Garuda - Garba Rujukan Digital

p-Index From 2019 - 2024

5.569

P-Index

This Author published in this journals

All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) JOIN (Jurnal Online Informatika) JOIV : International Journal on Informatics Visualization Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) IJIS - Indonesian Journal On Information System JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI Jurnal Tekno Insentif jurnal teknik informatika dan sistem informasi Journal of Informatics, Information System, Software Engineering and Applications (INISTA) Jurnal Teknik Informatika (JUTIF) Journal of Dinda : Data Science, Information Technology, and Data Analytics Jurnal INFOTEL SmartComp Jurnal Informatika: Jurnal Pengembangan IT

Agi Prasetiadi

Institut Teknologi Telkom Purwokerto

Author-ID : 1690708

Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

Published : 21 Documents Claim Missing Document

Claim Missing Document

Articles

1 2 3

KLASIFIKASI RASA BERDASARKAN CITRA BUAH MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK DENGAN TEKNIK IDENTITAS GANDA Arum, Refiani Pintan; Prasetiadi, Agi; Ramdani, Cepi
IJIS - Indonesian Journal On Information System Vol 6, No 1 (2021): APRIL
Publisher : POLITEKNIK SAINS DAN TEKNOLOGI WIRATAMA MALUKU UTARA

Identitas ganda yang merupakan hal yang wajar dijumpai di dunia nyata, misal transgender salah satunya. Dalam penelitian ini, membedakan buah yang memiliki jenis rasa yang lebih dari satu, seperti buah lemon mempunyai identitas ganda yaitu asam dan asin. Untuk pengkategorisasian Deep Learning, biasanya populasi dataset training memiliki objek yang berbeda satu sama lain. Pada rasa yang terkandung dalam buah, bisa kita eksploitasi untuk melihat perilaku CNN dalam mengenali objek – objek yang memiliki identitas lebih dari satu. Adapun fase training dalam penelitian ini yaitu pada dua kategori rasa yang berbeda dengan sengaja dimasukkan beberapa citra buah yang sama ke dalam dua kategori ini. Akurasi dari pengkategorisasian ini kemudian dibandingkan dengan akurasi dari pengkategorisasian yang murni tidak terdapat objek kembar di tiap – tiap kategorinya. Dari hasil simulasi didapatkan akurasi model ketika ada identitas ganda sebesar 95%, Adapun yang murni didapatkan sebesar 98%.Kata Kunci: Machine Learning, Deep Learning, CNN, Rasa, Buah

ANALISIS KESEHATAN TERUMBU KARANG BERDASARKAN KARAKTERISTIK SUNGAI, LAUT, DAN POPULASI AREA PEMUKIMAN MENGGUNAKAN MACHINE LEARNING habiba, adinda miftahul ilmi; Prasetiadi, Agi; Ramdani, Cepi
IJIS - Indonesian Journal On Information System Vol 5, No 2 (2020): SEPTEMBER
Publisher : POLITEKNIK SAINS DAN TEKNOLOGI WIRATAMA MALUKU UTARA

Penelitian ini untuk mengetahui kualitas kesehatan terumbu karang disuatu wilayah di Indonesia dengan mengambil beberapa faktor seperti wisatawan yang datang, latitude, longtitude, suhu, tahun, populasi warga, jumlah pemuda, dan jumlah industri, dan metode yang digunakan adalah machine learning dengan algoritma K-Nearest Neighbor, Support Vector Machine, dan Ensemble Classifier, untuk ensemble menggunkan randomforest untuk mengambil cabang-cabang pohon atau fitur keputusan yang paling relevan dengan output, penelitian ini diharapkan bisa menjadi acuan bagi wilayah yang kondisi terumbu karangnya masih kurang baik dapat mencontoh wilayah yang kondisi terumbu karangnya sudah baik dengan melihat faktor apa saja yang mempengaruhi terumbu karang disuatu wilayah itu masuk kategori baik. Hasil akhir dari penelitian ini pada algoritma K-Nearest Neighbor faktor yang berpengaruh bagi kesehatan terumbu karang yaitu wisatawan yang datang, latitude, longtitude, suhu, tahum dan pupulasi warga, sementara pada algoritma Support Vector Machine faktor yang berpengaruh wisatawan yang datang, Latitude, suhu dan tahun untuk algoritma Ensemble Classifier faktor yang berpengaruh wisatawan yang datang, latitude, longtitude, suhu dan jumlah industry, Pada kasus ini algoritma Support Vector Machine memiliki kinerja lebih baik dibandingkan K-Nearest Neighbor dan Ensemble Classifier.Kata Kunci: Ekosistem, Ensemble Classifier, K-Nearest Neighbor, Machine Learning, Support Vector Machine

