Claim Missing Document
Check
Articles

Found 31 Documents
Search

Klasifikasi Penyakit Diabetic Retinopathy Menggunakan Multilayer Perceptron Umri Erdiansyah; Ahmadi Irmansyah Lubis; Guntur Syahputra
Journal of Artificial Intelligence and Software Engineering Vol 2, No 1 (2022)
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v2i1.3084

Abstract

Diabetic Retinopathy merupakan salah satu komplikasi penyakit diabetes yang dapat menyebabkan kematian. Komplikasi ini berupa kerusakan pada retina mata. Kadar glukosa yang tinggi dalam darah dapat menyebabkan kapiler kecil pecah dan menyebabkan kebutaan. Penyakit ini dimulai dengan melemahnya atau rusaknya kapiler kecil di retina, memungkinkan darah mengalir dan kemudian menyebabkan penebalan jaringan, pembengkakan, dan pendarahan hebat. Penelitian ini bertujuan untuk menganalisis diagnosis retinopati diabetik berupa data rekam medis. Multilayer Perceptron merupakan salah satu algoritma jaringan syaraf tiruan yang sering digunakan untuk klasifikasi data dan digunakan dalam proses klasifikasi pada penelitian ini. Dataset yang digunakan dalam penelitian ini diperoleh dari UCI Machine Learning Repository, kumpulan data dari University of Debrecen, Hongaria, termasuk data pasien untuk retinopati diabetik. Evaluasi hasil klasifikasi yang digunakan adalah confusion matrix. Dari hasil perhitungan yang telah dilakukan, maka didapatkan hasil akurasi pada Multilayer Perceptron sebesar 71.80%, dengan nilai precision 72.50%, dan Recall 71.80%.
PROJECT-BASED LEARNING PERFORMANCE MEASUREMENT USING VIKOR METHOD AND RANK ORDER CENTROID Ahmadi Irmansyah Lubis; Supardianto Supardianto; Metta Santiputri; Noper Ardi; Alena Uperiati
JURTEKSI (Jurnal Teknologi dan Sistem Informasi) Vol 10, No 3 (2024): Juni 2024
Publisher : STMIK Royal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurteksi.v10i3.2853

Abstract

Abstract: Project-Based Learning is a type of learning that is quite widely recommended today, especially in vocational type institutions where the learning is effective in the aim of involving students with direct learning content. The process of evaluating project-based learning on project teams in the performance assessment of each team to rank the order of best performance of all teams is still assessed based on subjective assessments. To overcome these problems, in this study the performance measurement of the project-based learning team by applying the VIKOR method and Rank Order Centroid in conducting assessments with test samples, namely in the Introduction to Database course. The test results obtained based on the calculation of VIKOR and Rank Order Centroid, namely PBL-TRPL01 Team 1 as the best alternative by obtaining based on variations of testing the VIKOR index value with values v=0.4, v=0.5, and v=0.6. Thus, it can be seen that the VIKOR and Rank Order Centroid methods can be applied to the calculation process of measuring team performance in project-based learning.            Keywords: decision Support System; project-based learning; rank order centroid; VIKOR Abstrak: Pembelajaran Berbasis Proyek merupakan jenis pembelajaran yang cukup banyak direkomendasikan di masa kini khususnya pada institusi berjenis vokasional. Pembelajaran tersebut efektif dalam tujuan melibatkan para peserta didik dengan konten pembelajaran secara langsung. Proses evaluasi pembelajaran berbasis proyek pada tim proyek dalam penilaian performa dari masing-masing tim untuk memeringkatkan urutan performa terbaik dari seluruh tim masih dinilai berdasarkan penilaian secara subyektif. Untuk mengatasi persoalan tersebut, pada penelitian ini pengukuran performa tim project-based learning dengan menerapkan metode VIKOR dan Rank Order Centroid dalam melakukan penilaian dengan sampel pengujian yaitu pada mata kuliah Pengantar Basis Data. Hasil pengujian yang diperoleh berdasarkan perhitungan VIKOR dan Rank Order Centroid yaitu bahwa alternatif PBL-TRPL01 Tim 1 sebagai alternatif terbaik dengan peroleh berdasarkan variasi pengujian nilai indeks VIKOR. Maka dengan demikian, dapat diketahui bahwa metode VIKOR dan Rank Order Centroid dapat diterapkan pada proses perhitungan pengukuran performa tim pada pembelajaran berbasis proyek. Kata kunci: pembelajaran berbasis proyek; rank order centroid; sistem pendukung keputusan; VIKOR
The Application of Convolutional Neural Networks in Floristic Recognition Legito; Nuraini, Rini; Judijanto, Loso; Lubis, Ahmadi Irmansyah
International Journal Software Engineering and Computer Science (IJSECS) Vol. 3 No. 3 (2023): DECEMBER 2023
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v3i3.1827

