Article Per Year (5 Year)
p-Index From 2021 - 2026
6.062
P-Index
This Author published in this journals
All Journal Proceedings of KNASTIK Bulletin of Electrical Engineering and Informatics Prosiding Seminar Nasional Sains Dan Teknologi Fakultas Teknik Jurnal Teknologi Informasi dan Ilmu Komputer Telematika JUITA : Jurnal Informatika Jurnal Ilmiah Dinamika Rekayasa (DINAREK) Jurnal Eksplora Informatika Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal EDUMATIC: Jurnal Pendidikan Informatika Jurnal Abdi Insani Jurnal Teknik Informatika (JUTIF) Journal of Applied Data Sciences Jurnal Pendidikan dan Teknologi Indonesia Jurnal Pengabdian Masyarakat Indonesia JUSTIN (Jurnal Sistem dan Teknologi Informasi) Pamasa: Jurnal Pengabdian kepada Masyarakat Journal of Electronics Technology Exploration (JOeTEx) Mengabdi: Jurnal Hasil Kegiatan Bersama Masyarakat Journal of Industrial and Mechanical Engineering Journal of Current Research in Blockchain
Lasmedi Afuan
Informatika, Fakultas Teknik, Universitas Jenderal Soedirman, Indonesia
Agriculture, Biological Sciences & Forestry Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Mechanical Engineering Public Health Social Sciences Other

Published : 46 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 46 Documents
Search

 1   2   3   4   5 
OPTIMIZATION OF THE K-NEAREST NEIGHBORS ALGORITHM USING THE ELBOW METHOD ON STROKE PREDICTION Febri Sutomo; Daffa Ammar Muaafii; Daffa Naufaldi Al Rasyid; Yogiek Indra Kurniawan; Lasmedi Afuan; Teguh Cahyono; Eddy Maryanto; Dadang Iskandar
Jurnal Teknik Informatika (Jutif) Vol. 4 No. 1 (2023): JUTIF Volume 4, Number 1, February 2023
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2023.4.1.839

Abstract

Stroke is the second most deadly disease in the world according to WHO. The sufferer has an injury to the nervous system. Because of this, health experts, especially in the field of nursing, need special attention. Technological advances continue to change over time so that information needs are needed in life. Currently the data on stroke sufferers is extensive enough so that adequate information presentation techniques are needed so that the information received is very accurate and in accordance with user needs. Therefore, it is necessary to process data mining on stroke patient data to obtain useful information for users. This study aims to prove the performance of the Elbow Method to produce the optimum k value in the stroke prediction data using the K-Nearest Neighbors (KNN) algorithm. The optimum k value is generated from the Elbow Method which is executed with the Google Collaboratory using the Python programming language. The test results show that the Elbow Method produces the optimum k value at k = 7. The KNN model that uses the optimum k value from the Elbow Method can increase the accuracy and precision values ​​reaching 6% and 0.12, respectively.
IMPLEMENTATION OF PARTICLE SWARM OPTIMIZATION IN K-NEAREST NEIGHBOR ALGORITHM AS OPTIMIZATION HEPATITIS C CLASSIFICATION Susi Setianingsih; Maria Ulfa Chasanah; Yogiek Indra Kurniawan; Lasmedi Afuan
Jurnal Teknik Informatika (Jutif) Vol. 4 No. 2 (2023): JUTIF Volume 4, Number 2, April 2023
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2023.4.2.980

