Claim Missing Document
Check
Articles

Found 23 Documents
Search

Prediction of Sleep Disorders Based on Occupation and Lifestyle: Performance Comparison of Decision Tree, Random Forest, and Naïve Bayes Classifier Lestiawan, Heru; Jatmoko, Cahaya; Agustina, Feri; Sinaga, Daurat; Erawan, Lalang
(JAIS) Journal of Applied Intelligent System Vol. 8 No. 3 (2023): Journal of Applied Intelligent System
Publisher : LPPM Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33633/jais.v8i3.8987

Abstract

Health is a very important thing in life. Therefore, to maintain health, we need adequate rest. Without adequate rest, the body will not be healthy and fit. In this study, a person's sleep disorder prediction will be made based on their lifestyle and work. The predictions made will classify sleep disorders that are absent, sleep apnea and insomnia from certain lifestyles and work. The methods used to make predictions are decision tree classifier, random forest classifier and naïve Bayes classifier. The test was carried out using a total of 375 data which was broken down into 70% training data and 30% testing data. The results obtained after testing with test data are by using the decision tree classifier algorithm to get an accuracy of 89.431%, using the random forest classifier algorithm to get an accuracy of 90.244% and by using the naïve Bayes classifier algorithm to get an accuracy of 86.992%.
Gabor wavelet and multiclass support vector machine for braille image classification Agustina, Feri; Rachmawanto, Eko Hari; Putri, Ni Kadek Devi Adnyaswari; Saputro, Fakhri Rasyid; Lestiawan, Heru; Suprayogi, Suprayogi; Huda, Solichul
Journal of Soft Computing Exploration Vol. 5 No. 3 (2024): September 2024
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v5i3.474

Abstract

Braille is a letter designed for the visually impaired. As a family with normal vision who have a visually impaired child find it difficult to Teach their child how to learn and understand the process of learning from home. Learning braille requires good finger sensitivity and memory to memorize each letterform, making it difficult to learn.  With this study, braille letters can be detected from the image using the Gabor Wavelet method to extract braille images and combined with the Multiclass Support Vector Machine (Multiclass SVM) algorithm as a classification method for extracted braille images. Data testing was performed using a confusion matrix to determine the level of precision, accuracy, and recall. According to the results of tests performed on 910 braille data using confusion matrix, the highest recognition accuracy was 98,02%. The accuracy of these results is impacted by the parameters of the training process, the training data, and the test data used. This research has the opportunity to be developed in voice-based card recognition to help the visually impaired in the future research.
Comparative Study of Classification of Eye Disease Types Using DenseNet and EfficientNetB3 Jatmoko, Cahaya; Lestiawan, Heru; Agustina, Feri; Erawan, Lalang
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 9, No. 3, August 2024
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v9i3.1931

Abstract

The purpose of this research is to build a classification model that can perform the eye disease identification process so that the diagnosis of eye disease can be known and medical action can be taken as early as possible. This research used a dataset which has a total of 4217 eye image data and had 4 main classes namely cataract, diabetic retinopathy, glaucoma, and normal. With the data distribution of 1038 cataract images, 1098 diabetic retinopathy images, 1007 glaucoma images, and 1074 normal images, which of this data will be divided with a data percentage scheme of 50:10:40, 60:10:30, and 70:10:20, to see the results of which dataset division can produce optimal accuracy. In this study, the classification process will use 2 CNN transfer learning architectures, namely DenseNet, and efficientnetb3, which are both trained using the ImagiNet dataset. The results obtained after completing the testing process on the model built using the DenseNet architecture get optimal accuracy when using data division as much as 60:10:30, which is 78.59% while using the efficientnetb3 architecture optimal accuracy results when using the data division of 70:10:20, which is 95.66%. In research on the classification that had previously been done, it is very rare to find a classification process for eye disease types, therefore, in this study, the classification process will be carried out and provide an overview of the eye disease classification process with the CNN transfer learning method with more optimal accuracy results.
Improved imperceptible engagement-based 2D sigmoid logistic maps, Hill cipher, and Kronecker XOR product Lestiawan, Heru; Sani, Ramadhan Rakhmat; Abdussalam, Abdussalam; Rachmawanto, Eko Hari; Purwanto, Purwanto; Sari, Christy Atika; Doheir, Mohamed
Bulletin of Electrical Engineering and Informatics Vol 14, No 3: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i3.8331

