p-Index From 2021 - 2026
6.696
P-Index
Claim Missing Document
Check
Articles

Found 8 Documents
Search
Journal : jsai journal scientific and applied informatics

Automated Fruit Classification Menggunakan Model VGG16 dan MobileNetV2 Umniy Salamah; Anita Ratnasari; Sarwati Rahayu
JSAI (Journal Scientific and Applied Informatics) Vol 5 No 3 (2022): November 2022
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v5i3.3615

Abstract

Pengembangan robot atau mesin untuk membantu kegiatan pertanian memerlukan riset yang panjang. Teknologi tersebut harus dapat memiliki keahlian dalam melakukan berbagai macam aktivitas dan mampu mendeteksi objek yang menjadi sasaran pekerjaannya. Untuk memenuhi hal ini, riset untuk mendeteksi objek pertanian, misalnya buah, menjadi salah satu agenda riset yang perlu dilakukan dan dikembangkan. Tujuan penelitian ini adalah untuk mengetahui hasil perbandingan performa deep learning yaitu VGG16 dan MobileNetV2 untuk fruit classification. Penelitian ini menggunakan dataset dengan jumlah total 90.483 data dengan ukuran gambar 100x100 piksel dan jumlah kelas tanaman buah yang akan diklasifikasi adalah sebanyak 131 kelas. Pada proses testing menggunakan dataset yang ada, MobileNetV2 mendapatkan akurasi 98.4% dan ResNet50 mendapatkan akurasi 99,2%.
Pengaruh Tuning Parameter dan Cross Validation Pada Klasifikasi Teks Komplain Bahasa Indonesia Menggunakan Algoritma Support Vector Machine Vina Ayumi; Desi Ramayanti; Handrie Noprisson; Anita Ratnasari; Umniy Salamah
JSAI (Journal Scientific and Applied Informatics) Vol 6 No 3 (2023): November
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v6i3.6117

Abstract

Text classification aims to group text data, for example, to find some information from a large social media text dataset so that it can be used by the data owner. Manual text classification is time-consuming and difficult, so some researchers try to research text classification automatically. This study attempts to classify Indonesian text datasets using the SVM algorithm. The research was conducted in two stages, namely the first experiment without cross validation parameters and parameter tuning, then the second experiment was carried out with cross validation parameters and parameter tuning. Experiments without cross validation parameters and parameter tuning for support vector machines (SVM) obtained 89.47% accuracy with precision and recall values of 0.90 and 0.89 respectively. The second experiment used cross validation with k-5 and k-10 and tuning parameters with C constant and gamma values. Cross validation results with k-10 obtained the best accuracy with a value of 96.48% with a computation time of 40.118 seconds. Next, kernel functions in tuning parameters namely sigmoid, linear and radial basis functions are analyzed and it is found that sigmoid kernel functions achieve the best accuracy and computational time.
Evaluasi Usability pada Portal Basis Data Tanaman Obat Indonesia Menggunakan Metode System Usability Scale (SUS) Wachyu Hari Haji; Anita Ratnasari; Vina Ayumi; Handrie Noprisson; Nur Ani
JSAI (Journal Scientific and Applied Informatics) Vol 6 No 3 (2023): November
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v6i3.6263

Abstract

Previous research discussed valuable recommendations for the development of an Indonesian medicinal plant database portal. However, previous research has not discussed usability evaluation on the Indonesian medicinal plant database portal. One usability evaluation technique that is quite popular is the system usability scale (SUS). This study aims to analyze the portal database of medicinal plants using the usability scale (SUS) system to find out the next portal improvement. The SUS method allows researchers to collect data from users through surveys and calculate usability scores, providing recommendations for improving the design and functionality of web-based systems. From the experimental results in the form of calculation results using SUS measurement, it is known that the implementation of the medicinal plant database portal received an assessment of 72.14. This value if interpreted using the measurement level of the final value of SUS can be said that the implementation of the medicinal plant database portal can be accepted (acceptable) with a good category (good).
Klasifikasi Citra Tumor Otak Menggunakan Gaussian Model Berbasis Machine Learning Berdasarkan MRI Dataset Anita Ratnasari
JSAI (Journal Scientific and Applied Informatics) Vol 7 No 2 (2024): Juni
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v7i2.6419

