Claim Missing Document
Check
Articles

Found 12 Documents
Search

Classification of Stunting in Children Using the C4.5 Algorithm Muhajir Yunus; Muhammad Kunta Biddinika; Abdul Fadlil
JOIN (Jurnal Online Informatika) Vol 8 No 1 (2023)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v8i1.1062

Abstract

Stunting is a disease caused by malnutrition in children, which results in slow growth. Generally, stunting is characterized by a lack of weight and height in young children. This study aims to classify stunting in children aged 0-60 months using the Decision Tree C4.5 method based on z-score calculations with a sample size of 224 records, consisting of 4 attributes and 1 label, namely Gender, Age, Weight, Height, and Nutritional Status. The results of the study obtained a C4.5 decision tree where the Age variable influenced the classification of stunting with the highest Gain Ratio of 0.185016337. Meanwhile, the evaluation of the model using the Confusion matrix resulted in the highest accuracy of 61.82% and AUC of 0.584.
Implementation of association rule using apriori algorithm and frequent pattern growth for inventory control Imam Riadi; Herman Herman; Fitriah Fitriah; Suprihatin Suprihatin; Alwas Muis; Muhajir Yunus
JURNAL INFOTEL Vol 15 No 4 (2023): November 2023
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v15i4.980

Abstract

Business success is a business that is able to compete and grow keep abreast of developments in the business world. Especially in the retail sector, where competition is getting tighter. Business owners need to pay attention to the layout of goods and stock management to improve service and meet consumer needs because consumers often have difficulty in finding goods. On the other hand, shortages and excess stock often occur due to lack of goods management. Based on these problems, appropriate techniques are needed for the management of goods supply, one of which is to apply techniques found in the branch of science. Data mining is a technique of association rules. This study aims to find patterns of placement and purchase of goods in generating Association Rule using FP-Growth algorithm. The dataset in this study used data on sales of goods in clothing stores. The results of the study of 140 transactions there are 24 association rules consisting of 7 association rules with 2-itemsets and 17 association rules with 3-itemsets that most often appear in transactions. Based on the order of the highest support value, namely CKJ→STX^LK with a support value of 67%, while the highest confidence value, there are 3 association rules that get the same value, namely STX^CKJ→LK, STX^CAK→LK, STX^RI→LK with a value of 100%. Thus, the rules of association produced by the frequent itemset algorithm, FP-growth, can serve as decision support for the sales of goods in small and medium-sized retail businesses
Optimasi Algoritma Naïve Bayes Menggunakan Fitur Seleksi Backward Elimination untuk Klasifikasi Prevalensi Stunting Muhajir Yunus; Muhammad Kunta Biddinika; Abdul Fadlil
Decode: Jurnal Pendidikan Teknologi Informasi Vol. 3 No. 2: SEPTEMBER 2023
Publisher : Program Studi Pendidikan Teknologi Infromasi UMK

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51454/decode.v3i2.188

Abstract

Stunting adalah masalah kekurangan gizi kronis yang ditandai dengan tinggi badan anak di bawah normal untuk usianya. Anak yang mengalami stunting memiliki risiko lebih tinggi terhadap berbagai penyakit kronis dan masalah kesehatan lainnya dan cenderung memiliki intelligence quotient yang lebih rendah dan performa yang buruk di sekolah karena sebanyak 90% jumlah sel otak tercipta sejak dalam kandungan hingga anak berumur 24 bulan. Tujuan dari penelitian ini adalah untuk mengklasifikasi prevalensi stunting pada anak usia di bawah 5 tahun dengan mengimplementasikan metode naïve bayes menggunakan fitur seleksi backward elimination berdasarkan data perhitungan z-score dengan data sampel berjumlah 224 record, yang terdiri dari 4 atribut dan 1 label yaitu jenis kelamin, usia, berat badan, tinggi badan dan status gizi. Dari hasil penelitian yang telah dilakukan diperoleh nilai akurasi tertinggi sebesar 92,54% sedangkan hasil dari pengujian model tanpa menggunakan seleksi fitur mendapatkan akurasi sebesar 53,50%. Penelitian ini menggunakan data traning dan testing dengan ratio sebesar 70%:30%.
Digitalisasi Portofolio Siswa Berbasis Website di SMK Informatika Wonosobo Riadi, Imam; Umar, Rusydi; Muis, Alwas; Yunus, Muhajir
Jurnal Pengabdian Masyarakat Bumi Rafflesia Vol. 6 No. 3 (2023): Desember : Jurnal Pengabdian Kepada Masyarakat Bumi Raflesia
Publisher : Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jpmbr.v6i3.5869

