Claim Missing Document
Check
Articles

The Application of ANN Predicts Students' Understanding of Subjects During Online Learning Using the Backpropagation Algorithm at SMAN 1 Perbaungan rendiarno, rendiarno; Fahmi, Hasanul
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 1 No. 3 (2022): June 2022
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (534.212 KB) | DOI: 10.59934/jaiea.v1i3.87

Abstract

This study is a study to predict the level of students' understanding of the subjects given by educators at SMAN 1 Perbaungan. This study aims to determine how far the level of understanding of students in understanding lessons, especially during the current covid-19 pandemic, which is a process of teaching and learning activities carried out from their respective homes or using online learning media. The method used is an artificial neural network with Backpropagation algorithm with variables used are knowledge values, skill scores, mid-semester exam results, end-semester exam results, and attitude scores. The five variables are used to support predicting the level of student understanding of the subject using the single layer Backpropagation Algorithm. The architectural model used is 5-2-1 with a success accuracy of 85%. The smaller the error value that is close to 0, the smaller the deviation of the results of the Artificial Neural Network with the desired target.
EXPERT SYSTEM FOR HYPOTHYROIDISM DIAGNOSIS USING CASE BASED REASONING METHOD (CASE STUDY OF MELATI II Public Health Center) rimanti, dewinda; Fahmi, Hasanul
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 1 No. 3 (2022): June 2022
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (887.738 KB) | DOI: 10.59934/jaiea.v1i3.88

Abstract

In this study, we will discuss the development of an expert system application for diagnosing Hypothyroidism. In diagnosing Hypothyroidism, this expert system will use the Case-Based Reasoning (CBR) method. CBR uses artificial intelligence in solving problems based on knowledge from previously stored cases. Case data was obtained from medical records from the results of handling Hypothyroidism patients diagnosed by internal medicine specialists. There are 5 types of hypothyroidism disease with one symptom of the disease in the old case. And there are new cases that will be used to calculate the similarity value to the old cases that exist in the knowledge base owned by the system.
DECISION SUPPORT SYSTEM FOR DETERMINING THE BEST TEACHER USING TOPSIS METHOD (CASE STUDY : SMP NEGERI 1 GALANG) niar, iinvera; Fahmi, Hasanul
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 1 No. 3 (2022): June 2022
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (243.356 KB) | DOI: 10.59934/jaiea.v1i3.89

Abstract

SMP Negeri 1 Galang has activity in determining the best teacher, however, at SMP Negeri 1 Galang the determination of the best teacher still uses the manual method, namely by calculating on paper with a predetermined format. In this case, of course, it takes a long time, considering that there are many junior high school teachers, and also requires many criteria. This is what makes researchers want to conduct research in order to design a decision support system for determining the best teacher using the TOPSIS method at the 1st Galang Junior High School. The Technique for Order Preference by Similarity to Ideal Solution (Topsis) method is one method that is often used in determining a decision, therefore researchers use this method in making a system. With the existence of a decision support system, it can help the school in determining the best teacher, so that the determination of the best teacher can be done accurately and quickly
Penerapan Data Mining Clustering Pada Siswa-Siswi SMK Swasta Jaya Krama Beringin Dalam Menerima Potongan Biaya Administrasi Sekolah Dengan Menggunakan Algoritma K-Means Wika Wahyuni; Fahmi, Hasanul
Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI) Vol. 3 No. 2 (2020): Jurnal Ilmu Komputer dan Sistem Informasi
Publisher : Utility Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.9767/jikomsi.v3i2.49

