Article Per Year (5 Year)
p-Index From 2020 - 2025
0.61
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer Informatika Dikdimas : Jurnal Pengabdian Kepada Masyarakat Journal on Mathematics Education
Alfa Saleh, Alfa
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Humanities Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Engineering Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Nursing Social Sciences Other

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Integrating traditional food and technology in statistical learning: A learning trajectory Ramadhani, Rahmi; Prahmana, Rully Charitas Indra; Soeharto; Saleh, Alfa
Journal on Mathematics Education Vol. 15 No. 4 (2024): Journal on Mathematics Education
Publisher : Universitas Sriwijaya in collaboration with Indonesian Mathematical Society (IndoMS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22342/jme.v15i4.pp1277-1310

Abstract

In the 21st century, understanding variability and developing statistical investigation skills are crucial for enhancing students' data literacy. However, these essential skills are often overlooked, limiting students' growth in numeracy whereby statistical problems are frequently disconnected from real-world or cultural contexts, reducing student engagement. To address this issue, this study integrates the culturally relevant context of Lemang Batok, which enhances students' ability to understand, apply, and analyze data through appropriate statistical concepts. The research uses an ethno-flipped classroom model that promotes flexible, collaborative learning, aiming to design a learning trajectory for teaching descriptive statistics in this context to improve numeracy skills. Utilizing design research methodology, specifically a validation study, the research followed three phases: preliminary design, experimental design, and retrospective analysis. The subjects were junior high school students from Medan and Binjai Cities, North Sumatera-Indonesia. The results indicated that the learning trajectory developed through tiered discussions significantly improved students' numeracy skills in descriptive statistics, as evidenced by increased critical thinking and enhanced abilities to analyze variability.
PENINGKATAN ALGORITMA C4.5 MENGGUNAKAN ENSEMBLE LEARNING UNTUK MENDETEKSI PENYAKIT GINJAL Agusviyanda, Agusviyanda; Novita, Rita; saleh, Alfa; Jamaris, Muhammad
Jurnal Informatika Vol 12, No 3: INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i3.7542

Abstract

Deteksi dini penyakit ginjal sangat penting untuk menurunkan risiko komplikasi dan meningkatkan prognosis pasien. Permasalahan utama dalam diagnosis penyakit ginjal adalah adanya gejala yang tidak spesifik dan ketidakseimbangan distribusi data pasien. Penelitian ini mengusulkan peningkatan performa algoritma C4.5 untuk deteksi penyakit ginjal dengan mengintegrasikan beberapa tahapan modern, yaitu pra-pemrosesan menggunakan Label Encoder dan Ordinal Encoder untuk mengolah fitur kategorikal, penyeimbangan data menggunakan metode SMOTE-ENN, serta seleksi fitur dengan LASSO. Selanjutnya, model dasar C4.5 ditingkatkan dengan metode ensemble learning menggunakan AdaBoost. Hasil pengujian menunjukkan bahwa integrasi Adaboost pada algoritma C4.5 secara signifikan meningkatkan akurasi deteksi penyakit ginjal dibandingkan model dasar maupun model-model pada penelitian terdahulu. Model terbaik pada penelitian ini mencapai akurasi 99%, melebihi performa XGBoost maupun stacking ensemble pada kasus serupa. Kontribusi penelitian ini menegaskan efektivitas kombinasi boosting, balancing, dan seleksi fitur dalam membangun sistem pendukung keputusan berbasis machine learning untuk diagnosis penyakit ginjal.
Penggunaan Teknik Unsupervised Discretization pada Metode Naive Bayes dalam Menentukan Jurusan Siswa Madrasah Aliyah Saleh, Alfa; Nasari, Fina
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 5 No 3: Juni 2018
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (238.548 KB) | DOI: 10.25126/jtiik.201853705

