Article Per Year (5 Year)
p-Index From 2020 - 2025
2.757
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah KOMPUTASI Journal of Information System, Applied, Management, Accounting and Research Jurnal Restikom : Riset Teknik Informatika dan Komputer Bulletin of Information Technology (BIT) Pelita Teknologi : Jurnal Ilmiah Informatika, Arsitektur dan Lingkungan SIGMA: Information Technology Journal IT For Society : Journal of Information Technology SAINTEK
Muhammad Makmun Effendi
Universitas Pelita Bangsa
Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Engineering Industrial & Manufacturing Engineering

Published : 21 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 21 Documents
Search

 1   2   3 
Penerapan Data Mining Menggunakan Metode Algoritma Naive Bayes Untuk Menentukan Kelayakan Kredit Rumah Bersubsidi Muhammad Makmun Effendi
Jurnal SIGMA Vol 11 No 2 (2020): Juni 2020
Publisher : Teknik Informatika, Universitas Pelita Bangsa

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

Abstract

Data mining has been implemented in various fields, including business, education and telecommunications. In the business sector, for example, the results of implementing data mining can help in making decisions about the feasibility of subsidized home loans. In determining the feasibility of subsidized home loans, PT. Gernis Pratama Properti conducts an analysis so that it can be determined whether the subsidized home loan process can be approved or not. Currently there are several obstacles in the assessment process, namely the inaccurate results of the decision at interview stage 1 in the company as an initial stage of the consumer eligibility process. Naive Bayes Algorithm Method is an algorithm found in the classification technique that uses a simple probability method based on the theory of infants with high independent assumptions. The process carried out in this study uses Rapid Miner tools to process data with the Naive Bayes algorithm, from the tests carried out it produces an accuracy of 96.23%. With the application of the Naive Bayes method, it uses data to produce the probability of each criterion for different classes, so that the probability values of these criteria can be optimized to determine the eligibility of "Eligible" and "Eligible" subsidized home loans quickly and efficiently based on the classification made by Naive Bayes method. Keyword : Creditworthiness of subsidies ,Data Mining, Algorithm Naive Bayes.
Menentukan Prediksi Kelulusan Siswa Dengan Membandingkan Algoritma C4.5 Dan Naive Bayes Studi Kasus SMKN. 1 Cikarang Selatan Muhammad Makmun Effendi
Jurnal SIGMA Vol 11 No 3 (2020): September 2020
Publisher : Teknik Informatika, Universitas Pelita Bangsa

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

Abstract

The process of identifying information using statistical techniques, and machine learning is the meaning of data mining. Data mining can be applied in various fields of life such as health, business, and education. One of the applications of data mining in the field of education is to predict the graduation of school students. Prediction of student graduation using data derived from transcripts of the final grades of each student, while the attributes used are the average value of Indonesian, English, and Mathematics lessons from semester 1 to semester 5 as well as the history of SP that has been obtained during the student is in school. In this study, two data mining methods are used, namely the C4.5 algorithm and Naïve Bayes algorithm. The use of the two methods in this study aims to compare the performance of the two algorithms in predicting student graduation based on the level of accuracy, precision, and recall obtained. From the test results using data testing as much as 222 data which states that the C4.5 algorithm has an accuracy value of 98.64%, 100% precision and 100% recall, while Nave Bayes has an accuracy level of 97.75%, precision 95.52% and recall. 95.52%. And if the test uses 890 training data, it will state that the C4.5 algorithm has an accuracy level of 98.99%, precision 98.68% and recall 98.68% while nave Bayes has an accuracy level of 97.42%, precision 99, 39% and recalls 99.39%. From the above comparison, the C4.5 algorithm has an accuracy level that tends to be higher than the nave Bayes algorithm, so it was decided that in predicting student graduation, the C4.5 algorithm is better than the nave Bayes algorithm in predicting student graduation data. Keywords: Data mining, Clacification, C4.5 Algoritma, Naive Bayes
Perbandingan Algoritma Naïve Bayes, Svm Dan Trees J48 Pada Pengenalan Pengaruh Suara Konsonan Terhadap Vokal Muhammad Makmun Effendi
Jurnal SIGMA Vol 8 No 1 (2017): Maret 2017
Publisher : Teknik Informatika, Universitas Pelita Bangsa

