Claim Missing Document
Check
Articles

Found 35 Documents
Search

THE INFLUENCE OF DATA CATEGORIZATION AND ATTRIBUTE INSTANCES REDUCTION USING THE GINI INDEX ON THE ACCURACY OF THE CLASSIFICATION ALGORITHM MODEL Willy Fernando; Jollyta, Deny; Dadang Priyanto; Dwi Oktarina
Jurnal Ilmiah Kursor Vol. 12 No. 3 (2024)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v12i3.372

Abstract

Numerical data problems are typically caused by a failure to comprehend the data and the outcomes of its processing. In order to give richer context and a deeper understanding of the facts, numerical data must be transformed into categories. On the other hand, changes in data have a significant impact on the analysis's outcomes. The purpose of this study is to see how transforming numerical data into categories affects the model produced by the classification algorithms. The dataset used in this study is the Maternal Health Risk. Categorization refers to formal arrangements. Categorization is also accomplished by using the Gini Index to limit the number of instances of an attribute. The classification is carried out using the Random Forest (RF), K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM) algorithms to produce a model. The influence of data modifications to model can be observed in the confusion matrix with 5 different data splitting. The study results suggested that changing numerical data to categories data significantly improved the performance of the SVM model from 76.92% to 80.77% at a data splitting percentage of 95/5.
PARAMETER ASOSIASI UNTUK MENENTUKAN KORELASI JURUSAN DAN INDEKS PRESTASI KUMULATIF Buaton, Relita; Jollyta, Deny; Mawengkang, Herman; Zarlis, Muhammad; Effendi, Syahril
Jurnal Pilar Nusa Mandiri Vol 15 No 1 (2019): Pilar Nusa Mandiri : Journal of Computing and Information System Periode Maret 2
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (892.061 KB) | DOI: 10.33480/pilar.v15i1.285

Abstract

One of the problems in higher education is the mistake of prospective students in majors selection. This is caused by not paying attention to the suitability of the major in the original school with the chosen major in higher education so that it impacts not only non optimal processing and learning outcomes, such as the low GPA, but also on social life, such as increasing unemployment. The selection of the right major is very important and to help prospective students in choosing it requires an online system that can be accessed by everyone and select original school majors to see conformity with majors in higher education. This system uses association rules and parameters of support and confidence in data mining. The purpose of this research is to determine the correlation between majors in the original school, majors in higher education and the achievement of the GPA through the use of support and confidence parameters that process the knowledge base in the form of an alumni database on the online system created. Training or testing was conducted on 10,254 data in the database and produced new information and knowledge that between the majors of the original school, the choice of majors in higher education and GPA had a strong correlation with the value of confidence reaching 100%.
Cluster Validity for Optimizing Classification Model: Davies Bouldin Index – Random Forest Algorithm Prihandoko, Prihandoko; Jollyta, Deny; Gusrianty, Gusrianty; Siddik, Muhammad; Johan, Johan
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol 24 No 1 (2024)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v24i1.4043

Abstract

Several factors impact pregnant women’s health and mortality rates. The symptoms of disease in pregnant women are often similar. This makes it difficult to evaluate which factors contribute to a low, medium, or high risk of mortality among pregnant women. The purpose of this research is to generate classification rules for maternal health risk using optimal clusters. The optimal cluster is obtained from the process carried out by the validity cluster. The methods used are K-Means clustering, Davies Bouldin Index (DBI), and the Random Forest algorithm. These methods build optimum clusters from a set of k-tests to produce the best classification. Optimal clusters comprising cluster members withstrong similarities are high-dimensional data. Therefore, the Principal Component Analysis (PCA) technique is required to evaluate attribute value. The result of the research is that the best classification rule was obtained from k-tests = 22 on the 20th cluster, which has an accuracy of 97% to low, mid, and high risk. The novelty lies in using DBI for data that the Random Forest will classify. According to the research findings, the classification rules created through optimal clusters are 9.7% better than without the clustering process. This demonstrates that optimizing the data group has implications for enhancing the classification algorithm’s performance.
Menciptakan Collaborative Learning Guru dan Peserta Didik Melalui Aplikasi Padlet Pada Sekolah Menengah Atas Pekanbaru Jollyta, Deny; Nasien, Dewi; Nora Marlim, Yulvia; Gustientiedina, Gustientiedina; Adiya, M. Hasmil; Mukhsin, Mukhsin; Rahmadian Yuliendi, Rangga; Kamal, Ahmad; Hajjah, Alyauma; Johan, Johan
Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal Vol 8, No 2 (2025): April 2025
Publisher : STMIK Royal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurdimas.v8i2.3682

