Claim Missing Document
Check
Articles

Japanese Letter Pattern Recognition Application with Tesseract Engine Akhmad Imam Fahrizal; Ahmad Subhan Yazid; Shofwatul Uyun
IJID (International Journal on Informatics for Development) Vol. 4 No. 2 (2015): IJID December
Publisher : Faculty of Science and Technology, UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (733.244 KB) | DOI: 10.14421/ijid.2015.04202

Abstract

Digital image processing is a field that is being cultivated by many researchers at this time because it is interesting to apply to various activities, both analysis and production activities. One branch of the digital image is pattern recognition. This study uses Tesseract as a tool to recognize patterns from Hiragana letters. This study was conducted to find out how much Tesseract was able to recognize a Japanese text and handwritten text. This study uses 1 image as training data containing 74 Hiragana letters which are processed through training for each letter. This study has several testing criteria based on font size and resolution to find the best results in pattern recognition. This pattern recognition system is able to do data training and recognize 74 Hiragana letters using the Tesseract Engine. The system can also recognize images with the best success percentage of 98.24% with an image resolution of 200dpi (dots per inch) at size 18. This system can also recognize handwritten images with the best percentage of success of 90% with 200dpi image resolution.
AN APPLICATION OF MAMDANI IN SELECTING MAJORS IN HIGHER EDUCATION Heni Hapsari; Muhammad Dzulfikar Fauzi; Shofwatul Uyun
IJID (International Journal on Informatics for Development) Vol. 2 No. 1 (2013): IJID May
Publisher : Faculty of Science and Technology, UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1014.026 KB) | DOI: 10.14421/ijid.2013.%x

Abstract

The election for a right major at university will make a big difference because students should choose a major that suits their basic skills and talent preference. A research case uses a sample from various majors in state university in Indonesia. There are 29 majors available. Therefore, interest score, talent score, and basic ability score become a consideration matter in choosing the right major for them. The implementation of this system uses PHP programming language and MySQL database which based on the web. This research uses sample data of SMAN (state high school) 1 on Kutowinangun, Kebumen. It is including self-data, interest score, talent score, and basic skill score. This research uses a fuzzy inference system using Mamdani method. Mamdani method works based on linguistic principle and has a fuzzy algorithm which supply approximation to be entered by mathematic analysis. Data are processed through the calculation phase of fuzzy and result given by the system is a recommendation of a major suggested to be taken by the student. This system shows a recommendation of a major that suits the student. This system also gives information about universities which provide recommended major. This system is hope to help students in choosing their major.
Classification of Damaged Road Images Using the Convolutional Neural Network Method Arif Riyandi; Tony Widodo; Shofwatul Uyun
Telematika Vol 19, No 2 (2022): Edisi Juni 2022
Publisher : Jurusan Teknik Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v19i2.6460

Abstract

Objective: Automatic identification is carried out with the help of a tool that can take an image of road conditions and automatically distinguish the types of road damage, the location of road damage in the image and calculate the level of road damage according to the type of road damage.Design/method/approach: Identification of damaged roads usually uses manual RCI system which requires high cost. In this study, a comparison framework is proposed to determine the performance of the image pre-processing model on the image classification algorithm.Results: Based on 733 image data classified using the CNN method from 4 models of pre-processing stages, it can be concluded that training from grayscale images produces the best level of accuracy with a training accuracy value of 88% and validation accuracy reaching 99%.Authenticity/state of the art: Testing of 4 pre-processing models against the classification algorithm used as a comparison resulted in the best algorithm/method for managing road images.
Chest X-ray Image Classification for COVID-19 diagnoses Endra Yuliawan; Shofwatul ‘Uyun
Journal of Information Systems Engineering and Business Intelligence Vol. 8 No. 2 (2022): October
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jisebi.8.2.109-118

Abstract

Background: Radiologists used chest radiographs to detect coronavirus disease 2019 (COVID-19) in patients and determine the severity levels. The COVID-19 cases were grouped into five classes, each receiving different treatments. An intelligent system is needed to advance the detection and identify vector features of X-ray images with a quality that is too poor to be read by radiologists. Deep learning is an intelligent system that can be used in this case. Objective: The current study compares the classification and accuracy of detection methods with two, three dan five classes. Methods: Deep learning can classify visual geometry group VGG 19 architectures with 1000 classes. The classification of the five classes' convolutional neural network (CNN) underwent model validation with a confusion matrix to produce accuracy and class values. The system could then diagnose patients’ examinations by radiology specialists. Results: The results of the five-class method showed 98% accuracy, the three-class method showed 99.99%, and the two-class showed 99.99%. Conclusion: It can be concluded that using the VGG 19 model is effective. This system can classify and diagnose viruses in patients to assist radiologists by reading the images.   Keywords: COVID-19, CNN, Classification, Deep Learning
Classification of Student Graduation using Naïve Bayes by Comparing between Random Oversampling and Feature Selections of Information Gain and Forward Selection Dony Fahrudy; Shofwatul 'Uyun
JOIV : International Journal on Informatics Visualization Vol 6, No 4 (2022)
Publisher : Politeknik Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.6.4.982

