5 Karar Ağacı, Rastgele Orman ve k En Yakın Komşu algoritmaları ile oluşturulan öğrenme modelleri, test edilen veri setleri içerisindeki anomalileri tespit etme konusunda yüksek başarım oranı elde etmişlerdir. Özellikle bu algoritmalar içerisinde Rastgele Orman algoritması yaklaşık %98 seviyesindeki doğruluk performansı ile dikkat çekmiştir.

Anahtar Kelimeler

• Anomali Tespiti
• Sınıflandırma
• Makine Öğrenmesi
• Zeki Fabrikalar

Kaynakça

1. Akçetin, E., & Çelik, U. (2014). İstenmeyen Elektronik Posta (Spam) Tespitinde Karar Ağacı Algoritmalarının Performans Kıyaslaması. İnternet Uygulamaları ve Yönetimi, 5(2), 43-56.
2. Aksu, M. Ç., & Karaman, E. (2017). Karar Ağaçları ile Bir Web Sitesinde Link Analizi ve Tespiti. ACTA INFOLOGICA, 1(2), 84-91.
3. Alpaydın, E. (2017). Yapay Öğrenme. İstanbul: Boğaziçi Üniversitesi Yayınevi.
4. Arı, A., & Berberler, M. E. (2017). Yapay Sinir Ağları ile Tahmin ve Sınıflandırma Problemlerinin Çözümü İçin Arayüz Tasarımı. Acta - Infologica, 1(2), 55-73.
5. Aydemir, E. (2019). Weka ile Yapay Zeka. Ankara: Seçkin Yayıncılık.
6. Bagozi, A., Bianchini, D., Antonellis, V. D., Marini, A., & Ragazzi, D. (2017). Big Data Summarisation and Relevance Evaluation for Anomaly Detection in Cyber Physical Systems. OTM 2017: On the Move to Meaningful Internet Systems (s. 429-447). Rhodes, Greece: Springer.
7. Belgiu, M., & Drăgut, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing(114), 24-31.
8. Birgelen, A. v., & Niggeman, O. (2017). Using self-organizing maps to learn hybrid timed automata in absence of discrete events. 2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) (s. 1-8). Limassol: IEEE.