Hierarchical and K-means Clustering in the Line Drawing Data Shape Using Procrustes Analysis Ridho Ananda; Agi Prasetiadi
JOIV : International Journal on Informatics Visualization Vol 5, No 3 (2021)
Publisher : Politeknik Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.5.3.532

One of the problems in the clustering process is that the objects under inquiry are multivariate measures containing geometrical information that requires shape clustering. Because Procrustes is a technique to obtaining the similarity measure of two shapes, it can become the solution. Therefore, this paper tried to use Procrustes as the main process in the clustering method. Several algorithms proposed for the shape clustering process using Procrustes were namely hierarchical the goodness-of-fit of Procrustes (HGoFP), k-means the goodness-of-fit of Procrustes (KMGoFP), hierarchical ordinary Procrustes analysis (HOPA), and k-means ordinary Procrustes analysis (KMOPA). Those algorithms were evaluated using Rand index, Jaccard index, F-measure, and Purity. Data used was the line drawing dataset that consisted of 180 drawings classified into six clusters. The results showed that the HGoFP, KMGoFP, HOPA and KMOPA algorithms were good enough in Rand index, F-measure, and Purity with 0.697 as a minimum value. Meanwhile, the good clustering results in the Jaccard index were only the HGoFP, KMGoFP, and HOPA algorithms with 0.561 as a minimum value. KMGoFP has the worst result in the Jaccard index that is about 0.300. In the time complexity, the fastest algorithm is the HGoFP algorithm; the time complexity is 4.733. Based on the results, the algorithms proposed in this paper particularly deserve to be proposed as new algorithms to cluster the objects in the line drawing dataset. Then, the HGoFP is suggested clustering the objects in the dataset used.

PEMISAHAN SUARA MANUSIA BERDASARKAN JENIS KELAMIN MENGGUNAKAN FAST FOURIER TRANSFORM (FFT) Lela Sari Kristina; Gita Fadila Fitriana; Agi Prasetiadi
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 7 No 3 (2020): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v7i3.461

Voice is one of the characteristics possessed by humans. One of the human abilities to identify someone by seeing and hearing. Through this ability one can easily distinguish gender, based on physical and voice categories. voices that previously can be recognized easily by humans, for now can also be recognized by computers, which aims to separate sounds based on gender. The final result of this research is to know the average error of data objects that have been inputted with the algorithm used in this study is the Fast Fourier Transform. The results of the implementation process of the Fast Fourier Transform Algorithm show whether or not the average sound error is influenced by the high or low amplitude of the sound being tested and from the results obtained the average error amplitude of the female voice is lower than the average error amplitude. Male voice. Of the two sources of human voices used, the lowest average error was produced in the 7th cluster for Female 3 votes with an average error result of 132.840, while the results of trials conducted with 3 sound sources resulted in the lowest average error in the second cluster. -3 for Female 3 votes with an average error result of 212,976, and for the four sound sources used it produces the lowest average error in the 3rd cluster on Mela's voice with an average error result of 217,462.

Identifikasi Spesies Reptil Menggunakan Convolutional Neural Network (CNN) Olvy Diaz Annesa; Condro Kartiko; Agi Prasetiadi
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 5 (2020): Oktober 2020
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Reptiles are one of the most common fauna in the territory of Indonesia. quite a lot of people who have an interest in knowing more about this fauna in order to increase knowledge. Based on previous research, Deep Learning is needed in particular the CNN method for computer programs to identify reptile species through images. This reseacrh aims to determine the right model in producing high accuracy in the identification of reptile species. Thousands of images are generated through data augmentation processes for manually captured images. Using the Python programming language and Dropout technique, an accuracy of 93% was obtained by this research in identifying 14 different types of reptiles.

