Kusmanto Kusmanto
Universitas Al Washliyah Labuhanbatu, Rantauprapat

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

Model Pengenalan Suara Teks Bebas Menggunakan Algoritma Support Vector Machine Muhammad Bobbi Kurniawan Nasution; Kusmanto Kusmanto; Sudi Suryadi; Ronal Watrianthos
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 4, No 4 (2020): Oktober 2020
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v4i4.2436

Abstract

Voice authentication can be done because there are physical differences in the voice production organs of each person. The user's spoken sound pattern can be used as a voice command as desired. Some features such as accents, intonation, and the way pronunciation produce different patterns. For identification verification, voice data is divided into two groups: voice with defined text and voice with free text. Sounds resulting from the pronunciation of a particular word can be changed from analog to digital form. This change process will result in representation in vector form. One technique in voice recognition classification is the Support Vector Machine (SVM). The study aims to develop SVM algorithms to create free text-based speech patterns, recognition models. The sound pattern classification process uses three kernels for the data set so that the comparison results will be more accurate. The highest accuracy in the linear kernel is found in the 4th loop in the third fold with an accuracy rate of 94.40%. While in the polynomial kernel the highest accuracy at the 6th iteration of the second fold with an accuracy of 96.80%. The highest accuracy rate is found in the RBF kernel on the 8th loop of the third fold with 98.20% accuracy. These test results prove the RBF kernel has the best level of accuracy in free text-based speech recognition.
Analisa Penerapan Metode Operational Competitiveness Rating Analysis (OCRA) dan Metode Multi Attribute Utility Theory (MAUT) Dalam Pemilihan Calon Karyawan Tetap Menerapkan Pembobotan Rank Order Centroid (ROC) Abdul Karim; Shinta Esabella; Kusmanto Kusmanto; Mesran Mesran; Uswatun Hasanah
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 5, No 4 (2021): Oktober 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v5i4.3265

Abstract

For companies, employees are an important aspect that must be supported by quality human resources. In the selection of permanent employees, usually the leadership in a company conducts an objective selection process in accordance with predetermined criteria. However, leaders often face several problems in this process, such as the selection is carried out in stages so that it takes a long time and the assessment of prospective employees is still done manually, making mistakes often occur. Therefore, a decision support system is needed as a solution to these problems by applying a comparison of the Operational Competitiveness Rating Analysis (OCRA) method and the Multi Attribute Utility Theory (MAUT) method and the weighting obtained by the Rank Order Centroid (ROC) method. The test results obtained the best alternative that is considered feasible as a permanent employee is in the same alternative, namely A5 on behalf of Risa Sabrani. The OCRA method produces the best preference value of 1.56 while the MAUT method produces the best preference value of 0.456 as the first rank
Implementation Naïve Bayes Classification for Sentiment Analysis on Internet Movie Database Samsir Samsir; Kusmanto Kusmanto; Abdul Hakim Dalimunthe; Rahmad Aditiya; Ronal Watrianthos
Building of Informatics, Technology and Science (BITS) Vol 4 No 1 (2022): Juni 2022
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (376.705 KB) | DOI: 10.47065/bits.v4i1.1468

Abstract

A film review is a subjective opinion of someone who has different feelings about each film. As a result, film enthusiasts will struggle to assess whether the film meets their requirements. Based on these issues, sentiment analysis is the best way to fix them. Sentiment analysis, also known as opinion mining, is the study of assigning views or emotional labels to texts in order to determine if the text contains positive or negative thoughts. The Nave Bayes method was chosen because it can classify data based on the computation of each class's probability against objects in a given data sample. The best model was created utilizing data without lemmatization, 500 vector sizes, and Nave Bayes classification, with an accuracy of 78.96 percent and a f1-score of 78.81 percent. Changes in vector size affect the system's capacity to foresee positive and negative sentiments. The difference in accuracy and recall values shows that when vector size 300 is utilized, the precision and recall outcomes are lower than when vector size 500 is used.