Claim Missing Document
Check
Articles

Penerapan Teknik Random Undersampling untuk Mengatasi Imbalance Class dalam Prediksi Kebakaran Hutan Menggunakan Algoritma Decision Tree Ilham Kurniawan; Duwi Cahya Putri Buani; abdussomad abdussomad; Widya Apriliah; Eka Fitriani
Academic Journal of Computer Science Research Vol 5, No 1 (2023): Academic Journal of Computer Science Research (AJCSR)
Publisher : Institut Teknologi dan Bisnis Bina Sarana Global

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38101/ajcsr.v5i1.617

Abstract

Kebakaran hutan ialah bencana yang memicu kerusakan ekonomi dan ekologi juga meneror kehidupan manusia. Oleh karena itu, memprediksi problem lingkungan semacam kebakaran hutan benar-benar penting untuk meminimalisir ancaman kejadian bencana alam seperti kebakaran hutan. Dalam penelitian ini kami mengusulkan algoritma klasifikasi decision tree untuk memprediksi kebakaran hutan. Prediksi kebakaran hutan dilandaskan pada data meteorologi yang sesuai dengan elemen cuaca yang mempengaruhi terjadinya kebakaran hutan, yaitu suhu, kelembaban relatif dan kecepatan angin. Kami telah mendapati akurasi sekitar 94,52% mengenai prediksi kebakaran hutan dengan algoritma klasifikasi decision tree yang diusulkan. Nilai akurasi tersebut diperkuat dengan nilai ROC sebesar 0,950 yang melambangkan representasi dari algoritma klasifikasi yang dibangun untuk memprediksi kebakaran hutan, semakin mendekati angka 1 maka semakin baik juga algoritma klasifikasi yang dibangun.
Analisis Sentimen Kendaraan Listrik Menggunakan Algoritma Naive Bayes dengan Seleksi Fitur Information Gain dan Particle Swarm Optimization Salman Alfarizi; Eka Fitriani
Indonesian Journal on Software Engineering (IJSE) Vol 9, No 1 (2023): IJSE 2023
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/ijse.v9i1.15671

Abstract

Kendaraan listrik telah menjadi tren global sebagai alternatif kendaraan berbahan bakar fosil.  Namun masih terdapat beberapa permasalahan seperti infrastruktur yang belum memadai, harga yang relatif mahal, dan waktu pengisian baterai yang lama. Untuk meningkatkan penggunaan kendaraan listrik, diperlukan pemahaman dan kesadaran masyarakat terhadap kendaraan listrik. Oleh karena itu, penelitian ini bertujuan untuk menganalisis sentimen opini masyarakat terhadap kendaraan listrik dengan menggunakan algoritma Naive Bayes dengan seleksi fitur Information Gain dan Particle Swarm Optimization dan. Data yang digunakan dalam penelitian ini adalah data komentar dan ulasan pada media sosial (Twitter) yang terkait dengan kendaraan listrik. Data diambil dengan teknik web crawling data menggunakan API Twitter dan dicoba menggunakan software rapidminer. Dalam penelitian ini menggunakan algoritma Naive Bayes dihasilkan nilai akurasi 79,43% dan AUC 0,639. Selanjutnya dilakukan seleksi fitur menggunakan Information Gain dan Particle Swarm Optimization untuk menganalisis sentimen opini masyarakat dalam penggunaan kendaraan listrik untuk meningkatan akurasi dan AUC. Hasil akurasi yang didapat setelah menggunakan algoritma Naïve Bayes dengan seleksi fitur Information Gain dan Particle Swarm Optimization adalah 84,54% dan AUC 0,729. Sehingga dapat disimpulkan bahwa penerapan algoritma Naïve Bayes menggunakan seleksi fitur Information Gain dan Particle Swarm Optimization menjadi metode yang baik dalam analisis sentimen opini masyarakat tentang kendaraan listrik. Penelitian ini diharapkan dapat memberikan informasi yang berguna bagi produsen kendaraan listrik dalam mengembangkan produk mereka, serta memberikan masukan bagi pemerintah dalam mengembangkan kebijakan untuk mendukung penggunaan kendaraan listrik di Indonesia.               Kata kunci: Analisis Sentimen, Naive Bayes, PSO, Information Gain, Kendaraan Listrik
ANALISIS SENTIMEN REVIEW PADA APLIKASI MEDIA SOSIAL TIKTOK MENGGUNAKAN ALGORITMA K-NN DAN SVM BERBASIS PSO Dian Ardiansyah; Atang Saepudin; Riska Aryanti; Eka Fitriani; Royadi
Jurnal Informatika Kaputama (JIK) Vol 7 No 2 (2023): Volume 7, Nomor 2, Juli 2023
Publisher : STMIK KAPUTAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59697/jik.v7i2.148