Klasifikasi Analisis Sentimen Pada Gambar Meme Politik Dengan Library Tesseract Dan Algoritme Support vector machine Eko Sanjaya; Agi Prasetiadi; WAHYU ANDI SAPUTRA
Journal of INISTA Vol 2 No 1 (2019): November 2019
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/inista.v2i1.96

Meme merupakan penyebaran informasi dalam bentuk gambar. Berdasarkan data yang diperoleh, pengembangan meme mulai meningkat menjelang pemilu 2019. Informasi yang diperoleh dari meme politik beragam. Salah satunya memberikan dukungan untuk suatu partai atau tokoh politik atau digunakan untuk mengkritik / mencaci-maki partai politik atau tokoh. Sehingga diperlukan suatu sistem yang dapat mengklasifikasikan meme berdasarkan kelas Penelitian ini bertujuan untuk menciptakan sistem yang dapat mengklasifikasikan meme politik berdasarkan kelas. Algoritma yang akan digunakan dalam mengklasifikasikan adalah Support vector macine (SVM) dengan ekstraksi fitur TF-IDF. Library yang akan digunakan dalam optical character recognition (OCR) adalah Tesseract. Berdasarkan hasil pengujian diketahui bahwa akurasi yang dihasilkan oleh SVM linier lebih baik daripada SVM non-linear. Akurasi terbaik dalam SVM linear dengan kombinasi TF-IDF adalah 75.71%.

Perbandingan Performa Antara Algoritma Naive Bayes Dan K-Nearest Neighbour Pada Klasifikasi Kanker Payudara Annisa Nugraheni; Rima Dias Ramadhani; Amalia Beladinna Arifa; Agi Prasetiadi
Indonesian Journal of Data Science, IoT, Machine Learning and Informatics Vol 2 No 1 (2022): February
Publisher : Research Group of Data Engineering, Faculty of Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/dinda.v2i1.391

Breast cancer is the second most common cause of death from cancer after lung cancer is in the first place. Breast cancer occurs when cells in breast tissue begin to grow uncontrollably and can disrupt existing healthy tissue. Therefore, there is a need for a classification to distinguish breast cancer patients and healthy people. Based on previous research, the Naïve Bayes and K-Nearest Neighbor algorithms are considered capable of classifying breast cancer. In the research process using the breast cancer dataset from the Breast Cancer Coimbra dataset in 2018 UCI Machine Learning Repository with a total of 116 data, while for the calculation of the feasibility of the method using the Confusion Matrix (Accuracy, Precision, and Recall) and the ROC-AUC curve. The purpose of this study is to compare the performance of the Naïve Bayes and K-Nearest Neighbor algorithms. In testing using the Naïve Bayes algorithm and the K-Nearest Neighbor algorithm, there are several test scenarios, namely, data testing before and after normalization, model testing based on a comparison of training data and testing data, model testing based on K values in K-Nearest Neighbors, and model testing. based on the selection of the strongest attribute with the Pearson correlation test. The results of this study indicate that the Naïve Bayes algorithm has the highest average accuracy of 69.12%, healthy precision 64.90%, pain precision 83%, healthy recall 88%, sick recall 61.11% and AUC 0.82 which is included in the good classification category. Meanwhile, the highest average results of the K-Nearest Neighbor algorithm are 76.83% for accuracy, 76% healthy precision, 80.21% pain precision, 74.18% for healthy recall, 80.81% sick recall and 0.91 AUC which is included in the excellent classification category.

IDENTIFICATION OF MENTAL ILNESS FROM PATIENT DISEASES USING KNN AND LEVENSHTEIN DISTANCE ALGORITHM Yustika Rahma; Agi Prasetiadi; Merlinda Wibowo
Jurnal Teknik Informatika (Jutif) Vol. 3 No. 5 (2022): JUTIF Volume 3, Number 5, October 2022
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20884/1.jutif.2022.3.5.371

According to WHO, in 2017, the estimated number of people with mental disorders worldwide was around 450 million people, including schizophrenia. Globally, for the condition of Southeast Asia alone, the number of people affected by mental disorders is 13.5%. Meanwhile, 13.4% of cases in Indonesia are affected by mental illness. The Association of Mental Medicine Specialists (PDSKJ) during October 2020 noted that 5661 people who did self-examination through the PDSKJ website came from 31 provinces and found that 32% of the population had psychological problems and 68% had no psychological issues. Seeing that the level of mental illness in Indonesia is increasing, it is necessary to have a system to help the community with early prevention and treatment. With the growth of technology at its peak, Machine Learning technology can overcome the problem which is part of artificial intelligence. Furthermore, machine learning has an important role in improving the quality of health services because it is able to provide a medical diagnosis to predict disease. Therefore, the authors conducted a study to create a system to identify mental illness using the TF-IDF method. This method calculates the word weighting from a collection of complaints that the user gives. Then, these complaints will be classified using the KNN algorithm classification method and the Levenshtein Distance method to find the distance between the word inputted by the user and the word in the database and then calculate the number of differences between the two strings in the form of a matrix. The accuracy result of this machine learning classification is 0.928 or 93%, and will be visualized through web-based software using the Flask framework.