9. Breiman, L. (2001). Random Forests. Machine Learning(45), 5-32.
10. Brownlee, J. (2019). Machine Learning Mastery With Weka.
11. Chen, B., Wan, J., Shu, L., Li, P., Mukherjee, M., & Yin, B. (2017). Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges. IEEE Access(6), 6505-6519.
12. Elmas, Ç. (2016). Yapay Zeka Uygulamaları 3. Baskı. Ankara: Seçkin Yayıncılık.
13. Feizizadeh, B., Roodposhti, M. S., Blaschke, T., & Aryal, J. (2017). Comparing GIS-based support vector machine kernel functions for landslide susceptibility mapping. Arabian Journal of Geosciences, 10(117).
14. Frank, A. G., Dalenogare, L. S., & Ayala, N. F. (2019). Industry 4.0 technologies: Implementation patterns in manufacturing companies. International Journal of Production Economics(210), 15-26.
15. Gürsakal, N. (2018). Makine Öğrenmesi. Bursa: Dora Yayınevi.
16. Han, J., & Kamber, M. (2006). Data Mining, Concepts and Techniques 2nd Edition. San Francisco: Morgan Kaufmann Publishers.
17. Hand, D., Manila, H., & Smyth, P. (2001). Principles of Data Mining. London: Massachusetts Institute of Technology.
18. Harefa, J., Alexander, A., & Pratiwi, M. (2016). Comparison Classifier: Support Vector Machine (SVM) and K-Nearest Neighbor (K-NN) In Digital Mammogram Images. Jurnal Informatika dan Sistem Informasi, 2(2), 35-40.
19. Hasan, M., Islam, M. M., Zarif, M. I., & Hashem, M. (2019). Attack and anomaly detection in IoT sensors in IoT sites using machine learning approaches. Internet of Things, 1-14.
20. Holzinger, A., Malle, B., Kieseberg, P., Roth, P. M., Müller, H., Reihs, R., & Zatloukal, K. (2017). Machine Learning and Knowledge Extraction in Digital Pathology Needs an Integrative Approach. A. Holzinger, R. Goebel, M. Ferri, & V. Palade içinde, Towards Integrative Machine Learning and Knowledge Extraction (s. 13-50). Springer.
21. Hranisavljevic, N., Maier, A., & Niggeman, O. (2020). Discretization of hybrid CPPS data into timed automaton using restricted Boltzmann machines. Engineering Applications of Artificial Intelligence(95), 1-9.
22. Hranisavljevic, N., Niggemann, O., & Maier, A. (2016). A Novel Anomaly Detection Algorithm for Hybrid Production Systems based on Deep Learning and Timed Automata. The 27th International Workshop on Principles of Diagnosis: DX. Denver, USA.
23. Hranisavljevic, N., Niggemann, O., & Maier, A. (2018, 07 19). High Storage System Data for Energy Optimization. 03 15, 2020 tarihinde Kaggle: https://www.kaggle.com/inIT-OWL/high-storage-system-data-for-energy-optimization adresinden alındı
24. Hsieh, R.-J., Chou, J., & Ho, C.-H. (2019). Unsupervised Online Anomaly Detection on Multivariate Sensing Time Series Data for Smart Manufacturing. IEEE 12th Conference on Service-Oriented Computing and Applications (SOCA) (s. 90-97). Kaohsiung, Taiwan: IEEE.
25. Indriani, O. R., Kusuma, E. J., Sari, C. A., Rachmawanto, E. H., & Setiadi, D. I. (2017). Tomatoes classification using K-NN based on GLCM and HSV color space. International Conference on Innovative and Creative Information Technology (ICITech) (s. 1-6). Salatiga: IEEE.
26. İşçimen, B., Kutlu, Y., Reyhaniye, A. N., & Turan, C. (2014). Balık tanınmasında görüntü analiz yöntemleri. 22nd Signal Processing and Communications Applications Conference. Trabzon.
27. Jadhav, S. D., & Channe, S. P. (2016). Comparative Study of K-NN, Naive Bayes and Decision Tree Classification Techniques. International Journal of Science and Research, 5(1), 1842-1845.
28. Jain, M., Narayan, S., Pratibha, B., Bhowmick, A., & Muthu, R. (2018). Speech Emotion Recognition using Support Vector Machine. International Conference on Informatics Computing in Engineering Systems (ICICES). Chennai, India: IEEE.
29. Kim, K. H., Shim, S., Lim, Y., Jeon, J., Choi, J., Kim, B., & Yoon, A. S. (2019). RaPP: Novelty Detection with Reconstruction along Projection Pathway. International Conference on Learning Representations (ICLR 2020), (s. 1-10). Addis Ababa, Ethiopia.
30. Mansournia, M. A., Geroldinger, A., Greenland, S., & Heinze, G. (2018). Separation in Logistic Regression: Causes, Consequences, and Control. American Journal of Epidemiology, 187(4), 864-870.
31. Nizam, H., & Akın, S. S. (2014). Sosyal Medyada Makine Öğrenmesi ile Duygu Analizinde Sosyal Medyada Makine Öğrenmesi ile Duygu Analizinde Karşılaştırılması. XIX. Türkiye'de İnternet Konferansı. İzmir.
32. Pahl, M.-O., & Aubet, F.-X. (2018). All Eyes on You: Distributed Multi-Dimensional IoT Microservice Anomaly Detection. 14th International Conference on Network and Service Management (CNSM 2018) (s. 72-80). Italy: Aconf.
33. Patil, T. R., & Sherekar, S. S. (2013). Performance Analysis of Naive Bayes and J48 Classification Algorithm for Data Classification. International Journal Of Computer Science And Applications, 6(2), 256-261.
34. Radziwon, A., Bilberg, A., Bogers, M., & Madsen, E. S. (2014). The Smart Factory: Exploring Adaptive and Flexible Manufacturing Solutions. Procedia Engineering(69), 1184-1190.
35. Riordan, A. O., Coady, J., Toal, D., Newe, T., & Dooly, G. (2019). Industry 4.0: Pillars for Smart Manufacturing - A Review. no. February.
36. Shin, S. Y., & Kim, H.-J. (2020). Extended Autoencoder for Novelty Detection with Reconstruction along Projection Pathway. Applied Sciences, 10(13), 1-14.
37. Staub, S., Karaman, E., Kaya, S., Karapınar, H., & Güven, E. (2015). Artificial Neural Network and Agility. Procedia - Social and Behavioral Sciences, 195, 1477-1485.
38. Şeker, H. İ., Tuna, M., & Koyuncu, İ. (2018). Gerçek Zamanlı Wavelet Dönüşümleri için FPGA-Tabanlı Meksika Şapkası Dalgacığının Tasarımı ve Gerçeklenmesi. 3rd International Conference on Engineering Technology and Applied Sciences (ICETAS) , (s. 168-173). Skopje Macedonia.
39. Şeker, Ş. E. (2016). Weka ile Veri Madenciliği. İstanbul: Bilgisayar Kavramları Yayınları.
40. Tanha, J., Someren, M. V., & Afsarmanesh, H. (2017). Semi-supervised self-training for decision tree classifiers. International Journal of Machine Learning and Cybernetics(8), 355-370.
41. Wan, J., Li, J., Imran, M., Li, D., & Amin, F.-e. (2019). A Blockchain-Based Solution for Enhancing Security and Privacy in Smart Factory. IEEE Transactions on Industrial Informatics, 15(6), 3652-3660.
42. Wang, R., Nie, K., Wang, T., Yang, Y., & Long, B. (2020). Deep Learning for Anomaly Detection. 13th International Conference on Web Search and Data Mining (s. 894-896). Houston, TX, USA: WSDM.
43. Yakut, E., Elmas, B., & Yavuz, S. (2014). Yapay Sinir Ağları ve Destek Vektör Makineleri Yöntemleriyle Borsa Endeks Tahmini. Süleyman Demirel Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 19(1), 139-157.
44. Yoon, S., Um, J., Suh, S.-H., Stroud, I., & Yoon, J.-S. (2019). Smart Factory Information Service Bus (SIBUS) for manufacturing application: requirement, architecture and implementation. Journal of Intelligent Manufacturing(30), 363-382.