Abstract

Collaborative Learning requires teachers and students to maintain an engaging learning environment at all times. Problems emerge when teachers, notably high school teachers in Pekanbaru, employ learning material that do not support this. Teachers' creativity is pushed to constantly update how they present materials and evaluate students' knowledge in order to foster a collaborative and pleasurable learning environment. This community service project will help Pekanbaru high school instructors create collaborative and real-time learning tools. The Community Service Team employed an observation strategy to get a sense of learning at Santa Maria High School, which served as an example school. The proposed solution is technologically based, making use of the Padlet application. The Community Service Team offers training methods on smartphones and computers to help people grasp Padlet. The community effort resulted in a polished Padlet that teachers may use to study with students at any time. It is intended that studying using the Padlet application would boost teacher innovation and student learning results at Santa Maria High School, as well as high schools around Pekanbaru.Keywords: Teacher; padlet; collaborative learning; learners;SMA. Abstrak: Pembelajaran Kolaboratif (Collaborative Learning) mengarahkan guru dan peserta didik dalam suasana belajar yang interaktif setiap saat. Permasalahan muncul pada saat media pembelajaran yang digunakan guru tidak mendukung hal tersebut, termasuk guru-guru Sekolah Menengah Atas (SMA) di Pekanbaru. Kreativitas guru ditantang untuk selalu memperbaharui cara penyampaian materi, cara mengevaluasi pemahaman peserta didik hingga penilaian, demi terciptanya suasana belajar yang kolaboratif dan menyenangkan. Kegiatan pengabdian ini bertujuan untuk membantu guru SMA di Pekanbaru dalam mempersiapkan bahan pembelajaran yang kolaboratif dan real time. Tim Pengabdian melakukan metode observasi untuk mendapatkan gambaran pembelajaran melalui SMA Santa Maria yang dijadikan sebagai sekolah sampel. Metode yang diusulkan berbasis teknologi melalui pemanfaatan aplikasi Padlet. Untuk memudahkan pemahaman Padlet, Tim Pengabdian menggunakan metode pelatihan, baik melalui komputer maupun smartphone. Hasil pengabdian adalah Padlet jadi yang dapat digunakan guru dalam pembelajaran bersama peserta didik setiap waktu. Diharapkan pembelajaran melalui aplikasi Padlet mampu meningkatkan kreativitas guru dan hasil belajar peserta didik SMA Santa Maria khususnya dan SMA di Pekanbaru umumnya.Kata kunci: guru; padlet; pembelajaran kolaboratif; peserta didik; SMA.
FEATURE ALIGNMENT OF THE INTERNAL QUALITY AUDIT SYSTEM BASED ON PPEPP Jollyta, Deny; Hajjah, Alyauma; Mukhsin, Mukhsin; Prihandoko, Prihandoko
JURTEKSI (Jurnal Teknologi dan Sistem Informasi) Vol 11, No 3 (2025): Juni 2025
Publisher : Universitas Royal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurteksi.v11i3.3896

