Claim Missing Document
Check
Articles

Found 8 Documents
Search

Performance Analysis of Weather Forecasting using Machine Learning Algorithms (Analisis Performansi Prakiraan Cuaca Menggunakan Algoritma Machine Learning) Indo Intan; Rismayani Rismayani; St. Aminah Dinayati Ghani; Nurdin Nurdin; Aswar TC. Koswara
Jurnal Pekommas Vol 6, No 2 (2021): Oktober 2021
Publisher : BBPSDMP KOMINFO MAKASSAR

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30818/jpkm.2021.2060221

Abstract

Weather forecasting are very important in various fields of human life, including in big cities. The need for accurate weather forecasts will be effective and efficient in managing the quality of civilization flexibly. In many cases it is found that the results of weather forecasts in the same city differ depending on the radius. This of course requires a precise and accurate algorithm to determine it. The algorithm used is based on machine learning type of artificial neural network which compares backpropagation and bayessian regularization. The results obtained show that bayessian regularization outperforms backpropagation with the smallest MSE and the highest accuracy and the shortest computation time to determine sunny, cloudy, light rain and heavy rain forecasts. The unbalanced distribution of data causes fluctuations in the MSE calculation and accuracy. The addition of training will improve system performance which is indicated by a significant increase in accuracy. Likewise, decreasing the MSE can increase the accuracy of the system to reach the point of convergence. This is an indicator that the performance of Bayessian regularization is the recommended algorithm for forecasting weather in cities and their surroundings, even between provinces or between countries.
Implementasi Aplikasi Berbasis Android Pengembangan Ide Resep Makanan dan Minuman Pada Restoran Sitti Aisa; ST. Aminah Dinayati Ghani
(JurTI) Jurnal Teknologi Informasi Vol 5, No 1 (2021): JUNI 2021
Publisher : Universitas Asahan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36294/jurti.v5i1.1790

Abstract

Abstract – This study aims to design and implement an android-based application for the development of food and beverage recipe ideas. Data collection techniques in this study are observation and interviews. The test model that will be carried out in this study is Black Box testing. System modeling using Unifield Modeling Language (UML) The results of testing an android-based application for the development of cooking and beverage ideas in restaurants and tests carried out using this application restaurant owners can develop recipes where they receive recipe ideas from visitors and can easily see the sales that occur in restaurants and can assist chefs in implementing recipes given by visitors so as to increase the number of food menus in the restaurant. Keywords  - Android, Applications, Food, Beverages, Restaurants Abstrak - Penelitian ini bertujuan untuk merancang dan mengimplementasikan aplikasi berbasis android pengembangan ide Resep makanan dan minuman. Teknik pengumpulan data dalam penelitian ini yaitu observasi dan wawancara. Model pengujian yang akan dilakukan dalam penelitian ini adalah pengujian Black Box. Pemodelan sistem dangan Unifield Modeling Language (UML)  Hasil pengujian implementasi aplikasi berbasis android untuk pengembangan ide masakan dan minuman pada restoran serta pengujian yang dilakukan penggunaan aplikasi ini pemilik restoran dapat mengembangkan resep masakan dimana menerima ide resep masakan dari pengunjung dan dapat dengan mudah melihat penjualan yang terjadi di restoran serta dapat membantu koki dalam mengimplemetasi resep yang telah diberikan oleh pengunjung sehingga menambah jumlah menu makanan yang ada direstoran. Kata Kunci – Android, Aplikasi, Makanan, Minuman, Restoran
Aplikasi Pengenalan Pola Penyakit Kulit Menggunakan Algoritma Linear Discriminant Analysis ST. Aminah Dinayati Ghani; Indo Intan; Nur Salman
CogITo Smart Journal Vol. 8 No. 1 (2022): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v8i1.365.206-218