Abstract

Class-imbalanced data with high attribute dimensions in datasets frequently contribute to issues in a classification process as this can affect algorithms’ performance in the computing process because there are imbalanced numbers of data in each class and irrelevant attributes that must be processed; therefore, this needs for some techniques to overcome the class-imbalanced data and feature selection to reduce data complexity and irrelevant features. Therefore, this study applied random oversampling (ROs) method to overcome the class-imbalanced data and two feature selections (information gain and forward selection) compared to determine which feature selection is superior, more effective and more appropriate to apply. The results of feature selection then were used to classify the student graduation by creating a classification model of Naïve Bayes algorithm. This study indicated an increase in the average accuracy of the Naïve Bayes method without the ROs preprocessing and the feature selection (81.83%), with the ROs (83.84%), with information gain with 3 selected features (86.03%) and forward selection with 2 selected features (86.42%); consequently, these led to increasing accuracy of 4.2% from no pre-processing to information gain and 4.59% from no pre-processing to forward selection. Therefore, the best feature selection was the forward selection with 2 selected features (GPA of the 8th semester and the overall GPA), and the ROs and both feature selections were proven to improve the performance of the Naïve Bayes method.
Deep Transfer Learning untuk Meningkatkan Akurasi Klasifikasi pada Citra Dermoskopi Kanker Kulit Qorry Aina Fitroh; Shofwatul 'Uyun
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 12 No 2: Mei 2023
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jnteti.v12i2.6502

Abstract

Benign and malignant cancers are the most common skin cancer types. It is essential to know skin cancer symptoms with an early diagnosis to provide an appropriate treatment and reduce the mortality rate. Dermoscopic image is one of the diagnostic media that many researchers have developed. It provides more optimal results in computational-based diagnosis than visual detection. Deep learning and transfer learning are two models that have been used successfully in computational-based analysis, although optimization is still needed. In this study, transfer learning was used to separate dermoscopic images of skin cancer into two categories: benign and malignant. This study used 2,000 images to increase previous research’s accuracy conducted on the Kaggle public dataset containing 3,297 images. Two pretrained models, namely VGG-16 and residual network (ResNet)-50, were compared and used as feature extractors. Fine-tuning was conducted by adding a flatten layer, two dense layers with the ReLU activation function, and one dense layer with the Softmax activation function to classify images into two categories. Hyperparameter tuning on the optimizer, batch size, learning rate, and epoch were performed to get each model’s best performance parameter combination. Before hyperparameter tuning, the model was tested by resizing the input image using different sizes. The results of model testing on the VGG-16 model gave the best performance at an image size of 128 × 128 pixels with a combination of Adam parameters as an optimizer, batch size of 64, learning rate of 0.001, and epoch of 10 with an accuracy value of 91% and loss of 0.2712. The ResNet-50 model yielded better accuracy of 94% and a loss of 0.2198 using the optimizer parameter RMSprop, batch size of 64, learning rate of 0.0001, and epoch of 100. The results indicate that the proposed method provides good accuracies and can assist dermatologist in the early detection of skin cancer.
Pengaruh Penggunaan Information Gain untuk Seleksi Fitur Citra Tanah dalam Rangka Menilai Kesesuaian Lahan pada Tanaman Cengkeh Danang Aji Bimantoro; Shofwatul Uyun
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 2 No. 1 (2017): Mei 2017
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (465.103 KB) | DOI: 10.14421/jiska.2017.21-06