Abstract

Image encryption is a crucial facet of secure data transmission and storage, and this study explores the efficacy of combining sigmoid logistic maps (SLM), Hill cipher, and Kronecker's product method in enhancing image encryption processes. The evaluation, conducted on diverse images such as Lena, Rice, Peppers, Cameraman, and Baboon, unveils noteworthy findings. The Lena image emerges as the most successfully encrypted, as evidenced by the lowest mean squared error (MSE) at 92.81 and the highest peak signal-to-noise ratio (PSNR) at 19.43, reflecting superior fidelity and quality preservation. Additionally, the encryption of 64×64 pixels images consistently demonstrate robustness, with a high number of pixels change rate (NPCR) and unified average change intensity (UACI) values, particularly notable for the Cameraman image. Even for 128×128 pixels images, commendable encryption performance persists across the tested images. The amalgamation of SLM, Hill cipher, and Kronecker's product emerges as an effective strategy for balancing security and perceptual quality in image encryption, with the Lena image consistently outperforming others based on comprehensive metrics. This research provides valuable insights for future studies in the dynamic domain of image encryption, emphasizing the potential of advanced cryptographic techniques in ensuring secure multimedia communication.
Pemanfaatan Artificial Intelegence untuk Membangun Website Pembelajaran bagi Guru dan Dosen pada Perkumpulan Profesi Multimedia dan Teknologi Informasi (PPMULTINDO) Cahaya Jatmoko; Sindhu Rakasiwi; Feri Agustina; Daurat Sinaga; Heru Lestiawan
Kesejahteraan Bersama : Jurnal Pengabdian dan Keberlanjutan Masyarakat Vol. 2 No. 3 (2025): Juli : Kesejahteraan Bersama : Jurnal Pengabdian dan Keberlanjutan Masyarakat
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62383/bersama.v2i3.1725

Abstract

The utilization of Artificial Intelligence (AI) technology in education has become increasingly important with the development of information technology. This research aims to provide training for teachers and lecturers in using AI to build interactive and effective learning websites. The method used is online training via Zoom Meeting, which includes an introduction to basic AI concepts, practice creating learning websites, and evaluating training outcomes. The training was conducted over three days from October 26 to 28, 2024, with participants from various regions across Indonesia. The results showed that participants were able to understand AI concepts and apply them effectively in building learning websites more efficiently and creatively. Additionally, the use of AI helped improve the quality of learning content to be more personalized and adaptive to students' needs. Thus, the application of AI in education can serve as an innovative solution to enhance the quality of learning in the digital era.
Optimized Visualization of Digital Image Steganography using Least Significant Bits and AES for Secret Key Encryption Jatmoko, Cahaya; Sinaga, Daurat; Lestiawan, Heru; Astuti, Erna Zuni; Sari, Christy Atika; Shidik, Guruh Fajar; Andono, Pulung Nurtantio; Yaacob, Noorayisahbe Mohd
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 10, No. 3, August 2025
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v10i3.2252

Abstract

Data hiding is a technique used to embed secret information into a cover medium, such as an image, audio, or video, with minimal distortion, ensuring that the hidden data remains imperceptible to an observer. The key challenge lies in embedding secret information securely while maintaining the original quality of the host medium. In image-based data hiding, this often means ensuring the hidden data cannot be easily detected or extracted while still preserving the visual integrity of the host image. To overcome this, we propose a combination of AES (Advanced Encryption Standard) encryption and Least Significant Bit (LSB) steganography. AES encryption is used to protect the secret images, while the LSB technique is applied to embed the encrypted images into the host images, ensuring secure data transfer. The dataset includes grayscale 256x256 images, specifically "aerial.jpg," "airplane.jpg," and "boat.jpg" as host images, and "Secret1," "Secret2," and "Secret3" as the encrypted secret images. Evaluation metrics such as Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), Unified Average Changing Intensity (UACI), and Number of Pixels Changed Rate (NPCR) were used to assess both the image quality and security of the stego images. The results showed low MSE (0.0012 to 0.0013), high PSNR (58 dB), and consistent UACI and NPCR values, confirming both the preservation of image quality and the effectiveness of encryption for securing the secret data.
XGBoost-Powered Ransomware Detection: A Gradient-Based Machine Learning Approach for Robust Performance Ghozi, Wildanil; Lestiawan, Heru; Sani, Ramadhan Rakhmat; Hussein, Jassim Nadheer; Rafrastara, Fauzi Adi
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 10, No. 4, November 2025
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v10i4.2405

Abstract

Ransomware remains a rapidly evolving cyber threat, causing substantial financial and operational disruptions globally. Traditional signature-based detection systems are ineffective against sophisticated, zero-day attacks due to their static nature. Consequently, machine learning-based approaches offer a more effective and adaptive alternative. This study proposes an approach utilizing XGBoost for highly effective ransomware detection. We conducted a rigorous comparative analysis of prominent ensemble learning algorithms—XGBoost, Random Forest, Gradient Boosting, and AdaBoost—on the RISS Ransomware Dataset, comprising 1,524 instances. Our experimental results unequivocally demonstrate XGBoost as the superior ensemble model, achieving an impressive 97.60% accuracy and F1-Score. This performance surpassed Gradient Boosting (97.20%), Random Forest (96.94%), and AdaBoost (96.50%). Furthermore, this study benchmarked XGBoost against established state-of-the-art (SOTA) methods, including Support Vector Machine (SVM) and the SA-CNN-IS deep learning approach. The comprehensive results underscore the core contribution of this study: by applying XGBoost with a carefully structured machine learning pipeline, our approach consistently outperforms two state-of-the-art methods (SVM and SA-CNN-IS) as well as other ensemble algorithms. This highlights the critical role of methodological precision in maximizing detection performance against evolving ransomware threats.
PREDIKSI PENYAKIT MATA MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK Jatmoko, Cahaya; Lestiawan, Heru
Semnas Ristek (Seminar Nasional Riset dan Inovasi Teknologi) Vol 8, No 01 (2024): SEMNAS RISTEK 2024
Publisher : Universitas Indraprasta PGRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/semnasristek.v8i01.7129