Abstract

In the dynamic field of computer vision, this research explores the application of Convolutional Neural Networks (CNNs) for the complex task of floristic recognition, a critical aspect of botanical and ecological studies. Addressing the challenges posed by the vast diversity and subtle morphological differences among plants, our study leverages CNNs for an efficient and accurate plant identification method. Distinguished by a comprehensive dataset encompassing a wide range of plant species and employing a state-of-the-art CNN model, our research significantly advances the methodology of flower recognition. This paper highlights the CNN model's sophisticated feature extraction and image analysis capabilities, demonstrating its superior performance in classifying a diverse range of flora compared to traditional methods and other machine learning techniques like Support Vector Machines (SVM) and decision trees. Our approach emphasizes practical applications in areas such as agriculture, ecology, and conservation, and offers a powerful tool for rapid and efficient plant identification, crucial in biodiversity studies. The research contributes to the fields of botany, ecology, and environmental conservation, underscoring the transformative potential of CNNs in floristic recognition. It also outlines the future direction for enhancing the model's efficiency, including developing more computationally efficient architectures and expanding training datasets.
Penerapan Neural Network Dalam Klasifikasi Citra Permainan Batu Kertas Gunting dengan Probabilistic Neural Network Siregar, Siti Julianita; Lubis, Ahmadi Irmansyah; Ginting, Erika Fahmi
Building of Informatics, Technology and Science (BITS) Vol 3 No 3 (2021): December 2021
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (552.519 KB) | DOI: 10.47065/bits.v3i3.1143

Abstract

In this research, an image classification model was developed to distinguish hand objects pointing at rock, paper, and scissors using one of the popular image classification methods, namely the Probabilistic Neural Network. Probabilistic Neural Network is a method in an artificial neural network that is used to classify a category based on the results of calculating the distance between the density function and the probability. PNN has 4 stages of processing, namely Input Layer, Pattern Layer, Summation Layer, and Output Layer. Tests in the study were carried out with a total of 60 testing data from three object classes from the dataset. Then the results of the classification of Batu, Scissors, and Paper hand images using the application of the PNN algorithm in this research test obtained an average accuracy value of 90%
Application of Certainty Factor Method in Intelligent System for Diagnosis of Periodontal Disease in Cigarette AddictsApplication of Certainty Factor Method in Intelligent System for Diagnosis of Periodontal Disease in Cigarette Addicts Lubis, Ahmadi Irmansyah; Gaol, Nur Yanti Lumban
Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 4 (2022): Article Research: Volume 6 Number 4, October 2022
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v7i4.11695

