Claim Missing Document
Check
Articles

Found 3 Documents
Search

Klasifikasi Bahan Biodegradable dan Non-Biodegradable Menggunakan Convolutional Neural Network (CNN) Latief, Muhammad Abdul; Azfa Riyyasy, Muhammad Rasikh; Ulya, Fadilla Zundina; Puspita, Popy Laras; Claudia, Gavrilla; Nabila, Luthfi Rakan
STRING (Satuan Tulisan Riset dan Inovasi Teknologi) Vol 8, No 3 (2024)
Publisher : Universitas Indraprasta PGRI Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/string.v8i3.19314

Abstract

Deep Learning is a new scientific field in the field of Machine Learning which has recently developed. Deep Learning has excellent capabilities in computer vision. One of its uses is in the case of classifying objects into biodegradable and non-biodegradable materials. By implementing the CNN method in this case, it is possible to classify biodegradable and non-biodegradable waste appropriately and efficiently. This study uses image data of biodegradable and non-biodegradable materials sourced from Kaggle. The stages in this study consist of six stages. The first stage is to retrieve the dataset. The second stage is the preprocessing stage by rescaling the image. The third stage is to create a CNN model. The fourth stage is model training to get higher accuracy. The fifth stage is model evaluation and the last is testing the model. From the classification test using the CNN method, an accuracy of 93% is obtained. So it can be concluded that the CNN method used in this paper is capable of performing a good classification.
ANALISA APLIKASI KONSEP ARSITEKTUR INDUSTRIAL PADA BANGUNAN PARKIR, STADION ESPORTS, DAN KANTOR GOOGLE (Studi Kasus : The Amazing VW Autostadt, Stadium Esports Arlington, dan Kantor Google) Latief, Muhammad Abdul; Ramadhan, Bayu; Ardiansyah, Ridho
PURWARUPA Jurnal Arsitektur Vol 6, No 2 (2022): Purwarupa Vol 6 No 2 September 2022
Publisher : Arsitektur UMJ

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24853/purwarupa.6.2.25-32

Abstract

ABSTRAK. Peningkatan jumlah kendaraan yang parkir diruas jalan mengakibatkan kemacetan, kurangnya sarana dan wadah yang disediakan bagi atlet esport di Indonesia, sampai peningkatan persahaan-perusahaan baru yang membutuhkan tempat. Keingintahuan akan pengaplikasian prinsip arsitektur industrial pada bangunan Gedung Parkir, Esport Stadium dan Kantor Google menjadi alasan dilakukannya penelitian ini. Metode penelitian ini menggunakan metode literatur yang dimana semua data yang dikumpulkan bersumber dari internet dan buku – buku yang membahas tentang Arsitektur Industrial. Dan penelitian ini menganalisis konsep Arsitektur Industrial dari 3 aspek, yang pertama dari aspek penerapan wujud geometric disiplin, yang kedua aspek susunan rangka terbuka, dan yang ketiga kejujuran material. Dimana aspek – aspek tersebut dianalisis dari ketiga obyek bangunan tersebut. Pengaplikasian konsep industrial pada ketiga bangunan tersebut didasari dari prinsip – prinsip arsitektur industrial, yaitu harus memiliki sifat bersih (clean) dan rapi (discipline), dan diwujudkan pada elemen arsitektur berupa bidang, dapat berupa bidang dinding, bidang, lantai, bidang langit-langit, dan bidang atap dengan menggunakan bentuk-bentuk dasar geometrik. Kata Kunci: Arsitektur Industrial, Gedung Parkir, Stadion Esports, Kantor Google, Material, Struktur, Warna ABSTRACT. The increase in the number of vehicles parked on the road causes congestion, lack of facilities and containers provided for esports athletes in Indonesia, to an increase in new companies that need a place. Curiosity about the application of industrial architectural principles in the Parking Building, Esport Stadium and Google Office buildings is the reason for doing this research. This research method uses the literature method in which all the data collected is sourced from the internet and books that discuss Industrial Architecture. And this study analyzes the concept of Industrial Architecture from 3 aspects, the first is from the aspect of applying the geometric form of the discipline, the second is the aspect of the open frame arrangement, and the third is material honesty. Where these aspects are analyzed from the three objects of the building. The application of industrial concepts to the three buildings is based on the principles of industrial architecture, which must have clean and neat characteristics (discipline), and is manifested in architectural elements in the form of fields, which can be in the form of walls, planes, floors, ceiling planes, and the roof plane by using basic geometric shapes. Keywords: Industrial Architecture, Parking Building, Esports Stadium, Google Office, Material, Structure, Color
Dimension-Expanding MLP in Transformer: Inappropriate Sentences and Paragraph Digital Content Filtering Wardhana, Ariq Cahya; Yunus, Andi Prademon; Adhitama, Rifki; Latief, Muhammad Abdul; Sofia, Martryatus
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.627

Abstract

The creation of digital content is now a pivotal element of today’s digital environment, driven by the need for both individuals and organizations to engage audiences effectively. As digital platforms grow in scope and impact, ensuring the security, professionalism, and appropriateness of user-generated content has become crucial. This study introduces a new approach for filtering inappropriate digital content by integrating dimension-expanding multi-layer perceptions (MLPs) into transformer architectures. The dimension-expanding MLP processed more high-dimensional features in the Transformers network, giving the ability to understand more specific contexts. Experimental findings reveal that the proposed model outperforms Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), Transformer (Baseline) in accuracy, computational efficiency, and scalability. The research highlights the model’s practical applications in areas like social media content moderation, legal document compliance monitoring, and filtering harmful content in e-learning and gaming platforms with 0.744 accuracy.