Abstract

Hepatitis has become a public health problem that is generally caused by infection with the hepatitis virus. One type of hepatitis caused by a virus is Hepatitis C. This disease can cause patients to experience inflammation of the liver. In the worst conditions, it can even lead to death. Initial predictions need to be made to increase the awareness of each individual against the threat of Hepatitis C by using the K-Nearest Neighbor method. K-Nearest Neighbor is a classification method that can give a pretty good percentage result in classifying, especially when using large training data. However, K-Nearest Neighbor still has a weakness, namely the determination of the value of K that is less precise so that it can reduce classification performance. To overcome these shortcomings, the researchers used the implementation of Particle Swarm Optimization on K-Nearest Neighbor to find the optimal K value. The existence of this implementation is expected to be able to increase the value of accuracy in classification and overcome solutions to weaknesses in the K-Nearest Neighbor algorithm. From the results of the K-Nearest Neighbor test, the accuracy value is 97.24% at K=5 and K=3. As for the results of testing the implementation of Particle Swarm Optimization on the K-Nearest Neighbor, there was an increase in the accuracy value of 2.07% to 99.31%. This test shows that the implementation of PSO can overcome the shortcomings of KNN and this model can be used as the best solution to determine the classification of Hepatitis C disease.
Sistem Pendataan Mahasiswa Dan Dosen di Program Studi Informatika Universitas Jenderal Soedirman Berbasis Website Muhammad Zein Albalki; Muhammad Difi Luthfi; Anin Ammbya Soulani; Yogiek Indra Kurniawan; Teguh Cahyono; Lasmedi Afuan
Jurnal Pendidikan dan Teknologi Indonesia Vol 3 No 5 (2023): JPTI - Mei 2023
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.288

Abstract

Salah satu universitas negeri yang ada di Indonesia yaitu Universitas Jenderal Soedirman. Salah satu program studi yang ada di Universitas Jenderal Soedirman adalah program studi Informatika. Setiap tahun, program studi Informatika menerima mahasiswa baru yang jumlahnya tidak sedikit. Dengan banyaknya data ini, kebutuhan akan akses informasi data mahasiswa dan dosen pun menjadi tinggi. Setiap dosen dan mahasiswa ingin mengetahui dengan mudah dosen atau mahasiswa yang ada di program studinya. Dalam kasus ini, sistem informasi pendataan mahasiswa dan dosen akan dapat membantu mengatasi masalah tersebut sehingga dapat didata dan dimanage dengan mudah. Sistem ini terdiri dari beberapa menu seperti menu dashboard, data dosen, data mahasiswa dan mahasiswa bimbingan. Uji blackbox yang dilakukan menunjukan hasil valid yang berarti sudah dibuat sesuai dengan yang diharapkan. Pada uji compability pun hanya satu web browser dari empat web browser yang diuji mengalami lag yang menunjukan performa cukup baik di berbagai browser. Selain itu, hasil dari User Acceptance Test menunjukan nilai rata-rata 86.3% dengan kategori "Sangat Baik". Sistem ini dapat membantu masalah pendataan mahasiswa yang ditunjukan dengan semakin mudahnya dosen maupun mahasiswa dalam memanage dan mengetahui data dosen dan mahasiswa di program studi Informatika.
Rancang Bangun Sistem Informasi Pengelolaan Pendadaran Menggunakan Framework Laravel lasmedi afuan; Nofiyati Nofiyati; Ahmad Fauzi Ridlwan
JUSTIN (Jurnal Sistem dan Teknologi Informasi) Vol 10, No 1 (2022)
Publisher : Jurusan Informatika Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (991.984 KB) | DOI: 10.26418/justin.v10i1.45678