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

Abstract

Sound is the most basic communication tool that humans have. Technological developments are increasingly high so that human needs in living his life with practical and automatic, then the development of technology toward the field biometrica. This study was conducted to determine whether between the male and female voice types can be recognized by recording the consonant letters that have been influenced by vowels, by comparing the Naive Bayes algorithm, SVM algorithm, and J48. Research methods used in building this voice recognition system based on consonants that have been influenced by vowels by comparing the Naïve Bayes, SVM and Trees J48 algorithms. This is done to find out from the two algorithms compared which are better at recognizing consonant sounds that have been affected by the vowel sound. Keywords : Sound, Naïve Bayes, SVM and Trees J48
Analisis Sentimen Masyarakat Indonesia Dalam Konflik Rusia-Ukraina Di Twitter Muhammad Makmun Effendi; Zaenal Mustofa; Ahmad Turmudi
Bulletin of Information Technology (BIT) Vol 3 No 4: Desember 2022
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v3i4.418

Abstract

Russia is a big superpower that has power and plays an important role in international politics, while Ukraine, a former Soviet Union country, became independent on December 1, 1991. In 2014 there was also a conflict between Russia and Ukraine which was a meeting of superpowers. In February 2022, Russia resumed armed conflict with Ukraine. The Russia-Ukraine conflict has garnered many responses in the form of tweets from various circles of society, resulting in many traces of tweets containing public opinion on the Russia- Ukraine conflict on Twitter social media. This study aims to determine the results of the positive or negative impact of the conflict between Russia and Ukraine on the economy in Indonesia and to determine the results of accuracy, precision, recall resulting from the use of the Naïve Bayes method and feature selection Particle Swarm Optimization in RapidMiner Studio software. Particle Swarm Optimization is an optimization method inspired by the behavior of fish and poultry flocks in search of food sources. The preprocessing stage in this research includes cleansing, removing duplicates, data selection, normalization, case folding, tokenizing, filtering, stopwords, stemming, and labeling. The classification results obtained by 55.11% of twitter users commented negatively and 44.89% of twitter users commented positively about the conflict between Russia and Ukraine. By looking at the results of the sentiment analysis data above, where the number of Twitter users who commented negatively is higher, it can be concluded that the Indonesian people are worried about the surge in prices of basic daily necessities, as indicated by one of the tweets commenting on rising oil and gas prices BBM
Analisis Sentimen pada Teks Opini Penilaian Kinerja Dosen dengan Pendekatan Algoritma KNN: Array A. Yudi Permana; M. Makmun Effendi
Jurnal Ilmiah Komputasi Vol. 19 No. 1 (2020): Jurnal Ilmiah Komputasi Volume: 19 No. 1, Maret 2020
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32409/jikstik.19.1.154

Abstract

Dalam peneltian ini di maksudkan untuk melakukan analisis sentimen pada dokumen opini penilaian mahasiswa terhadap kinerja dosen dengan 3 kategori sentimen analisis diantaranya sentimen negative, sentimen positif dan sentimen netral. Opini mahasiswa terhadap kinerja dosen merupakan bagian dari salah satu faktor penilaian terhadap kualitas dosen dalam melakukan program kerja di lingkungan kampus universitas pelita bangsa. Oleh karena itu penting adanya suatu proses pengolahan data opini dari mahasiswa, sehingga opini tersebut menjadi sebuah keluaran berupa nilai pada sentimen. Semakin sentiment positif maka nilai kualitas dosen semakin baik begitu sebaliknya jika opini mahasiswa negative berarti menunjukan kualitas dosen tidak baik. Metode penelitian yang digunakan pada penelitian ini memliki tahapan diantaranya adalah dengan terlebih dahulu melakukan Preprocessing pada dokumen opini mahasiswa yang terdiri dari 300 dokumen opini yang dibagi menjadi data training dan testing 70:30 dengan asumsi pembagian dokumen 250 data training dan 50 data testing. Pada tahapan awal proses sentimen analisa pada dokumen opini mahasiswa dilakukan proses preprocessing dengan beberapa tahapan diantaranya stopword removal, case folding dan fitering serta stemming. Dari hasil stemming kemudian dilakukan proses pengujian data training dan data testing dengan algoritma KNN Pada penelitian ini dihasilkan nilai akurasi training sebesar 100%, sedangkan hasil prediksi dari sentimen analisisnya memiliki tingkat akurasi sebesar 80%, precission training bernilai 1 dan testing bernilai 0.909 dan hasil recall training bernilai 1 dan hasil recall testing bernilai 0.889.
Prediksi Penyakit Jantung Dengan Algoritma Regresi Linier Agung Wijayadhi; Muhammad Makmun Effendi; Sugeng Budi Rahardjo
Bulletin of Information Technology (BIT) Vol 4 No 1: Maret 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v4i1.463