Abstract

Review sentiment analysis on social media applications is one of the methods used to analyze opinions and feelings (sentiment) of social media users towards a particular product, service or topic. Tiktok social media users are the second most in the world. The Tiktok app is the leading social media platform and the ultimate destination for short-form videos. Music, dance, education, beauty, passion, or talent show. This research uses data from Tiktok application reviews based on positive and negative sentiments to compare the K-Nearest Neighbor (K-NN) and Particle Swarm Optimization (PSO)-based Support Vector Machine (SVM) algorithms. To test the results of the PSO-based K-NN and SVM algorithms using the Cross Validation method from the test results that the PSO optimization SVM algorithm has the best accuracy compared to the KNN algorithm. Where the accuracy value of SVM is 86.40% and AUC is 0.908. The PSO optimization SVM has an accuracy of 88.20% and an AUC of 0.91. While the K-NN algorithm has an accuracy of 83.40% and an AUC of 0.903 then the accuracy value of the K-NN optimization PSO gets an accuracy of 69.20% and an AUC of 0.77. This means that the use of the PSO optimization SVM algorithm has the highest level of accuracy.
Penerapan Model Information Retrieval Untuk Pencarian Konten Pada Perpustakaan Digital Fitriani, Eka; Indrajit, Richardus Eko; Aryanti, Riska
Perspektif : Jurnal Ekonomi dan Manajemen Akademi Bina Sarana Informatika Vol 15, No 2 (2017): September 2017
Publisher : www.bsi.ac.id

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (353.375 KB) | DOI: 10.31294/jp.v15i2.2350

Abstract

Digital library is the source of user information for library data search. The growing technology makes it easier for users to get the information they need. Digital libraries have a lot of content that causes search difficulties based on the interests of users. Using the N-Gram Method and Spelling Correction index applied to the search program will allow users to find the information they need, especially interest-based searches. This search process utilizes text information stored in digital library documents. In text documents, information is obtained directly from the content of the intended document. Keywords: Digital Library, information retrieval, N-Gram, Spelling Correction.
Optimalisasi Sistem Informasi Akademik SMA Panca Moral Cikampek dengan SMS Gateway Aryanti, Riska; Indrajit, Richardus Eko; Fitriani, Eka
Perspektif : Jurnal Ekonomi dan Manajemen Akademi Bina Sarana Informatika Vol 15, No 2 (2017): September 2017
Publisher : www.bsi.ac.id

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (531.183 KB) | DOI: 10.31294/jp.v15i2.2354

Abstract

Abstract  –  SMA Panca Moral Cikampek is a form of manifestation in guiding the younger generation in order to educate the nation of Indonesia, the increasing number of learners who are increasing each year from year to year, are required to provide information fast, precise and accurate. SMA Panca Moral Cikampek desperately needs an information system that support in the process of academic information services in the form of Short Message Service (SMS) gateway that can facilitate the students so that information obtained more quickly to be accepted by students. Short Message Service (SMS) is a facility to send and get text short message that many application on wireless communication scheme (wireless). To obtain the data searched based on the query from the user, forward or send the search results to the intended Short Message Service (SMS) then the query specified by this content is to apply information retrival algorithm with the N-Gram method and the biword index to group in certain categories more relevant. Kata Kunci:SMS gateway, information retrieval,N-Gram, index biword 
Sistem Informasi Akuntansi Pendapatan Penjualan Pada Usaha Dagang Bahan Bangunan Dede Saefudin; Muhammad Faittullah Akbar; Rizal Amegia Saputra; Eka Fitriani
JSAI (Journal Scientific and Applied Informatics) Vol 6 No 3 (2023): November
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v6i3.5840

