Berita telah menjadi konsumsi masyarakat setiap harinya, namun tidak semua berita yang beredar merupakan berita yang valid kebenarannya. Berita palsu dapat menggiring opini publik, dan berisiko terhadap keselamatan bangsa. Oleh karena itu diperlukan klasifikasi berita palsu untuk dapat meredamkan berita palsu yang beredar pada masyarakat. Penelitian sebelumnya telah dilakukan klasifikasi berita palsu menggunakan model <em>Recurrent Neural Network</em> (RNN) yaitu <em>Long Short-Term Memories</em> (LSTM), dengan nilai F1 sebesar 0,24 dan menyarankan untuk mencari parameter model sistem yang tepat agar dihasilkan kinerja model yang lebih baik. Maka pada penelitian ini dilakukan klasifikasi berita palsu berbahasa Indonesia dengan menggunakan perbandingan model <em>Recurrent Neural Network</em> yaitu LSTM dan <em>Gated Recurrent Unit</em> (GRU), serta mencari parameter terbaik untuk menghasilkan hasil kinerja klasifikasi paling optimal. Data yang digunakan merupakan berita mengenai kejadian yang terjadi di Indonesia dan berbahasa Indonesia. Didapatkan nilai parameter <em>epochs</em>: 15, fungsi <em>optimizer gradient descent</em> yaitu <em>rmsprop</em>, dan <em>batch_size</em>: 64 untuk mendapatkan kinerja optimal dalam klasifikasi berita palsu menggunakan metode LSTM. Nilai akurasi yang dihasilkan oleh model yaitu 73% untuk metode LSTM dan 64% dengan menggunakan metode GRU
Learning modality is the sensory sensitivity of the individual when receiving, storing, and conveying information. Each individual has a personal character and varied sex that influences the type of learning modality. Learning modality consists of four types of visual, auditorial, read-write and kinesthetic (VARK). To measure students’ learning modalities preference was used VARK Questionnaire 7.1 which contained 16 standard questions through paper media. Paper media is less efficient and effective both in the dissemination and analysis of questionnaires results based on study program and sex, because it made the application of determinants of student-based learning modalities modality using Research and Development (R&D) method with PHP programming language and MySQL database, this application features a percentage analysis of students’ learning modalities preference based on study program and sex. This application aims to facilitate the students to know the analysis of modal preference results in accordance with the rules of the limit of the difference of points specified and can display the percentage of overall learning modalities based on sex in accordance with the study program. Based on the results of application acceptance test by students of Faculty of Communication and Informatics Muhammadiyah University of Surakarta known as many as 87% of respondents agreed that the application determinants of learning modalities preference can present information and determine the preferences of learning modalities, easy to use and looks interesting.
Perekomendasian oli secara manual, tanpa menggunakan perhitungan yang akurat cenderung bersifat subyektif serta cukup sulit mengenali karakteristik oli yang paling tepat untuk jenis motor tertentu. Proses analisis data transaksi secara manual berdasarkan pada pengamatan akan mempengaruhi kualitas mesin. Sebagai contoh untuk memberikan rekomendasi oli terbaik bagi seorang konsumen, maka sebuah perusahaan/bengkel sepeda motor harus melihat data transaksi ganti oli yang lalu untuk mendapatkan data tentang oli yang digunakan untuk mengganti oli motor konsumen tersebut. . Penggunaan perangkat komputer dapat digunakan sebagai pendukung keputusan menjadi lebih cepat, tepat, dan akurat. Proses perekomendasian oli terbaik bagi kendaraan bermotor menggunakan metode fuzzy. Hasil perhitungan diperoleh direkomendasikan A3=0.72, A2 = 0.66, A1= 0.55, A4= 0.40.
Psoriasis is characterized by hyperkeratosis and thickening of the epidermal layer followed by an increase in vascularity and infiltration of inflammatory cells to the dermis, as a result of this process the scales appear, erythema and induration. In the field of health, identification and image analysis can be used as a conclusion to support expert decisions such as identification of tumors, cancers or other diseases including Psoriasis. Ant Colony Optimization (ACO) algorithms are the most successful and widely recognized algorithmic techniques based on ant behaviours. These algorithms have been applied to numerous problems; moreover, for many problems ACO algorithms are among the current high performing algorithms. The goal of this research is to develop a detection emphasize on the contour detection of Psoriasis using ACO. By using the parameters of the Pheromone intensity control values (α), the visibility (β), Evaporation coefficient of pheromone intensity (ρ) and the constant Q the results show that this method is can detect the contour an image of psoriasis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.