Abstract

Penyakit mata merupakan sebuah penyakit yang sangat berbahaya dan memiliki dampak yang dapat menghambat aktivitas kita sebagai manusia. Oleh karena itu, kita perlu melakukan proses identifikasi dan diagnosis terlebih dahulu untuk dapat mengetahui gejala yang terjadi pada penyakit mata. Pada penelitian ini, akan dilakukan proses klasifikasi penyakit mata dengan menggunakan metode CNN. Dataset yang digunakan pada penelitian ini yaitu merupakan dataset penyakit mata yang memiliki total data citra sebanyak 4217 citra dengan 4 kelas yaitu cataract, diabetic retinopathy, glaucoma dan normal. Pada penelitian ini, akan menggunakan metode Convolutional Neural Network untuk melakukan proses klasifikasi. Hasil yang didapatkan steelah dilakukannya pengujian pada penelitian ini yaitu mendapatkan akurasi pengujian yaitu sebesar 75.27%.
Imperceptible Watermarking Using Discrete Wavelet Transform and Daisy Descriptor for Hiding Noisy Watermark Abdussalam, Abdussalam; Umam, Chaerul; Sari, Wellia Shinta; Rachmawanto, Eko Hari; Shidik, Guruh Fajar; Andono, Pulung Nurtantio; Lestiawan, Heru; Islam, Hussain Md Mehedul
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 2 (2025): JUTIF Volume 6, Number 2, April 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.2.4423

Abstract

This research aims at overcoming the challenge of improving security and robustness in digital image watermarking, a critical activity in protecting intellectual property against misuse and manipulation. In a move to overcome such a challenge, this work introduces a new form of watermarking that incorporates Discrete Wavelet Transform (DWT) and Daisy Descriptor, with a view to enhancing both durability and invisibility of the watermark. The proposed method embeds a noise-variant watermark into selected frequency sub-bands using DWT, while the Daisy Descriptor enhances resistance to noise-based attacks. Testing conducted with three grayscale images, namely Lena, Cameraman, and Lion, each with a resolution of 512 × 512 pixels, showed that the proposed DWT-Daisy Descriptor outperforms current methodologies, producing high Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) values. In fact, in Lena, a PSNR value of 63.71 dB and an SSIM value of 1 were attained, with Cameraman having a PSNR value of 68.33 dB and an SSIM value of 1. As for attack resistivity, a high PSNR value of 50.11 dB under Gaussian attack and 55.70 dB under Salt-and-Pepper attack, with SSIM values approaching 1, confirm the robustness of the proposed scheme. This study highlights the significance of an efficient and secure watermarking technique that not only preserves image quality but also withstands various distortions, making it highly relevant for digital content protection in modern multimedia applications.
Pelatihan Diklat Visualisasi Data Menggunakan Google Data Studio untuk Guru dan Dosen pada Perkumpulan Profesi Multimedia dan Teknologi Informasi (PPMultindo) Rokhman, Nur; Jatmiko, Cahaya; Rakasiwi, Sindhu; Heru Lestiawan
Community : Jurnal Pengabdian Pada Masyarakat Vol. 3 No. 3 (2023): November : Jurnal Pengabdian Pada Masyarakat
Publisher : LPPM Sekolah Tinggi Ilmu Ekonomi - Studi Ekonomi Modern

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/community.v3i3.415

Abstract

Situasi pandemic COVID-19 membuat dunia pembelajaran perlu penyesuaian cepat salah satunya dalam pembuatan media pembelajaran, dimana guru dan deosen berperan dalam menyajikan metode-metode dengan pemanfaatan teknologi informasi salah satunya melalui media pembelajaran. Kegiatan pengabdian yang dilaksanakan secara daring melalui aplikasi Zoom ini menitikberatkan pada Pelatihan Membangun Visualisasi Data Menggunakan Google Data Studio berwawasan teknologi agar dimiliki dan dikuasai guru dan dosen sebagai tenaga pendidik pada Perkumpulan Profesi Multimedia dan Teknologi Informasi (PPMultindo). Pelatihan ini juga mengubah pola pikir bahwa membuat media pembelajaran adalah sesuatu yang rumit dan membosankan dikarenakan tidak banyaknya guru dan dosen yang berkompetensi di bidang teknologi informasi, menjadi mudah dan menyenangkan. Hasilnya para guru dan dosen mempunyai kemampuan dasar untuk membuat media pembelajaran dan mengembangkannya dengan visualisasi data menggunakan Google Data Studio dan siswa nantinya dapat secara interaktif untuk mengaksesnya dan dapat meningkatkan pemahaman materi yang diberikan.