Abstract

Bantuan potongan biaya administrai sekolah saat ini sangatdibutuhkan oleh keluarga yang kurang mampu karena banyaknyakeluarga yang mengalami ekonomi yang sangat rendah di daerah sekitarkhususnya pada siswa-siswi SMK Swasta Jaya Krama Beringinsehingga, menyebabkan Pihak Sekolah memberikan sebuah bantuanPotongan biaya administrasi sekolah akan tetapi dengan banyaknyajumlah siswa-siswi sekitar 585 orang, sehingga staff keuangan harusmengelompokkan data siapa saja yang berhak mendapatkan potonganbiaya administrasi sekolah, penerapan algoritma K-Means Clusteringsangat dibutuhkan dalam menunjang s ebuah potongan biayaadministrasi sekolah di SMK Swasta Jaya Krama Beringin makadibutuhkan sebuah data mining clustering, dengan adanya penerapanMetode K-Means Clustering tersebut agar dapat memudahkan StaffAdministrasi dalam proses pendataan data siswa-siswi penerimapotongan biaya administrasi sekolah, Sehingga dapat mempermudahKepala Sekolah dalam menentukan siswa-siswi yang berhakmendapatkan potongan biaya administrasi sekolah.
Penerapan Data Mining Pada Penjualan Kartu Paket Internet Yang Banyak Diminati Konsumen Dengan Metode K-Means Turnip, Hendra Nicodemus; Fahmi, Hasanul
Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI) Vol. 4 No. 2 (2021): Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI)
Publisher : Utility Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.9767/jikomsi.v4i2.135

Abstract

Currently, Royal Ponsel has a problem where to determine which internet package card consumers are most interested in from selling internet cards Telkomsel, XL, Axis, Im3, 3 (Tri), and Smartfren. A lot of information is owned but it is not enough if the information is not utilized properly, so it is necessary to group sales data to determine the competitiveness of which internet card products have the highest sales level based on sales in the Royal Ponsel business. Of course, this problem requires a technology that can analyze data on internet package card sales transactions. One of them is by applying data mining to the sale of internet package cards which are in great demand by using the K-Means Clustering method calculation. With the existence of grouping types of internet cards that are used to improve the performance of sales so as to determine the steps to increase stock on internet package cards appropriately.
Penerapan Sistem Pakar Mendiagnosa Kerusakan Sepeda Motor Automatic Dan Injeksi Berbasis Android Dengan Metode Forward Chaining Sihombing, Darvin Markus; Fahmi, Hasanul
Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI) Vol. 4 No. 2 (2021): Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI)
Publisher : Utility Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.9767/jikomsi.v4i2.144

Abstract

Motorbikes are a means of transportation that is widely used by Indonesians, therefore knowledge about motorbikes, especially if there is damage, needs to be controlled by the user. The system that was developed to diagnose motorcycle damage is called an automatic motorcycle failure diagnosis system and injection. The purpose of this research is to develop a diagnosis system for automatic motorcycle damage and injection, which uses the Forward Chaining method where the steps are carried out using basic data and certain rules or codes to build a knowledge base in the form of rules used in diagnosing automatic motorcycle damage and injection. . Method stages starting from assessment, knowledge acquisition, design, testing, documentation and maintenance. Based on the steps that have been carried out, a prototype system for automatic motorcycle damage diagnosis and injection is obtained using the Android Studio programming language. This expert system provides facilities in the form of a page containing the automatic motorcycle damage diagnosis system and injection, then a damage list page, then the user can consult about automatic motorcycle damage and injection according to the symptoms, so the system will display the results of diagnosing automatic motorcycle damage. and injection in the form of the name of the vehicle damage and its solution.
Analisis Sistem Pakar Dengan Metode Forward Chaining untuk Pengenalan Jenis Kulit Wajah pada Manusia Sulindawaty, Sulindawaty; Fahmi, Hasanul
Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI) Vol. 5 No. 2 (2022): Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI)
Publisher : Utility Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55338/jikomsi.v5i2.336