Abstract

In managing business revenue, the sale of raw materials for the owner uses manual methods that are often constrained in managing financial statements and recording revenue accounting so that in the financial reporting period there are often delays so that a computerized system is needed to handle these problems. In this case, the author focuses on the problem of recording data on sales of goods and income transactions starting from recording the purchase of goods, data collection of goods, storage. Data related to the sales process to the process of making reports. With the description of the problem, the author implements a desktop-based application as a tool for managing financial data for trading businesses and provides time and human resource efficiency. The method used is Waterfall and system design using the UML (Unified Modelling Language) method. The result achieved is a sales revenue accounting information system that can support the processing of revenue data with a computerized system using desktop-based Java Netbeans, so that effective and efficient activities can be achieved in supporting business activities in revenue management. The measurement with the blackbox testing test by producing a valid average in each application procedure that is carried out.
Pengaruh Modal, Jam Kerja, Jumlah Tenaga Kerja, Jumlah Produksi, dan Penjualan Terhadap Pendapatan Usaha Mikro Kecil dan Menengah Pada Sentra Keripik Khas Lampung di Kedaton Bandar Lampung Wuryanti, Lestari; Listyaningsih, Erna; Fitriani, Eka
Jurnal Riset Akuntansi dan Manajemen Malahayati (JRAMM) Vol 10, No 1 (2021): VOLUME 10 NOMOR 1
Publisher : Universitas Malahayati

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33024/jur.jeram.v10i1.4793

Abstract

Small and Medium Enterprises (MSMEs) are one of the sectors that are expected to help develop the national economy. this allows it to contribute to efforts to reduce disparities between groups, alleviate poverty, and absorb labor. This study aims to determine the effect of capital, working hours, and number of workers. Total production, and sales to revenue. The object of this research is MSMEs in the typical chips center of Lampung. There are 38 samples in this study, namely kiosk owners who are willing to provide information regarding their financial data, which are processed using SPSS 22. From the results of multiple linear regression tests, it is stated that partially the Sales variable (X5) has a significance of 0.015 less than 0.05 which means it has a significant and significant effect on income, while the variables of capital (X1), working hours (X2), number of workers (X3), and total production (X4) have values greater than 0.05 which means they have no effect on income. The test results simultaneously state that all X variables (capital, working hours, number of workers, total production, sales) have a significance of 0.006 which is smaller than 0.05 which means that it has a significant and significant effect on income. The test results of the coefficient of determination R2 are 0.389, which means that the independent variable has an influence of 38.9% on the dependent variable, while the rest may be influenced by other variables outside the variables in this study.Keyword : MSME, Capital, working hours, number of workers, total production, sales, income
Pelaksanaan Program UKS Di Sma Negeri 3 Pekalongan Tahun 2017 Fitriani, Eka; Latif, Rr. Vita Nur; Yuniarti, Yuniarti
Pena Medika Jurnal Kesehatan Vol 8, No 1 (2018): PENA MEDIKA JURNAL KESEHATAN
Publisher : Universitas Pekalongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31941/pmjk.v8i1.748