Abstract

Early detection of brain tumors using brain magnetic resonance imaging is needed to prevent benign tumors from developing into malignant tumors. This study aims to classify brain tumors using thresholding and support vector machine (SVM) methods. The thresholding methods used in this study are global thresholding, adaptive thresholding and gaussian thresholding. The evaluation methods used are accuracy, recall, precision, and specificity. This study has used magnetic resonance imaging (MRI) based image datasets totaling 3,079 data. Overall, the accuracy of the support vector machine (SVM) algorithm and adaptive thresholding method got the best accuracy of 84.25%, while the gaussian thresholding method got 82.81% accuracy and global thresholding got 81.25% accuracy.
Retinal Optical Coherence Tomography (OCT) Analysis for Retinal Damage Detection Using Machine Learning Methods Anita Ratnasari
JSAI (Journal Scientific and Applied Informatics) Vol 7 No 2 (2024): Juni
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v7i2.6420

Abstract

This study attempts to use support vector machine and otsu thresholding as proposed algorithm models to classify Retinal optical coherence tomography (OCT) images. In this study, there are two types implemented in classifying retinal image datasets. The first scenario is to classify using the support vector machine algorithm without the otsu thresholding method and the second scenario is to classify using the support vector machine algorithm with the otsu thresholding method with various parameter values. Based on the experimental results, classification of retina image datasets using the support vector machine algorithm without the otsu thresholding method obtained an accuracy of 63.00% while classification using the support vector machine algorithm with the otsu thresholding method with parameter values (0, 255), (50, 255), (100, 255), (150, 255) obtained an accuracy of 59.30%.
Analisis Faktor Kepercayaan dan Kepuasan Pengguna Website Marketplace: Studi Empiris pada E-Commerce Lazada Hari Haji, Wachyu; Ratnasari, Anita; Ayumi, Vina; Noprisson, Handrie; Ani, Nur
JSAI (Journal Scientific and Applied Informatics) Vol 7 No 3 (2024): November
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v7i3.7476

Abstract

This study aims to identify the factors influencing trust and user satisfaction in online marketplaces by applying the DeLone & McLean information system success model. Data were collected through an online questionnaire distributed to Lazada marketplace buyers in Indonesia. The empirical results indicate that trust is a key predictor in determining the quality of sellers and their ability to provide the best services. Statistically, the first hypothesis (H1) shows a significant influence of website reputation on user trust (**T-Stat = 8.50; Sig = *). The second hypothesis (H2), regarding the influence of perceived website size on trust, is not significant (T-Stat = 1.42; Sig = NS). The third hypothesis (H3) demonstrates a significant positive relationship between trust and user satisfaction with the website (**T-Stat = 5.62; Sig = *). The fourth hypothesis (H4) confirms a highly significant positive relationship between trust and perceived website quality (**T-Stat = 14.59; Sig = *). This study recommends that online marketplaces enhance the prestige of sellers and maintain customer trust, as these factors play a critical role in improving user satisfaction when shopping on online marketplaces.
Model HSI-EfficientNetB7 Untuk Analisis Citra Histopatologi Kanker Payudara Ratnasari, Anita
JSAI (Journal Scientific and Applied Informatics) Vol 7 No 3 (2024): November
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v7i3.7477

Abstract

The practice of analysis is expanding in tandem with the advancement of computer science and histopathology image technologies. Combining different types of learning, such as deep learning, machine learning, and image processing, is one way to get the highest level of Precision. The purpose of the research that has been proposed is to evaluate the effectiveness of the EfficientNetB7 transfer learning approach in assessing the histology of breast cancer. This investigation is divided into three primary stages: data gathering, image categorization, and analysis. EfficientNetB7 transfer learning is the methodology that is utilized for data classification. Histopathological pictures of breast cancer specimens with a resolution of 50 x 50 were used as the source of the evaluated data (198,738 negative classes and 78,786 positive classes). Evaluation of the training accuracy, validity, and testing of breast cancer histopathological specimen images with a resolution of 50 x 50 (198,738 negative class and 78,786 positive class) obtained 91.63% accuracy (training stage) and 90.34%ccuracy (validation stage), and the accuracy result (testing stage) is 62.67%. This is the final result of evaluating the training accuracy, validity, and testing of the breast cancer histopathological specimen images. A score of 0.1158 was acquired for Cohen's Kappa, a score of 0.5422 was obtained for the F1-Score, a score of 0.6558 was obtained for Precision, and a score of 0.6267 was received for Recall for the alternative evaluation model.
Human Resource (HR) Performance Analysis Model in Higher Education Based on Multi-modal Data Using Machine Learning Reni Utami; Ari Hidayatullah; Anita Ratnasari
JSAI (Journal Scientific and Applied Informatics) Vol 8 No 3 (2025): November
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v8i3.9381