Abstract

In this study, we evaluated the ability of a linear regression algorithm to predict heart disease risk in individuals. We use data from trusted sources and perform the necessary preprocessing to clean and provide the data for the model. The results of the analysis show that the linear regression algorithm can be used well to predict the risk of heart disease in individuals with a fairly high degree of accuracy. We also evaluated several factors that influence heart disease risk and demonstrated that they could be identified and integrated into our model to improve its performance. In addition, we also evaluated the validation methods used to evaluate our models and demonstrated that they can be used to objectively determine model performance. The results from this study provide a solid foundation for developing a better heart disease prediction system in the future. And the results of this study are quite accurate enough to give good results with a Root Mean Squared Error: 0.379 +/- 0.000 and Squared Error: 0.144 +/- 0.229
Prediksi Persediaan Barang Tepat Waktu dengan Menerapkan Algoritma Apriori Muhammad Makmun Effendi; Farish Al Khairi; Arif Siswandi
Bulletin of Information Technology (BIT) Vol 4 No 2: Juni 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v4i2.622

Abstract

he Apriori algorithm is a data mining technique for determining associative rules for a combination of components, this study aims to find the pattern frequency of each component that has been ordered by the customer so that the order is in accordance with the number and timely delivery, therefore to support the problems faced by PT. . SMF for the combination of inventory to purchase of goods, PT SMF applies the Apriori Algorithm to predict stock of goods so that when there is an order, the goods are not lacking and the delivery is also on time. The results of the research carried out obtained the most data on goods produced every 1 month, including the Pipe Bracket and Solenoid Bracket pattern of linkages in terms of predicting the number of goods at PT. If SMF produces Pipe Brackets, it must also produce Selenoid Brackets where the resulting confidence is 60%, Nc : 4, and for the lift ratio test it is 2.307. Whereas if you produce the Selenoid Valve Bracket, you must also produce the air pipe bracket for the resulting confidence of 75%, Nc: 5, and the lift ratio test of 2.272.
PENGEMBANGAN SISTEM INFORMASI PERSEDIAN BARANG BERBASIS DESKTOP DENGAN METODE RAD PADA CV MENEMBUS BATAS Farid Wajdillah; Suherman Suherman; Muhammad Makmun Effendi
JISAMAR (Journal of Information System, Applied, Management, Accounting and Research) Vol 7 No 3 (2023): JISAMAR (Agustus 2023)
Publisher : Sekolah Tinggi Manajemen Informatika dan Komputer Jayakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52362/jisamar.v7i3.1141

Abstract

In the era of globalization and increasingly fierce business competition, the company's operational efficiency is an important key in achieving greater profits. Good and effective inventory management is one of the factors that affect operational efficiency. CV Menembus Batas, a plastic waste recycling company, faces efficiency problems due to the use of manual systems in processing inventory data. This leads to slow data processing processes, inventory miscalculations, and other problems. To overcome this problem, CV Menembus Batas needs to implement the development of a desktop-based inventory information system with the Rapid Application Development (RAD) method. With an integrated information system, companies can speed up the data processing process, improve inventory control, facilitate report generation, and improve the right decision making. The implementation of this inventory information system can improve CV Menembus Batas operational efficiency and provide accurate and fast information.
KLASIFIKASI EMAIL PHISHING MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR Muhammad Adipa; Ahmad Turmudi Zy; M. Makmun Effendi
Jurnal RESTIKOM : Riset Teknik Informatika dan Komputer Vol 5 No 2 (2023): Agustus
Publisher : Program Studi Teknik Informatika Universitas Nusa Putra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52005/restikom.v5i2.152