Abstract

Abstract: The Ministry of Education, Culture, Research, and Technology, has developed guidelines for the Internal Quality Assurance System or known as SPMI, that is being implemented through the Internal Quality Audit (IQA) with the PPEPP cycle, namely Determination (P), Implemen-tation (P), Evaluation (E), Control (P), and Improvement (P). Some universities have implemented IQA with system. The problem is that the system does not line well with the PPEPP cycle, which results in unsatisfactory audit results. The purpose of this study is to evaluate how well the university-owned AQI system features in line the PPEPP cycle and to highlight development opportunities. The method used Feature Oriented Domain analysis (FODA) and Acceptance Testing. This study delivered an analysis of IQA system features that consistent with PPEPP. The FODA results were validated by expert and tested with User Acceptance Test (UAT) with 89.98% user response that the system is acceptable. The research contributes to universities' understanding of the features necessary in the AQI system, which has an impact on the perfection of the university AQI system design in accordance with the PPEPP cycle.            Keywords: FODA; IQA system; PPEPP cycle; SPMI  Abstrak: Kementerian Pendidikan, Kebudayaan, Riset, dan Teknologi telah menyusun pedoman Sistem Penjaminan Mutu Internal atau yang dikenal dengan SPMI, yang diimplementasikan melalui Audit Mutu Internal (AMI) dengan siklus PPEPP, yaitu Penetapan (P), Pelaksanaan (P), Evaluasi (E), Pengendalian (P), dan Peningkatan (P). Beberapa perguruan tinggi telah mengimplementasikan AMI dengan sistem. Permasalahannya, sistem tersebut tidak sejalan dengan siklus PPEPP, sehingga hasil audit kurang memuaskan. Tujuan dari penelitian ini adalah untuk mengevaluasi seberapa baik fitur sistem AMI milik perguruan tinggi sejalan dengan siklus PPEPP dan menyoroti peluang pengembangan. Metode yang digunakan adalah analisis Feature Oriented Domain (FODA) dan Acceptance Testing. Penelitian ini menghasilkan analisis fitur sistem AMI yang konsisten dengan PPEPP. Hasil FODA divalidasi oleh ahli dan diuji dengan User Acceptance Test (UAT) dengan 89,98% respon pengguna bahwa sistem dapat diterima. Penelitian ini memberikan kontribusi terhadap pemahaman universitas terhadap fitur-fitur yang diperlukan dalam sistem AMI, yang berdampak pada kesempurnaan desain sistem AMI universitas sesuai dengan siklus PPEPP. Kata kunci: FODA; siklus PPEPP; sistem AMI; SPMI
Transfer Learning Model Evaluation on CNN Algorithm: Indonesian Sign Language System (SIBI) Jollyta, Deny; Prihandoko, Prihandoko; Johan, Johan; Ramdhan, William; Santoso, Erick
Journal of Applied Business and Technology Vol. 6 No. 2 (2025): Journal of Applied Business and Technology
Publisher : Institut Bisnis dan Teknologi Pelita Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35145/jabt.v6i2.213

Abstract

In Indonesia as much as elsewhere, the deaf can communicate using sign language. The Indonesian Sign Language System (SIBI) is one of the sign language systems used in Indonesia. A model produced by the Convolutional Neural Network (CNN) method can be used in computer science for the recognition of sign language. By using the Transfer Learning paradigm, CNN's performance may be enhanced. However, not many researches have been conducted to assess the effectiveness of transfer learning on sign language models, particularly those that use the TensorFlow library. In fact, the evaluation results can influence the selection of the transfer learning model together with CNN. This study aims to evaluate the efficacy of using the CNN model for SIBI sign language through Transfer Learning. The data used are images of 24 SIBI alphabets and are processed through the TensorFlow library. The images will be recognized through the transfer learning performance of 6 models, namely VGG16, VGG19, Resnet50, Desenet121, Inception-V3 and MobileNet-V2. The results of the study found that through the TensorFlow library, Mobilenetv2 had the highest accuracy of 78% after 20 epochs.
Penerapan Linear Discriminant Analysis Untuk Meningkatkan Kinerja Algoritma Support Vector Machine Gusrianty, Gusrianty; Fenly, Fenly; Jollyta, Deny; Erlin, Erlin; Putri, Ramalia Noratama; Oktariana, Dwi
Jurnal Informatika: Jurnal Pengembangan IT Vol 10, No 4 (2025)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v10i4.8772