Abstract

Wajah merupakan hal utama yang menjadi perhatian maupun daya tarik bagi sesorang dalam berpenampilan. Kulit wajah yang sehat dan bersih menjadi hal yang sangat didambakan oleh manusia. Keberagaman produk kosmetik serta praktik kecantikan menjadi salah satu yang sangat diminati untuk memberikan solusi kesehatan dan kecantikan kulit wajah. Untuk mempermudah setiap orang dalam mengenali jenis kulit wajah, dapat diterapkan sistem pakar dengan menggunakan metode forward chaining. Sistem Pakar dapat memberikan solusi dalam menganalisis jenis kulit wajah karena pada sistem ini data yang diperoleh dari para pakar secara langsusng. Forward chaining digunakan untuk menelusuri jenis kulit wajah berdasarkan penalaran atau pelacakan suatu data dari fakta-fakta yang diperoleh untuk mendapatkan kesimpulan. Dari pengujian yang dilakukan dalam penelitian ini menunjukkan nilai akurasi sebesar 83,3% yang menunjukkan hasil sesuai dengan diagnosa pakar. Hasil penelitian ini menunjukan bahwa sistem pakar dengan menerapkan metode backward chaining efektif dalam menghasilkan informasi untuk mengetahui jenis kulit wajah pada manusia sehingga dapat melakukan perawatan maupun memilih jenis kosmetik yang sesuai.
Deblurring Photos With Lucy-Richardson And Wiener Filter Algorithm In Rgba Color Rustam, Michiavelly; Fahmi, Hasanul; Herry Utomo, Wiranto
Journal of Comprehensive Science Vol. 3 No. 3 (2024): Journal of Comprehensive Science (JCS)
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/jcs.v3i3.655

Abstract

Photographers and social media influencers create engaging posts every day to captivate their audience with engaging content.Central to success is the need for high-quality images that allow the viewer to clearly perceive and engage with the information being conveyed. However, a persistent challenge in the field of photography is that hand tremors during image capture can result in accidentally blurred photos. In response, I propose a comprehensive solution that leverages the advanced Lucy-Richardson (L-R) and Wiener filter algorithms.This innovative approach is tailored to reduce the effects of blur caused by unstable handling, allowing for sharper, noise-free images. By incorporating these cutting-edge algorithms into their workflows, creators can not only reduce the frustration of blurry footage, but also increase the overall visual impact of their posts, foster deeper connections with their viewers, and create dynamic setting a new standard of excellence in a global world.
Digital Signature Trends and Forecast (2021 – 2022) for Indonesian Government Affairs Gerhard T, Jonathan; Fahmi, Hasanul
Eduvest - Journal of Universal Studies Vol. 5 No. 8 (2025): Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v5i8.51005

Abstract

Since 2018, the Indonesian government has issued a policy regarding Electronic-Based Government Systems. One of the steps taken is to transform documents into electronic documents. The security aspect that can be applied to electronic documents is the digital signature. After the enactment of this policy, digital signature users and transactions have increased. Increasing dynamic electronic signature transactions needs more attention. To deal with this increase in usage, anticipating and predicting the trends in digital signature usage is crucial. Trends prediction data can be used to consider capacity planning of infrastructure resources and improving user experience. The Prophet algorithm is a forecasting tool that has the ability for robust handling of time series data with strong seasonal patterns. The prophet algorithm can analyze patterns in digital signature transactions by accommodating irregular time series. Our research uses a comprehensive set of the Indonesian government’s digital signature transactions over a period of time. This dataset contains seasonal trends, like holidays, weekends, and special events. This condition makes the dataset fluctuate. This research aims to forecast trends and seasonality of digital signature transaction volumes in the future. This research demonstrates the implementation of the Prophet algorithm to digital signature transaction data. It is hoped that the forecasting data resulting from this research can be used as a model in the digital signature sector. Then this model can be used to determine infrastructure resource allocation.
Handling Long Sequences in BERT for Question Answering Systems Pratama, Andreyanto; Fahmi, Hasanul
Eduvest - Journal of Universal Studies Vol. 5 No. 8 (2025): Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v5i8.51006

Abstract

The Question Answering System is an important component of Natural Language Processing applications, allowing for efficient information processing and improving user experience. Despite the fact that BERT has provided additional work in QA tasks, the fact that it only supports up to 512 tokens has reduced its effectiveness in large-scale scenarios. This study addresses the problem by introducing a new algorithm that integrates hierarchical and dynamic memory networks with BERT. The method used to collect broad contexts into chunks that may be used for independent research, ensuring that no important information is missing. The dynamic memory module integrates and stores information in real time throughout the system, allowing for comprehensive context understanding. Depending on the SQuAD v2.0 dataset, the model achieved an Exact Match score of 78.10% and an F1 score of 87.27%. The F1-score value of standard BERT with a value of 81.9% increased to 87.27% with this approach. This research investigated the potential of structured and memory networks to overcome the weaknesses of BERT, provide solutions, and adapt to QA tasks.