Article Per Year (5 Year)
p-Index From 2021 - 2026
12.521
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) TEKNIK INFORMATIKA SITEKIN: Jurnal Sains, Teknologi dan Industri Prosiding Semnastek Scientific Journal of Informatics Sistemasi: Jurnal Sistem Informasi Jurnal CoreIT JURNAL MEDIA INFORMATIKA BUDIDARMA IT JOURNAL RESEARCH AND DEVELOPMENT Indonesian Journal of Artificial Intelligence and Data Mining Seminar Nasional Teknologi Informasi Komunikasi dan Industri Journal of Economic, Bussines and Accounting (COSTING) INOVTEK Polbeng - Seri Informatika Jurnal Informatika Universitas Pamulang Jurnal Nasional Komputasi dan Teknologi Informasi JURIKOM (Jurnal Riset Komputer) JOISIE (Journal Of Information Systems And Informatics Engineering) Building of Informatics, Technology and Science Zonasi: Jurnal Sistem Informasi INFORMASI (Jurnal Informatika dan Sistem Informasi) JOURNAL OF INFORMATION SYSTEM MANAGEMENT (JOISM) JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Journal of Computer System and Informatics (JoSYC) Jurnal Sistem Komputer dan Informatika (JSON) TIN: TERAPAN INFORMATIKA NUSANTARA Jurnal Teknik Informatika (JUTIF) Information System Journal (INFOS) Jurnal Computer Science and Information Technology (CoSciTech) Jurnal UNITEK Bulletin of Computer Science Research KLIK: Kajian Ilmiah Informatika dan Komputer Jurnal Informatika Teknologi dan Sains (Jinteks) Knowbase : International Journal of Knowledge in Database Indonesian Journal of Innovation Multidisipliner Research Bulletin of Informatics and Data Science Jurnal Informatika: Jurnal Pengembangan IT Indonesian Journal of Innovation Multidisipliner Research Jurnal Komtika (Komputasi dan Informatika)
Elvia Budianita
Universitas Islam Negeri Sultan Syarif Kasim Riau
Religion Aerospace Engineering Arts Humanities Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Physics Social Sciences Transportation Veterinary Other

Published : 125 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 125 Documents
Search

 6   7   8   9   10 
Analisis Sentimen Akun Twitter Apex Legends Menggunakan VADER Dicky Abimanyu; Elvia Budianita; Eka Pandu Cynthia; Febi Yanto; Yusra Yusra
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 3 (2022): Juni 2022
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i3.4382