Abstract

Pemilihan jurusan bagi siswa merupakan langkah positif yang dilakukan untuk memfokuskan siswa sesuai dengan potensi yang dimiliki, hal ini dianggap penting karena dengan adanya jurusan, siswa diharapkan mampu mengembangkan kemampuan akademis sesuai bidang yang dikuasai. Pada penelitian sebelumnya, telah dilakukan pengujian dengan metode Naive Bayes yang bertujuan untuk mengkasifikasikan jurusan siswa bedasarkan kriteria yang menunjang dengan studi kasus pada siswa Madrasah Aliyah Swasta PAB 6 Helvetia, dan didapatkan hasil pengujian dari 100 data siswa dengan tingkat keakuratan 90%. pada penelitian ini, dilakukan optimalisasi metode yang digunakan sebelumnya dengan menerapkan teknik Unsupervised Discretization yang akan mentransformasikan kriteria numerik/kontinyu menjadi kriteria kategorikal dan mengeliminasi satu kriteria yang dianggap tidak mempengaruhi keakuratan hasil pengujian, dengan begitu keakurasian hasil klasifikasi dapat meningkat. Dari 120 data siswa yang diuji, terbukti bahwa hasil klasifikasi penerapan teknik unsupervised discretization pada metode naive bayes naik dari 90% menjadi 92.8%. AbstractSelection of majors for students is a positive step that is done to focus students in accordance with their potential, it is considered important because with the majors, students are expected to develop academic ability according to the controlled field. In previous research, Naive Bayes method has been tested to classify the students department based on the supportive criterias (case study on Madrasah Aliyah PAB 6 Helvetia), and the test result of 100 students data, the classification accuracy is about 90% . in this study, optimizaton is done with a method used earlier by applying Unsupervised Discretization techniques that would transform numerical / continuous criteria into categorical criteria and eliminating one criterion that is considered not affect the accuracy of test results. thus the accuracy of classification results could increase. 120 students data is tested, it is evident that the results of the classification of the application of unsupervised discretization techniques on the Naive Bayes method rose from 90% to 92.8%.
Training on Developing Website-Based SAPA Science Process Skills Assessment for the Langsa City Science Teacher Working Group Putri, Mentari Darma; Zatya, Ismi; Saleh, Alfa; Oktaviani, Coryna
DIKDIMAS : Jurnal Pengabdian Kepada Masyarakat Vol. 4 No. 3 (2025): DIKDIMAS : JURNAL PENGABDIAN KEPADA MASYARAKAT VOL 4 NO 3 DESEMBER 2025
Publisher : Asosiasi Profesi Multimedia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58723/dikdimas.v4i3.526

Abstract

Background: Science Process Skills (SPS) are important competencies in science learning because they emphasize students' critical, analytical, and practical thinking skills. However, the practice of SPS assessment in schools is still limited, mainly due to the dominance of conventional instruments and the limited use of digital technology.Aims: This community service activity aimed to improve the understanding and skills of junior high school science teachers in Langsa City to develop and implement technology-based SPS assessments.Method: This community service activity was a training and mentoring-based program which consisted of four main stages: socialization, training, technology implementation, and mentoring and evaluation, involving 25 science teachers as participants. This approach not only provided knowledge transfer but also ensured real implementation in the field through practical activities and continuous feedback. The evaluation instruments consisted of pretests and posttests, assessment products (student worksheets, rubrics, and SPS questions), and participant response questionnaires.Results: The results of the activity showed an increase in the average pretest score from 60.4 to 92.8 on the posttest with an N-gain value of 0.8 (high category). In addition, more than 85% of teachers responded positively to the activity.Conclusion: These findings indicate that training in developing SPS assessments integrating the Smart Performance Assessment (SAPA) platform, Canva, and ChatGPT has proven effective in strengthening teachers' competencies, both conceptually and practically, thereby supporting improvements in the quality of science learning.
Co-Authors Agusviyanda, Agusviyanda Jamaris, Muhammad Nasari, Fina Oktaviani, Coryna Putri, Mentari Darma Rahmi Ramadhani Rita Novita Rully Charitas Indra Prahmana Soeharto Zatya, Ismi