Claim Missing Document
Check
Articles

PENGARUH OPTIMASI BOBOT MENGGUNAKAN ALGORITMA GENETIKA PADA KLASIFIKASI TINGKAT KERAWANAN DBD Bayu Hadi Sudrajat; Muliadi; Muhamad Reza Faisal; Radityo Adi Nugroho; Dwi Kartini
Journal of Data Science and Software Engineering Vol 2 No 02 (2021)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (271.92 KB)

Abstract

Dengue Hemorrhagic Fever (DHF) is a disease transmitted by the Aedes Ageypti mosquito. In South Kalimantan, especially in the city of Banjarbaru, the number of cases tends to increase every year. Existing research has identified the level of dengue susceptibility by using computational methods, one of which is classification. The method used in this research is Neural Network Backpropagation with weight optimization using Genetic Algorithms for data classification of dengue disease in Banjarbaru City. The purpose of this study was to determine the performance of the classification of dengue susceptibility levels using Neural Network Backpropagation and weighting using Genetic Algorithms. The results showed that the performance obtained for the classification of the level of dengue susceptibility using the Neural Network Backpropagation Algorithm was 83.33% in the accuracy, 96.51% precision, and 84.69% recall, whereas when using the Neural Network Backpropagation Algorithm based on Genetic Algorithm for weight optimization, obtained an accuracy value of 96.29%, a precision of 98.97%, and a recall of 97%.
PERFORMANCE COMPARISON OF ADAPTIVE NEURO FUZZY INFERENCE SYSTEM AND SUPPORT VECTOR MACHINE ALGORITHM IN BALANCED AND UNBALANCED MULTICLASS DATA CLASSIFICATION Muhammad Irfan Saputra; Irwan Budiman; Dwi Kartini; Dodon Turianto Nugrahadi; Mohammad Reza Faisal
Journal of Data Science and Software Engineering Vol 2 No 03 (2021)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (278.287 KB)

Abstract

Data is a record collection of facts. At first the data in the real world were largely unbalanced. Although, the existence of data on fewer categories is much more important to know data on more categories. However, there are some balanced data. This balanced data is the possibility of a ratio of 1:1 in which, the data in the dataset is the same. In this study, using the ANFIS algorithm and SVM to see affected performance on balanced and imbalanced data with multiclass. Data is taken from the UCI Machine Learning. From the research conducted, it is known that the SVM method on the Wine dataset has an accuracy of 96.6% and the ANFIS method on the Iris dataset has an accuracy of 94.7%.
SOLUSI KLASIFIKASI DATA TIDAK SEIMBANG DENGAN PENDEKATAN BERBASIS COMBINATION OF OVERSAMPLING AND UNDERSAMPLING Riza Susanto Banner; Irwan Budiman; Dodon Turianto Nugrahadi; M. Reza Faisal; Friska Abadi
Journal of Data Science and Software Engineering Vol 3 No 01 (2022)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (345.141 KB)

Abstract

This study applies the Combination of Oversampling and Undersampling method to deal with class imbalances. Researchers do Preprocessing to normalize the attributes used for prediction, then divide the training data and testing data. Researchers resampled unbalanced data using Oversampling, Undersampling and a combination of Oversampling and Undersampling. The results of the classification with the experimental data class balancing approach, the best classification performance is the combination of Oversampling and Undersampling classified by the k-Nearest Neighbor (KNN) method with an accuracy of 0.8672; sensitivity of 0.9000; specificity of 0.3750; and AUC of 0.6651042. Classification with Oversampling has performance results, namely accuracy of 0.875; sensitivity of 0.9250; specificity of 0.1250; and AUC of 0.6078125, while Undersampling classification has classification performance, namely accuracy of 0.3438; sensitivity of 0.33333; specificity of 0.50000; and AUC of 0.3645833.
Text Mining Untuk Mengklasifikasi Judul Berita Online Studi Kasus Radar Banjarmasin Menggunakan Metode TF-IDF dan K-NN Salsabila Anjani; Andi Farmadi; Dwi Kartini; Irwan Budiman; Mohammad Reza Faisal
Journal of Data Science and Software Engineering Vol 3 No 01 (2022)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (299.003 KB)