Abstract

Siswa dilatih untuk memiliki skill dan pengetahuan agar dapat bekerja pada industri. Setiap siswa dituntut memiliki pengetahuan yang dapat digunakan untuk mencari kerja setelah lulus. Kebutuhan akan adaptasi terhadap perkembangan teknologi informasi dan komunikasi dalam dunia pendidikan semakin meningkat. Sehingga dibutuhkan pelatihan terkait penggunaan teknologi informasi untuk membantu siswa beradaptasi dengan perkembangan teknologi. Tujuan pelatihan ini yaitu untuk memperkenalkan siswa tentang konsep portofolio digital berbasis website dan membekali mereka dengan keterampilan menggunakan teknologi informasi yang relevan untuk membangun dan mengelola portofolio. Manfaat pelatihan ini yaitu membantu siswa untuk mempresentasikan karya-karya mereka secara efektif kepada pihak-pihak yang berkepentingan seperti calon perguruan tinggi dan pemberi kerja. Metode analisis data pada pelatihan ini menggunakan metode likert dengan memberikan pernyataan dan memberikan jawaban mulai dari sangat setuju, setuju, netral, tidak setuju, dan sangat tidak setuju. Siswa berhasil membangun portofolio digital yang menarik dan profesional, memamerkan karya-karya mereka dengan efektif. Metode pengumpulan data pada kegiatan ini yaitu menggunakan kuesioner. ini menunjukkan bahwa pelatihan portofolio menggunakan website sangat mudah dipahami oleh siswa. Selain itu, seluruh siswa berharap pelatihan seperti sering diadakan untuk membantu dalam memanfaatkan teknologi informasi untuk pengembangan diri. Penerapan pelatihan ini di SMK Informatika Wonosobo memberikan manfaat yang signifikan bagi siswa dalam menghadapi tantangan di era digital.   Kata Kunci: Google sites, pelatihan, portofolio, website
The Role of Sentiment Analysis in Election Predictions Compared to Electability Surveys Firdaus, Asno Azzawagama; Faresta, Rangga Alif; Yunus, Muhajir
Indonesian Journal of Modern Science and Technology Vol. 1 No. 1 (2025): January
Publisher : CV. Abhinaya Indo Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64021/ijmst.1.1.1-8.2025

Abstract

Indonesia has just held the voting process for the Presidential Election. This has become a discussion of various media to social media, especially Twitter. However, when making predictions based on social media it will be so difficult if there is no specific technique or method for handling it. The prediction method we found in Indonesia often uses electability surveys in elections, but this research will compare it with sentiment analysis that utilizes social media in data collection. Another novelty is the data used during candidate campaign debates using the Support Vector Machine (SVM) method in class classification. The results obtained show that there are still differences between electability and sentiment, but this is due to several factors such as the amount of data, data objects, data collection time span, and methods. Overall, the SVM method has an accuracy of more than 0.75 on all three candidate datasets, proving that this method can be applied to similar cases.
Internet of Things-Based Automatic Trash Can Prototype Using Arduino Mega 2560 Sumarno Wijaya; Ahmad Fatoni Dwi Putra; Yuan Sa'adati; Hadi San, Ahmad Syahrul; Yunus, Muhajir; Talirongan, Florence Jean B.; G. Tangaro, Diana May Glaiza; Grancho, Bernadine
Indonesian Journal of Modern Science and Technology Vol. 1 No. 2 (2025): May
Publisher : CV. Abhinaya Indo Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64021/ijmst.1.2.43-49.2025

Abstract

The development of Internet of Things (IoT) technology encourages the creation of various smart device innovations that can be applied in everyday life, one of which is an automatic waste management system. This research aims to design and implement an IoT-based automatic trash can prototype using an Arduino Mega 2560 microcontroller that is able to detect the presence of people who will throw away garbage, open and close the lid of the tub automatically, and provide notification if the trash can is full. This research uses an experimental method by combining ultrasonic sensors, servo motors, and LED indicators as the main components. The test results show that the device works well and in accordance with the researcher's expectations. Ultrasonic sensor 1 can detect the presence of objects in front of the trash can and trigger the servo motor to open and close the lid automatically. Ultrasonic sensors 2 and 3 are also able to detect the height of the garbage and activate the servo motor while the indicator LEDs also function as designed: LED 1 blinks when someone approaches to take out the trash, while LED 2 and LED 3 light up when the sensors detect that the trash has reached a certain height limit. In addition, the system is energy efficient as it only activates when an object is detected, making it suitable for households and educational institutions.
Sentiment Analysis of User Reviews of TikTok App on Google Play Store Using Naïve Bayes Algorithm Hasanah, Rakyatol; Sani SR, Sahrul; Munzir, Misbahul; Firdaus, Asno Azzawagama; Sulton, Chaerus; Yunus, Muhajir
Indonesian Journal of Modern Science and Technology Vol. 1 No. 2 (2025): May
Publisher : CV. Abhinaya Indo Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64021/ijmst.1.2.58-64.2025