Abstract

Salah satu kegiatan yang harus diikuti oleh mahasiswa tingkat akhir untuk memperoleh gelar sarjana S1 adalah Pendadaran. Pendadaran di Fakultas Teknik Universitas Jenderal Soedirman (UNSOED) terdiri dari beberapa proses yaitu pendaftaran, penjadwalan pendadaran, dan pengelolaan nilai. Permasalahan yang terjadi dalam pengelolaan proses pendadaran di Fakultas Teknik UNSOED adalah pengelolaan pendadaran pada proses–proses tersebut dilakukan dengan mencatat data dalam buku dan papan tulis. Hal ini menyebabkan proses pengelolaan pendadaran menjadi kurang efektif dan efisien, kekurangan tersebut akan mempersulit kinerja dari staff bapendik, dan dalam hal ini tentunya akan menghambat bagi dosen penguji dan mahasiswa. Untuk mengatasi permasalahan tersebut, penelitian ini telah mengembangkan sebuah sistem informasi pengelolaan pendadaran (SIPENDAR) di Fakultas Teknik UNSOED. Ada beberapa tahapan yang dilakukan dalam pengembangan SIPENDAR yaitu pengumpulan data, analisis dan perancangan, tahapan pengembangan SIPENDAR, dan pengujian sistem informasi. Pengembangan SIPENDAR menggunakan framework Laravel dan menggunakan MySQL sebagai Database Management System. Pengujian dilakukan menggunakan pengujian blackbox dan Mean Opinion Score. Dari hasil pengembangan dan pengujian dapat disimpulkan bahwa SIPENDAR dapat digunakan untuk mempermudah dalam proses pengelolaan pendadaran di Fakultas Teknik UNSOED.
Pengelompokan Prioritas Negara Yang Membutuhkan Bantuan Menggunakan Clustering K-Means dengan Elbow Dan Silhouette Yogiek Indra Kurniawan; Priandika Ratmadani Anugrah; Rochmat Mulyo Sugihono; Faris Akbar Abimanyu; Lasmedi Afuan
Jurnal Pendidikan dan Teknologi Indonesia Vol 3 No 10 (2023): JPTI - Oktober 2023
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.343

Abstract

Sistem kesehatan mencakup personal, lembaga, komoditas, informasi, pembiayaan, dan strategi pemerintah dalam memberikan layanan kesehatan kepada Masyarakat dengan tujuan untuk memenuhi kebutuhan dan harapan masyarakat secara adil dan merata. Status kesehatan masyarakat penting untuk meningkatkan kualitas sumber daya manusia dan produktivitas dari sebuah negara. LSM kemanusiaan HELP International memilih negara-negara yang membutuhkan bantuan berdasarkan faktor sosial, ekonomi, dan kesehatan. Maka dari itu penelitian ini bertujuan melakukan clustering untuk mengelompokkan prioritas negara yang membutuhkan bantuan. Metode yang digunakan dalam pengelompokan negara menggunakan algoritma K-Means dengan metode Elbow dan Silhouette. Tools yang digunakan dalam pengelompokan adalah python. Clustering dan pencarian Silhouette Coefficient dilakukan menggunakan Tools Orange. Dataset yang digunakan mencakup informasi tentang negara-negara di seluruh dunia. Hasil dari penelitian ini adalah clustering negara-negara yang termasuk dalam kelompok C5 hingga C1, dengan kebutuhan prioritas tertinggi di C5 dan terendah di C1.
Analisis Sentimen Kemungkinan Depresi dan Kecemasan pada Twitter Menggunakan Support Vector Machine Darmawan, Ferry; Joe, Michael; Kurniawan, Yogiek Indra; Afuan, Lasmedi
Jurnal Eksplora Informatika Vol 13 No 1 (2023): Jurnal Eksplora Informatika
Publisher : Institut Teknologi dan Bisnis STIKOM Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30864/eksplora.v13i1.854

Abstract

IMPLEMENTATION OF AUTOREGRESSIVE INTEGRATED MOVING AVERAGE (ARIMA) METHOD FOR PT XL AXIATA TBK STOCK PRICE PREDICTION WITH WEBSITE-BASED DASHBOARD VISUALIZATION Alawiyah, Tuti; Permadi, Ipung; Afuan, Lasmedi; Maryanto, Eddy; Rahayu, Swahesti Puspita
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 4 (2024): JUTIF Volume 5, Number 4, August 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.4.2700