Abstract

Abstrak - Pesatnya peningkatan jasa internet saat ini, ada banyak informasi yang dihasilkan dalam jumlah besar secara terus menerus dalam waktu yang singkat. Akhir-akhir ini, analisis sentimen dengan menggunakan ulasan dan pesan telah menjadi topik penelitian yang populer dibicarakan di bidang Natural Language Processing. Selama bertahun-tahun, permainan online telah menjadi suatu aktivitas yang tidak bisa dipisahkan dari sebagian besar orang. Apex Legends adalah salah satu contoh game yang sangat popular di seluruh dunia. Untuk mendapatkan informasi bagaimana pendapat para pemain tentang permainan ini diperlukan analisis sentimen. Pada penelitian ini dilakukan analisis sentimen menggunakan bantuan aplikasi Orange Data Mining dengan metode VADER pada akun twitter Apex Legends menggunakan data sebanyak 500 tweet. Pengujian data dilakukan dengan membandingkan hasil yang didapat menggunakan metode VADER dengan hasil pengujian pakar, yaitu native speaker dari Canada dan Amerika. VADER mengklasifikasikan data yang didapatkan melalui twitter berdasarkan nilai compound yang didapat. Penelitian ini menghasilkan kesimpulan yaitu perbandingan dari pengujian menggunakan VADER dan pengujian pakar tidak berbeda jauh, yang mana total persentase dari penggunaan metode VADER untuk menganalisis sentiment dari twitter ini adalah : Positif = 18%, Negatif = 4,6%, Netral = 73,6%. Sedangkan   hasil pengujian pakar adalah : Positif = 27%, Negatif = 10,8%, Netral = 62,2%.Kata kunci: VADER, Apex Legends, Game, Twitter, Uji Pakar Abstract - With the rapid increase in internet services today, there is a lot of information produced in large quantities continuously in a short time. Recently, sentiment analysis using reviews and messages has become a popular research topic discussed in the Natural Language Processing field. Over the years, online gaming has become an activity that cannot be separated from most of the people. Apex Legends is one example of a game that is very popular around the world. To get information on how the players think about the game, sentiment analysis is needed. In this study, sentiment analysis was carried out using the Orange Data Mining application with the VADER method on the Apex Legends twitter account using 500 tweets (data). Data testing is done by comparing the results obtained using the VADER method with the results of expert testing, native speaker from Canada and America. VADER classifies the data obtained through twitter based on the compound value obtained. This study concludes that the comparison of testing using VADER and expert testing is not much different, where the total percentage of using the VADER method to analyze sentiment from Twitter is : Positive = 18%, Negative = 4,6%, Neutral = 73,6%. While the results of expert testing is : Positive = 27%, Negative = 10,8%, Neutral = 62,2%.Keywords : VADER, Apex Legends, Game, Twitter, Expert Test (Uji Pakar)
Analisis Sentimen Komentar Di YouTube Tentang Ceramah Ustadz Abdul Somad Menggunakan Algoritma Naïve Bayes Habibi Al Rasyid Harpizon; Rahmad Kurniawan; Iwan Iskandar; Roni Salambue; Elvia Budianita; Fadhilah Syafria
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 1 (2022): Februari 2022
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i1.4008

Abstract

Abstrak - Sosial media tidak hanya digunakan oleh masyarakat Indonesia untuk hiburan, tetapi juga sebagai media edukasi. Youtube merupakan salah satu media sosial yang terkenal di Indonesia dengan 93,8% pengguna. Youtube juga dimanfaatkan sebagai media Dakwah seperti yang dilakukan oleh Ustadz Abdul Somad. Ustadz Abdul Somad merupakan ulama yang berpengaruh di Indonesia. Beliau sering mengunggah video yang membahas berbagai jenis persoalan agama khususnya pada bidang hadist dan fiqih. Pengguna Youtube dapat memberikan feedback berupa like, dislike dan komentar terhadap video yang ditayangkan. Feedback diperlukan oleh pembuat konten di Youtube untuk melihat tanggapan pengguna. Analisa secara manual sulit dilakukan karena jumlah data yang besar. Oleh karena itu, penelitian ini bertujuan untuk menganalisis sentimen masyarakat terhadap Ustadz Abdul Somad melalui  komentar youtube menggunakan algoritma Naïve Bayes. Penelitian ini menggunakan 1000 komentar dari 10 video yang ada di Youtube mengenai Ustad Abdul Somad. Naïve Bayes merupakan algoritma yang sederhana, namun memiliki akurasi yang tinggi dan dapat digunakan pada data yang sedikit. Berdasarkan hasil penelitian, didapatkan sebanyak 67% berkomentar positif, 27% berkomentar netral  dan 6% berkomentar negatif. Berdasarkan pengujian didapatkan akurasi sebesar 87%, presisi 91% dan recall 97%. Berdasarkan pengujian tersebut dapat disimpulkan bahwa penelitian ini dapat digunakan untuk hasil sentimen dengan cepat di Youtube.Kata kunci: Analisis Sentimen, Naïve Bayes, Ustadz Abdul Somad, Youtube Abstract - Indonesian people have been used Youtube for entertainment and as an education. As Indonesia's most popular social media, Youtube has 93.8% users. YouTube is also used as a medium of Da'wah, like Ustadz Abdul Somad. Ustadz Abdul Somad is an influential Preacher in Indonesia. He often uploads videos that lecture various types of religious issues, especially in the fields of hadith and fiqh. YouTube users can provide feedback in the form of likes, dislikes, and comments on videos that are shown. Creators need feedback on YouTube to see user feedback. Manual analysis is complicated because of the large amount of data. Therefore, this study aimed to analyze public sentiment towards Ustadz Abdul Somad through YouTube comments using the Naïve Bayes algorithm. This study obtained 1000 comments from 10 videos about Ustad Abdul Somad. Naïve Bayes is a simple algorithm with high accuracy and can be used on small data. Based on the results, it was found that 67% commented positively, 27% commented neutrally, and 6% commented negatively. Based on the experimental testing, the accuracy is 87%, precision is 91%, and recall is 97%. Based on these tests, it can be concluded that this research can be used for quick sentiment results on YouTube.Keywords: Sentiment Analysis, Naïve Bayes, Ustadz Abdul Somad, Youtube
Pengelompokan Tingkat Kecanduan Game Online Menggunakan Algoritma Fuzzy C-Means Ammar Muhammad; Elvia Budianita
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 4 (2022): Agustus 2022
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i4.4511

