Claim Missing Document
Check
Articles

Found 7 Documents
Search

Segmentasi Dan Perbaikan Citra Untuk Proses Pengukuran Dimensi Beras Very Kurnia Bakti; Dairoh Dairoh; Miftakhul Huda
JURNAL INFOTEL Vol 8 No 1 (2016): May 2016
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v8i1.56

Abstract

Pada model pengukuran fisik beras masih menggunakan model pengukuran manual yaitu menggunakan micrometer dimana penggunaannya masih memerlukan waktu yang cukup lama dan hasil pengukurannya masih bersifat subjektif dikarenakan hasil pengukuran menggunakan micrometer. Bergantung juga kepada kemampuan penglihatan masing-masing individu yang melakukan pengukuran. Maka perlu adanya cara pengukuran yang lebih cepat dalam mengukur dimensi beras tanpa mengurangi tingkat akurasi dengan menggunakan teknologi pemprosesan citra. Tujuan penelitian adalah mendapatkan cara yang lebih cepat dibandingkan menggunakan micrometer dengan memanfaatkan teknologi pemrosesan citra sebagai alat bantu instrumen pengukuran yang dapat menampilkan nilai ukur yang jelas terbaca. Penelitian dilakukan menggunakan data beras dari BULOG Kota Tegal. Dilakukan pengukuran panjang dan lebar beras tersebut baik dengan caliper dan dibandingkan dengan hasil citra menggunakan digital microscope dengan bantuan coding pada MATLAB secara realtime dari ruang warna YCBCR menjadi RGB diubah ke grayscale. Hasilnya menunjukkan bahwa pengukuran dimensi beras berupa panjang dan lebar suatu beras dapat dilakukan dalam pemrosesan citra dan hasil klasifikasi beras berdasarkan ukuran panjang dan lebarnya diperoleh beras memiliki ukuran 6.67-7.50 mm yang merupakan bentuk panjang, dan bahwa dari 100 beras diperoleh klasifikasi beras berdasarkan dimensi untuk lebarnya berupa bulat dengan ukuran < 2 mm
Pengaruh Parameter Word2Vec terhadap Performa Deep Learning pada Klasifikasi Sentimen Dwi Intan Af&#039;idah; Dairoh Dairoh; Sharfina Febbi Handayani; Riszki Wijayatun Pratiwi
Jurnal Informatika: Jurnal Pengembangan IT Vol 6, No 3 (2021): JPIT, September 2021
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v6i3.3016

Abstract

The difficulty of sentiment classification on this big data can be overcome using deep learning. Before the deep learning training and testing process is carried out, a word features extraction process is needed. Word2Vec as a word features extraction is often used in sentiment classification pre-training because it can capture the semantic meaning of the text by representing a similar vector for each word that has a close meaning. Word2Vec has three parameters that affect the model learning process namely architecture, evaluation method, and dimensions. This study aims to determine the effect of each Word2Vec parameter on deep learning performance in sentiment classification. The accuracy results of the deep learning model were evaluated to determine the effect of the Word2Vec parameter. The results of this study indicate that the three Word2Vec parameters have an influence on the performance of the deep learning model in sentiment classification. The combination of Word2Vec parameters that produces the highest average accuracy include CBOW (Continuous Bag of Word) architecture, Hierarchical Softmax evaluation method, and a dimension of 100. CBOW produces better performance, because it has slightly better accuracy for words that often appear and in this research dataset there are many words that often appear. Hierarchical Softmax shows better results because it uses a binary tree model which makes words that occur rarely will inherit the vector representation above them. The dimension with a value of 100 produces better accuracy because it is in line with the number of datasets of 10,000 reviews.  
Opinion Mining Terhadap Toko Online Di Media Sosial Menggunakan Algoritma Naïve Bayes (Studi Kasus: Akun Facebook Dugal Delivry) Yustia Hapsari; Muhammad Fikri Hidayattullah; Dairoh Dairoh; Mohammad Khambali
Jurnal Informatika: Jurnal Pengembangan IT Vol 3, No 2 (2018): JPIT, Mei 2018
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v3i2.919

Abstract

The Internet era has had an impact in various sectors of human life. One is the economic sector. Economic transactions change from the traditional pattern (face to face) to online. The customer does not need to ask about the condition of an item to be purchased to a close friend or family, but simply by reviewing the product from the same buyer's comments. Products that get good reviews mean good quality. However, a problem arises if the comment data is very large and will make it difficult for customers to summarize the quality. Therefore, an automatic opinion mining system is required which can directly give conclusions about the quality of a product. This research makes an opinion mining system by applying the Naïve Bayes algorithm by taking a case study of facebook account Dugal Delivry. The measurement result with confusion matrix gives precision value of 88,89%, recall 80% and accuracy equal to 85%.
Sistem Informasi Manajemen Legalisir Online Berbasis Website Dairoh Dairoh; Riszki Wijayatun Pratiwi; Dwi Intan Af’idah; Sharfina Febbi Handayani; Ferian Andhika Toarsi
Infotekmesin Vol 15 No 1 (2024): Infotekmesin: Januari, 2024
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v15i1.1778