Abstract

Sometimes, someone underestimates to check up skin disease unless the disease has affected his face or body in severe condition. The checkup fees for skin diseases are relatively expensive because they require a specialist. While the reach of society, in general, is the lower community. The purpose of this study is to bridge the gap between the patient and the examination of the disease based on the patient's skin image. The methods used in feature extraction and classification are Linear Discriminant Analysis LDA and Euclidean Distance respectively. LDA performs image feature extraction through a matrix operation process and distinguishing features in the same class and different classes. Classification will give the output of disease: abscess, eczema, ringworm, and urticaria. The accuracy results obtained are 80%. The next research is on adding features in the form of skin color so that it can be an input feature in the image as well as to improve its performance in the future. This application can be an alternative initial checkup for patients. It will detect the type of skin disease be suffered before consulting an expert.
Neural Network Berbasis Algoritma Genetika untuk Prediksi Kesempatan Kerja Siti Aminah Dinayati G.
Joined Journal (Journal of Informatics Education) Vol 1 No 1 (2018): JOINED Journal of Informatics Education
Publisher : Universitas Ivet

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (785.397 KB) | DOI: 10.31331/joined.v1i1.611

Abstract

ABSTRAK Kesempatan kerja merupakan aspek kehidupan yang paling dibutuhkan dalam memenuhi kebutuhan hidup manusia. Oleh karena itu perlu diketahui faktor-faktor ekonomi apa saja yang mempengaruhi pertumbuhan kesempatan kerja dengan cara pengelolaan yang tepat untuk mengantisipasi kemungkinan buruk yang dapat mengganggu pertumbuhan kesempatan kerja. Tujuan dari penelitian ini adalah untuk mengetahui akurasi dari prediksi kesempatan kerja dengan menggunakan Neural Network dan pembobotan menggunakan Algoritma Genetika. Hasil penelitian menunjukkan bahwa akurasi yang didapatkan untuk prediksi kesempatan kerja menggunakan Algoritma Neural Network adalah sebesar 87,45 % dengan AUC 0,89 termasuk dalam good classification, sedangkan apabila menggunakan Algoritma Neural Network berbasis Algoritma Genetika untuk pembobotan atribut maka nilai akurasi yang didapatkan adalah sebesar 88,30 % dan AUC 0,92 termasuk dalam excelent classification. ABSTRACT Employment is an aspect of life is most needed in meeting human needs. Therefore, please note the economic factors that influence the growth of employment by means of proper management to anticipate the possibility of bad that can interfere with the growth of employment. The purpose of this study was to determine the accuracy of the prediction of employment by using Neural Network and weighting using Genetic Algorithms. The results showed that the prediction accuracy is obtained for employment using Neural Network algorithm is equal to 87.45% with 0.89 AUC included in good classification.
Implementasi Convolutional Neural Network terhadap Citra X-Ray Dada COVID-19 Berbasis Mobile Indo Intan; Suryani Suryani; ST Aminah Dinayati Ghani; Moh. Rifkan; Syamsul Bahri
CogITo Smart Journal Vol. 10 No. 1 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i1.640.625-641

Abstract

The COVID-19 pandemic outbreak is the most significant event from 2019 until 2021. A medical examination of radiological images is carried out to check the condition of the patient's lungs. The limitations of this examination need alternative computer-assisted applications for patient CXR. This research aims to implement a back-end and front-end-based Convolutional Neural Network (CNN) model. Its advantage is that it can detect CXR images in real-time and non-real-time using multi-classification, namely normal, pneumonia, and COVID-19. The CNN model carries out the process of convolutional feature extraction and multi-layer perceptron classification at the back-end stage. In contrast, it uses an Android mobile-based application at the front-end stage. The research results show that the non-real-time condition has an accuracy of 98%, while the real-time is 95% lower. This research produces model and application performance that is flexible for user needs. The results can be recommended for developing applications for more comprehensive users.
Rancang Bangun Aplikasi Katalog Augmented Reality Design Setup Ruang Kerja Minimalis berbasis Android ST. Aminah Dinayati Ghani; Andi Alfian
AGENTS: Journal of Artificial Intelligence and Data Science Vol 3 No 2 (2023): Maret - Agustus
Publisher : Prodi Teknik Informatika Universitas Islam Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/jagti.v3i2.66