Abstract

Abstrak - Game online  merupakan aplikasi permainan yang berupa petualangan, pengaturan strategi, simulasi dan bermain peran yang memiliki aturan main dan tingkatan-tingkatan tertentu. Bermain game online  membuat pemain merasa senang karena mendapat kepuasan psikologis. Kepuasan yang diperoleh dari game tersebut akan membuat pemain semakin tertarik dalam memainkannya.Kecanduan game online merupakan aktifitas yang dilakukan secara terus menerus dan berkepanjangan yang menimbulkan sikap yang cenderung menarik diri dari kehidupan sosial.  Penerapan data mining dengan menggunakan metode clustering untuk meneliti tingkat kecanduan game online  dengan menggunakan algoritma Fuzzy C-Means. Dengan menggunakan metode ini kita dapat menentukan jumlah clustering dan dapat diatur  keragaman tingkat kecanduan berdasarkan clusternya, metode ini juga dapat mendeteksi cluster tingkat tinggi serta hubungan antar cluster yang berbeda. Pengujian pada metode menggunakan metode Silhouette Coefficient. Data kecanduan game online didapatkan dari Pengumpulan data melalui kuisioner yang mengacu kepada  skala Game addict scale (GAS). Dari hasil pengujian didapatkan hasil yaitu  148 record pada cluster 1, 50 record pada cluster 2 dan 102 record pada cluster 3.Kata Kunci: Candu, Clustering, Data Mining, Fuzzy C-Means, Game Online Abstract - Online games are game applications in the form of adventure, strategy setting, simulation and role playing that have certain rules and levels. Playing online games makes players feel happy because they get psychological satisfaction. The satisfaction obtained from the game will make players more interested in playingit. Online game addiction is an activity that is carried out continuously and for a long time which causes an attitude that tends to withdraw from social life. Application of data mining using the clustering to examine the level of online game addiction using the Fuzzy C-Means algorithm. By using this method we can determine the number , and can adjust the diversity of addiction levels based on the clusterthis method can also detect clusters high-level clusters . Testing on the method using the Silhouette Coefficient method. Data on online game addiction is obtained from collecting data through a questionnaire that refers to the Game addict scale (GAS). From the test results, the results obtained are  148 records in cluster 1, 50 records in cluster 2 and 102 records in cluster 3.Keywords: Opium, Clustering, Data Mining, Fuzzy C-Means, Online Game 
Analisa Pola Makan Mahasiswa Penderita Gastritis (Maag) Dengan Menerapkan Metode Frequent Pattern-Growth (FP-Growth) Fitri Astuti; Elvia Budianita; Alwis Nazir; Reski Mai Candra
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 3 (2022): Juni 2022
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i3.4447

