Claim Missing Document
Check
Articles

Found 25 Documents
Search

Toddler Nutritional Status Classification Using C4.5 and Particle Swarm Optimization Nazir, Alwis; Akhyar, Amany; Yusra, Yusra; Budianita, Elvia
Scientific Journal of Informatics Vol 9, No 1 (2022): May 2022
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v9i1.33158

Abstract

Abstract. Purpose: This research was conducted to create a classification model in the form of the most optimal decision tree. Optimal in this case is the combination of parameters used that will produce the highest accuracy compared to other parameter combinations. From this best model, it will be used to predict the nutritional status class for the new data.Methods/Study design/approach: The dataset used is from Nutritional Status Monitoring in 2017 in Riau Province, Indonesia. From the dataset, the Knowledge Discovery in Database (KDD) stages were carried out to build several classification models in the form of decision trees. The decision tree that has the highest accuracy will then be selected to predict the class for the new data. Predictions for new data (unclassified data) will be made in a web-based system.Result/Findings: Particle Swarm Optimization is used to find optimal parameters. Before PSO is used, there are 213 parameters in the dataset that can be used to do classification. However, using many such parameters is time-consuming. After PSO is used, the optimal parameters found are the combination of 4 parameters, which can produce the most optimal decision tree. The 4 chosen parameters are gender, age (in months), height, and the way to measure the height (either stand up or lie down). The most optimal decision tree has an accuracy of 94.49%. From the most optimal decision tree, a web-based system was built to predict the class for new data (unclassified data).Novelty/Originality/Value: Particle Swarm Optimization (PSO) is a method that can help to select the most optimal parameters, or in other words produce the highest classification accuracy. The combination of parameters selected has also been confirmed by the nutritionist. The prediction system has been declared feasible to be used by nutritionists through the User Acceptance Test (UAT).
Sistem Pendukung Keputusan Penerimaan Beasiswa Gubernur Riau Menggunakan Fuzzy dengan Metode Profile Matching Budianita, Elvia; Syahputra, Armadani
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 2, No 1 (2016): Juni 2016
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (994.676 KB) | DOI: 10.24014/coreit.v2i1.2352

Abstract

Beasiswa Gubernur Riau bertujuan meningkatkan kualitas pendidikan yang ada di Provinsi Riau. Penelitian ini ditujukan kepada beasiswa program D3 dan S1, dengan kriteria penilaian seperti status keluarga, penghasilan wali perbulan, jumlah anak dari wali, jumlah saudara menikah, jumlah saudara kandung kuliah dan belum menikah, biaya semester, semester dan IPK. Sistem ini merupakan Sistem Pendukung Keputusan (SPK) menggunakan fuzzy dengan metode profile matching. Fuzzy sebagai nilai kriterianya menutupi kekurangan profile matching menangani data yang bervariatif menjadi kesuatu nilai antara 0 sampai 1, nilai diproses dengan metode profile matching, menghasilkan sebuah perangkingan penerima beasiswa. Berdasarkan hasil pengujian SPK dari 15 data pemohon tahun sebelumnya, bahwa data 5 terbawah merupakan data yang memang tidak lulus seleksi, artinya hasil perangkingan SPK sesuai dengan yang diharapkan oleh tim penyeleksi Beasiswa Gubernur Riau dan mampu mengurangi subyektifitas penilaian.
Penerapan Learning Vector Quantization Penentuan Bidang Konsentrasi Tugas Akhir (Studi Kasus: Mahasiswa Teknik Informatika UIN Suska Riau) Budianita, Elvia; Arni, Ulti Desi
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 1, No 2 (2015): Desember 2015
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (612.198 KB) | DOI: 10.24014/coreit.v1i2.1235

