Articles
Multi-Label Classification for Opinion Mining in The Presidential Election using TF-IDF with NB And SVM
Ardiansyah, Ricy;
Yuliansyah, Herman;
Yudhana, Anton
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 9 No. 1 (2025)
Publisher : P3M Politeknik Negeri Banjarmasin
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31961/eltikom.v9i1.1432
Public opinion plays a crucial role in presidential elections, shaping voter choices and influencing outcomes. Most sentiment analysis studies focus on binary (positive vs. negative) or multiclass (positive, negative, neutral) classification, which limits their ability to capture opinions that express multiple sentiments simultaneously. In presidential elections, a single opinion may support one candidate while criticizing another. This study proposes a MultiLabelBinarizer model to classify candidate and sentiment labels simultaneously—an approach that remains underexplored. The model combines Naïve Bayes (NB) and Support Vector Machine (SVM) for opinion mining using public data and TF-IDF for feature extraction, applying Multinomial and Linear kernels. Performance is evaluated using Accuracy, Precision, Recall, and F1-score. The study is conducted in two stages: developing a multi-label analysis model for presidential candidates and testing the effectiveness of cross-validation. Results show that multi-label classification is effective for both candidate and sentiment categories. Cross-validation with NB and SVM yields high accuracy. NB achieves 0.89 for candidate labels and 0.86 for sentiment labels. SVM performs better, with 0.93 for candidate labels and 0.94 for sentiment labels. While SVM provides higher accuracy, NB offers faster implementation with still competitive results.
Identifikasi Kesegaran Ikan Menggunakan Algoritma KNN Berbasis Citra Digital
Saputra, Sabarudin;
Yudhana, Anton;
Umar, Rusydi
Krea-TIF: Jurnal Teknik Informatika Vol 10 No 1 (2022)
Publisher : Fakultas Teknik dan Sains, Universitas Ibn Khaldun Bogor
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32832/krea-tif.v10i1.6845
Ikan merupakan komoditas utama laut yang penting sebagai sumber makanan. Ikan perlu diketahui kesegarannya sebelum dikonsumsi manusia. Tingkat kesegaran ikan biasanya diidentifikasi dengan cara konvensional seperti analisis kimiawi atau biokimiawi ikan, analisis kandungan mikrobiologi pada ikan, dan metode pemeriksaan sensori. Metode-metode tersebut dapat dilakukan namun membutuhkan kekuatan manusia yang cenderung mengalami kelelahan. Penelitian ini bertujuan untuk mengidentifikasi kesegaran ikan hasil tangkapan dengan menggunakan sistem komputerisasi digital. Metode yang digunakan adalah K-Nearest Neighbor dengan memanfaatkan citra mata ikan berbasis nilai fitur warna RGB. Data yang digunakan adalah 150 citra mata ikan yang diambil pada rentang waktu satu jam, lima jam, dan 10 jam. Citra mata ikan tersebut sebelumnya telah dilakukan cropping, segmentasi dan ekstraksi nilai RGB untuk kemudian diklasifikasikan berdasarkan kelas target. Data penelitian dibagi menjadi 120 citra untuk pelatihan dan 30 citra untuk pengujian. Hasil pengujian menunjukkan bahwa nilai akurasi paling tinggi menggunakan nilai K=1 yaitu sebesar 93,33%. Berdasarkan hasil akurasi tersebut maka metode KNN dapat menjadi model pengembangan identifikasi kesegaran ikan menggunakan citra digital.
Android-based Heart Rate and Blood Oxygen Level Monitoring System (Oximeter)
Saputra, Candra Deska;
Yudhana, Anton
Signal and Image Processing Letters Vol 3, No 1 (2021)
Publisher : Association for Scientific Computing Electrical and Engineering (ASCEE)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/simple.v3i1.34
The development of increasingly modern technology makes it possible to create a more advanced tool. The health sector as one of the important components of life also does not escape the support of technology. One of its implementations is an android-based heart rate and oxygen level monitoring system (oximeter). Heart rate monitoring can be done by everyone by utilizing existing technological developments. Measurements are made using only the fingers of the hand as input. The purpose of this study was to determine the design of a research tool for a heart rate monitoring system and blood oxygen levels (oximeter) based on android. This measuring instrument uses a Max30100 sensor which is attached to one person's fingertip to detect a heart rate signal, then the data generated by the sensor is received by Arduino, after that it is forwarded to Bluetooth and displayed on the Android application, then it will be processed into beats per minute (BPM) and blood oxygen levels (SPO2) so that you can find out the results of heart rate and oxygen levels displayed on Android. Based on the results obtained in heart rate monitoring, it can work well so that it can be seen the results of measurements using a device made with a person in normal conditions the heart rate beats between 60 to 75 beats per minute (BPM) and oxygen levels (SpO2) which can beat between 95 to 100, while using pulse oximetry results in normal body conditions the heart rate beats between 60 to 75 beats per minute (bpm) and oxygen levels (SpO2) which can be between 95 and 100 oxygen levels (SpO2).
Automation of Water Circulation Regulation and Nutritional Administration in Catfish Cultivation Ponds with Bioflocculation Technology
Ashari, Irvan;
Yudhana, Anton
Signal and Image Processing Letters Vol 5, No 1 (2023)
Publisher : Association for Scientific Computing Electrical and Engineering (ASCEE)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/simple.v5i1.52
Many catfish cultivators in Indonesia have failed due to lack of attention to the quality of the water used in aquaculture ponds. Water quality is very influential on the catfish farming system with biofloc technology, water has the most important role for the survival of catfish. This research periodically measures the level of turbidity and pH in the water, then the readings from the sensor will be processed by Arduino Uno which will be displayed on the LCD. In addition, this tool can also schedule the provision of nutrients as desired and is able to perform automatic water changes according to the conditions of the aquaculture pond, if the pH and turbidity conditions of the pond exceed the existing threshold, it will activate the drain pump and water increase. The accuracy of the acidity (pH) sensor has an accuracy rate of 96.21% which is very good, with a standard deviation of 2.49. The turbidity sensor has a standard deviation of 0.133. So this tool is designed to make it easier for cultivators to take care of the pond. The hope is that by making this tool it can overcome or overcome the mortality rate of catfish among cultivators.
Design a Heart Rate Counter Based on the Atmega328 Microcontroller Displayed Via Smartpone
Pratama, Gilang Ariya;
Yudhana, Anton
Signal and Image Processing Letters Vol 3, No 2 (2021)
Publisher : Association for Scientific Computing Electrical and Engineering (ASCEE)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/simple.v3i2.35
In today's era, technological advances are experiencing a rapid impact on human life as well as smartphones that trigger and influence technological developments in the health sector. The process of monitoring human heart rate can be known by its pulse that can be done by everyone by utilizing technological developments. The purpose of this study was to determine the design of a pulse response detection research test kit with a heartbeat sensor and display data through a smartphone. Using a pulse heart sensor attached to one person's fingertip to detect the pulse rate signal, then the sensor reading data is received by the smartphone via an analog pin (AO), forwarded via Bluetooth and displayed on the serial monitor application in the smartphone, then it will be processed into BPM (beats per minute) so that it can find out the pulse ticking signal displayed on the smartphone. Based on the results of the simulation carried out, the results of testing the tool on the heart rate sensor were able to detect the pulse rate signal response. A person's pulse rate when doing sports activities beats quickly compared to the pulse before doing sports activities, because when doing sports activities the heartbeat pumps blood to all parts of the body quickly. After testing, the tool can detect the number of pulses a person can work normally ranging from 90 to 100 Beat Per Minute (BPM) and indicates that the tool can work properly.
Prototype of Automatic Cover Roof Control system for Grain Drying Based on Internet of Things (IoT)
Putri, Dadva Pramesty Etsria;
Yudhana, Anton
Signal and Image Processing Letters Vol 2, No 1 (2020)
Publisher : Association for Scientific Computing Electrical and Engineering (ASCEE)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/simple.v2i1.76
The sun is the largest source of heat energy on earth. Sunlight as an energy source can be used for the drying process in drying grain. Grain drying is done by drying in the open field or often referred to as traditional drying. Drying using sunlight has weaknesses, including if the weather changes, such as sudden rain, it will be difficult to move the grain. As a result, the dry grain becomes wet again so it takes more time to dry. From these problems, this research makes an automatic roof design when it rains, the roof will be closed automatically. If the weather is sunny and it is not raining, the roof will open. The sensors used are rain sensors and LDR sensors as light sensors that can produce several weather outputs such as sunny, cloudy and dark. While the material used is like a motor to be able to move the pulley. And the motor will move after getting instructions from the NodeMCU that the light received from the light sensor is in accordance with the command then the motor will move and the pulley will lift the light and strong plastic roof to be able to cover the roof perfectly after the rain sensor works. System testing shows an error in light of 5.5% while the system error shown at temperature is 0.01% and an error in humidity is 0.11%. The ability of the system to cover the roof when it is cloudy or when it is raining.
Identification of Biodiesel from Used Cooking Oil Based on Image Color Characteristics
Sahta, Bobo;
Yudhana, Anton
Signal and Image Processing Letters Vol 2, No 2 (2020)
Publisher : Association for Scientific Computing Electrical and Engineering (ASCEE)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.31763/simple.v2i2.50
Biodiesel is a biofuel that will be used against the machine or motor type diesel, in the form of ester methyl fatty acids made from vegetable oils or animal. Biodiesel can overcome the problem of the depletion of petroleum and energy crisis. One of the raw materials to make the biodiesel is used cooking oil. Hardware design consists of the design of the black box measuring 27cm x 17cm x 13cm (Length x Width x Height) with 2 pieces of LED as lighting and those ones powered by a 9 Volt battery so that all samples taken in the same conditions. Then the software design consists of designing a GUI in MATLAB. Data retrieval biodiesel utilizing the camera of android SONY Docomo Xperia Z3 which has been equipped with a rear camera 20MP front camera and 5MP. Process to process the image itself with the transformation of the RGB color to HSV to the image by simply selecting the image Hue and the image of the saturation of the course, for the extraction of features (calculate the value of the mean on the image hue and saturation according to the columns or rows of a matrix). The determination of the class using the method of the closest distance that is Euclidean. The first stage to determine the traits that have standard data for reference. and the second stage testing process. Data to determine the characteristic wear 10 of each sample on each of biodiesel, which consists of 3 types. With a total of 30 samples were used as standard data for reference. A system test is performed with the test data, a total of 18 samples only. The results obtained for 15 samples of the test data successfully detected recognizable and 3 sample test data other not successfully detected. The level of accuracy of the system is the introduction of biodiesel shows the results of 83.3% by using the method of Euclidean distance, which means the level of accuracy is high.
Driving school program to strengthening anti-corruption education within the integrity zone policy
Suyadi, Suyadi;
Nuryana, Zalik;
Asmorojati, Anom Wahyu;
Yudhana, Anton
International Journal of Evaluation and Research in Education (IJERE) Vol 14, No 4: August 2025
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijere.v14i4.28773
For an extended period, education institutions have functioned independently, resulting in a notable disparity in educational quality. The Merdeka Belajar Kampus Merdeka (MBKM) promotes collaboration between educational institutions and schools, with the aim of serving as mentors for joint program development. This groundbreaking research delves deeply into the pivotal roles played by both lecturers and students within the MBKM program. They emerge as mentors in the crusade for implementing anti-corruption education within the dynamic context of Sekolah Penggerak, also known as the driving school program (DSP). Conducted as a qualitative descriptive study, this research draws its data from the collaborative efforts between higher education institutions and schools in developing anti-corruption education, leading to recognition from the Indonesian Corruption Eradication Commission (KPK-RI). The data collection process unfolds through a meticulously orchestrated combination of observations, in-depth interviews, and thorough documentation. The findings of this study are nothing short of transformative, as they underscore how the active involvement of MBKM’s lecturers and students in anti-corruption education serves as a potent catalyst, reinforcing the integrity zone policy within the DSP program. This seamless integration of anti-corruption education with Islamic education, encompassing profound concepts like riswah (bribery), ghulul (betrayal), and mukabarah-ghasab (seizing), represents a paradigm shift in pedagogical strategies.
IMPLEMENTASI METODE BUSINESS TO COSTUMER PADA SISTEM INFORMASI TOKO KGS RIZKY MOTOR
Utama, Kiagus Muhammad Rizky Aditra;
Umar, Rusydi;
Yudhana, Anton
RADIAL : Jurnal Peradaban Sains, Rekayasa dan Teknologi Vol. 9 No. 2 (2021): RADIAL: JuRnal PerADaban SaIns RekAyasan dan TeknoLogi
Publisher : Universitas Bina Taruna Gorontalo
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37971/radial.v9i2.234
Implemantasi Business To Costumer (B2C) merupakan bagian e-commerce dalam bentuk jual-beli produk yang melibatkan perusahaan penjual yang secara online melalui media website. Sistem yang sedang berjalan saat ini masih menggunakan sistem manual atau offline. Ini terjadi apabila pelanggan konsumen membeli produk sparepart harus datang langsung ke tokonya. Pada implementasi business to customer ini pada Toko Kgs Rizky Motor berupa online melalui media website yang mencakup berbagai informasi bagi pelaku consumer tentang penjualan sparepart secara online, dapat menampilkan produk-produk sparepart, cara pembelian pemesanan, keranjang belanja, catalog, akun pengusaha dan kontak pengusaha. Pada penelitian ini konsep tahapan-tahapan menggunakan metode waterfall dengan mengikuti alur proses analisis kebutuhan, desain sistem, coding dan implementasi, penerapan dan pemeliharaan.. Hal ini juga memakan waktu biaya yang dikeluarkan bisa jadi lebih tinggi. Dengan salah satu upaya adanya menggunakan implementasi E-Commerce business to customer diharapkan terus meningkatkan pelaku konsumen yang terjangkau dan memudahkan pelaku konsumen ingin membeli produk sparepart tanpa harus datang langsung ketoko pada saat jam tertentu. Hal ini dapat membantu menghemat biaya yang dikeluarkan. Sistem informasi yang dibangun mengimplementasikan tahapan-tahapan pengembangan dengan bahasa pemrograman PHP dengan Adobe Dreamweaver CS 5 dan My SQL menggunakan XAMPP.
Identifikasi Jenis Daun untuk Ecoprint Mengunakan Metode Convolutional Neural Network
Hajar, Siti;
Murinto, Murinto;
Yudhana, Anton
Jurnal Sains dan Informatika Vol. 11 No. 1 (2025): Jurnal Sains dan Informatika
Publisher : Teknik Informatika, Politeknik Negeri Tanah Laut
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.34128/jsi.v11i1.1774
Tumbuhan yang berdaun merupakan salah satu kategori tumbuhan yang memiliki berbagai manfaat. Tumbuhan ini dapat dimanfaatkan sebagai bahan dalam produk kecantikan, makanan, obat-obatan, pewarna alami, dan kain. Makalah ini membahas cara mengidentifikasi jenis daun untuk ecoprint dengan menggunakan metode Deep Learning, khususnya Convolutional Neural Network (CNN). Tujuan dari identifikasi ini adalah untuk mempermudah menentukan jenis daun yang bisa dan tidak bisa untuk ecoprint teknik steaming. Metode yang digunakan saat ini masih manual, dengan mengambil beberapa jenis daun dan diproses. Dalam pemrosesan manual sangat lama lebih dari satu hari, dan tidak efisien untuk membuktikan bahwa sampel daun yang dicoba tersebut bisa atau tidak untuk ecoprint. Mengatasi masalah ini, solusi mengunakan Convolutional Neural Network (CNN) algoritma Deep Learning lebih tepat. Penelitian ini menganalisis 400 gambar daun yang diambil dari 10 jenis daun untuk diidentifikasi. Proses pelatihan dilakukan dalam dua tahap: Feature Learning dan Klasifikasi, dengan jumlah epoch sebanyak 15. Hasil training (0,9850) dan valisasi (0,9796) sedangkan hasil pengujian accuracy rata-rata diperoleh (0,9194). Dapat disimpulkan bahwa algoritma Deep Learning yaitu Convolutional Neural Network (CNN) bisa mengidentifikasi jenis daun untuk ecoprint.