Abstract

Abstract— Gastritis is an inflammation that occurs in the walls of the stomach. Young and mature age belongs to the category of productive age, where the productive age is more at risk of developing gastritis. This study aims to find the diet of students of Sultan Syarif Kasim Riau Islamic University by applying the fp-growth algorithm. This study used 502 records of data obtained from interviews with several students of the Sultan Syarif Kasim Riau Islamic University. The attributes used are faculty, semester, gender, place to live, busy college schedule solutions, the habit of consuming staple foods, snacks, instant noodles, fast food, spicy food, coffee, soft drinks, and snacks. Based on the results of the implementation of the application that was built and tested using the RapidMiner tools with a minimum support of 6%, and a minimum confidence of 100%, 4 patterns were found with a lift ratio of 1.88. From the 4 association patterns produced, it can be concluded that students with gastritis who have the habit of consuming staple food 2 x / day, spicy food and fast food 2-3 x / week or 4-5 x / week, consume coffee sometimes or 1 x / week, and endure hunger as a solution to a busy college schedule, the student is a student who lives in a boarding house / rented.Keywords : Data Mining, Pattern Association, FP-Growth, Gastritis Disease Abstrak— Gastritis adalah peradangan yang terjadi pada dinding lambung. Usia muda dan dewasa termasuk dalam kategori usia produktif, dimana usia produktif lebih berisiko terkena gastritis. Penelitian ini bertujuan untuk menemukan pola makan mahasiswa Universitas Islam Sultan Syarif Kasim Riau dengan menerapkan algoritma fp-growth. Penelitian ini menggunakan 502 records data yang diperoleh dari hasil wawancara terhadap beberapa mahasiswa Universitas Islam Sultan Syarif Kasim Riau. Atribut yang digunakan adalah fakultas, semester, jenis kelamin, tempat tinggal,  solusi jadwal kuliah padat, kebiasaan mengkonsumsi makanan pokok, makanan ringan, mie instan, fast food, makanan pedas, kopi, minuman bersoda, dan jajanan. Berdasarkan hasil implementasi aplikasi yang dibangun dan pengujian menggunakan tools RapidMiner dengan minimum support 6% dan minimun confidence 100% ditemukan 4 pola dengan lift ratio 1,88. Berdasarkan 4 pola asosiasi yang dihasilkan dapat disimpulkan bahwa bahwa Mahasiswa penderita gastritis yang memiliki kebiasaan mengkonsumsi makanan pokok 2 x/hari, makanan pedas dan fast food  2-3 x/minggu atau 4-5 x/minggu, mengkonsumsi kopi kadang – kadang atau 1 x/minggu, serta menahan lapar sebagai solusi jadwal kuliah yang padat maka mahasiswa tersebut merupakan mahasiswa yang tinggal di kos/kontrakanKata kunci : Data Mining, Pola Asosiasi, FP-Growth, Penyakit Gastritis
Penerapan Algoritma Hash Based Untuk Analisis Pola Pemilihan Mata Kuliah Pilihan Jurusan Teknik Informatika UIN Sultan Syarif Kasim Riau Desra Rizki Riyandi; Elvia Budianita; Zulkarnain Zulkarnain
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 4 (2022): Agustus 2022
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i4.4449

Abstract

Abstrak - Mata kuliah pilihan merupakan sebuah cara yang digunakan oleh jurusan dalam rangka meningkatkan mutu dan skill mahasiswa. Namun, tidak sedikit mahasiswa yang salah mengambil mata kuliah pilihan karena tidak menyadari potensi dalam dirinya yang mengakibatkan menurunnya prestasi akademik mahasiswa tersebut. Selama ini juga belum ada penyimpanan data yang digunakan sebagai history atau bahan pertimbangan bagi mahasiswa. Asosiasi menjadi salah satu solusi  pencarian pola pada data mining dengan bantuan algoritama hash bashed. Algoritma ini mampu memperbaiki kelemahan algoritma apriori dalam menentukan frequent itemset. Algoritma Hash-based merupakan algoritma yang  menggunakan teknik hashing untuk menyaring keluar itemset yang tidak penting untuk pembangkitan itemset selanjutnya.Aturan pola yang didapatkan dari total data sejumlah 530 data menghasilkan pola akhir 3 itemset dengan pola faktor dosen pengampu, minat tersendiri dan, topik tugas akhir (DS,MN,TA) dengan nilai confidence tertinggi senilai 73%, sehingga menjadi faktor yang paling mepengaruhi mahasiswa dalam memilih mata kuliah pilihan.Kata Kunci: Akademik, Asosiasi, Mahasiswa, Mata Kuliah Pilihan, Hash Bashed Abstract - Elective courses are a method used by majors in order to improve the quality and skills of students. However, not a few students take the wrong elective courses because they do not realize their potential which results in a decline in the student's academic achievement. So far, there is no data storage that is used as history or consideration for students. Association is one of the solutions for finding patterns in data mining with the help of hash bashed algorithms. This algorithm is able to improve the weaknesses of the a priori algorithm in determining frequent itemset. Hash-based algorithm is an algorithm that uses a hashing technique to filter out itemsets that are not important for the next itemset generation. The pattern rules obtained from a total of 530 data produce a final pattern of 3 itemsets with a pattern of supporting lecturer factors, special interests and, the topic of the final project (DS, MN, TA) with the highest confidence value of 73%, so that it becomes the most influencing factor for students in choosing elective courses.Keywords: Academic, Association, Student, Elective Course, Hash Based
Penerapan Metode FP-GROWTH Untuk Analisa Pola Konsumsi Makan Penderita Diabetes Melitus Fratiwi Rahayu; Elvia Budianita; Fadhilah Syafria; Iis Afrianty
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 3 (2022): Juni 2022
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i3.4401