Abstract

Penentuan bidang konsentrasi studi tugas akhir diharapkan dapat mempermudah mahasiswa dalam menentukan bidang tugas akhirnya sesuai dengan pola nilai mata kuliah yang diambilnya. Banyaknya bidang tugas akhir membuat mahasiswa merasa bingung menentukan tema tugas akhirnya. Sehingga banyak mahasiswa menentukan bidang konsentrasi studi tugas akhirnya diluar mata kuliah yang mereka ambil. Jika mahasiswa memilih bidang konsentrasi tugas akhir sesuai mata kuliah yang mereka ambil, maka mahasiswa tersebut dapat dengan cepat menyelesaikan tugas akhirnya tanpa harus mempelajari metode terlebih dahulu. Oleh karena itu dibutuhkan sebuah media yang dapat membantu mahasiswa dalam menentukan bidang tugas akhirnya yang sesuai dengan pola nilai mata kuliah yang diambil. Metode yang digunakan yaitu Metode Learning Vector Quantization (LVQ). LVQ adalah metode jaringan syaraf tiruan yang mempelajari pola nilai dan secara otomatis belajar untuk mengklasifikasikan vektorvektor input. Kelas-kelas yang didapatkan sebagai hasil dari lapisan kompetitif ini tergantung pada jarak antara vector input. Jika dua vektor input mendekati sama, maka lapisan kompetitif akan meletakkan kedua vektor input tersebut kedalam kelas yang sama.
Implementasi Algoritma K-Means dalam Menentukan Clustering pada Penilaian Kepuasan Pelanggan di Badan Pelatihan Kesehatan Pekanbaru Fahrozi, Aqshol Al; Insani, Fitri; Budianita, Elvia; Afrianty, Iis
Indonesian Journal of Innovation Multidisipliner Research Vol. 1 No. 4 (2023): December
Publisher : Institute of Advanced Knowledge and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/ijim.v1i4.53

Abstract

This research discusses the implementation of the K-Means algorithm in determining clustering in customer satisfaction assessments at the Pekanbaru Health Training Agency. Customer satisfaction is the level of a person's feelings to perceive the comparison between the consumer's impression of the level of product and service performance and the customer's or buyer's expectations. The aim of this research is to see the level of customer satisfaction with the Pekanbaru Health Training Agency (Bapalkes) services using K-means clustering and how high the level of customer satisfaction is using the K-means Clustering method. In this research, the data used is Health Training Center customer data from 2019 and 2023. Data was collected through questionnaires distributed via Google form. Creating a rule model for the collected data using the k-means algorithm and rapidminer software. From the research results obtained using the K-Means algorithm in clustering customer data, it can provide customer segmentation results that are in line with expectations, so that the Pekanbaru Health Training Agency can easily understand the characteristics of its customers based on their clusters and their satisfaction. Then, using the elbow and Davies Bouldin methods, we also provide a solution for selecting the right number of clusters so that performance is more optimal and produces more accurate customer segmentation results. From the calculations of the k-means algorithm, it was obtained that the response value was very dominant at 259 who expressed satisfaction and 44 people who expressed dissatisfaction from 303 customers, so that the k-means algorithm used sensitivity and specificity tests, 86% expressed satisfaction and 14% expressed dissatisfaction with services provided by the Pekanbaru Health Training Agency.
Penerapan Neural Network dengan Menggunakan Algoritma Backpropagation pada Prediksi Putusan Perceraian Zulastri, Zulastri; Afrianty, Iis; Budianita, Elvia; Syafria, Fadhilah
Building of Informatics, Technology and Science (BITS) Vol 4 No 3 (2022): December 2022
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v4i3.2437

Abstract

The high divorce rate has a negative impact on couples who will file for divorce and also has an extreme impact on children such as psychological disorders of children. The magnitude of the impact of divorce, it is necessary to predict the divorce decision. In this study, the application of the backpropagation method to predict divorce decisions was carried out. The data used is data on divorce decisions from the Pekanbaru Religious Court from 2020 - 2021 totaling 779. The dataset obtained is not balanced with 724 accepted classes and 55 rejected classes, balancing is done by reducing excess classes. The parameters used in this study build 3 architectural models [6-7-1], [6-9-1], [6-12-1], learning rate (0.01, 0.03, 0.09), max epoch and data sharing (70:30), (80:20), (90:10). The results of this study indicate that the best architectural model is in the network architecture [6-9-1] learning rate 0.09 epoch 300 dataset distribution 80% training data and 20% test data the accuracy value is 80% and the Mean Squared Error (MSE) is 0.1402. In this study, the backpropagation method was successful in predicting divorce decisions.
Klasifikasi Kematangan Buah Mangga Menggunakan Pendekatan Deep Learning Dengan Arsitektur DenseNet-121 dan Augmentasi Data Permata, Rizkiya Indah; Yanto, Febi; Budianita, Elvia; Iskandar, Iwan; Syafria, Fadhilah
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5381