Abstract

Management and submission of legalization at the Harapan Bersama Polytechnic have not been computerized. The legalization process is carried out face-to-face by leaving legalized documents and returning them when the legalized documents are ready. This process is problematic because going to campus requires quite a long time, and there is no certainty or travel history from the management of legalized documents. The research objective is to build a legalization system to facilitate the process of implementing legalization in BAA units using the website-based waterfall method. This system validates alumni data in the form of NIM at registration, processes payments through payment gateways, pays for selected shipments, and tracks travel history from the submitted legalized documents. This system is called Simaleja, and there are two actors involved. As a result, the system runs according to the functions of the actors involved and has been tested. As for the results of the black box (actor) test, the system has been running according to the function of each actor, and the UI/UX usability results were obtained for 38 users, 82% of whom fall into the very good category.
Neural Network dan Particle Swam Optimization untuk Penunjang Keputusan Antipasi Mahasiswa Pra Lulus Bekerja Sesuai Bidang Dairoh Dairoh; Very Kurnia Bakti; Muhammad Naufal
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 21 No. 1 (2021)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v21i1.1164

Abstract

Lulusan di Perguruan Tinggi yang bekerja sesuai bidang belum ideal dalam tiga tahun terakhir, salah satunya di Politeknik Harapan Bersama. Hal ini masih menunjukkan keselarasan horizontal. Sehingga pertanyaaan nya adalah kenapa hal tersebut terjadi dan disebabkan oleh apa saja yang dapat menentukan kualitas lulusan yang bekerja tidak sesuai bidang. Untuk itu, dibuat sebuah model yang dapat digunakan untuk dapat melihat pola lulusan, agar lulusan bisa bekerja sesuai bidang keilmuan. Model tersebut menggunakan kombinasi antara Algorithma Neural Network dengan PSO. Diperoleh perbandingan akurasi model kombinasi antara Neural Network dengan PSO sebesar 71.51% untuk PSO, sedangkan dengan menggunakan metode Neural Network sebesar 64.32%.
Sentimen Ulasan Destinasi Wisata Pulau Bali Menggunakan Bidirectional Long Short Term Memory Dwi Intan Af&#039;idah; Dairoh Dairoh; Sharfina Febbi Handayani; Riszki Wijayatun Pratiwi; Susi Indah Sari
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 21 No. 3 (2022)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v21i3.1402

Abstract

Pemerintah dan pelaku industri pariwisata mengalami permasalahan dalam menentukan prioritas pengembangan suatu destinasi wisata. Karena itu, diperlukan identifikasi objek wisata yang diminati namun banyak mendapat ulasan buruk melalui ulasan dari masyarakat yang tersebar di internet. Penelitian ini bertujuan melakukan analisis sentimen terhadap ulasan objek wisata di Pulau Bali menggunakan Bi-LSTM dan Word2Vec, sehingga diperoleh model terbaik yang dapat digunakan untuk mengidentifikasi objek wisata potensial namun mendapat ulasan buruk. Bi-LSTM merupakan deep learning yang menawarkan akurasi yang lebih baik daripada LSTM biasa. Sedangkan Word2Vec merupakan pretraining yang dipilih karena dapat menangkap makna semantik teks. Penelitian ini menggunakan data ulasan objek wisata di Pulau Bali yang berasal dari situs tripadvisor.com. Penelitian dimulai dari pengumpulan data, perancangan alur program, preprocessing, pretraining Word2Vec, pembagian data uji dan data latih, pelatihan dan pengujian, serta evaluasi penentuan model terbaik. Akurasi terbaik dihasilkan oleh kombisasi Word2Vec terdiri dari CBOW, Hierarchical Softmax, dimensi 200, Bi-LSTM dengan dropout sebesar 0,5 dan learning rate sebesar 0,0001. Kombinasi tersebut menghasilkan akurasi tertinggi dari keseluruhan 108 kombinasi yaitu sebesar 96,86%, precission sebesar 96,53%, Recall sebesar 96,31%, F1 Measure sebesar 96,41%. Akurasi yang baik tersebut membuktikan bahwa kombinasi parameter Bi-LSTM dan Word2Vec cocok digunakan untuk analisis sentimen ulasan objek wisata di Pulau Bali.
Comparative Study of KNN, SVM and Decision Tree Algorithm for Student’s Performance Prediction Slamet Wiyono; Dega Surono Wibowo; M. Fikri Hidayatullah; Dairoh Dairoh
(IJCSAM) International Journal of Computing Science and Applied Mathematics Vol. 6 No. 2 (2020)
Publisher : LPPM Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Students who are not-active will affect the number of students who graduate on time. Prevention of not-active students can be done by predicting student performance. The study was conducted by comparing the KNN, SVM, and Decision Tree algorithms to obtain the best predictive model. The model making process was carried out by the following steps: data collecting, pre-processing, model building, comparison of models, and evaluation. The results show that the SVM algorithm has the best accuracy in predicting with a precision value of 95%. The Decision Tree algorithm has a prediction accuracy of 93% and the KNN algorithm has a prediction accuracy value of 92%.