Abstract

The financial market is a dynamic and uncertain sector, with stocks being one of the most commonly used investment instruments. PT XL Axiata Tbk, a telecommunications company listed on the Indonesia Stock Exchange as a blue chip stock, attracts the attention of many investors due to its financial stability and consistent performance. Technical analysis, particularly the ARIMA (Autoregressive Integrated Moving Average) method is used to predict prices. This research focuses on the use of the ARIMA method in predicting the closing price of PT XL Axiata Tbk shares and the implementation of visualization of prediction results through a web-based dashboard. The results of the analysis obtained the best model for stock prediction is ARIMA (2,1,2) with RMSE and MAPE are 50.743 and 0.01653, respectively. The closing price prediction results for 10 consecutive days are 2,190; 2,194; 2,193; 2,196; 2,194; 2,197; 2,195; 2,197; 2,195; and 2,197. Visualization for the results of this prediction is based on a website with the Streamlit framework that presents the results of stock prediction analysis. The existence of a website-based dashboard visualization can help readers find out the prediction results easily and interactively.
CORRELATION ANALYSIS OF SENTIMENT OF 2024 ELECTION RESULTS AND STOCK MOVEMENTS OF POLITICAL ACTORS IN INDONESIA Sari, Enjelita; Afuan, Lasmedi; Permadi, Ipung; Maryanto, Eddy; Rahayu, Swahesti Puspita
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 4 (2024): JUTIF Volume 5, Number 4, August 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.4.2701

Abstract

General elections (elections) are one of the crucial moments in the political life of a country, where the public democratically elects leaders and their deputies to manage the government. Public sentiment towards the results of elections significantly impacts the political stability and economic conditions of a country. This research aims to analyze the relationship between public sentiment towards the 2024 General Elections in Indonesia and changes in the stock prices of political actors using technological approaches and data analysis. The Long Short-Term Memory (LSTM) method is used to classify sentiment based on Twitter data collected with Harvest Tweet. Evaluation of the LSTM model shows an accuracy rate of 90%, precision of 93.6%, and recall of 92.7%. The correlation analysis using the Spearman coefficient indicates a significant negative relationship with a coefficient of 0.402 and a p-value of 0.046. Implementation of an interactive dashboard using Streamlit facilitates visualization of the data used in this study. Recommendations include increasing the amount of training data for sentiment models, exploring alternative correlation methods for deeper analysis, and refining the interface and data integration on the dashboard to enhance user experience and analysis accuracy. This research is expected to contribute to understanding the dynamics of public sentiment and its impact on the stock market in the context of Indonesian politics.
Enhanced Fall Detection using Optimized Random Forest Classifier on Wearable Sensor Data Afuan, Lasmedi; Isnanto, R. Rizal
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.498

Abstract

This study aims to enhance the performance of fall detection systems for elderly care using wearable sensors by optimizing the Random Forest (RF) algorithm. Falls among the elderly are a major health risk, and timely detection can mitigate serious injuries or fatalities. The primary contributions of this research include developing an optimized RF model specifically tailored for real-time fall detection on resource-constrained devices such as smartwatches. Our approach involves feature engineering, hyperparameter tuning using Grid Search and Randomized Search, and model evaluation to achieve optimal performance. Key findings indicate that the optimized RF model achieved an accuracy of 92%, precision of 91%, recall of 89%, and an F1-score of 90%, with an average processing time of 0.045 seconds per prediction. These metrics underscore the model's capability for real-time deployment, demonstrating improved computational efficiency and predictive accuracy compared to traditional machine learning algorithms and deep learning models. The novelty of this study lies in its targeted optimization of the RF model to balance accuracy with low computational demand, addressing the limitations of existing methods that are either computationally intensive or prone to misclassification. This research provides a scalable solution for continuous fall monitoring, with significant implications for wearable healthcare technology, improving both accessibility and response times in elderly care. 
Sentiment Analysis of the Kampus Merdeka Program on Twitter Using Support Vector Machine and a Feature Extraction Comparison: TF-IDF vs. FastText Afuan, Lasmedi; Hidayat, Nurul; Nofiyati, Nofiyati; As'ad, Mohamad Faris
Journal of Applied Data Sciences Vol 5, No 4: DECEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i4.436