Abstract

Mango is a seasonal fruit in Indonesia. In lowland areas and hot climates, this mango plant can grow abundantly. People who use mangoes generally focus more on the characteristics of the fruit which require a more precise classification to be more certain. Traditional classifications sometimes fail to properly articulate maturity criteria. This research classifies mango ripeness using a deep learning approach with densenet-121 architecture, parameters, learning rate, dropout, and data augmentation. Augmentation is the process of changing or modifying an image in such a way that the computer will detect that the image has been changed is the same picture. The original dataset was 895 data, after being augmented it became 1790 data consisting of three classes, namely ripe mango, young mango, and rotten mango. The test compares the original data and the original data added with augmentation. Accuracy using original data is 95.95%. Meanwhile, using original data combined with augmentation gets an accuracy of 99.73%
Klasifikasi Tulang Tengkorak Berdasarkan Jenis Kelamin dalam Antropologi Forensik Menggunakan Metode Support Vector Machine Rahayu, Siti Sri; Afrianty, Iis; Budianita, Elvia; Syafria, Fadhilah
Jurnal Inovtek Polbeng Seri Informatika Vol 9, No 1 (2024)
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/isi.v9i1.4046

Abstract

Classification of skull bones by sex is part of human biological profile identification in forensic anthropology that aims to determine whether the skeleton belongs to a male or female. The most popular method for determining sex from bones is DNA analysis. However, under some conditions such as burnt, damaged, or very dry skeletal remains, DNA analysis cannot provide accurate results. So forensic anthropology is developing by utilizing the help of machine learning technology. This research shows the performance of Support Vector Machine in classifying skull bones based on gender. The skull parameter data used is data collected by Dr. William Howells from craniometric measurements consisting of male and female data with a total of 2524 data and 82 features, namely bizygomatic breadth, glabello-occipital lenght and others.  In building the skull bone classification model, the Support Vector Machine kernels used are linear, RBF, and polynomial. Based on the test results, the best accuracy was obtained in each kernel function, namely the linear kernel obtained the best accuracy of 88.14% with C = 2. For the RBF kernel, the best accuracy was 91.30% at C = 2, γ = 'auto'. For the polynomial kernel, the best accuracy was 88.14% at C = 1 and 2, γ = 1 and 2, d = 1. The evaluation results show that the Support Vector Machine model with the RBF kernel has proven to be the optimal choice in skull bone classification compared to other kernels, based on accuracy, precision, recall, and CrossValidation measurements reaching values above 90%. These results indicate that the skull bone classification model based on gender using Support Vector Machine is recommended in forensic anthropology.
Klasifikasi Status Stunting Balita Dengan Metode Support Vector Machine Berbasis Web Adzhima, Fauzan; Budianita, Elvia; Nazir, Alwis; Syafria, Fadhilah
Jurnal Inovtek Polbeng Seri Informatika Vol 8, No 2 (2023)
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/isi.v8i2.3641