Abstract

This study discusses the design of an Android-based innovative application that is useful in the early diagnosis of periodontal disease in cigarette addicts. The problem which is the main topic of discussion in this study is the health issue of organs that are often ignored by humans, namely the teeth and mouth. Then one of the types of dental and oral diseases that many people often complain about is the periodontal disease which also gets less attention in Indonesian society. And one of the causes of this periodontal disease is caused by smoking habits. So to facilitate the identification in knowing the periodontal symptoms caused by the cigarette, a system that can identify the early symptoms of periodontal disease is needed. The technology proposed to build the system applies expert system technology with Certainty Factor. In building an android-based innovative application to diagnose periodontal disease, there are cigarette addicts in this study with the Research & Development research method to produce an output that can be right on target by the expected target. In addition, interviews and direct observation techniques were also carried out with experts or experts in the field of dental and oral diseases to collect the required data on the needs of the system to be built.
Forward Selection Attribute Reduction Technique for Optimizing Naïve Bayes Performance in Sperm Fertility Prediction Lubis, Ahmadi Irmansyah; Chandra, Rudy
Sinkron : jurnal dan penelitian teknik informatika Vol. 7 No. 1 (2023): Articles Research Volume 7 Issue 1, 2023
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i1.11967

Abstract

The problem of infertility between husband and wife is an important issue that destroys family harmony, and many people still consider infertility or infertility a female problem. However, about 7% of men of childbearing age suffer from infertility. The biggest factor causing male infertility is sperm quality problems. Sperm analysis can be the best predictor of male fertility potential. Machine learning and data mining techniques can be used to automate disease diagnosis. This study aims to obtain a regular form classification model from sperm sample data of 100 volunteers. This classification model can be used to predict male fertility levels into 2 classes, namely normal and alter (decreased fertility). This study uses a fertility dataset obtained from the UCI Machine Learning Repository. Before the data mining process, data preprocessing is required. The classification process is carried out using Naive Bayes and attribute reduction techniques using forward selection to see the increase in the accuracy of Naive Bayes performance. The Naive Bayes test without attribute reduction has an accuracy of 85%, while attribute reduction with forward selection has an accuracy of 88% in predicting sperm fertility. Therefore, by using forward selection with Naive Bayes to reduce attributes in this study, this study was able to increase accuracy by 3% and can be used to help predict sperm fertility
PENGEMBANGAN DAN IMPLEMENTASI SISTEM INFORMASI ORGANISASI PADA PIMPINAN CABANG MUHAMMADIYAH KECAMATAN BATAM KOTA Irmansyah Lubis, Ahmadi; Riyadi, Agung; Purnamasari, Dwi Amalia; Ardi, Noper; Mu'minin, Amirul; Suwarno, Suwarno; Ramadhan, Gilang Bagus
Journal of Community Service Vol 6 No 2 (2024): JCS, December 2024
Publisher : Ikatan Dosen Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56670/jcs.v6i2.275

Abstract

The management of an organization often has many obstacles such as less optimal management of organizational documents, news portals, financial reports, correspondence documentation, activity documentation or data collection of members of the organization. Therefore, a reliable management system is needed so that management in the organization can be carried out more optimally. Likewise with the management in the Muhammadiyah Branch Executive, Batam Kota District, a reliable system is also needed to support the movement of various activities in the organization. The website-based information system developed is an answer to this problem. This system can be used to manage various activities and monitor their progress as well as make it easier for administrators to collect data on their members. This system can also display various institutional news so that the public is more familiar with the Muhammadiyah Branch Executive of Batam Kota District as a community organization with Islamic nuances that also carries out da'wah activities to spread goodness. So this is an agenda in this community service activity for the development of information systems and assistance in the implementation of the system both for managers and users of the system, as well as as a concrete step for the contribution of Higher Education in empowering the community by applying scientific principles that are useful for the benefit of the community.
Predicting Missing Value Data on IEC TC10 Datasets for Dissolved Gas Analysis using Tertius Algorithm Ardi, Noper; S, Supardianto; Irmansyah Lubis, Ahmadi
Journal of Applied Informatics and Computing Vol. 7 No. 1 (2023): July 2023
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v7i1.5361

