Garuda - Garba Rujukan Digital

Deep neural networks and conventional machine learning classifiers to analyze thoracic survival data Ika Agustyaningrum, Cucu; Ramdhani, Yudi; Purnama Alamsyah, Doni; B. Hariyanto, Oda I.
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 3: September 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i3.pp3686-3694

Lung cancer is a prevalent global health concern and most prevalent malignancy in Indonesian hospitals. Following thoracic surgery, patients were categorized into two classes: individuals who experienced mortality within a year and those who achieved survival. Despite being about socks, the dataset for the deceased category consisted of 70 data samples, while the dataset for the final group comprised 400 samples. Data calculation involves the utilization of both deep neural networks and standard machine learning algorithms. The study use the Python programming language to evaluate the algorithms, and it measures their performance using metrics such as accuracy, F1-Score, precision, recall, receiver operating characteristic (ROC), and area under curve (AUC). The test results indicate that the deep neural network method achieves an accuracy of 95,56%, an F1 score of 79,24%, a precision of 91,96%, a recall of 85,52%, and an AUC of 85,52%. This study suggests that utilizing deep neural network data mining techniques, specifically with a cross-validation fold of 10, variations of six hidden layer encoder-decoder, relu, sigmoid activation function, optimizer Adam, and learning rate of 0,01, dropout rate of 0,2. Employing the Synthetic Minority Over-sampling Technique data preprocessing method, can effectively analyze thoracic patient survival data sets.

ALGORITMA KLASIFIKASI DECISION TREE UNTUK REKOMENDASI BUKU BERDASARKAN KATEGORI BUKU Maulidah, Mawadatul; Windu Gata; Rizki Aulianita; Cucu Ika Agustyaningrum
E-Bisnis : Jurnal Ilmiah Ekonomi dan Bisnis Vol 13 No 2 (2020): Jurnal Ilmiah Ekonomi dan Bisnis
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/e-bisnis.v13i2.251

With the increasing development of technology the more variety of books circulating on the internet. As is the recommendation system on online book sites that provide books relevantly and as needed with one's preferences. One alternative is GoodReads, a social networking site that specializes in cataloging books and users can share reading book recommendations with each other by rating, reviewing, and commenting. As a large book recommendation site, it has a lot of data that can be processed by applying machine learning methods, but still not known as the most accurate model. By using the right model, we can provide more accurate recommendations. Therefore, this study will analyze the data obtained from the www.kaggle.com namely the goodreads-books dataset. This study proposed a data mining classification model to get the best model in recommending books on GoodReads. The algorithms used are Decision Tree, K-Nearest Neighbor, Naïve Bayes, Random Forest, and Support Vector Classifier, then for model evaluation using accuracy, precision, recall, f1-score, confusion matrix, AUC, and Mean Error Absolute. The test results of several classification algorithms found that Decision Tree has the highest accuracy among the methods presented by 99.95%, precision by 100%, recall by 96%, f1-score of 98% with MAE of 0.05 and AUC of 99.96%. This is proof that decision tree algorithms can be used as book recommendations based on book categories on GoodReads.

ALGORITMA KLASIFIKASI DECISION TREE UNTUK REKOMENDASI BUKU BERDASARKAN KATEGORI BUKU Maulidah, Mawadatul; Windu Gata; Rizki Aulianita; Cucu Ika Agustyaningrum
E-Bisnis : Jurnal Ilmiah Ekonomi dan Bisnis Vol 13 No 2 (2020): Jurnal Ilmiah Ekonomi dan Bisnis
Publisher : LPPM Universitas Sains dan Teknologi Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/e-bisnis.v13i2.251

With the increasing development of technology the more variety of books circulating on the internet. As is the recommendation system on online book sites that provide books relevantly and as needed with one's preferences. One alternative is GoodReads, a social networking site that specializes in cataloging books and users can share reading book recommendations with each other by rating, reviewing, and commenting. As a large book recommendation site, it has a lot of data that can be processed by applying machine learning methods, but still not known as the most accurate model. By using the right model, we can provide more accurate recommendations. Therefore, this study will analyze the data obtained from the www.kaggle.com namely the goodreads-books dataset. This study proposed a data mining classification model to get the best model in recommending books on GoodReads. The algorithms used are Decision Tree, K-Nearest Neighbor, Naïve Bayes, Random Forest, and Support Vector Classifier, then for model evaluation using accuracy, precision, recall, f1-score, confusion matrix, AUC, and Mean Error Absolute. The test results of several classification algorithms found that Decision Tree has the highest accuracy among the methods presented by 99.95%, precision by 100%, recall by 96%, f1-score of 98% with MAE of 0.05 and AUC of 99.96%. This is proof that decision tree algorithms can be used as book recommendations based on book categories on GoodReads.