Abstract

Abstrak - Penyakit diabetes melitus adalah gejala yang timbul terhadap seseorang akibat kadar gula darah yang tinggi atau hiperglikemia. Kemenkes (2018) menyebutkan bahwa faktor yang dapat menyebabkan terjadinya diabetes melitus salah satunya adalah berdasarkan faktor konsumsi makan. Penelitian ini bertujuan untuk menemukan pola makan dari penderita diabetes melitus. Data yang digunakan pada penelitian ini adalah data yang didapat setelah melakukan wawancara dan penyebaran kuesioner pada penderita diabetes melitus di Puskesmas Melur dan Rumah Sakit Aulia Hospital. Adapun atribut yang akan digunakan pada penelitian ini yaitu jenis kelamin, penyakit penyerta, terapi, frekuensi makan, makanan pokok, konsumsi sayur, konsumsi buah, konsumsi protein nabati, protein hewani, konsumsi gula, makanan ringan, makanan instan, dan minuman manis. Penelitian menggunakan algoritma FP-Growth dengan nilai confidence 100% dan minimum support 40%. Tools yang digunakan RapidMiner 9.1 sehingga didapatkan 13 rules. Dari 13 aturan asosiasi yang dihasilkan dapat disimpulkan bahwa penderita diabetes melitus yang mengkonsumsi sayur 1 porsi dalam sehari, konsumsi buah 1x dalam sehari, dan mengkonsumsi makanan instan 3x dalam seminggu maka penderita diabetes melitus merupakan penderita diabetes terkontrol.Kata kunci: Algoritma FP-Growth, Diabetes Melitus, RapidMiner, Support Abstract - Diabetes mellitus is a symptom that arises in a person due to high blood sugar levels or hyperglycemia. The Ministry of Health (2018) stated that one of the factors that can cause diabetes mellitus is based on eating consumption factors. This study aims to find the diet of people with diabetes mellitus. The data used in this study are data obtained after conducting interviews and the distribution of questionnaires in people with diabetes mellitus at the Melur Health Center and Aulia Hospital. The attributes that will be used in this study are gender, comorbidities, therapy, frequency of eating, staple foods, vegetable consumption, fruit consumption, consumption of vegetable protein, animal protein, sugar consumption, snacks, instant foods, and sugary drinks. The study used the FP-Growth algorithm with a confidence value of 100% and a minimum support of 40%. Tools used by RapidMiner 9.1 so that 13 rules are obtained. From the 13 association rules produced, it can be concluded that people with diabetes mellitus who consume 1 serving of vegetables in a day, consume fruit 1x in a day, and consume instant food 3x in a week, people with diabetes mellitus are controlled diabetics.Keywords : FP-Growth Algorithm, Diabetes Mellitus, RapidMiner, Support
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.
