Garuda - Garba Rujukan Digital

Mobile Application to Identify Indonesian Flowers on Android Platform Karlita, Tita; Basuki, Achmad; Makarti, Lakmi
EMITTER International Journal of Engineering Technology Vol 1, No 1 (2013)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

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

Although many people love flowers, they do not know their name. Especially, many people do not recognize local flowers. To find the flower image, we can use search engine such as Google, but it does not give much help to find the name of local flower. Sometimes, Google cannotshow the correct name of local flowers. This study proposes an application to identify Indonesian flowers that runs on the Android platform for easy use anywhere. Flower recognition is based on the color features using the Hue-Index, shape feature using Centroid Contour Distance (CCD), and the similarity measurement using Entropy calculations. The outputs of this application are information about inputted flower image including Latinname, local name, description, distribution and ecology. Based on tests performed on 44 types of flowers with 181 images in the database, the best similarity percentage is 97.72%. With this application, people will be expected to know more about Indonesia flowers.Keywords: Indonesian flowers, android, hue-index, CCD, entropy

Mobile Application to Identify Indonesian Flowers on Android Platform Karlita, Tita; Basuki, Achmad; Makarti, Lakmi
EMITTER International Journal of Engineering Technology Vol 1, No 1 (2013)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24003/emitter.v1i1.10

Although many people love flowers, they do not know their name. Especially, many people do not recognize local flowers. To find the flower image, we can use search engine such as Google, but it does not give much help to find the name of local flower. Sometimes, Google cannotshow the correct name of local flowers. This study proposes an application to identify Indonesian flowers that runs on the Android platform for easy use anywhere. Flower recognition is based on the color features using the Hue-Index, shape feature using Centroid Contour Distance (CCD), and the similarity measurement using Entropy calculations. The outputs of this application are information about inputted flower image including Latinname, local name, description, distribution and ecology. Based on tests performed on 44 types of flowers with 181 images in the database, the best similarity percentage is 97.72%. With this application, people will be expected to know more about Indonesia flowers.Keywords: Indonesian flowers, android, hue-index, CCD, entropy

Deep Learning Models for Dental Conditions Classification Using Intraoral Images Makarim, Ahmad Fauzi; Karlita, Tita; Sigit, Riyanto; Bayu Dewantara, Bima Sena; Brahmanta, Arya
JOIV : International Journal on Informatics Visualization Vol 8, No 3 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.3.1914

This paper presents the digitalization of dentistry medical records to support the dentist in the patient examination process. A dentist uses manual input to fill out the evaluation form by drawing and labeling each patient’s tooth condition based on their observations. Consequently, it takes too long to finish only one examination. For time efficiency, using AI-based digitalization technology can be a promising solution. To address the problem, we made and compared several classification models to recognize human dental conditions to help doctors analyze patient teeth. We apply the YOLOv5, MobileNet V2, and IONet (proposed CNN model) as deep learning models to recognize the five common human dental conditions: normal, filling, caries, gangrene radix, and impaction. We tested the ability of YOLO classification as an object detection model and compared it with classification models. We used a dataset of 3.708 intraoral dental images generated by various augmentation methods from 1.767 original images. We collected and annotated the dataset with the help of dentists. Furthermore, the dataset is divided into three parts: 90% of the total dataset is used as training and validation data, then divided again into 80% training data and 20% validation data. 10% of the total dataset will be used as testing data to compare classification performance. Based on our experiments, YOLOv5, as an object detection model, can classify dental conditions in humans better than the classification model. YOLOv5 produces an 82% accuracy testing value and performs better than the classification model. MobileNet V2 and IONet only get 80% and 70% testing accuracy. Although statistically, there is not much of a difference between the test accuracy values for YOLOv5 and MobileNet v2, the speed in classifying dental objects using YOLOv5 is more efficient, considering that YOLOv5 is an object detection model. There are still challenges with the deep learning technique used in this research, but these can be addressed in further development. A more complex model and the enlargement of more data, ensuring it is varied and balanced, can be used to address the limitations.

Deteksi Ras Kucing Menggunakan Compound Model Scaling Convolutional Neural Network Azahro Choirunisa, Nadia; Karlita, Tita; Asmara, Rengga
Technomedia Journal Vol 6 No 2 Februari (2022): TMJ (Technomedia Journal)
Publisher : Pandawan Incorporation, Alphabet Incubator Universitas Raharja

Cat is one of a popular animals in the world. Number of cat breeds in the world only about 1%, so most are dominated by cats mixed or domestic cat. Nevertheless, there are so many different types of cat breeds in the world, that it is sometimes difficult to identify them. Therefore, we need a system that can recognize the types of cat breeds. One technique of deep learning that may apprehend and hit upon gadgets in a photograph is Convolutional Neural Network (CNN). CNN functionality is alleged because the nice technique in phrases of item detection and item recognition. The author used 9 different types of cat breeds containing 2700 images. The EfficientNet-B0 architecture is used on the system. The most optimal model has earned the accuracy of 95%. Keywords : Deep Learning, Convolutional Neural Network (CNN), Cat breeds, EfficientNet-B0.

