Garuda - Garba Rujukan Digital

Pendeteksian Jumlah Bangunan Berbasis Citra Menggunakan Metode Deep Learning Bagaskara, Radhinka; Rizkita, Alya Khairunnisa; Fernandes, Rivaldo; Yulita, Winda
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 6, No 1 (2022): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v6i1.428

Counting residential houses is one of the problems faced when determining population density level in Indonesia, therefore it’s required to find a method that’s able to solve said problem. Deep learning method is capable of creating a prediction model for detecting the number of buildings from an image. The deep learning prediction model is created with MobileNetv2 application. The prediction model is trained by using a dataset from Kaggle. The prediction model is tested using satellite photos taken from Way Kandis-Sukarame, Bandar Lampung. The result is a deep learning prediction model with accuracy of 91.30% for SenseFly and 10.34% for Way Kandis dataset. The research can be further improved by using a better training and testing dataset

Pendeteksian Jumlah Bangunan Berbasis Citra Menggunakan Metode Deep Learning Bagaskara, Radhinka; Rizkita, Alya Khairunnisa; Fernandes, Rivaldo; Yulita, Winda
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 6, No 1 (2022): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v6i1.428

Counting residential houses is one of the problems faced when determining population density level in Indonesia, therefore it’s required to find a method that’s able to solve said problem. Deep learning method is capable of creating a prediction model for detecting the number of buildings from an image. The deep learning prediction model is created with MobileNetv2 application. The prediction model is trained by using a dataset from Kaggle. The prediction model is tested using satellite photos taken from Way Kandis-Sukarame, Bandar Lampung. The result is a deep learning prediction model with accuracy of 91.30% for SenseFly and 10.34% for Way Kandis dataset. The research can be further improved by using a better training and testing dataset

Improved human image density detection with comparison of YOLOv8 depth level architecture and drop-out implementation Yulita, Winda; Ramadhani, Uri Arta; Mufidah, Zunanik; Atmajaya, Gde KM; Bagaskara, Radhinka; Kesuma, Rahman Indra; Aprilianda, Mohamad Meazza
Journal of Soft Computing Exploration Vol. 6 No. 1 (2025): March 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v6i1.556

Energy inefficiency due to Air Conditioners (AC) running in empty rooms contribute to unnecessary energy consumption and increased CO₂ emissions. This study explores how different depth levels of the YOLOv8 architecture and dropout regularization can enhance human density detection for smarter AC control systems. By evaluating model accuracy through Mean Average Precision (mAP50-95), we provide quantitative insights into how these modifications improve detection performance. Our dataset consists of 1363 images taken in an office environment at ITERA under varying lighting conditions and different human presence densities. The results show that the YOLOv8m model performs best, achieving an mAP50-95 score of 0.814 in training and 0.813 in validation, outperforming other YOLOv8 variants. Furthermore, applying dropout regularization improves model generalization, increasing mAP50-95 from 0.552 to 0.6 and effectively reducing overfitting. This study highlights the balance between architectural depth and dropout regularization in YOLOv8, demonstrating its effectiveness in energy-efficient smart buildings. The findings support the potential of deep learning-based human density detection in improving energy conservation strategies, making it a valuable solution for intelligent automation systems.

Evaluasi Logistic Regression dan Neural Network pada Klasifikasi Gagal Jantung Berbasis Threshold Anggraini, Leslie; Akram Abdillah, Attar; Kartadilaga, Muhammad Qaessar; Verdiana, Miranti; Nugroho, Eko; Afriansyah, Aidil; Febrianto, Andre; Bagaskara, Radhinka
Jurnal Teknik Informatika UNIKA Santo Thomas Vol 10 No. 1 : Tahun 2025
Publisher : LPPM UNIKA Santo Thomas