Abstract

Kesehatan Sekolah (UKS) bertujuan meningkatkan mutu pendidikan dan prestasi belajar peserta didik dengan meningkatkan perilaku hidup bersih dan sehat serta derajat kesehatan peserta didik dan menciptakan lingkungan yang sehat. (Pedoman Pelaksanaan UKS tahun 2014). Kelemahan UKS yang menjadikannya belum berjalan optimal hingga saat ini adalah masih beranggapan bahwa UKS hanyalah sebuah ruangan berisi tempat tidur dan kotak P3K sebagai tempat istirahat siswa yang sakit. SMA Negeri 3 Kota Pekalongan merupakan salah satu SMA sederajat di Kota Pekalongan dengan strata PHBS Paripurna. Strata paripurna yaitu strata tertinggi dari suatu tingkatan dengan memenuhi 15 indikator PHBS di sekolah. (Pendataan PHBS di sekolah Puskesmas Dukuh 2016). Tujuan penelitian ini yaitu mengetahui pelaksanaan program Usaha Kesehatan Sekolah (UKS) di SMA Negeri 3 Kota Pekalongan. Metode penelitian yaitu kuantitatif. Hasil penelitian menunjukan bahwa keterlaksanaan Trias UKS : Pendidikan kesehatan 93,8% kategori baik, Pelayanan kesehatan 56,8% kategori baik dan Pembinaan kesehatan lingkungan 93,4 kategori baik. Kata Kunci      : Trias UKS, Program UKS, UKS SMA N 3 Pekalongan School Health (UKS) aims to improve the quality of education and learning achievements of learners by increasing clean and healthy lifestyles as well as the degree of health learners and create a healthy environment. (Guidelines for implementation of the UKS year 2014). The weakness of the INFIRMARY which have not run optimally to this day is still contended that the INFIRMARY is simply a room contains a bed and a first aid box as a place to rest the ill student. SMA Negeri 3 city of Pekalongan is one of equal HIGH SCHOOL in the town of Pekalongan with strata PHBS Plenary. I.e. highest strata plenary strata of a level by meeting the 15 indicators of PHBS in school. (Logging PHBS in school Clinics Dukuh 2016). The purpose of the research is to find out the School Health program implementation (UKS) in SMA Negeri 3 city of Pekalongan. Quantitative research methods IE. Research results show that keterlaksanaan Triassic UKS: 93.8% health education categories good, health services 56.8% category either and the construction of environmental health 93.4 category either. Keywords       : Trias UKS, UKS program, School Health graduate HIGH SCHOOL 3         .                          Pekalongan  
Analisis Sentimen Pemanfaatan Artificial Intelligence di Dunia Pendidikan Menggunakan SVM Berbasis Particle Swarm Optimization Saepudin, Atang; Aryanti, Riska; Fitriani, Eka; Royadi, Royadi; Ardiansyah, Dian
Computer Science (CO-SCIENCE) Vol. 4 No. 1 (2024): Januari 2024
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/coscience.v4i1.2921

Abstract

The utilization of Artificial Intelligence (AI) in the field of education in Indonesia has witnessed significant developments in recent years. The advancements in AI technology have opened up new opportunities to enhance the quality of education, and address various challenges faced by the Indonesian education system. This has naturally sparked diverse opinions and comments from the public, particularly on the social media platform X/Twitter. This research focuses on sentiment analysis of reviews expressed on the X/Twitter social media platform. The primary goal of this study is to develop an effective sentiment analysis method by leveraging the Support Vector Machine (SVM) algorithm optimized with Particle Swarm Optimization (PSO) for feature selection. In this research, user reviews from X/Twitter were collected and analyzed to identify positive or negative sentiments within the context of each comment. The SVM algorithm was used to classify sentiments based on similarity to comments with known sentiments. Feature Selection PSO was employed to optimize the parameters within SVM to enhance sentiment analysis accuracy. The results of sentiment analysis on comments or tweets on the X/Twitter social media platform using both SVM and PSO-based SVM algorithms indicated that the PSO-based SVM algorithm achieved a higher accuracy. The SVM algorithm with feature selection PSO produced accuracy 89.50%, precision 86.98%, recall 93.00%, and AUC 0.964. Meanwhile, the SVM algorithm had accuracy 87.50%, precision 85.46%, recall 90.50%, and AUC 0.956. This demonstrates that the use of feature selection PSO in the SVM algorithm is capable of improving the accuracy of the results.
PENERAPAN SISTEM INFORMASI AKADEMIK BERBASIS WEB MENGGUNAKAN METODE RAPID APPLICATION DEVELOPMENT Fitriani, Eka; Royadi, Royadi; Ardiansyah, Dian; Saepudin, Atang; Aryanti, Riska
Journal of Information System, Applied, Management, Accounting and Research Vol 8 No 4 (2024): JISAMAR (September-November 2024)
Publisher : Sekolah Tinggi Manajemen Informatika dan Komputer Jayakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52362/jisamar.v8i4.1551

Abstract

The world of technology is advancing rapidly in all fields every day, including education. Systems that support information delivery are now presented in applications or web platforms. SMK Negeri Pertanian requires an adequate information system to convey academic information to students and teachers and to manage student data at the school. To address this issue, it is necessary to implement a web-based academic information system at SMK Negeri Pertanian using the Rapid Application Development (RAD) method for system development. The Rapid Application Development (RAD) method was chosen because it emphasizes speed and flexibility, allowing the application to be completed more quickly. The developed academic information system will manage and display information such as teacher data, student data, subject data, grades, teaching schedules, and other academic-related information. The result of this implementation is an effective and efficient web-based information system for delivering academic information to students and teachers.