Deteksi Kondisi Gigi Manusia pada Citra Intraoral Menggunakan YOLOv5 Makarim, Ahmad Fauzi; Karlita, Tita; Sigit, Riyanto; Dewantara, Bima Sena Bayu; Brahmanta, Arya
The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v12i4.3355

Proses identifikasi dan pencatatan rekam medis pada praktik kedokteran gigi masih dilakukan secara manual. Akibatnya, proses tersebut memakan waktu yang cukup lama. Pada penelitian ini metode deteksi objek dimanfaatkan untuk membantu dokter melakukan identifikasi pada gigi pasien. YOLOv5 dipilih untuk dilatihkan pada dataset citra intraoral dengan lima kelas kondisi gigi (normal, karies, tumpatan, sisa akar, dan impaksi). Dataset yang digunakan berjumlah 1.767 data citra intraoral yang diambil dan dilabeli oleh dokter gigi. Dataset dibagi menjadi tiga bagian, 10% digunakan untuk data testing dan 90% digunakan untuk data training dan validation. Dilakukan komparasi performa berdasarkan nilai metrik evaluasi terhadap tiga jenis model YOLOv5 (S, M, L). Dari hasil pelatihan, YOLOv5 M sebagai model terbaik mendapatkan nilai mAP sebesar 84%, dan 82% nilai akurasi testing. Penelitian ini telah memenuhi tujuan utama untuk membangun sebuah model deep learning yang robust untuk mendeteksi dan mengklasifikasi beberapa kondisi gigi pada manusia.

Sistem Informasi Manajemen Budidaya Tanaman Melon Modul Pengelolaan Keuangan di CV Agro Utama Mandiri Lestari Fitrah Maharani Humaira; Nikma Prastita, Valentia; Karlita, Tita; Asmara, Rengga
Riau Jurnal Teknik Informatika Vol. 4 No. 1 (2025): Maret 2025
Publisher : Prodi Teknik Informatika Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v4i1.3246

The advancement of technology is progressing rapidly and will continue in line with the development of science. This progress is inevitable in all aspects of life, including in the corporate environment. CV Agro Utama Mandiri Lestari is a company engaged in agriculture as well as a training and self-sufficient rural development center. A company can grow quickly if its financial management data is accurate and precise. Financial management involves organizing the resources owned by the company to achieve its goals and objectives. In financial management, there are cash inflows and outflows, which are activities that always exist in every business entity. In this company, melon cultivation is still managed using a manual and simple financial system, making administrative activities prone to document loss, inaccuracy, and difficulties in analyzing fertilizer expenses. Therefore, a financial management system is highly necessary for CV Agro Utama Mandiri Lestari. This system features data management for income, expenses, human resources, harvests, capital, and profit and loss per harvest. Additionally, it can generate financial reports based on predefined filters. The system also provides a data visualization dashboard displaying financial information for CV Agro Utama Mandiri Lestari.

Implementasi Aplikasi Chatbot Informasi Pelayanan Kelurahan Keputih, Surabaya Edelani, Renovita; Satriyanto, Edi; Nadhori, Isbat Uzzin; Susetyoko, Ronny; Barakbah, Aliridho; Karlita, Tita; Muliawati, Tri Hadiah; Fadliana, Alfi; Maulana, Wahyu Ikbal; Insani, Fawzan; Fauzi Nafi'Ubadah, Kriza; Haikal Yuniarta Krisgianto, Ricko; Saputra, Muhammad Krisnanda Vilovan; Ridho, Bistiana Syafina; Ni'Ma, Najma Akmalina; Damayanti, Anita; Febrianto, Ardiansyah Indra; Alde, Muhammad Riski
El-Mujtama: Jurnal Pengabdian Masyarakat Vol. 5 No. 2 (2025): El-Mujtama: Jurnal Pengabdian Masyarakat
Publisher : Intitut Agama Islam Nasional Laa Roiba Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47467/elmujtama.v5i2.6272

In today's era of digital transformation, the government, particularly Kelurahan Keputih, is aware of the community's need for information regarding the management of kependudukan and non-kependudukan documents. Given their busy lifestyles, residents require a medium to access information related to these matters. This service information is needed to improve bureaucratic efficiency, accelerate information access, and reduce the burden of manual administrative work. Therefore, researchers have developed an AI-based Intelligent Chatbot application using Large Language Modeling (LLM) technology to assist both employees and residents of Kelurahan Keputih in obtaining information related to the management of kependudukan and non-kependudukan services. The implementation of this Chatbot utilizes the Hugging Face library and the LangChain model, one of the Llama models developed by Meta. This Kelurahan Keputih Service Information Chatbot application is named "BambuBot". This application benefits the residents of Keputih by providing them with interactive, comprehensive, and easily accessible information regarding services for managing kependudukan and non-kependudukan documents, as well as platforms for processing these documents.