Abstract

IEC TC10 is the most widely used Dissolved Gas Analysis (DGA) measurement dataset nowadays. Many DGA-based studies have been carried out using conventional methods and methods based on Artificial Intelligence Techniques (AITs). DGA is a diagnostic test performed on power transformers to detect and diagnose potential faults. The test involves analyzing the gases that are dissolved in the transformer oil, which can provide important information about the condition of the transformer. DGA is a widely used technique for transformer monitoring and maintenance in the power industry. However, this dataset is not perfect. There are still many problems in this dataset, one of which is the problem of missing value data. This problem will be significant if not appropriately handled. More reliable data from DGA measurement results is an in-dispensable reference in diagnosing faults in power transformers. This study focuses on dealing with the problem of missing value data using the Tertius algorithm, then testing the results using the J48 and Random Forest algorithms. The results obtained are pretty significant. Of the total 56 missing data, 36 could be predicted perfectly. And received the results of measuring accuracy using the J48 method of 62.73% and the Random Forest method of 70.71%. This result shows that the approach we applied is relatively good for handling missing values in IEC TC10 datasets.
Media Pembelajaran Pengenalan Citra Pesawat Udara Dengan Memanfaatkan Metode Jaringan Saraf Tiruan Dzulfiqar, Mohamad Alif; Irmansyah Lubis, Ahmadi
Jurnal Teknologi dan Riset Terapan (JATRA) Vol. 6 No. 2 (2024): Jurnal Teknologi dan Riset Terapan (JATRA) - December 2024
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jatra.v6i2.8885

Abstract

This study developed an image classification model to help learn the recognition of aircraft types using the Probabilistic Neural Network (PNN) method, one of the techniques in artificial neural networks that is often used for image classification. PNN works by classifying categories based on the calculation of the distance between the concentration and probability functions. In the process, PNN consists of four main stages: Input Layer, Pattern Layer, Summation Layer, and Output Layer. This study used 90 test data from three different object classes taken from the available data sets. The test results show that the application of the PNN algorithm in aircraft image classification provides an average accuracy of 81.11 %, which is quite promising to be applied as a learning module for the introduction of aircraft types for Aircraft Maintenance Engineering students at the Batam State Polytechnic. The results of this study show that the PNN method has great potential to help automatic classification and can be optimized to improve the accuracy of classification in further learning.
Pemilihan Anggota Bidang Organisasi Menggunakan Metode Weighted Product dan Pembobotan Rank Order Centroid Ahmadi Irmansyah Lubis
CESS (Journal of Computer Engineering, System and Science) Vol. 10 No. 1 (2025): Januari 2025
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/cess.v10i1.65066

Abstract

Pemilihan anggota majelis pendidikan dasar dan menengah di Pimpinan Cabang Muhammadiyah (PCM) Batam Kota membutuhkan penilaian objektif atas kriteria seperti pengalaman, kompetensi, komitmen, dan kepemimpinan. Proses ini sering rentan terhadap subjektivitas dan bias tanpa sistem pendukung. Penelitian ini bertujuan merancang Sistem Pendukung Keputusan (SPK) untuk membantu PCM Kecamatan Batam Kota dalam memilih anggota majelis pendidikan dasar dan menengah secara efektif dan akurat. Metode Weighted Product digunakan untuk menghitung skor akhir setiap calon berdasarkan nilai kriteria dan bobotnya. Metode Rank Order Centroid (ROC) diterapkan untuk menentukan bobot kriteria secara kualitatif berdasarkan urutan prioritas. Sistem ini memungkinkan pengguna membandingkan kandidat secara komprehensif dengan mempertimbangkan semua kriteria. Hasil penelitian menunjukkan metode Weighted Product dan ROC efektif membantu PCM Kecamatan Batam Kota dalam memilih kandidat terbaik untuk menjadi anggota majelis Pendidikan dasar dan menengah. Kandidat terpilih yaitu A4 (Ketua) dengan nilai vektor 0.16706, A1 (Anggota) dengan nilai vektor 0.16163, dan A6 (Anggota) dengan nilai vektor 0.15951. Sistem ini mampu dalam meningkatkan obyektifitas, efisiensi, dan akuntabilitas proses seleksi, sekaligus mengurangi bias subjektif. Hasil penelitian ini diharapkan bermanfaat tidak hanya bagi PCM Batam Kota tetapi juga sebagai referensi bagi organisasi lain dengan kebutuhan seleksi berbasis kriteria multi-dimensi.