Abstract

ABSTRACT The news media that used to be commonly used were newspapers. However, with the development of the times, the news media is now entering the digital era. Many online news media spread on the internet. The sophistication of the internet makes it easier for readers to choose which news they want to read. Unlike newspapers, online news media have categories where readers can choose. In general, the categorization of a news in online media is determined by the editor. Given the number of news published in a day, of course, makes the editor's job difficult. A category in the news is usually not appropriate because usually the headline is made as attractive as possible to attract the interest of the reader. So there are times when the news title does not match the category that has been entered by the editor. The use of the K-Nearest Neighbor (K-NN) method can be used in determining the categorization of a news. By using a case study of the online media Radar Banjarmasin, a research was conducted to find out how well the Canberra and Euclidean classification methods were using news headline data for categorization. The results obtained in this study are the better classification method is Euclidean and with an accuracy value of 65.00%. Improvements that should be made for further research is to use other methods for comparison.
PENERAPAN METODE FUZZY NEUTROSOPHIC SOFT SETS UNTUK PREDIKSI STATUS PENGAWASAN COVID-19 Lisnawati; Andi Farmadi; Dwi Kartini; Mohammad Reza Faisal; Rudy Herteno
Journal of Data Science and Software Engineering Vol 3 No 03 (2022)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (618.944 KB)

Abstract

Coronavirus Disease 2019 (COVID-19) is a new type of disease that has never been previously identified in humans and has been declared a pandemic. The diagnosis of the disease is complicated by the variety of symptoms and imaging findings and the severity of the disease at the time of presentation. Fuzzy Neutrosophic Soft Sets are able to handle many types of uncertainty data such as ambiguity, inaccuracy, ambiguity, and inconsistency. Therefore, Fuzzy Neutrosophic Soft Sets can be applied to overcome the uncertainty of symptoms in COVID-19 surveillance. This research was conducted by collecting and presenting the respondent's Neutrosophic value and Neutrosophic value as a knowledge base, then performed Fuzzy Neutrosophic Soft Sets operations (composition, complement, value function, and score function) to obtain the monitoring status of the predicted results. Furthermore, the monitoring status of the predicted results is compared with the actual monitoring status of the respondents to obtain the accuracy level of Fuzzy Neutrosophic Soft Sets. Based on testing of 12 respondents, with 7 respondents as training data and 5 respondents as testing data, the accuracy of the Fuzzy Neutrosophic Soft Sets method in the diagnosis of COVID-19 surveillance status was 80%.
Implementasi Implementasi Kinerja Transmisi Data Dengan Modul Komunikasi LoRa dan Protokol MQTT-SN Pada Gateway Untuk Mendukung Transmisi Data Sensor Kelembapan Tanah Djordi Hadibaya; Dodon Turianto Nugrahadi; M. Reza Faisal; Andi Farmadi; M. Itqan Mazdadi
Journal of Data Science and Software Engineering Vol 3 No 03 (2022)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (325.963 KB)

Abstract

Wireless sensor network can help remote data transfer. Implementation of wireless sensor network in IoT system must be done with a good planning because IoT system typically have limited system resources. This limitation can affect performance of a wireless network sensor. The purpose of this study is to find out the effect of node range to the data transfer performance in terms of delay, throughput, RSSI, and SNR by using QOS (quality of service) analysis for LoRa and MQTT protocol. The results of LoRa’s protocol delay are between 2,82 ms to 37,27 ms. Throughput between 0,61 Kb/s to 24,29 Kb/s. SNR between 2,7 dBm to 8,34 dBm, and RSSI between -74,92 dBm to -122,36 dBm. On the other hand, the results of MQTT’s protocol delay are between 677,49 ms to 1182,69 ms. Throughput between 0,60 Kb/s to 1,12 Kb/s. SNR between 2,7 dBm to 8,34 dBm and RSSI between -74,92 dBm to -122,36 dBm.
Optimasi SVR dengan PSO untuk peramalan harga Cryptocurrency Arifin Hidayat; Andi Farmadi; Mohammad Reza Faisal; Dodon Turianto Nugrahadi; Rudy Herteno
Journal of Data Science and Software Engineering Vol 3 No 01 (2022)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (675.556 KB)

Abstract

Cryptocurrency is the nickname given to a system that uses Cryptography technology to securely transmit data and process digital currency exchanges in a dispersed manner. A Cryptocurrency is a form of risky investment, Cryptocurrency prices are very volatile (changing) making Cryptocurrency prices need to be predicted to make a profit. Support Vector Regression (SVR) is one method for predicting time series data such as Cryptocurrency prices. However, the SVR parameters need to be optimized to get accurate results. The Particle Swarm Optimization (PSO) algorithm is implemented to determine the effect on the optimization of SVR parameters. The implementation of SVR and SVR-PSO is carried out on Bitcoin and Shiba Inu Coin Cryptocurrency data. The result of this research is that the SVR algorithm has an accuracy of 13.19082% (Bitcoin) and 68.3221% (Shiba Inu Coin). The SVR-PSO algorithm obtained an accuracy of 96.92359% (BTC) and 94.74245% (SHIB).
IMPLEMENTASI PROTOKOL MQTT-SN PADA INTERNET GATEWAY DEVICE DENGAN PENGIRIMAN PAKET DATA UDP Wahyu Dwi Styadi; Dodon Turianto Nugrahadi; M. Itqan Mazdadi; Mohammad Reza Faisal; Friska Abadi
Journal of Data Science and Software Engineering Vol 3 No 03 (2022)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (275.431 KB)

