Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal JOURNAL OF SCIENCE AND SOCIAL RESEARCH Journal of Innovative and Creativity
Muhammad Ridho
Universitas Asahan
Computer Science & IT Economics, Econometrics & Finance Education Languange, Linguistic, Communication & Media Mathematics Social Sciences Other

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

Found 2 Documents
Search

 1 
Penerapan Teknologi Kecerdasan Buatan: Studi Komparatif Computer Vision Dan Sistem Pakar Di Era Digital Adellia Nur Annisa; Bagus Tata Abdillah; Muhammad Ridho; Ratu Salsabilah; Dicky Apdilah
Journal of Innovative and Creativity (Joecy) Vol. 6 No. 2 (2026)
Publisher : Fakultas Ilmu Pendidikan Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The development of Artificial Intelligence (AI) technology has transformed operational paradigms across various sectors of human life in the 21st century. Among the diverse branches of AI, Computer Vision (CV) and Expert Systems stand as two of the most widely implemented technological pillars, yet they possess starkly contrasting operational characteristics. This study aims to conduct an in-depth comparative analysis regarding the effectiveness, architecture, opportunities, and implementation challenges of both Computer Vision and Expert System technologies in the digital era. The method employed in this research is a comparative Systematic Literature Review (SLR), analyzing secondary data from 16 reliable sources including national journals, international journals, and recent academic modules. The data analysis process focuses on three main dimensions: system architectural methodology, functional efficiency in problem-solving, and the multidimensional impacts on the education, business, security, and user health sectors. The results indicate that Computer Vision excels in processing unstructured data (such as real-time images and videos) based on neural models (Convolutional Neural Network), but demands high computational power and poses a user health risk in the form of Computer Vision Syndrome. On the other hand, Expert Systems excel in declarative knowledge representation based on logical rules (rule-based) for deterministic, structured, and infrastructure-efficient decision-making, though they remain rigid against dynamic data changes. In conclusion, these two technologies are not mutually exclusive but rather complementary; integrating both into a Hybrid AI system represents the future direction for creating autonomous systems that are not only capable of visual perception but also capable of cognitive reasoning.
KLASIFIKASI TIPE KACA MENGGUNAKAN METODE K-NEAREST NEIGHBOR Muhammad Azwar Al Ayyub; Weny Nur Afdilla Simangunsong; Dini Farhatun; Emi Dea; Selfina Agustin; Zulfa Ar Rahman; Muhammad Ridho
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 1 (2026): February 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i1.5745

Abstract

Abstract: Glass is a material that is widely used in various fields, such as construction, the automotive industry, and household appliances. Each type of glass has different characteristics based on its chemical composition and production process. Problems arise when the process of identifying glass types is still done manually, which is time-consuming, costly, and prone to error. This study aims to apply the K-Nearest Neighbor (K-NN) method in classifying glass types based on their chemical content attributes. The data in this study was sourced from Kaggle, namely the Glass Identification Dataset. The data used consisted of several chemical features, such as Na, Mg, Al, Si, K, Ca, Ba, and Fe, with seven categories of glass classes. The results showed that the K-NN method was able to classify glass types well and could be an effective solution to assist in the automatic glass identification process. Keyword: Classification, K-Nearest Neighbor, Data Mining, Types of Glass. Abstrak: Kaca merupakan material yang banyak digunakan dalam berbagai bidang, seperti konstruksi, industri otomotif, dan peralatan rumah tangga. Setiap jenis kaca memiliki karakteristik yang berbeda berdasarkan komposisi kimia dan proses produksinya. Permasalahan muncul ketika proses identifikasi jenis kaca masih dilakukan secara manual, sehingga membutuhkan waktu, biaya, dan berpotensi menimbulkan kesalahan. Penelitian ini bertujuan untuk menerapkan metode K-Nearest Neighbor (K-NN) dalam mengklasifikasikan jenis kaca berdasarkan atribut kandungan kimianya. Data dalam penelitian ini bersumber dari Kaggle, yaitu Glass Identification Dataset. Data yang digunakan terdiri dari beberapa fitur kimia, seperti Na, Mg, Al, Si, K, Ca, Ba, dan Fe, dengan tujuh kategori kelas kaca. Hasil penelitian menunjukkan bahwa metode KNN mampu mengklasifikasikan jenis kaca dengan baik dan dapat menjadi solusi yang efektif untuk membantu proses identifikasi kaca secara otomatis. Kata kunci: Klasifikasi, K-Nearest Neighbor, Data Mining, Jenis Kaca.
Co-Authors Adellia Nur Annisa Bagus Tata Abdillah Dicky Apdilah Dini Farhatun Emi Dea Muhammad Azwar Al Ayyub Ratu Salsabilah Selfina Agustin Weny Nur Afdilla Simangunsong Zulfa Ar Rahman