Abstract

Orang tua harus memperhatikan anak mereka saat balita, karena di usia tersebut mereka rentan terhadap berbagai gangguan pertumbuhan dan perkembangan, salah satunya stunting. Stunting adalah gangguan pertumbuhan dan perkembangan yang disebabkan oleh kekurangan gizi dan ditandai dengan tinggi badan yang tidak memenuhi kriteria pertumbuhan normal anak seusianya. Untuk mencegah stunting, tenaga kesehatan atau kader posyandu mengukur antropometri tubuh anak-anak di posyandu. Data hasil pengukuran tubuh anak diproses secara manual, sehingga ada kemungkinan besar kesalahan pemrosesan karena kesalahan manusia (human error). Dengan mempelajari pola data pengukuran, data mining dapat mengatasi masalah dalam proses pengolahan data pengukuran. SVM merupakan salah satu metode data mining yang umum dipakai untuk permasalahan klasifikasi dengan kelebihannya yang dapat bekerja dengan menggunakan memori yang kecil serta dapat memisah data yang tidak dapat dipisahkan secara linier. Usia, jenis kelamin, Inisiasi Menyusui Dini (IMD), berat badan, dan tinggi badan adalah atribut yang digunakan untuk klasifikasi menggunakan algoritma SVM ini. Berdasarkan pengujian yang dilakukan, terdapat 1172 data dengan hasil rata-rata performa model terbaik menggunakan parameter γ = 0.01 dan akurasi 98.99%, sehingga model dapat digunakan untuk memprediksi data pengukuran baru secara akurat dan tindakan pencegahan stunting dapat segera dilakukan.
Deep Learning Menggunakan Algoritma Xception dan Augmentasi Flip Pada Klasifikasi Kematangan Sawit Masaugi, Fathan Fanrita; Yanto, Febi; Budianita, Elvia; Sanjaya, Suwanto; Syafria, Fadhilah
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 6 (2024): Juni 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i6.1938

Abstract

Palm oil is an important commodity in Indonesia, especially as Indonesia is the highest palm oil exporting country in the world. Ripe palm fruit is marked by a change in color of the fruit from black to reddish yellow. Apart from that, immature palm fruit has a negative and significant effect on CPO production. The data collection process was carried out by directly taking pictures of palm fruit on oil palm plantations and data obtained from Kaggle. The total amount of data is 1000 images and 1000 data resulting from flip augmentation. The Xception algorithm is an algorithm in deep learning which stands for Extreme version of Inception. This combination was then proven to provide better accuracy in classifying images from a dataset. The optimizer used is the optimizer in TensorFlow, namely Adam (Adaptive Moment Estimation) using learning rate and dropout values. Images of mature and immature palm oil were classified using the Xception algorithm with augmented and without augmented data. In addition, experiments were carried out by changing the parameter values ??of learning rate to 0.1, 0.01, 0.001 and dropout to 0.1, 0.01, 0.001. It was found that the data division was (90;10) with the best accuracy reaching 95%. Test parameters carried out by trialling were proven to increase accuracy when compared to without using parameters and flip augmentation. The best accuracy of the Xception model is 95% on augmented data with a learning rate of 0.001 and a dropout of 0.1.
Implementasi VGG 16 dan Augmentasi Zoom Untuk Klasifikasi Kematangan Sawit Mazdavilaya, T Kaisyarendika; Yanto, Febi; Budianita, Elvia; Sanjaya, Suwanto; Syafria, Fadhilah
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 6 (2024): Juni 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i6.1940

Abstract

Indonesia is a country that has very abundant palm oil plantations and makes palm oil one of the largest export commodities in Indonesia. Fruit maturity on oil palms has a significant influence on palm oil and kernel production. The level of ripeness in palm oil fruit can affect several contents in it, such as tocopherol content, yield and FFA. The classification will be divided into 2 classes, namely between ripe and immature fruit with data on 500 images of ripe fruit and 500 images of immature fruit, data taken from the Kaggle site and private gardens taken using a cellphone camera. The data that has been obtained is augmented which is useful for enriching the data to make it more abundant. Data augmentation uses zoom augmentation and makes the original 1000 data increase to 2000 data. The model used is VGG 16 which is part of deep learning. The existing dataset is then preprocessed, resized and rescaled, then divides the data into 3, namely train, test and valid data. After dividing the data, then carry out the classification process with VGG 16 and set the hyperparameters after that the model will learn with 20 epochs. The model will learn with 57 schemes to compare and find highest accuracy. After the model has finished learning, it is evaluated using a confusion matrix. The results obtained were that the 90:10 data division using data augmentation with a learning rate of 0.01 and a dropout of 0.001 obtained the best accuracy, reaching 93.8%.