Abstract

Internet of Things (IoT) is one of the new trends in the world of technology that is likely to become a trend in the future, to be able to make this happen, communication protocols such as MQTT-SN are needed which is a variant of the MQTT protocol and the connection protocol that supports IoT is NB- IoT to support this. Unlike MQTT which uses TCP as its communication protocol, MQTT-SN uses UDP as its data communication protocol. The purpose of this study is to determine the results of Quality of Service on the value of delay and throughput at QoS levels 0, 1, and 2. There are 2 test scenarios, namely real-time test scenarios and phased test scenarios. The design of the instrument consists of sensor instruments, Raspberry Pi microcontrollers for internet gateway device, and NB-IoT modules to then be tested with scenarios to get test results. Based on the test results, the best QoS results for the delay parameter in the real-time scenario are QoS level 2 with a delay value of 1.602 seconds, while for the gradual scenario there is QoS 0 with a delay value of 1.622 seconds. Furthermore, the best QoS results for throughput parameters in real-time scenarios are found at QoS level 2 with a throughput value of 245.79 bits per second and in a phased scenario found at QoS level 1 with a throughput value of 286.42 bits per second.
OPTIMASI ALGORITMA K-NEAREST NEIGHBOR DENGAN SELEKSI FITUR MENGGUNAKAN XGBOOST Muflih Ihza Rifatama; Mohammad Reza Faisal; Rudy Herteno; Irwan Budiman; Muhammad Itqan Mazdadi
Jurnal Informatika dan Rekayasa Elektronik Vol. 6 No. 1 (2023): JIRE April 2023
Publisher : LPPM STMIK Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36595/jire.v6i1.723

Abstract

Kankergmerupakan istilah umum untuk sekelompokgbesar penyakit yang dapatgmenyerang bagian tubuhgmanagpun. Salah satu kanker yang berbahaya adalah Kankerspayudara. Pencegahanskanker payudarasdapatsdilakukansdengan salah satu cara yaitu skrining atau diagnosa dini. Pendiagnosaan dapat menggunakan Machine learning dengan beberapa algoritma contohnya K-Nearest Neighbor. Algortima klasifikasi K-Nearest Neighbor (K-NN) merupakan algortima yang cukup terkenal dan sering digunakan, tetapi terdapat kelemahan pada algoritma KNN yaitu algoritma ini sangat berpengaruh dengan adanya data yang noise atau tidak relevan jika skala fitur tidak konsisten dengan kepentingannya. Salah satu cara mengatasinya adalah dengan cara menyeleksi fitur. Seleksi fitur yang digunakan yaitu menggunakan Extreme Gradient Boosting (XGBoost) berdasarkan kepentingan fitur yang didapatkan. Hasilnya menunjukkan bahwa KNN dengan seleksi fitur XGBoost menggungguli model KNN tanpa seleksi fitur, untuk nilai KNN dengan seleksi fitur XGBoost mendapatkan akurasi sebesar 0,977 sedangkan KNN tanpa seleksi fitur mendapatkan akurasi sebesar 0,974.
Perbandingan Ekstraksi Fitur dengan Pembobotan Supervised dan Unsupervised pada Algoritma Random Forest untuk Pemantauan Laporan Penderita COVID-19 di Twitter Sulastri Norindah Sari; Mohammad Reza Faisal; Dwi Kartini; Irwan Budiman; Triando Hamonangan Saragih; Muliadi Muliadi
Jurnal Komputasi Vol 11, No 1 (2023): Jurnal Komputasi
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v11i1.6650