CLASSIFICATION OF CAT SOUNDS USING CONVOLUTIONAL NEURAL NETWORK (CNN) AND LONG SHORT-TERM MEMORY (LSTM) METHODS Fadhilah Gusti Safinatunnajah; Agi Prasetiadi; Merlinda Wibowo
Jurnal Teknik Informatika (Jutif) Vol. 3 No. 5 (2022): JUTIF Volume 3, Number 5, October 2022
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20884/1.jutif.2022.3.5.373

Cats become pets who are very close to humans, and they convey messages by producing identical sounds. Therefore, analysis of pet voices is important for a better relationship between cats and human. Animal communication through sound, especially in cats, depends on the situation or context in which the sound is made such as in a state of danger. Based on these problems, a classification method is needed to classify the similarity of characteristics in the resulting sound pattern. The classification methods used are Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) which can remember information for a long time and are used for a long time period. This study aimed to determine feelings or moods based on the sound produced into 4 categories: The Purr, The Meow, The Mating Call, and The Howl. The result of this study is that the best architectural model is to use 4 CNN convolution layers measuring 8-8-8-8 and 2 LSTM layers measuring 8-8. The precision value in this architecture is 0.68, the recall value is 1.00, the accurary value is 0.5625 and the f1-score value is 0.77. The small value of the confusion matrix is caused by the lack of dataset duration in the training process, resulting in underfitting.

MAKHRAJ ‘AIN PRONUNCIATION ERROR DETECTION USING MEL FREQUENCY CEPSTRAL COEFFICIENT AND MODIFIED VGG-16 Ibnu Kasyful Haq; Agi Prasetiadi
Jurnal Teknik Informatika (Jutif) Vol. 4 No. 1 (2023): JUTIF Volume 4, Number 1, February 2023
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2023.4.1.419

Based on research conducted by the Institute of Qur'anic Sciences (IIQ) as many as 65% of Muslims in Indonesia are illiterate in the Qur'an. In previous studies, research was conducted on the detection of Arabic word pronunciation errors against non-natives using the Mel Frequency Cepstral Coefficient (MFCC) and Support Vector Machine (SVM) methods with a test result of 54.6%. Due to the low accuracy results in previous studies, this study aims to design and build a system that can correct the accuracy of the pronunciation of makhraj letter ‘ain with the method used is a combination of MFCC and Convolutional Neural Network (CNN) with a vgg-16 structure that has been modified. The dataset used is 1,600 voice recordings divided into two categories of the correct pronunciation of the letter ‘ain and incorrect pronunciation of the letter ‘ain and four variations of pronunciation with different vowels with a total data of 800 records in each category. This study conducted several experiments on variations of the CNN kernel. The results of the training model that produced the best accuracy in all variations were the training model on kernels 16, 32, 64 with a final accuracy rate of 100% for all variations with 96% accuracy validation. In the fathah variation, the validation accuracy is 94%. In the variation of dhommah and the variation of kasrah obtained a validation accuracy of 97%. Therefore, this study succeeded in distinguishing the sound of the pronunciation of the letter ‘ain with different vowels and measuring the accuracy of the pronunciation of the letter ‘ain. Implementing the modified vgg-16 produces high accuracy and validation values for each speech variation during the model train process.

Co-Authors Amalia Beladinna Arifa Annisa Nugraheni Arum, Refiani Pintan Asti Dwi Sripamuji Condro Kartiko Condro Kartiko Diandra Chika Fransisca Eko Sanjaya Elisa Usada Fadhilah Gusti Safinatunnajah habiba, adinda miftahul ilmi Harry Pratama Ramadhan Ibnu Kasyful Haq Imada Ramadhanti Imada Ramadhanti Iqsyahiro Kresna Jihan Rihadatul Aisya Julian Saputra Julian Saputra Kartiko, Condro Lela Sari Kristina Merlinda Wibowo Merlinda Wibowo Olvy Diaz Annesa Pratama, Afrillebar Putra Ramadhan, Harry Pratama Ramadhani, Rima Dias Ramdani, Cepi Ridho Ananda Ridho Ananda Risa Riski Amalia Salma Pusriwijayanti Wahyu Andi Saputra Yustika Rahma

Title

Found 21 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 21 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 21 Documents
Search