Abstract

In recent years, user interaction through mobile applications has grown rapidly, making user reviews an important source of feedback for improving service quality. This study explores sentiment analysis on 5,000 user reviews of the TikTok application, collected from the Google Play Store using the google-play-scraper library. The data underwent several preprocessing steps, such as case folding, text cleaning, and selecting relevant columns like review content and rating score. Sentiment labeling was based on rating values: scores of 4 and 5 were treated as positive, while scores of 1 and 2 were considered negative. From the results, it was observed that negative reviews appeared more frequently, indicating an imbalance in the dataset. Despite this, the Naïve Bayes classification algorithm still achieved a reasonably good performance in categorizing the sentiments. These findings suggest that even with simple models, valuable insights can be gained from user-generated content. Moreover, the results provide meaningful input for TikTok developers to better understand user concerns and emphasize the potential need for applying balancing techniques in future analysis. Further studies are encouraged to explore other algorithms that may improve sentiment classification accuracy on more complex datasets.    
Analisis Algoritma C4.5 untuk Prediksi Minat Baca Yunus, Muhajir; I. S. Aziz, Azminuddin; Fitriah
Journal of Technopreneurship and Information System (JTIS) Vol 8 No 1 (2025): Februari
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jtis.v8i1.8834

Abstract

Minat baca merupakan indikator penting dari tingkat literasi dan berkorelasi langsung dengan kemampuan berpikir analitis dan kualitas pendidikan secara keseluruhan. Prediksi minat baca dapat diselesaikan dengan pendekatan machine leraning menggunakan algoritma C4.5 yang handal dalam mengolah data. Berdasarkan hasil analisis yang telah dilakukan, diperoleh pohon keputusan C4.5 untuk prediksi minat baca, di mana variabel lingkungan membaca tidak mempengaruhi prediksi minat baca, sedangkan variabel umur yang paling berpengaruh terhadap prediksi minat baca. Sedangkan hasil evaluasi model menggunakan confusion matrix menghasilkan akurasi sebesar 71.14%, dimana menurut tafsiran guilford empirical rules akurasi tersebut termasuk tinggi/handal. Hasil interval kepercayaan didapatkan batas atas = 0.743437, dan batas bawah = 0.6771. Dengan demikian diperoleh model C4.5 untuk prediksi minat baca yang akurasinya tinggi/handal.
Unveiling the Predictive Power of Machine Learning and Deep Learning: A Comparative Study on Disease Diagnosis, Detection, and Mortality Risk in Healthcare Santoso, Daniel; Firdaus, Asno Azzawagama; Yunus, Muhajir; Pangri, Muzakkir
Journal of Robotics and Control (JRC) Vol. 6 No. 4 (2025)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v6i4.26223

Abstract

This study compares the roles of machine learning (ML) and deep learning (DL) in healthcare, focusing on their applications, challenges, and prospects. It addresses the increasing relevance of AI in public health systems and contributes a structured analysis of how ML and DL process different healthcare data types. A systematic literature review was conducted using sources from Google Scholar, Elsevier, Springer, IEEE, and MDPI, applying inclusion criteria based on relevance, publication quality, and recency (2018–2024). Article selection and synthesis using meta-analysis followed the PRISMA framework. The review identified four key application areas: (1) disease outbreak prediction, (2) disease forecasting, (3) disease diagnosis and detection, and (4) disease hotspot monitoring and mapping. ML techniques such as Random Forest and ensemble methods show high performance in handling structured data like patient records, whereas DL architectures like convolutional neural network (CNN) and long-short term memory (LSTM) are superior for unstructured data, including medical imaging and bio signals. Challenges common to both approaches include data quality issues, dataset bias, privacy concerns, and integration into existing healthcare infrastructures. Looking forward, promising directions include explainable AI (XAI), transfer learning, federated learning, and real-time data use from wearable and internet of things (IoT) devices. The study concludes that while ML and DL can significantly improve diagnosis, response to health threats, and resource allocation, maximizing their impact requires continuous cross-sector collaboration, transparency, and ethical governance.
Comparison of Machine Learning Algorithms for Stunting Classification Yunus, Muhajir; Biddinika, Muhammad Kunta; Fadlil, Abdul
Scientific Journal of Engineering Research Vol. 1 No. 2 (2025): April
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v1i2.2025.9

Abstract

Indonesia is one of the countries with medium stunting data over the past decade, around 21.6%. Stunting prevention is a national program in Indonesia, and stunting reduction in children is the first of the six goals in the Global Nutrition Target for 2025. Based on SSGI data in 2022, the prevalence of stunting in Gorontalo Province is 23.8% and is in the high category. Stunting prevention is an early effort to improve the ability and quality of human resources. This study compared two Machine Learning algorithms for stunting classification in children, namely the Naive Bayes method and Decision Tree C4.5 using Python by dividing the training and testing data a total ratio of 80:20. The performance of each algorithm was evaluated using a dataset of child health information based on z-score calculation data with a total of 224 records, consisting of 4 attributes and 1 label, namely gender, age, weight, height and nutritional status. The results of the research that have been conducted show that the Decision Tree C4.5 algorithm achieves the highest accuracy in the classification of stunting events with an accuracy of 87% while for the Naïve Bayes algorithm produces a low accuracy of 71% so that for this study the Decision tree C4.5 algorithm is the best algorithm for the classification of stunting events. These findings suggest this algorithm can be a valuable tool for classifying children's stunting.