Abstract

The Kampus Merdeka program, launched by the Indonesian Ministry of Education, Culture, Research, and Technology in 2020, aims to enhance students' skills through hands-on work experience. Considering the rising significance of social media, particularly Twitter, in gauging public opinion, this research focuses on analyzing the sentiment towards the Kampus Merdeka program. The primary objective is to classify the sentiments expressed in tweets related to the program and compare two feature extraction techniques—TF-IDF and FastText—to identify the best approach for transforming text data into numerical vectors. The sentiment classification model was built using the Support Vector Machine (SVM) algorithm, a machine learning technique known for its accuracy in text classification. A total of 16,730 tweets were collected and analyzed, yielding an accuracy of 73% for FastText and 72% for TF-IDF. Results show that FastText is more effective in capturing semantic relationships, leading to higher accuracy in sentiment classification. Findings indicate that the public sentiment towards the Kampus Merdeka program is predominantly positive (60.7%), with negative and neutral sentiments at 33.5% and 5.8%, respectively. The success of the FastText method underscores the importance of advanced feature extraction techniques in text classification. The novelty of this research lies in its use of FastText for educational policy evaluation, providing a new perspective on using sentiment analysis to assess public perception of educational programs.
Co-Authors Abidin, Dodo Zaenal Adi Pangestu Adyatma, Adrian Dwinanda Afrizal Nehemia Toscany Ahmad Ashari Ahmad Fauzi Ridlwan Aji, Pandu Wahyu Alfarez Marchelian, Reyno Alkaf, Zakiyyan Andreas, Roy Anin Ammbya Soulani Arief Kelik Arief Kelik Nugroho Arief Kelik Nugroho Arief Kelik Nugroho Arief Kelik Nugroho Arkan, Naofal Dhia As'ad, Mohamad Faris Asmoro Widagdo, Asmoro Bangun Wijayanto Bintang Pradana Yosua, Panky Dadang Iskandar Dadang Iskandar Daffa Ammar Muaafii Daffa Naufaldi Al Rasyid Didit Suprihanto, Didit Dodi Sandra Eddy Maryanto Eddy Maryanto Fandy Setyo Utomo Faris Akbar Abimanyu Febri Sutomo Ferry Darmawan Hidayat, Nurul Indah Cahya Febriani Indyastuti, Devani Laksmi Ipung Permadi Ipung Permadi Ipung Permadi Ipung Permadi Iqbal Iqbal Irfan Agus Tiawan Jasmir, Jasmir Joe, Michael Khanza, Muthia Kharisun, Kharisun Kurniawan, Yogiek Indra Maria Ulfa Chasanah Muhammad Fikri Rivaldi Muhammad Luthfi Muhammad Randy Cahya Mardika Muhammad Zein Albalki Muhammad, Katon Mulki Indana Zulfa, Mulki Indana Musaadah, Khalimah Najmudin Nandha Arwiansyah Nasichatul Umayah Niko Siameva Uletika Nofiyati Nofiyati, Nofiyati Nofiyati, Nofiyati Nur Chasanah Nurhadi Nurul Hidayat Nurul Hidayat Nurul Ismailiah Priandika Ratmadani Anugrah Purnama, Benni R. Rizal Isnanto Rahayu, Swahesti Puspita Rif’an, Muhammad Rista Afifah Rochmat Mulyo Sugihono Said, Rahaini Mohd Sari, Enjelita Sharipuddin, Sharipuddin Siti Nurhayati Slamet Widodo SRI LESTARI Susi Setianingsih Teguh Cahyono Tuti Alawiyah Victoria Angela Sugianto Wahid, Arif Mu'amar Yohanes Suyanto Yunindar, Galih Arditiya Zahira Hasyati, Adila