Abstract

Obesity is a complex chronic disease influenced by various factors, such as genetic, environmental, and lifestyle, which is characterized by excess body weight due to the excessive accumulation of body fat. With the rapid advancement of technology and digitalization across all sectors, data has become increasingly vital, as large datasets generate valuable information. However, a key challenge in data analysis is addressing redundancy, noise, and high dimensionality, which can affect the performance of machine learning algorithms. This study aims to investigate the effectiveness of combining Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) in enhancing the accuracy and efficiency of high-dimensional data classification, particularly in predicting obesity levels. LDA is employed to reduce data dimensionality while retaining the most relevant features, whereas SVM is utilized as the classification algorithm to predict obesity levels based on patterns identified within the dataset. The research was conducted using a dataset consisting of 779 training samples and 195 testing samples. The results reveal that the combination of LDA and SVM achieved a classification accuracy of up to 99%, with a 50% reduction in data dimensionality and a computation speed of 0,0696 second. Moreover, computation time was significantly reduced, indicating that LDA not only facilitates data simplification but also improves the overall efficiency of the classification process.
Analisis Penerapan Augmented Reality Sebagai Strategi Pemasaran: Uji Black Box dan Korelasi Kody, Jeffry; Jollyta, Deny; Hajjah, Alyauma; Pratama, Teddy
The Indonesian Journal of Computer Science Vol. 11 No. 1 (2022): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v11i1.3037

Abstract

Traditional marketing no longer ensures greater revenue. Businesses in the advertising industry are also feeling the effects of this circumstance. People with a lot of mobility have less time to go shopping and visit stores. The demand for seeing product designs continues to rise, yet many people are unable to attend in person, resulting in greater time spent at work. Entrepreneurs must alter their marketing strategy to address these issues utilizing technology that is simple to use and available at all times. The goal of this research is to design an Augmented Reality (AR) application that can be used on a smartphone and can process sales via the internet. Black Box, light intensity, and the proper distance are used to create and test applications for functioning so that product photos seem at their best. The existence of the app also generates a strong correlation between customer interest of product and desire to purchase it. This is demonstrated by a correlation test with a value of 0.673191. It is envisaged that the designed application can aid advertising enterprises in enhancing marketing and sales.
Cluster Validity for Optimizing Classification Model: Davies Bouldin Index – Random Forest Algorithm Prihandoko, Prihandoko; Jollyta, Deny; Gusrianty, Gusrianty; Siddik, Muhammad; Johan, Johan
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 24 No. 1 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v24i1.4043

Abstract

Several factors impact pregnant women’s health and mortality rates. The symptoms of disease in pregnant women are often similar. This makes it difficult to evaluate which factors contribute to a low, medium, or high risk of mortality among pregnant women. The purpose of this research is to generate classification rules for maternal health risk using optimal clusters. The optimal cluster is obtained from the process carried out by the validity cluster. The methods used are K-Means clustering, Davies Bouldin Index (DBI), and the Random Forest algorithm. These methods build optimum clusters from a set of k-tests to produce the best classification. Optimal clusters comprising cluster members withstrong similarities are high-dimensional data. Therefore, the Principal Component Analysis (PCA) technique is required to evaluate attribute value. The result of the research is that the best classification rule was obtained from k-tests = 22 on the 20th cluster, which has an accuracy of 97% to low, mid, and high risk. The novelty lies in using DBI for data that the Random Forest will classify. According to the research findings, the classification rules created through optimal clusters are 9.7% better than without the clustering process. This demonstrates that optimizing the data group has implications for enhancing the classification algorithm’s performance.
Cluster Analysis Based on McKinsey 7s Framework in Improving University Services Jollyta, Deny; Oktarina, Dwi; Gusrianty; Astri , Renita; Kadim, Lina Arliana Nur; Dasriani, Ni Gusti Ayu
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 1 No. 1 (2021): October 2021
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2005.51 KB) | DOI: 10.59934/jaiea.v1i1.45

Abstract

The epidemic of Covid-19 has impacted all aspects of human life, including education. Academic and administrative services for academic community are suffering, as a result of the fact that not all universities are able to provide online services to help break the chain of Covid-19 distribution. This is due to a lack of human competencies to use technology and a lack of information technology resources, necessitating the development of new strategies by universities to address these flaws. The goal of this study is to develop a university service strategy based on McKinsey 7s cluster results on the part that is having issues based on questionnaire data. The questionnaire is organized on seven McKinsey elements. The Manhattan distance calculation and the K-Medoids algorithm results demonstrated that the structure, system, skill and staff are all part of elements that clustered in k=2 and has to be addressed in aiding services during the Covid-19 pandemic. The McKinsey 7s showed that universities service enhancements may be achieved by combining clustering techniques and McKinsey framework.