Real-Time Tuberculosis Bacteria Detection Using YOLOv8 Sigit, Riyanto; Yuniarti, Heny; Karlita, Tita; Kusumawati, Ratna; Maulana, Firja Hanif
JOIV : International Journal on Informatics Visualization Vol 9, No 5 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.5.3147

Tuberculosis (TB) is a contagious disease caused by the bacterium Mycobacterium tuberculosis. If not adequately managed, TB can become a fatal, life-threatening condition. In Indonesia, TB remains a critical public health issue, with millions affected and the country ranking third globally in TB cases, following India and China. Symptoms of TB include persistent cough lasting more than three weeks, hemoptysis (bloody sputum), fever, chest pain, and night sweats. The widely used diagnostic method in Indonesia is the Ziehl-Neelsen stained sputum smear technique, which processes sputum samples with specific reagents, allowing acid-fast bacilli to be visualized through microscopic examination. However, this process is labor-intensive and time-consuming, often requiring between half an hour and several hours for an accurate diagnosis. To address these challenges, there is a crucial need to develop technology that accelerates the TB diagnosis process, facilitating easier labor for healthcare workers. This study focuses on employing YOLOv8 to automate the detection of acid-fast bacilli. The system acquires sputum sample images from a microscope, and the acquired data is then used to train the model for detecting tuberculosis bacteria. The proposed real-time approach, employing the YOLOv8 algorithm, has demonstrated adequate performance for one of our specialized models, achieving a precision score of 0.88, a recall score of 0.77, and an F1 score of 0.82. This research aims to enhance TB case detection and increase treatment coverage, thereby improving overall public health outcomes in Indonesia.

Programming Language Selection for The Development of Deep Learning Library Rachmawati, Oktavia Citra Resmi; Barakbah, Ali Ridho; Karlita, Tita
JOIV : International Journal on Informatics Visualization Vol 8, No 1 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.1.2437

Recently, deep learning has become very successful in various applications, leading to an increasing need for software tools to keep up with the rapid pace of innovation in deep learning research. As a result, we suggested the development of a software library related to deep learning that would be useful for researchers and practitioners in academia and industry for their research endeavors. The programming language is the core of deep learning library development, so this paper describes the selection stage to find the most suitable programming language for developing a deep learning library based on two criteria, including coverage on many projects and the ability to handle high-dimensional array processing. We addressed the comparison of programming languages with two approaches. First, we looked for the most demanding programming languages for AI Jobs by conducting a data-driven approach against the data gathered from several Job-Hunting Platforms. Then, we found the findings that imply Python, C++, and Java as the top three. After that, we compared the three most widely used programming languages by calculating interval time to three different programs that contain an array of exploitation processes. Based on the result of the experiments that were executed in the computer terminal, Java outperformed Python and C++ in two of the three experiments conducted with 5,4047 milliseconds faster than C++ and 231,1639 milliseconds faster than Python to run quick sort algorithm for arrays that contain 100.000 integer values.

CNN with Batch Normalization Adjustment for Offline Hand-written Signature Genuine Verification Fatihia, Wifda Muna; Fariza, Arna; Karlita, Tita
JOIV : International Journal on Informatics Visualization Vol 7, No 1 (2023)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.7.1.1443

Signature genuine verifications of offline hand-written signatures are critical for preventing forgery and fraud. With the growth of protecting personal identity and preventing fraud, the demand for an automatic system for signature verification is high. The signature verification system is then studied by many researchers using various methods, especially deep learning-based methods. Hence, deep learning has a problem. Deep learning requires much training time for the data to obtain the best model accuracy result. Therefore, this paper proposed a CNN Batch Normalization, the CNN architectural adaptation model with a normalization batch number added, to obtain a CNN model optimization with high accuracy and less training time for offline hand-written signature verification. We compare CNN with our proposed model in the experiments. The research method in this study is data collection, pre-processing, and testing using our private signature dataset (collected by capturing signature images using a smartphone), which becomes the difficulties of our study because of the different lighting, media, and pen used to sign. Experiment results show that our model ranks first, with a training accuracy of 88.89%, an accuracy validation of 75.93%, and a testing accuracy of 84.84%â€”also, the result of 2638.63 s for the training time consumed with CPU usage. The model evaluation results show that our model has a smaller EER value; 2.583, with FAR = 0.333 and FRR = 4.833. Although the results of our proposed model are better than basic CNN, it is still low and overfitted. It has to be enhanced by better pre-processing steps using another augmentation method required to improve dataset quality.Â

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