Abstract

Saat ini perkembangan teknologi informasi sangat pesat dan cepat, bahkan di Indonesia sendiri. Evolusi teknologi dunia internet terus berlanjut, dan inovasi baru terus bermunculan, membentuk masa depan yang lebih terhubung dan terintegrasi. Namun selain manfaat, muncul tantangan baru, seperti masalah terkait privasi, keamanan siber, dan pengolahan data. Pada satu sisi, perkembangan teknologi informasi yang demikian mengagumkan itu memang telah membawa manfaat yang luar biasa bagi kemajuan peradaban umat manusia. Di sisi lain, berkembangnya teknologi informasi menimbulkan pula sisi rawan yang gelap sampai tahap mencemaskan dengan kekhawatiran pada perkembangan tindak pidana di bidang teknologi informasi yang berhubungan dengan kejahatan mayantara atau “Cybercrime”. Salah satu kejahatan (cybercrime) yang terjadi di Indonesia yaitu Email Phishing. Badan Siber dan Sandi Negara (BSSN) melaporkan, ada 164.131 kasus email phishing di Indonesia pada 2022. Tingginya angka kasus email phishing terus meningkat, oleh karena itu akan dilakukan pengujian untuk mengklasifikasi email phishing menggunakan algoritma K-Nearest Neighbor. Didapatkan hasil akurasi dengan nilai sebesar 84%, precision sebesar 73%, dan recall sebesar 96%. Hasil ini membuktikan bahwa algoritma K-Nearest Neighbor memberikan hasil yang cukup baik dalam mengklasifikasi email phishing. Kata Kunci: Cybercrime, Email Phishing, Klasifikasi, Data Mining, K-Nearest Neighbor Currently the development of information technology is very fast and fast, even in Indonesia itself. The technological evolution of the internet world continues, and new innovations continue to emerge, shaping a more connected and integrated future. But apart from the benefits, new challenges arise, such as issues related to privacy, cyber security, and data processing. On the one hand, the development of such amazing information technology has indeed brought extraordinary benefits to the advancement of human civilization. On the other hand, the development of information technology has also created a dark vulnerable side to the point of worrying about the development of criminal acts in the field of information technology related to mayantara crime or "Cybercrime". One of the crimes (cybercrime) that occurred in Indonesia, namely Email Phishing. The National Cyber ​​and Crypto Agency (BSSN) reported that there were 164,131 phishing email cases in Indonesia in 2022. The high number of phishing email cases continues to increase, therefore a test will be carried out to classify phishing emails using the K-Nearest Neighbor algorithm. Accuracy results were obtained with a value of 84%, precision of 73%, and recall of 96%. These results prove that the K-Nearest Neighbor algorithm gives good results in classifying phishing emails. Keywords: Cybercrime, Phishing Email, Classification, Data Mining, K-Nearest Neighbor
Analisis Gempa Bumi Di Indonesia Dengan Metode Clustering Arji Prasetio; M. Makmun Effendi; M. Najamuddin Dwi M
Bulletin of Information Technology (BIT) Vol 4 No 3: September 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v4i3.820

Abstract

Indonesia is known as an archipelagic country because it consists of thousands of islands stretching from Sabang in the west to Merauke in the east. Testing earthquake data using the K-Means algorithm, where the results also show a new insight, namely the grouping of earthquake-prone areas in Indonesia based on 3 clusters. Cluster 1 is a category of areas with a relatively low level of earthquake-prone areas in Indonesia, namely 209 out of 1113 categories of the number of cases based on the area tested, then cluster 2 is a category of areas with a moderate level of earthquake-prone areas in Indonesia, namely 863 out of 1113 the category of the number of cases based on the area tested, and finally cluster 3 is the category of area with a high level of earthquake-prone areas in Indonesia, namely 41 out of 1113 categories of the number of cases based on the area tested. Tests using the earthquake clustering method with the K-Means algorithm can produce clusters that have cluster group members according to manual calculations such as Cluster_0 in Rapid Miner has 209 cluster members representing the Low cluster, Cluster_1 has 863 cluster group members representing the Medium cluster, and Cluster_2 has 41 cluster members corresponding to the cluster representation High.
Co-Authors A Yudi Permana A. Yudi Permana Agung Wijayadhi Ahmad Turmudi Ahmad Turmudi Zy Aida Ratnasari2 Arie Setiawan2 Arif Siswandi Arji Prasetio Diah Rahmawati Ermanto Ermanto Farid Wajdillah Farish Al Khairi Hengki Anthony Juliyanto M. Najamuddin Dwi M Mochammad Rahmat Faisal Moh Khamim Muhammad Adipa Puguh Ariyadi Sugeng Budi Rahardjo Sugeng Budi Raharjo Suherman Suherman Zaenal Mustofa