Co-Authors Abdul Halim Adzhima, Fauzan Afrianti, Liza Afriyanti, Iis Agnesti, Syafira Agung Syaiful Rahman Agustina, Auliyah Aji Pangestu Adek Akbar, Lionita Asa Akhyar, Amany Al Rasyid, Nabila Alfaiza, Raihan Zia Alfarabi.B, Alif Alwis Nazir Alwis Nazir Alwis Nazir Amalia Hanifah Artya Ammar Muhammad Anggi Pranata Aprilia, Tasya Aprima, Muhammad Dzaky Arif Pratama Budiman Azhima, Mohd Baehaqi Berliana, Trisia Intan Boni Iqbal buhfi arides hanyodi Chely Aulia Misrun Damayanti, Elok Desra Rizki Riyandi Dicky Abimanyu Dinyah Fithara Dodi Efendi doli fancius silalahi Dwitama, Raja Zaidaan Putera Eka Pandu Cynthia Eka Pandu Cynthia Eka Pandu Cynthia Eka Suryani Indra Septiawati Elin Haerani Elin Haerani Elin Haerani Elin Haerani Ellin Haerani Fadhilah Syafria Fahrozi, Aqshol Al Faska, Ridho Mahardika Fatma Hayati Fauzan Adzim Febi Yanto Fikri Utri Amri Fikry Utri Amri Fitri Astuti Fitri Insani Fitri Insani Fitri Insani Fitri Insani Fitri, Anisa Fratiwi Rahayu Gusrifaris Yuda Alhafis Gusti, Siska Kurnia Guswanti, Widya Habibi Al Rasyid Harpizon Habibi, M. Ilham Hara Novina Putri Hariansyah, Jul Hasibuan, Ilham Habibi Ibnu Afdhal Ichsan Permana Putra Ihda Syurfi Ihlal Hanafi Harahap Iis Afrianty Iis Afrianty Ikhsanul Hamdi Indah Wulandari Isra Almahsa, Muhammad Iwan Iskandar Iwan Iskandar Iwan Iskandar Iwan Iskandar Jasril Jasril Jasril Jasril jasril jasril jasril Jeki Dwi Arisandi Khair, Nada Tsawaabul Lestari Handayani Lestari Handayani Lili Rahmawati Lola Oktavia M Fikry M Ikhsan Maulana M ridwan Ma'rifah, Laila Alfi Masaugi, Fathan Fanrita Matondang, Irfan Jamal Mawadda Warohma Mazdavilaya, T Kaisyarendika Megawati Megawati Meiky Surya Cahyana Mhd. Kadarman Mohd. Ridho Zarkasih Rahim Muhammad Affandes Muhammad Fikry Muhammad Fikry Muhammad Fikry Muhammad Fikry Muhammad Hafiz Muhammad Irsyad Muhammad Rizky Ramadhan Mulyati, Sabar Mulyono, Makmur Musa Irfan Mustasaruddin Mustasaruddin Nabyl Alfahrez Ramadhan Amril Nanda Sepriadi Nazir, Alwis Nazruddin Safaat H Neni Sari Putri Juana Novi Yanti Novi Yanti Novriyanto Novriyanto Nur Iza Nuradha Liza Utami Nurafni Syahfitri Nurfadilah, Nova Siska Okfalisa Okfalisa Pasiolo, Lugas Permata, Rizkiya Indah Pizaini Pizaini Putri, Widya Maulida Rahmad Abdillah Rahmad Kurniawan Ramadani, Repi Ramadhan, Aweldri Ramadhani, Astrid Ramadhani, Siti Reni Susanti Reski Mai Candra Reski Mai Candra Rinaldi Syarfianto Robby Azhar Roni Salambue Rusnedy, Hidayati Said Nurfan Hidayad Tillah Saktioto Saktioto Sephia Pratista Silfia Silfia Siti Sri Rahayu Surya Agustian Suwanto Sanjaya Syahputra, Armadani Ulti Desi Arni, Ulti Desi Wahyuni, Ayu Sri Wang, Shir Li Widodo Prijodiprodjo Wiranti, Lusi Diah Yeni Fariati Yusra Yusra Yusra Yusra Yusra Yusra Yusra Yusra Yusra, Yusra Zabihullah, Fayat Zulastri, Zulastri Zulkarnain Zulkarnain