Abstract

Dimasa sekarang masyarakat sudah berani melaporkan dirinya terpapar COVID-19 melalui unggahan di media sosial seperti Twitter. Hal ini dapat dimanfaatkan oleh masyarakat sekitar atau lembaga kesehatan untuk memberikan bantuan terhadap pelapor. Pemantauan laporan penderita COVID-19 di Twitter dapat dilakukan secara otomatis dengan algoritma machine learning untuk klasifikasi teks. Pada kasus klasifikasi teks, algoritma machine learning menerima input berupa data terstruktur hasil ekstraksi fitur dengan teknik unigram dengan pembobotan. Metode pembobotan kata unsupervised merupakan pembobotan yang tidak memperhatikan letak term di kelas positif atau negatif. Kemudian metode pembobotan ini dikembangkan menjadi pembobotan supervised, karena dalam proses pembobotannya metode ini membobotkan term dengan memperhatikan letak term di kelas positif atau negatif. Pada riset ini dilakukan perbandingan kedua jenis pembobotan pada klasifikasi data tweet gejala covid dengan algoritma machine learning yaitu Random Forest. Dari hasil penelitian didapat hasil kinerja klasifikasi dengan pembobotan supervised Delta TF-IDF terbukti lebih bagus dengan akurasi sebesar 88,5% sedangkan dengan pembobotan unsupervised TF-IDF diperoleh hasil akurasi 87,9%
Co-Authors Abdul Gafur Abdullayev, Vugar Achmad Zainudin Nur Adawiyah, Laila Admi Syarif Ahmad Rusadi Ahmad Rusadi Arrahimi - Universitas Lambung Mangkurat) Ahmad Rusadi Arrahimi - Universitas Lambung Mangkurat) Andi Farmadi Andi Farmadi Andi Farmadi Angga Maulana Akbar Annisa Rizqiana Arie Sapta Nugraha Arif, Nuuruddin Hamid Arifin Hidayat Azizah, Azkiya Nur Bachtiar, Adam Mukharil Bahriddin Abapihi Bayu Hadi Sudrajat Dike Bayu Magfira, Dike Bayu Djordi Hadibaya Dodon Turianto Nugrahadi Dwi Kartini Dwi Kartini Dwi Kartini Dwi Kartini, Dwi Emma Andini Fatma Indriani Fatma Indriani Fatma Indriani Favorisen R. Lumbanraja Fitra Ahya Mubarok Fitriyana, Silfia Friska Abadi Friska Abadi Friska Abadi Ghinaya, Helma Hanif Rahardian Herteno, Rudy Irwan Budiman Irwan Budiman Irwan Budiman Ivan Sitohang Julius Tunggono Jumadi Mabe Parenreng Junaidi, Ridha Fahmi Karlina Elreine Fitriani Keswani, Ryan Rhiveldi Kevin Yudhaprawira Halim Kurnianingsih, Nia Lilies Handayani Liling Triyasmono Lisnawati Mahmud Mahmud Mauldy Laya Mera Kartika Delimayanti Miftahul Muhaemen Muflih Ihza Rifatama Muhamad Ihsanul Qamil Muhammad Al Ichsan Nur Rizqi Said Muhammad Alkaff Muhammad Angga Wiratama Muhammad Fauzan Nafiz Muhammad Haekal Muhammad Haekal Muhammad Iqbal Muhammad Irfan Saputra Muhammad Itqan Mazdadi Muhammad Janawi Muhammad Khairi Ihsan Muhammad Mada Muhammad Mursyidan Amini Muhammad Rizky Adriansyah Muhammad Rusli Muhammad Sholih Afif Muhammad Zaien MUJIZAT KAWAROE Muliadi Muliadi Muliadi Muliadi Aziz Muliadi Muliadi Muliadi Muliadi Muliadi Muliadi Mustofa, Fahmi Charish Ngo, Luu Duc Nor Indrani Noryasminda Nugrahadi, Dodon Nurlatifah Amini Nursyifa Azizah Oni Soesanto Prastya, Septyan Eka Purnajaya, Akhmad Rezki Putri Nabella Radityo Adi Nugroho Radityo Adi Nugroho Rahayu, Fenny Winda Rahmad Ubaidillah Rahmat Ramadhani Rahmat Ramadhani Rahmina Ulfah Aflaha Ratna Septia Devi RAUDLATUL MUNAWARAH Reina Alya Rahma Reza Rendian Septiawan Riadi, Putri Agustina Rinaldi Riza Susanto Banner Rizal, Muhammad Nur Rizki, M. Alfi Rizky, Muhammad Hevny Rossyking, Favorisen Rozaq, Hasri Akbar Awal Rudy Herteno Rudy Herteno Rudy Herteno Rudy Herteno Said, Muhammad Al Ichsan Nur Rizqi SALLY LUTFIANI Salsabila Anjani Saputro, Setyo Wahyu Saragih, Triando Hamonangan Sarah Monika Nooralifa Sari, Risna Sa’diah, Halimatus Septyan Eka Prastya Septyan Eka Prastya Setyo Wahyu Saputro Setyo Wahyu Saputro Siti Aisyah Solechah Solly Aryza Sri Redjeki Sri Redjeki Sugiarto, Iyon Titok Sulastri Norindah Sari Suryadi, Mulia Kevin Tri Mulyani Triando Hamonangan Saragih Umar Ali Ahmad Utami, Juliyatin Putri Vina Maulida, Vina Wahyu Caesarendra Wahyu Dwi Styadi Wahyudi Wahyudi Wildan Panji Tresna Winda Agustina Yenni Rahman YILDIZ, Oktay Yudha Sulistiyo Wibowo Yunida, Rahmi