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

Kardiovaskular adalah sistem jantung dan pembuluh darah dalam tubuh manusia yang bertanggung jawab atas sirkulasi darah dalam jantung, pembuluh darah, dan darah sendiri. Gangguan pada fungsi sistem ini dapat menyebabkan penyakit kardiovaskular, seperti gagal jantung, yang menjadi salah satu penyebab utama kematian di seluruh dunia. Kematian yang disebabkan oleh gagal jantung mempengaruhi 1.5 juta pasien di seluruh dunia. Dikarenakan oleh data statistik tersebut, maka ada kebutuhan untuk dapat memprediksi dampak gagal jantung untuk membantu tingkat kelangsungan hidup pasien. Sebagai bentuk kontribusi terhadap kebutuhan tersebut, penelitian ini akan menganalisis sebuah dataset pelayanan kesehatan, yaitu dataset rekam gagal jantung dari UCI. Dataset tersebut akan digunakan untuk mengklasifikasi dan memprediksi peluang kematian dari pasien gagal jantung. Kami akan membandingkan antara dua metode klasifikasi dari machine learning, yaitu Logistic Regression (LR), dan deep learning, yaitu Shallow Neural Network (SNN). Mutual Information (MI) dipilih sebagai metode pemilihan fitur. Hasil menunjukkan bahwa SNN menghasilkan akurasi lebih tinggi dengan skor 0.75, dibandingkan LR dengan akurasi sebesar 0.63.

Prediksi Penyakit Daun Pisang Menggunakan Metode LSTM (Long Short-Term Memory) Ba’its, Alfian Kafilah; Bagaskara, Radhinka; Setiawan, Andika; Yulita, Winda; Harmiansyah, Harmiansyah; Listiani, Amalia; Untoro, Meida Cahyo; Drantantiyas, Nike Dwi Grevika; Faisal, Amir; Anggraini, Leslie; Febrianto, Andre; Aprilianda, Mohamad Meazza; Fitrawan, Mhd. Kadar
Jurnal Teknik Informatika UNIKA Santo Thomas Vol 10 No. 1 : Tahun 2025
Publisher : LPPM UNIKA Santo Thomas

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

Dalam sektor pertanian, tanaman yang memiliki peran signifikan dalam skala global adalah pisang, yaitu buah yang mudah didapatkan, dapat tumbuh dimana saja, memiliki gizi yang tinggi, serta memiliki nilai ekonomi & budaya yang tinggi. Pisang mempunyai kontribusi yang signifikan terhadap pendapatan nasional Indonesia, terutama di Provinsi Lampung sebagai penghasil pisang nasional terbesar. Tetapi, proses produksi pisang seringkali mengalami kendala, salah satunya karena faktor serangan penyakit Black Sigatoka. Penyakit tersebut memberikan kerugian pada tanaman pisang, seperti daun yang meranggas, panen tertunda, bakal buah rontok, dan kualitas buah yang rendah, dan dapat menyebar melalui aliran udara atau percikan air hujan. Tingkat keparahan penyakit Black Sigatoka perlu diprediksi agar penyakit tersebut dapat dikontrol dan dapat dicegah sedini mungkin. Model yang digunakan untuk memprediksi permasalahan ini dalam jangka panjang adalah model Long Short-Term Memory (LSTM), salah satu jenis dari arsitektur Recurrent Neural Network (RNN), yang mempunyai kinerja yang baik dan mempunyai model yang prediktif. Aplikasi LSTM diterapkan terhadap dataset pohon pisang yang terdampak penyakit Black Sigatoka. Hasil dari model LSTM dalam melakukan prediksi penyakit Black Sigatoka menghasilkan model dengan nilai error yang kecil, dengan nilai MAE dan MAPE masing-masing sebesar 0.084 dan 5.7%

Analisis Hubungan dan Prediksi Depresi Mahasiswa Berdasarkan Faktor Akademik dan Gender Verdiana, Miranti; Dwi Nugroho, Eko; Anggraini, Leslie; Bagaskara, Radhinka; Yulita, Winda; Afriansyah, Aidil; Habib Algifari, Muhammad
Jurnal Teknik Informatika UNIKA Santo Thomas Vol 10 No. 1 : Tahun 2025
Publisher : LPPM UNIKA Santo Thomas

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

This study aims to analyze the level of depression among university students by examining gender and several academic indicators. The dataset includes responses from 27,901 students across various regions, with variables covering age, gender, academic pressure, study satisfaction, work/study hours, CGPA, and depression status. The analytical methods applied in this study include the chi-square test to eval_uate the association between gender and depression status, point-biserial correlation to examine relationships between numeric variables and depression, and logistic regression to develop a prediction model. The chi-square test results revealed no significant relationship between gender and depression (p = 0.774), indicating that depression affects both genders. In contrast, academic pressure exhibited the strongest correlation with depression status (r = 0.47), followed by work/study hours (r = 0.209) and study satisfaction (r = -0.168). The Logistic Regression model constructed using the four most relevant variables demonstrated satisfactory performance, achieving 75.5% accuracy and 82.1% recall in identifying students experiencing depression. These findings highlight the critical role of academic-related factors—particularly academic pressure—in influencing students’ mental health. Therefore, targeted academic support strategies are essential to mitigate depression risks in higher education environments. Keywords— Student Depression, Academic Pressure, Gender, Logistic Regression, Mental Health Prediction

Evaluasi Logistic Regression dan Neural Network pada Klasifikasi Gagal Jantung Berbasis Threshold Anggraini, Leslie; Akram Abdillah, Attar; Kartadilaga, Muhammad Qaessar; Verdiana, Miranti; Nugroho, Eko; Afriansyah, Aidil; Febrianto, Andre; Bagaskara, Radhinka
Jurnal Teknik Informatika UNIKA Santo Thomas Vol 10 No. 1 : Tahun 2025
Publisher : LPPM UNIKA Santo Thomas

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

Kardiovaskular adalah sistem jantung dan pembuluh darah dalam tubuh manusia yang bertanggung jawab atas sirkulasi darah dalam jantung, pembuluh darah, dan darah sendiri. Gangguan pada fungsi sistem ini dapat menyebabkan penyakit kardiovaskular, seperti gagal jantung, yang menjadi salah satu penyebab utama kematian di seluruh dunia. Kematian yang disebabkan oleh gagal jantung mempengaruhi 1.5 juta pasien di seluruh dunia. Dikarenakan oleh data statistik tersebut, maka ada kebutuhan untuk dapat memprediksi dampak gagal jantung untuk membantu tingkat kelangsungan hidup pasien. Sebagai bentuk kontribusi terhadap kebutuhan tersebut, penelitian ini akan menganalisis sebuah dataset pelayanan kesehatan, yaitu dataset rekam gagal jantung dari UCI. Dataset tersebut akan digunakan untuk mengklasifikasi dan memprediksi peluang kematian dari pasien gagal jantung. Kami akan membandingkan antara dua metode klasifikasi dari machine learning, yaitu Logistic Regression (LR), dan deep learning, yaitu Shallow Neural Network (SNN). Mutual Information (MI) dipilih sebagai metode pemilihan fitur. Hasil menunjukkan bahwa SNN menghasilkan akurasi lebih tinggi dengan skor 0.75, dibandingkan LR dengan akurasi sebesar 0.63.

Prediksi Penyakit Daun Pisang Menggunakan Metode LSTM (Long Short-Term Memory) Ba’its, Alfian Kafilah; Bagaskara, Radhinka; Setiawan, Andika; Yulita, Winda; Harmiansyah, Harmiansyah; Listiani, Amalia; Untoro, Meida Cahyo; Drantantiyas, Nike Dwi Grevika; Faisal, Amir; Anggraini, Leslie; Febrianto, Andre; Aprilianda, Mohamad Meazza; Fitrawan, Mhd. Kadar
Jurnal Teknik Informatika UNIKA Santo Thomas Vol 10 No. 1 : Tahun 2025
Publisher : LPPM UNIKA Santo Thomas

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

Dalam sektor pertanian, tanaman yang memiliki peran signifikan dalam skala global adalah pisang, yaitu buah yang mudah didapatkan, dapat tumbuh dimana saja, memiliki gizi yang tinggi, serta memiliki nilai ekonomi & budaya yang tinggi. Pisang mempunyai kontribusi yang signifikan terhadap pendapatan nasional Indonesia, terutama di Provinsi Lampung sebagai penghasil pisang nasional terbesar. Tetapi, proses produksi pisang seringkali mengalami kendala, salah satunya karena faktor serangan penyakit Black Sigatoka. Penyakit tersebut memberikan kerugian pada tanaman pisang, seperti daun yang meranggas, panen tertunda, bakal buah rontok, dan kualitas buah yang rendah, dan dapat menyebar melalui aliran udara atau percikan air hujan. Tingkat keparahan penyakit Black Sigatoka perlu diprediksi agar penyakit tersebut dapat dikontrol dan dapat dicegah sedini mungkin. Model yang digunakan untuk memprediksi permasalahan ini dalam jangka panjang adalah model Long Short-Term Memory (LSTM), salah satu jenis dari arsitektur Recurrent Neural Network (RNN), yang mempunyai kinerja yang baik dan mempunyai model yang prediktif. Aplikasi LSTM diterapkan terhadap dataset pohon pisang yang terdampak penyakit Black Sigatoka. Hasil dari model LSTM dalam melakukan prediksi penyakit Black Sigatoka menghasilkan model dengan nilai error yang kecil, dengan nilai MAE dan MAPE masing-masing sebesar 0.084 dan 5.7%

Analisis Hubungan dan Prediksi Depresi Mahasiswa Berdasarkan Faktor Akademik dan Gender Verdiana, Miranti; Dwi Nugroho, Eko; Anggraini, Leslie; Bagaskara, Radhinka; Yulita, Winda; Afriansyah, Aidil; Habib Algifari, Muhammad
Jurnal Teknik Informatika UNIKA Santo Thomas Vol 10 No. 1 : Tahun 2025
Publisher : LPPM UNIKA Santo Thomas

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

This study aims to analyze the level of depression among university students by examining gender and several academic indicators. The dataset includes responses from 27,901 students across various regions, with variables covering age, gender, academic pressure, study satisfaction, work/study hours, CGPA, and depression status. The analytical methods applied in this study include the chi-square test to eval_uate the association between gender and depression status, point-biserial correlation to examine relationships between numeric variables and depression, and logistic regression to develop a prediction model. The chi-square test results revealed no significant relationship between gender and depression (p = 0.774), indicating that depression affects both genders. In contrast, academic pressure exhibited the strongest correlation with depression status (r = 0.47), followed by work/study hours (r = 0.209) and study satisfaction (r = -0.168). The Logistic Regression model constructed using the four most relevant variables demonstrated satisfactory performance, achieving 75.5% accuracy and 82.1% recall in identifying students experiencing depression. These findings highlight the critical role of academic-related factors—particularly academic pressure—in influencing students’ mental health. Therefore, targeted academic support strategies are essential to mitigate depression risks in higher education environments. Keywords— Student Depression, Academic Pressure, Gender, Logistic Regression, Mental Health Prediction

Ideal Temperature Classification of Meeting Rooms Using You Only Look Once Architecture Version 8 and Multilayer Perceptron Based on Human Density Image Data Ridwan, Naufal Taufiq; Yulita, Winda; Kesuma, Rahman Indra; Ramadhani, Uri Arta; Bagaskara, Radhinka
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 2 (2025): July 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i2.34230

Indonesia, located along the equator, experiences a tropical climate that results in high indoor temperatures. Elevated temperatures can affect health, making air conditioning (AC) necessary to regulate indoor environments. However, improper use of AC systems, such as leaving them on even when a room is unoccupied, can lead to significant energy waste. This research focuses on the efficient use of AC systems through the integration of sensors and cameras, combining two distinct technologies. The first technology is object detection using You Only Look Once (YOLOv8), which was chosen for its superior performance in terms of speed, accuracy, and computational efficiency. The second is the classification of optimal AC temperatures using the Multilayer Perceptron (MLP) algorithm, selected for its high performance in accuracy, sensitivity, and speed. In addition, the study takes into account human density in the room to optimize temperature regulation. The integration of object detection and temperature classification technologies enables the system to operate in real time and automatically adjust temperature settings based on dynamic room conditions. The research successfully implemented YOLOv8 for object detection and Multilayer Perceptron for optimal room temperature classification. Test results showed precision, recall, and F1-score values of 0.82, 0.92, and 0.86, respectively.

Title

Found 10 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 10 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 10 Documents
Search