Abstract

This research aimed to develop a machine learning-based model for human resource (HR) performance analysis in higher education institutions using a multi-modal approach, combining static data and text data analysis. For static data analysis, the random forest (RF) algorithm was employed to assess HR performance based on attributes such as years of service, training attended, and performance evaluations. The dataset for this experiment consisted of 250 data points, which were divided into 70% for training, 10% for validation, and 20% for testing. The experimental results with the RF model showed high accuracy in training (90.4%), although there was a performance drop during validation and testing, with accuracies of 85.7% and 82.5%, respectively. For the text data, which contained feedback with negative, positive, and neutral sentiments, the CNN-BiLSTM model achieved an accuracy of 92.6% in training, despite a decrease in validation (87.4%) and testing (84.4%) accuracies. The text dataset comprised 1,000 data points, divided into 70% for training, 10% for validation, and 20% for testing. The study recommends the application of a multi-model approach to assess HR performance using the RF algorithm for static data and the CNN-BiLSTM model for more complex data in future research.
Co-Authors Abdillah Fikri Abdul Kholiq Abi Nala Wiatma Adji, Widwi Handari Afri Liandy Agung Fadillah Agung Priambodo Agung, Budi Ahmad, Hasnan Syah Alen Boby Hartanto Andi Nugroho, Andi Andika Andika Aqbar, Harry Ari Hidayatullah Ari Purnadi, Mochamad Arif, Gunawan Syarifah Ayumi, Vina Bagus Priambodo Bagus Priambodo Bayu Aji, Aditya Bosar Panjaitan Defriansyah Demario, Demario Deni Tri Muslimin Desi Ramayanti Diah Intan Kusumo Dewi Dicky Herlambang Doni Darmawan Edi Kartawijaya Enrico Setya Damaputra Estiarto, Lintang Putri Faizal Zuli, Faizal Fauzian Abdillah, Muhammad Geni, Bias Yulisa Grace Gata Grace Gata, Grace Gulo, Isati Haji, Wahu Hari Hasnan Syah Ahmad Hasnan Syah Ahmad Herlambang, Dicky Hernalom Sitorus Indra Agustina Inge Handriani Irawan, Indra Ade Islam, Rahman Islamiah Kamil Juliansyah, Arman Jumaryadi, Yuwan Mardiansah Mardiansah Meiliyah Ariani, Meiliyah Michail, Michail Misbahul Fajri Mohamad Alfis Dava Cahyoga Muhammad Asyraf Fadhli Muslimin, Deni Tri Nia Rahma Kurnianda Noprisson, Handrie Nur Ani Nur Ani Nurul Ainul Shifa Pangilinan Gunawan Panjaitan, Bosar Pratama , Steven Aditya Reni Utami Riama Sibarani Rina Afrina Rinto Priambodo Rizka Fauziah Salamah, Umniy Saputra, Tio Aji Sarwati Rahayu Sianturi, Heriston Siti Maesaroh Sitorus, Berlin P Sri Dianing Asri Sukarno Bahat Nauli Sukrisna Setiawan Turkhamun Adi Kurniawan Wachyu Hari Haji Wachyu Hari Haji Wahu Hari Haji Wahyuningsih, Erfiana Widwi Handari Yani Prabowo Yoga Pranata Yolifiandri, Yolifiandri Yostian Ari Sujarwo Yuliadi, Boy yulisa geni, bias Yustika Erliani