Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal SENTIA 2015 Journal of Electrical, Electronic, Information, and Communication Technology (JEEICT)
Devira Anggi Maharani
Seminar Nasional Teknologi Informasi Politeknik Neheri Malang
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Combination of Natural Language Understanding and Reinforcement Learning for Booking Bot Dinda Ayu Permatasari; Devira Anggi Maharani
Journal of Electrical, Electronic, Information, and Communication Technology Vol 3, No 1 (2021): JOURNAL OF ELECTRICAL, ELECTRONIC, INFORMATION, AND COMMUNICATION TECHNOLOGY
Publisher : Universitas Sebelas Maret (UNS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/jeeict.3.1.49818

Abstract

At present, some popular messaging applications have evolved specifically with bots starting to emerge into development. One of the developments of chatbots is to help humans booking flight with Named Entity Recognition in the text, trace sentences to detect user intentions, and respond even though the context of the conversation domain is limited. This study proposes to conduct analysis and design chatbot interactions using NLU (Natural Language Understanding) with the aim that the bot understands what is meant by the user and provides the best and right response. Classification using Support Vector Machine (SVM) method with (erm Frequency-Inverse Document Frequency (TF-IDF) feature extraction is suitable combination methods that produce the highest accuracy value up to 97.5%. Conversation dialogue on chatbots developed using NLU which consists of NER and intent classification then dialog manager using Reinforcement Learning could make a low cost for computing in chatbots.
PENENTUAN NILAI VEKTOR PEWAKIL AWAL PADA ARSITEKTUR JARINGAN SYARAF TIRUAN LVQ UNTUK PENGENALAN WAJAH Devira Anggi Maharani; Mila Fauziyah; Denda Dewatama
SENTIA 2015 Vol 7, No 2 (2015)
Publisher : SENTIA 2015

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (696.612 KB)

Abstract

Artificial Neural Network (ANN) has special ability to do recognition of large, dynamic, and non-linar system through learning technique which could not be done by face recognition system using mathematical formulation methods. In this application, face recognition technique needs number of dynamic dimensions for the determination of model in this system. Therefore, mathematical methods are often not effective to resolve these problems. In the development of technology about face recognition, artificial neural network continues to develop, particularly in terms of fast and reliable. One type of familiar and commonly applied artificial neural network is Learning Vector Quantization (LVQ). This research will use LVQ as method of face recognition because the training process is relatively faster than other methods of ANN. To improve the reliability of this method, the determination of initial weight in training process will be one of reference to provide a good level of accuracy and make this system convergent with faster time. System used in this research is a face image 100 x 100 pixel as matrix input, alpha values at interval of 0.1 in the 0.1-0.9 range, 1000 maximum epoch, 2 layers (input layer and output layer), initial weight data each class (10 classes), and LVQ can reach the highest recognition rate of 4 technique of weight value determination that achieves up to 100%.
Co-Authors Dewatama, Denda Mila Fauziyah PERMATASARI, DINDA AYU