Strengthening Digital and English Skills for Work Readiness in RW 08 Kalideres West Jakarta Rizky Mirani Desi Pratama; Dwi Puji Hastuti; Cucu Ika Agustyaningrum
Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal Vol. 9 No. 1 (2026): Januari 2026
Publisher : STMIK Royal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurdimas.v9i1.4190

Abstract: This community service program was carried out by Universitas Bina Sarana Informatika (UBSI) with the aim of strengthening digital skills and English proficiency among high school/vocational school graduates in order to improve their job readiness. The activity took place at Balai RW 08, Kalideres, and West Jakarta. This program was motivated by the condition of high school/vocational graduates in RW 08, most of whom come from lower-middle-income families and are therefore more inclined to enter the workforce directly rather than pursue higher education. Thus, training is needed to enhance practical skills relevant to industry requirements.The training focused on three main aspects, developing a professional curriculum vitae (CV), strategies for facing job interviews in both Indonesian and English, and practicing digital skills through the use of Canva for CV creation. Participants were actively engaged through interactive sessions, simulations, and collaborative exercises. The results of the program indicated increased awareness, confidence, and skills among participants in preparing themselves to enter the workforce. The conclusion of this program is that integrating digital literacy and English proficiency in community-based training can enhance the competitiveness of high school/vocational school graduates and make a tangible contribution to supporting their readiness for the job market. Keywords: english proficiency, job readiness, digital skills, community service, vocational education Abstrak: Program pengabdian kepada masyarakat ini dilaksanakan oleh Universitas Bina Sarana Informatika (UBSI) dengan tujuan memperkuat keterampilan digital dan kemampuan berbahasa Inggris lulusan SMA/SMK untuk meningkatkan kesiapan kerja. Kegiatan ini berlangsung di Balai RW 08, Kalideres, Jakarta Barat. Program ini dilatarbelakangi oleh kondisi lulusan SMA/SMK di RW 08 yang sebagian besar berasal dari keluarga ekonomi menengah ke bawah, sehingga cenderung lebih memilih langsung bekerja daripada melanjutkan pendidikan ke jenjang yang lebih tinggi. Oleh karena itu, diperlukan pelatihan yang dapat meningkatkan keterampilan praktis sesuai kebutuhan industri.Pelatihan difokuskan pada tiga aspek utama: penyusunan curriculum vitae (CV) profesional, strategi menghadapi wawancara kerja dalam bahasa Indonesia maupun bahasa Inggris, serta keterampilan digital melalui penggunaan Canva untuk pembuatan CV. Peserta terlibat secara aktif melalui sesi interaktif, simulasi, dan latihan kolaboratif. Hasil kegiatan menunjukkan adanya peningkatan kesadaran, kepercayaan diri, dan keterampilan peserta dalam mempersiapkan diri menghadapi dunia kerja. Kesimpulannya, integrasi literasi digital dan kemampuan bahasa Inggris dalam pelatihan berbasis masyarakat dapat meningkatkan daya saing lulusan SMA/SMK serta memberikan kontribusi nyata dalam mendukung kesiapan mereka menghadapi pasar kerja. Kata kunci: kemampuan bahasa Inggris, kesiapan kerja, keterampilan digital, pengabdian masyarakat, pendidikan vokasi

Deep Neural Network Classifier for Analysis of the Debrecen Diabetic Retinopathy Dataset Cucu Ika Agustyaningrum; Haryani Haryani; Agus Junaidi; Iwan Fadilah
Jurnal Elektronika dan Telekomunikasi Vol. 24 No. 2 (2024)
Publisher : National Research and Innovation Agency

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55981/jet.640

Diabetic retinopathy (DR) is a serious complication that can occur in individuals who have diabetes. This disease affects the blood vessels in the retina, a part of the eye that is important for vision. Early detection of DR is key to preventing further complications and saving the patient’s vision. The goal of Diabetic Retinopathy Debrecen Data Set Analysis is to get the best, most accurate results for medical professionals to receive appropriate Diabetic Retinopathy Debrecen prediction results through the stages of data collection, evaluation, and classification. Data is collected from existing secondary sources, then assessed using a deep neural network algorithm with various variations. The classification algorithm in this research uses the Python programming language to measure accuracy, F1-Score, precision, recall, and ROC AUC. The test results show that the accuracy of the deep neural network algorithm is 79.94%, the F1 score reaches 79.16%, the precision is 79.58%, the recall is 79.60%, and the AUC is 79.56%. Thus, based on this research, the deep neural network data mining technique with variations of the four hidden layer encoder-decoder, sigmoid activation function, Adam optimizer, learning rate 0.001, and dropout 0.2 is proven to be effective. When compared with other variations such as decoder-encoder, 3-8 hidden layers, learning rate 0.1 and 0.01, the average difference in values between this variation and the others is 0.07% accuracy, 2.03% F1 score, 0.25% precision, 0.80% recall, and 0.90% AUC. Therefore, the deep neural network algorithm with the variation used shows significant dominance compared to other variations.Diabetic retinopathy (DR) is a serious complication that can occur in individuals who have diabetes. This disease affects the blood vessels in the retina, a part of the eye that is important for vision. Early detection of DR is key to preventing further complications and saving the patient’s vision. The goal of Diabetic Retinopathy Debrecen Data Set Analysis is to get the best, most accurate results for medical professionals to receive appropriate Diabetic Retinopathy Debrecen prediction results through the stages of data collection, evaluation, and classification. Data is collected from existing secondary sources, then assessed using a deep neural network algorithm with various variations. The classification algorithm in this research uses the Python programming language to measure accuracy, F1-Score, precision, recall, and ROC AUC. The test results show that the accuracy of the deep neural network algorithm is 79.94%, the F1 score reaches 79.16%, the precision is 79.58%, the recall is 79.60%, and the AUC is 79.56%. Thus, based on this research, the deep neural network data mining technique with variations of the four hidden layer encoder-decoder, sigmoid activation function, Adam optimizer, learning rate 0.001, and dropout 0.2 is proven to be effective. When compared with other variations such as decoder-encoder, 3-8 hidden layers, learning rate 0.1 and 0.01, the average difference in values between this variation and the others is 0.07% accuracy, 2.03% F1 score, 0.25% precision, 0.80% recall, and 0.90% AUC. Therefore, the deep neural network algorithm with the variation used shows significant dominance compared to other variations.

Comparative Analysis of Transfer Learning-Based Deep Learning Models for Jatropha Leaf Disease Classification Sarifah Agustiani; Sulistiyah; Agus Junaidi; Cucu Ika Agustyaningrum; Yoseph Tajul Arifin
SMATIKA JURNAL : STIKI Informatika Jurnal Vol 16 No 02 (2026): SMATIKA Jurnal : STIKI Informatika Jurnal
Publisher : LPPM Universitas Bhinneka Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/smatika.v16i02.2325

Plant disease identification is essential for enhancing agricultural productivity and promoting sustainable crop management practices. Jatropha curcas has considerable potential as a biofuel-producing plant; however, its growth and productivity can be significantly affected by various leaf diseases. Conventional disease diagnosis often requires substantial time and relies heavily on expert knowledge, creating a need for automated solutions based on deep learning techniques. Although deep learning has been widely applied in plant disease recognition, comparative studies focusing on transfer learning models for Jatropha leaf disease classification remain limited, particularly for datasets characterized by distinctive visual features and relatively small sample sizes. This research conducts a comparative assessment of several deep learning architectures to determine the most effective model for classifying Jatropha leaf diseases. The evaluated architectures include MobileNetV2, EfficientNetB0, ResNet50, DenseNet121, and VGG16. All models utilized ImageNet pre-trained weights and were adapted through fine-tuning of the final classification layers to accommodate a dataset containing healthy and diseased Jatropha leaf images. Experimental findings reveal that ResNet50 achieved the highest classification accuracy of 93.81%, followed by VGG16 at 93.58% and EfficientNetB0 at 90.49%. In comparison, DenseNet121 and MobileNetV2 attained accuracies of 85.40% and 74.56%, respectively. Model effectiveness was assessed using accuracy, training duration, confusion matrix analysis, and ROC curve evaluation to examine classification capability across categories. The results demonstrate that ResNet50 offers the most balanced combination of predictive accuracy and performance stability. Overall, the study confirms that transfer learning-based deep learning models are highly effective for Jatropha leaf disease classification, with ResNet50 emerging as the most suitable architecture among those investigated. These findings may serve as a valuable reference for the development of reliable and efficient plant disease detection systems in agricultural environments.

Queue System Implementation at PT. Mulia Persada Indonesia Call Center Services Haryani Haryani; Choirunisa Iqbar Qurotaaini; Cucu Ika Agustyaningrum; Artika Surniandari; Dedi Saputra
Paradigma - Jurnal Komputer dan Informatika Vol. 25 No. 2 (2023): September 2023 Period
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/p.v25i2.2310

In this modern era, call centers have become an important element in providing efficient and responsive customer service. One of the main challenges faced by call centers is how to efficiently manage customer call queues. This study aims to implement a queuing system at PT Mulia Persada Indonesia's call center service by utilizing a computer network, with the aim of increasing the efficiency and effectiveness of customer service. This research also includes an analysis of network security using a Virtual Private Network (VPN) and point-to-Point Tunneling Protocol (PPTP) as a security method for call center network connections. The results of the study show that the use of PPTP in PT Mulia Persada Indonesia's network security provides significant benefits. Call center employees can connect to the corporate network through a secure connection, even from an external location such as home. This access allows them to access the queuing system and perform call center tasks effectively without having to be in a physical office. Meanwhile, the implementation of a queue system at PT Mulia Persada Indonesia's call center service has had a positive impact, namely increasing customer satisfaction. With an effective queuing system, customer waiting time can be minimized and calls can be handled quickly.

Title

Found 17 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 17 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 17 Documents
Search