ANALISIS PENGAPLIKASIAN JARINGAN SARAF TIRUAN DALAM KEAMANAN JARINGAN KOMPUTER

Miftahur Rizki -  Universitas Indraprasta PGRI
Harry Dhika* -  Universitas Indraprasta PGRI

DOI : 10.24269/mtkind.v14i2.2056

ABSTRAK

 

Banyak kemajuan telah dibuat dalam pengembangan teknologi kecerdasan buatan, beberapa di antaranya diprakarsai oleh sistem jaringan saraf biologis. Ilmuwan dan peneliti dari semua disiplin ilmu telah merancang jaringan saraf tiruan yang bertujuan untuk memecahkan masalah yang berkaitan dengan prediksi, pengoptimalan, pengenalan pola, kontrol, dan asosiatif. Jaringan saraf sendiri adalah kelas algoritma pembelajaran mesin yang banyak digunakan dalam penambangan data berbasis komputer. Kontribusi aplikasi jaringan saraf berfokus pada pemeliharaan sistem kontrol data komunikasi melalui teknologi jaringan saraf ahli. Memperoleh informasi atau data yang relevan dan akuntabilitas merupakan kondisi yang tidak dapat kita hindari dalam bisnis modern. Informasi dapat dibedakan menjadi dua bagian yaitu informasi data, dan pengetahuan. Cara mengumpulkan, menyimpan, dan mengambilnya, dapat dipelajari dalam teori database. Bahkan dalam rekayasa pengetahuan, ada metode yang harus kita ketahui dan pelajari, yang didapat dari peneliti atau ahli di bidang yang ingin kita kaji. Penelitian ini bertujuan untuk melakukan perancangan sistem, pemilihan jenis jaringan saraf tiruan, pengambilan data, dan transformasi data. Metode prop cepat dipilih berdasarkan metode Newton, terdapat di bagian hasil jurnal ini. Penelitian ini menyimpulkan bahwa untuk menghasilkan keseimbangan dan kontinuitas dapat diperoleh antara memori data atau penyimpanan data dan kemampuan generalisasi umum atau universal pada pola masukan yang sama tetapi tidak identik dengan pola yang telah dipelajari, diteliti, dan diuji sebelumnya.

 

ABSTRACT

 

Many advances have been made in the development of artificial intelligence technology, some of which are initiated by a biological neural network system. Scientists and researchers from all various scientific disciplines have designed artificial neural networks that aim to solve problems related to prediction, optimization, pattern recognition, control and associative. Neural networks themselves are a class of machine learning algorithms widely used in computer-based data mining. The contribution of neural networks' application focuses on maintaining communication data control systems through the experts' neural network technology. Obtaining information or data relevant and accountability is a condition that we cannot avoid in a modern business. Information can be divided into two parts, namely data information, and knowledge. How to collect, store, and retrieve it, can study in database theory. Even in knowledge engineering, there are methods that we must know and learn from, which are obtained from researchers or experts in the field we want to study. This research aims to do system design, selecting the type of neural network, retrieval, and transformation data. The quick prop method is chosen based on the Newton method, found in this journal's results section. This research concludes that to produce a balance and continuity can be obtained between data memory or data storage and general or universal generalization capabilities on the same input patterns but not identical to patterns that have been previously studied, researched, and tested.

Keywords
Artificial Neural Networks, Network Security, Neural Network, Neuron
  1. P. M. Buscema, G. Massini, M. Breda, W. A. Lodwick, F. Newman, and M. Asadi-Zeydabadi, "Artificial neural networks," in Artificial adaptive systems using auto contractive maps: Springer, 2018, pp. 11-35.
  2. G. Conti and K. Abdullah, "Passive visual fingerprinting of network attack tools," in Proceedings of the 2004 ACM workshop on Visualization and data mining for computer security, 2004, pp. 45-54.
  3. A. K. Jain, J. Mao, and K. M. Mohiuddin, "Artificial neural networks: A tutorial," IEEE Computer, vol. 29, no. 3, pp. 31-44, 1996.
  4. R. E. Neapolitan and X. Jiang, Artificial intelligence: With an introduction to machine learning. CRC Press, 2018.
  5. A. Sinkov, G. Asyaev, A. Mursalimov, and K. Nikolskaya, "Neural networks in data mining," in 2016 2nd International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM), 2016, pp. 1-5: IEEE.
  6. C.-L. Su, S.-M. Yang, and W. Huang, "A two-stage algorithm integrating genetic algorithm and modified Newton method for neural network training in engineering systems," Expert Systems with Applications, vol. 38, no. 10, pp. 12189-12194, 2011.
  7. M. Thottan and C. Ji, "Anomaly detection in IP networks," IEEE Transactions on signal processing, vol. 51, no. 8, pp. 2191-2204, 2003.
  8. P. Vassiliadis and A. Simitsis, "Near real-time ETL," in New trends in data warehousing and data analysis: Springer, 2009, pp. 1-31.

Full Text:
Article Info
Submitted: 2019-10-31
Published: 2021-01-23
Section: Artikel
Article Statistics: