Claim Missing Document
Check
Articles

Found 34 Documents
Search

Perbandingan Akurasi Algoritma Data Mining dalam Memprediksi Kelulusan Tepat Waktu Ricoida, Desy Iba; Hermanto, Dedy; Pibriana, Desi; Rusbandi, Rusbandi; Pribadi, Muhammad Rizky
DoubleClick: Journal of Computer and Information Technology Vol 7, No 2 (2024): Edisi Februari 2024
Publisher : Universitas PGRI Madiun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25273/doubleclick.v7i2.19300

Abstract

Lulusan tepat waktu menjadi salah satu poin penilaian sangat penting bagi sebuah perguruan tinggi untuk memperoleh nilai akreditasi. Dikatakan lulusan tepat waktu jika seorang mahasiswa dapat lulus empat tahun atau dibawah empat tahun jika berada pada jenjang Strata-1. Penelitian ini menggunakan dataset yang diperoleh dari universitas dengan data dari angkatan 2015-2019, dimana total data yang digunakan yaitu sebanyak 1307 baris. Sebanyak 26 atribut yang digunakan dalam penelitian ini yaitu tahun_masuk, waktu_kuliah, jenis_kelamin, tipe_sekolah, jurusan, IPS 1-10, SKS 1-10 dan status. Algoritma yang digunakan dalam penelitian ini yaitu decision tree, naive bayes, logistic regression, KNN dan random forest. Hasil yang diperoleh dalam penelitian ini yaitu algoritma random forest memiliki tingkat akurasi yang paling tinggi sebesar 90.88% dengan hasil dari AUC yang diperoleh yaitu sebesar 97.2% dan perhitungan F1-Score dari hasil nilai precision dan recall diperoleh sebesar 89.9%, tertinggi dari empat algoritma lainnya. Sedang untuk algoritma decision tree dan logistic regression memiliki nilai akurasi masing-masing yaitu sebesar 89.12% dan 89.47%. Nilai dari logistic regressing lebih tinggi untuk akurasi, akan tetapi untuk nilai F1-Score decision tree lebih baik dari logistic regression yaitu 88.7% berbanding 87.6%.
Perancangan UI/UX Website Pengontrol Kelembapan Tanah Berbasis IoT dan Sensor Kynta, Diva Putri; Laksono, Ivan Luthfi; Wijaya, Vannes; Fadli, Muhammad; Hermanto, Dedy
MDP Student Conference Vol 3 No 1 (2024): The 3rd MDP Student Conference 2024
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/mdp-sc.v3i1.7278

Abstract

Soil moisture is an important factor in agriculture, affecting plant health and crop productivity. Indonesia has experienced droughts that resulted in crop failure of 1,177 (31.95%) hectares out of a total of 3,685 hectares of agricultural land. With the arrival of the industrial era 5.0, there is an opportunity to improve soil moisture management. This research aims to design the UI/UX of an IoT and sensor-based soil moisture control website application. This system is designed to make it easier for farmers to monitor and manage soil moisture, so as to improve irrigation efficiency and crop quality. The method used in the design process of this application is the Design Thinking method. The final result obtained from this research is a User Interface and User Experience that can be a solution to existing problems. 61% of 12 respondents stated that the UI design of KeTan was very good, and 42% of 12 respondents gave very good scores for the UX of KeTan.
Penentuan Epochs Hasil Model Terbaik: Studi Kasus Algoritma YOLOv8 Jonathan, Jasen; Dedy Hermanto
Digital Transformation Technology Vol. 4 No. 2 (2024): Periode September 2024
Publisher : Information Technology and Science(ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/digitech.v4i2.4640

Abstract

Salah satu pengembangan machine learning yaitu deep learning merupakan salah satu metode inti dalam artificial intelligence yang sedang berkembang dengan pesat, dikarenakan kemampuannya dalam mempelajari informasi dalam jumlah besar. Salah satu cabang dari deep learning adalah computer vision, dan Convolutional Neural Network (CNN) yang merupakan metode yang paling banyak digunakan untuk melakukan pemrosesan citra. YOLOv8 merupakan salah satu algoritma yang menggunakan CNN yang telah dimodifikasi sebagai dasar, YOLOv8 merupakan algoritma open-source yang paling banyak digunakan dikarenakan menghasilkan hasil pengenalan objek yang akurat, cepat, dan mudah untuk di implementasikan. Proses pelatihan model dari YOLOv8 membutuhkan perangkat yang cukup memadai dengan jumlah epochs yang ditentukan secara manual. Penelitian ini bertujuan untuk mengetahui jumlah epoch yang dibutuhkan dalam membuat model YOLOv8 sesuai dengan kriteria yang di tentukan pada penelitian ini. Pelatihan akan dilakukan dengan menggunakan 50 epochs, 100 epochs, 150 epochs, 200 epochs, 250 epochs, dan 300 epochs. Pelatihan akan di jalankan dengan menggunakan dataset citra bibit ikan lele yang terdiri dari 753 gambar bibit ikan lele yang telah di anotasikan. Pelatihan dijalankan dengan menggunakan CPU Ryzen 5 4600H. Berdasarkan dari hasil pelatihan didapatkan bahwa 50 epochs memiliki waktu pelatihan tercepat dengan hasil yang kurang baik. Hasil terbaik terdapat pada 200-300 epochs dengan rata-rata precision sebesar 96% dengan waktu pelatihan yang cukup lama.
Analysis of Student Graduation Prediction Using Machine Learning Techniques on an Imbalanced Dataset: An Approach to Address Class Imbalance Hermanto, Dedy; Desy Iba Ricoida; Desi Pibriana; Rusbandi; Muhammad Rizky Pribadi
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.5528

Abstract

Purpose: Machine learning is a key area of artificial intelligence, applicable in various fields, including the prediction of timely graduation. One method within machine learning is supervised learning. However, the results are influenced by the distribution of data, particularly in the case of imbalanced classes, where the minority class is significantly smaller than the majority class, affecting classification performance. Timely graduation from a university is crucial for its sustainability and accreditation. This research aims to identify a suitable method to address the issue of predicting timely graduation by managing class imbalance using SMOTE (Synthetic Minority Oversampling Technique). Methods: This study uses a five-year dataset with 26 attributes and 1328 records, including status labels. The preprocessing stages involve applying five classification algorithms: Decision Tree (DT), Naive Bayes (NB), Logistic Regression (LR), K-Nearest Neighbors (KNN), and Random Forest (RF). Each algorithm is used both with and without SMOTE to handle the class imbalance. The dataset indicates that 60.84% of the cases represent timely graduations. To mitigate the imbalance, over/under-sampling methods are employed to balance the data. The evaluation metric used is the confusion matrix, which assesses the classification performance. Result: Without SMOTE, the accuracies were 89.12% for DT, 79.65% for NB, 89.47% for LR, 87.72% for KNN, and 90.88% for RF. With SMOTE, the accuracies were 88.89% for DT, 81.48% for NB, 91.05% for LR, 92.59% for KNN, and 89.81% for RF. The algorithms NB, LR, and KNN showed improvement with SMOTE, with KNN yielding the best results. Novelty: Based on the comparison results, a comparison of five algorithms with and without SMOTE can reasonably classify several of the algorithms being compared.
Pengembangan Website Perpustakaan menggunakan Agile Software Development Saputra, Darwin; Theng, Arifin; Hermanto, Dedy
JURMATIS (Jurnal Manajemen Teknologi dan Teknik Industri) Vol. 5 No. 2 (2023): August
Publisher : Universitas Kadiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30737/jurmatis.v5i2.3837

Abstract

SD Muhammadiyah 10 Palembang as an educational service with a travel time of 19 minutes from Jalan Jenderal Ahmad Yani, Palembang.  Library facilities attract students because of the availability of the latest books.  However, the current system has not been able to manage collections properly. Upgrading the latest system becomes a competitiveness to create the latest and agility of the website system. The development of website systems has experienced technological development by 61.9% in the last 10 decades.  The change of HTML to javascript is a challenge in the development of this system.  An agile website is the main solution to facilitate library services. The features that users need and functionality become the right solution. Case study design becomes the main approach, because it adopts realistic conditions. Designing use case and entity relationship diagrams as technical to visualize and structure the features needed. Respondents in charge of testing when the prototype is ready to run. The success of the website prototype is tested through the pieces approach.  The development of agile website systems has been successfully tested. Javascript as a programming language does not experience errors.  This has proven that the development of the website is true and the development conditions have been able to manage the collection well according to the features needed by users. The library website of SD Muhammadiyah 10 Palembang has been successfully used, thus increasing the attractiveness for prospective students in the future.
Pemantauan Kelembaban tanah Berbasis IoT Menggunakan Sensor Soil Moisture Laksono, Ivan Luthfi; Kynta, Diva Putri; Fadli, Muhammad; Wijaya, Vannes; Hermanto, Dedy
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 5 No 1 (2024): Oktober 2024 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v5i1.8961

Abstract

Soil is commonly utilized as a substrate for the cultivation of plants. The level of soil moisture has a significant impact on the growth and survival of nearby plants. Flourishing vegetation assimilates water from the soil, thereby impacting soil moisture. In addition, solar radiation induces water evaporation in the soil, leading to its desiccation. Excessively arid soil leads to plant wilting, whereas excessively saturated soil hinders the optimal growth of neighboring plants. This study focuses on the real-time detection of soil moisture using a Soil Moisture sensor. The approach employed in this research is Research and Development. The research process consists of three stages: planning, design, and assessment. The Soil Moisture sensor will collect data on the moisture content of the soil. This data will then be retrieved and documented by the ESP32 device, which will transmit and store it in a Firebase database. Once the data is recorded, it will be showcased on a website developed with the PHP programming language and the Laravel framework. This will allow users to monitor the exhibited information directly. The investigation yielded variations within each category for dry soil 28.5%, moist 58.4%, and wet 68%.
Pengenalan Makanan Khas Palembang Secara Realtime Menggunakan Yolov8 dan Text to Speech Valentino, Calvin Bertnas; Hermanto, Dedy
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 5 No 2 (2025): April 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v5i2.9937

Abstract

The introduction of traditional Palembang food has an important role in preserving local cultural and culinary heritage. As interest in object recognition technology grows, challenges arise in creating a system that is able to recognize typical types of Palembang food effectively and efficiently. This research aims to overcome these challenges by developing a food detection system based on the You Only Look Once (YOLO) algorithm, which is known for its ability to detect objects in real-time with high accuracy. The dataset used consists of 1,234 images, which are divided into three parts: 70% for training data, 20% for validation data, and 10% for test data. By utilizing YOLO, this system can detect and recognize typical Palembang food in an average time of 3.15 seconds, and achieve an accuracy of 99.28%. Apart from that, this research also integrates a Text-to-Speech feature which provides a verbal description of the detected food, thereby increasing interaction and convenience for users.
Early Mental Health Detection with Machine Learning : A Practical Approach to Model Development and Implementation Hermawan, Latius; Syakurah, Rizma Adlia; Meilinda, Meilinda; Stiawan, Deris; Negara, Edi Surya; Ramayanti, Indri; Fahmi, Muhammad; Rizqie, Muhammad Qurhanul; Hermanto, Dedy
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 13, No 2: June 2025
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v13i2.6111

Abstract

Academic pressures, lifestyle changes, and socio-economic factors significantly impact mental health, a critical determinant of academic success and well-being. Early detection and intervention are crucial to mitigate severe outcomes like academic underperformance and suicidal tendencies. Leveraging tools like the DASS-42, this study examines mental health patterns using Support Vector Machine (SVM) models, achieving accuracies of 88% for depression, 71% for stress, and 57% for anxiety. While the model excels in identifying "Normal" cases, its performance for "Mild," "Moderate," and "Severe" cases highlights limitations due to class imbalance and feature representation. The findings reveal that anxiety is the most volatile and severe condition, with peaks in 2018 and 2022, while stress remains manageable and depression moderately stable. Gender and program-specific differences emphasize the need for tailored interventions. Addressing challenges related to data quality, algorithmic transparency, and ethical concerns is essential for real-world applications. This study highlights the potential of machine learning in early detection and intervention for mental health issues. Future research should explore advanced feature engineering techniques and develop more interpretable models to enhance clinical decision-making.
Performance Comparison of YOLOv10, YOLOv11, and YOLOv12 Models on Human Detection Datasets Hendriko, Viky; Hermanto, Dedy
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.6447

Abstract

One popular of object detection model for object detection is You Only Look Once (YOLO) with humans are among the most often utilized for detection objects. Despite the various of human datasets, just a few research that compared the datasets performance against various versions of the YOLO algorithm. This study compares the performance of YOLOv10, YOLOv11, and YOLOv12 on eight different datasets, such as CrowdHuman, CityPersons, Wider Person, Mall Dataset, INRIA, Microsoft Common Object (MS COCO), PASCAL VOC, and MOT17. Precision, recall, mAP@50, and mAP@50-95 are used to measure the YOLO model version's performance on each dataset. The results indicate that each datasets have different perfomance on each version of YOLO, so the performance on model depends on the variation of the dataset. The best results on the MOT17 dataset are obtained by YOLOv12, with 0.909 in precision, 0.775 in recall, 0.88 in mAP@50, and 0.695 in mAP@50-95. On the City Person dataset. However, YOLOv11 performs best result, with 0.782 in precision, 0.529 in recall, 0.694 in mAP@50, and 0.476 in mAP@50-95. Therefore, choosing a YOLO version that is appropriate for the dataset's complexity is essential to creating the best detection model Therefore, selecting the appropriate YOLO version according to the dataset complexity is crucial to obtain the most optimal detection model.
Classification of Mango Varieties from Leaf Images Using ResNet-50 CNN Architecture Komah, Neilsen Nicholas; Hermanto, Dedy
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.6571

Abstract

Early identification of mango (Mangifera indica L.) varieties is crucial for optimizing cultivation, as each variety possesses distinct characteristics and regional adaptability. However, the morphological similarities in leaf shape and texture especially among Harumanis, Erwin, Cokanan, Gedong Gincu, and Mahatir pose challenges for novice farmers and hobbyists. This study proposes a classification system using the Convolutional Neural Network (CNN) method with the ResNet-50 architecture to classify mango leaf varieties based on image data. A total of 5,000 images were collected and augmented from 1,250 original samples using a high-resolution camera under controlled indoor conditions. The dataset was split into training (80%), validation (10%), and testing (10%). Sixteen experimental configurations were evaluated using combinations of image resolutions (160×160 and 320×320 pixels), learning rates (0.01, 0.001), batch sizes (16, 32), and training epochs (50, 100). The best results were achieved using a 320×320 image size, learning rate of 0.001, batch size of 32, and 100 epochs, yielding a validation accuracy of 89.9%, precision of 89.87%, recall of 89.9%, and F1-score of 89.83%. These results confirm that high-resolution images and fine-tuned hyperparameters significantly enhance classification performance. The findings demonstrate the effectiveness of the ResNet-50 model for fine-grained classification in agriculture and support its future deployment in real-world environments for cultivar identification, quality control, and intelligent crop management.