Abstract

This research is motivated by the use of Augmented Reality on the catalog page which can help clients see visualizations of the Interior design of a minimalist workspace based on the desired Interior theme in 3-dimensional form. The problem that arises is how to build an application that can scan 3D objects on catalog pages along with interesting workspace concept information by utilizing Android-based devices. The purpose of this study is to design a catalog information media that can display the Interior design of a minimalist workspace by utilizing Augmented Reality features into Android-based devices. This application was created using the C# programming language and uses Unity 3D Engine, SketchUp, and Photoshop software. Functionally testing the software on catalog applications using the blackbox method. The applications resulting from this research can help clients see the theme of minimalist workspace design designed to attract clients' attention in visualizing into the form of 3D objects
Tinjauan Sentimen Terhadap Ulasan Aplikasi Peminjaman Online dengan Metode Support Vector Machine (SVM) ST. Aminah Dinayati Ghani; Nur Salman Nur Salman; Farhan Wahyuta Kusuma Farhan Wahyuta Kusuma
AGENTS: Journal of Artificial Intelligence and Data Science Vol 4 No 1 (2024): Vol 4 No 1 (2024): September - Februari
Publisher : Prodi Teknik Informatika Universitas Islam Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/jagti.v4i1.74

Abstract

Online loans, abbreviated as "Pinjol," refer to the practice of lending money online through applications or websites without involving traditional financial institutions such as banks or other traditional creditors. Examples of applications in this field include AkuLaku and Kredivo. These apps operate in the e-commerce and credit provision sectors in Southeast Asia, including Indonesia. Despite their operational strengths, these applications have both advantages and disadvantages, leading to positive and negative reviews on platforms like the Play Store. The research aims to identify positive and negative reviews within these online loan applications that can influence users' decisions when choosing a particular app. SVM classification technique is employed to analyze positive and negative sentiments from these reviews. The accuracy results obtained after sentiment analysis for Kredivo are 81%, while for AkuLaku, it is 75%. A higher accuracy value indicates a better ability of the model to predict sentiments correctly. Visualization of impactful words based on word frequency is presented in the form of a Word Cloud. Therefore, based on the sentiment analysis conducted using the SVM model, the author suggests choosing the Kredivo app when selecting an online loan application, as the analysis indicates that Kredivo has better quality compared to AkuLaku.
APLIKASI PREDIKSI STATUS PERTUMBUHAN BALITA MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBORS (K-NN) ST. Aminah Dinayati Ghani; Nur Salman; Rudy Donny Liklikwatil; Siti Hajratul Aswa; Maria Nova Sarembona
JED : Journal Entrepreneurship Digital Vol. 2 No. 1 (2024): JED (Journal Entreupreneur Digital)
Publisher : Pusat Penelitian dan Pengabdian kepada Masyarakat Universitas Dipa Makassar

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

Abstract

Pertumbuhan balita merupakan indikator penting dalam menentukan status kesehatan anak di usia dini. Posyandu sebagai layanan kesehatan masyarakat memiliki peran krusial dalam pemantauan tumbuh kembang balita. Posyandu Kuncup Mekar di Desa Je’nemadinging dalam pencatatan dan analisis data pertumbuhan balita masih dilakukan secara manual, sehingga kesalahan dalam interpretasi data dapat terjadi. Penelitian ini bertujuan untuk merancang aplikasi berbasis web yang dapat membantu tenaga kesehatan dalam memprediksi status pertumbuhan balita dengan menggunakan algoritma K-Nearest Neighbors (K-NN). Algoritma K-NN dipilih karena kemampuannya dalam melakukan klasifikasi berdasarkan data historis yang ada. Aplikasi ini akan memanfaatkan data seperti usia, berat badan, tinggi badan, dan lingkar kepala balita untuk melakukan prediksi status pertumbuhan berdasarkan standar WHO (World Health Organization). Pengujian aplikasi menghasilkan tingkat akurasi sebesar 92,98 %. Hal ini membuktikan bahwa aplikasi mampu memprediksi status pertumbuhan balita dengan tingkat kepercayaan yang tinggi, sehingga dapat mendukung deteksi dini masalah gizi serta memungkinkan intervensi yang lebih cepat dan tepat.Hasil penelitian ini diharapkan dapat meningkatkan efisiensi pencatatan data di Posyandu serta membantu tenaga kesehatan dalam mengambil keputusan yang lebih akurat terkait pertumbuhan balita.