Abstract

Cengkeh merupakan komoditas perkebunan yang memiliki nilai ekonomis cukup tinggi sehingga perlu penambahan lahan untuk meningkatkan produksinya. Penentuan lahan baru yang tepat perlu mempertimbangkan banyak faktor, salah satunya adalah karakteristik sifat tanah itu sendiri. Kesesuaian lahan untuk tanaman cengkeh dapat dibedakan secara visual menggunakan citra berdasarkan fitur warna dan tekstur. Parameter yang digunakan dari hasil ekstraksi kedua fitur tersebut adalah nilai rata-rata dari (red, green, blue) serta (mean, variance, kurtosis, skewness, entropy). Penggunaan seluruh parameter tersebut tidak berkolerasi positif dengan hasil akurasi penilaian kesesuaian lahan untuk tanaman cengkeh. Oleh Karena itu perlu dilakukan proses seleksi fitur untuk mendapatkan parameter yang memiliki pengaruh dalam penentuan hasil pengenalan lahan. Pada penelitian ini dilakukan analisis pengaruh penggunaan information gain untuk seleksi fitur citra tanah dalam rangka menilai kesesuaian lahan pada tanaman cengkeh. Jumlah data yang digunakan pada penelitian ini adalah 50 citra yang terbagi menjadi dua citra tanah  yang sesuai dan tidak sesuai untuk tanaman cengkeh. Tahapan penelitian ini diawali dengan akuisisi citra, pra pengolahan terhadap citra, ekstraksi fitur, seleksi fitur, clustering dilanjutkan dengan analisis. Hasil analisis menunjukkan penggunaan fitur hasil dari proses seleksi fitur menggunakan information gain terbukti mampu meningkatkan nilai akurasi. Hasil pengujian menunjukkan tingkat akurasi penggunaan fitur tanpa proses seleksi hanya 50%, sedangkan fitur terpilih dari hasil seleksi menggunakan information gain dengan nilai threshold 0,7 naik menjadi 88%.Kata Kunci: pengolahan citra digital, information gain, fuzzy c-means, tanah, cengkeh
Pengembangan Sistem Pemetaan Status Mutu Air Sungai Berbasis Web Menggunakan Extreme Programming Shofwatul Uyun
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 4 No. 3 (2020): Januari 2020
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (630.235 KB) | DOI: 10.14421/jiska.2020.43-05

Abstract

The high water pollution index causes a decrease in water quality so that it can interfere with the health of living things. In order to overcome this, the government has tried to monitor water quality whose results can be known by the community. However, information disclosure and ease of accessing information are felt to be lacking. This study aims to present information about the quality status of river water and its relatively up-to-date and easily accessed by the public online. The storet method is used to determine the status of river water quality with seven parameters: temperature, EC, TDS, pH, DO, BOD and E.coli. The features provided will be explained in the results and discussion presented in several UML diagrams. In order to get results that match user expectations, this system was developed with extreme programming system development methods.
Penentuan Emosi pada Video dengan Convolutional Neural Network Daru Prasetyawan; Shofwatul 'Uyun
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 5 No. 1 (2020): Mei 2020
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (581.165 KB) | DOI: 10.14421/jiska.2020.51-04

Abstract

Emosi seseorang dapat ditunjukan melalui ekspresi wajah. Ekspresi wajah manusia dapat berubah-ubah secara dinamis tanpa disadari oleh orang tersebut. Penelitian ini melakukan penentuan emosi dengan melakukan pengenalan ekspresi wajah manusia dan melakukan perekaman untuk setiap perubahan ekspresi wajah tersebut. Metode dalam penelitian ini adalah dengan melakukan klasifikasi terhadap 6 ekspresi dasar wajah manusia ditambah ekspresi netral dengan Convolutional Neural Network (CNN). Pemerataan distribusi data dilakukan untuk meningkatkan kinerja model. Dari pemodelan tersebut, dihasilkan model klasifikasi yang dapat diterapkan pada sebuah video. Model tersebut diuji menggunakan data yang terpisah dari data latih dan dievaluasi menggunakan confusion matrix. Sebagai hasil evaluasi, diperoleh akurasi 74%, rata-rata presisi 75,05%, dan rata-rata recall 74%. Di akhir penelitian ini, peneliti melakukan percobaan dengan menerapkan model klasifikasi tersebut pada beberapa video yang mewakili ekspresi seseorang di dalam video tersebut. Setiap perubahan ekspresi akan direkam dan dianalisis sehingga ditemukan emosi yang paling dominan.
Prapemrosesan pada Klasifikasi Status Mutu Air Sungai Menggunakan Random Oversampling dan Outlier Remover Clustering Uyun, Shofwatul; Sulistyowati, Eka; Fahrudy, Dony
Jurnal Teknologi dan Sistem Komputer [IN PRESS] Volume 10, Issue 4, Year 2022 (October 2022)
Publisher : Department of Computer Engineering, Engineering Faculty, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jtsiskom.2022.14450

Abstract

Ketidakseimbangan jumlah data pada setiap kelasnya serta adanya data outlier seringkali menjadi masalah dalam proses klasifikasi, hal tersebut tentu akan mempengaruhi performa kinerja pembelajaran mesin yang menurun. Oleh karena itupada penelitian ini diusulkan penggunaan teknik Random Oversampling (ROs) untuk mengatasi ketidakseimbangan data serta teknik Outlier Removal Clustering (ORC) untuk mengatasi data outlier pada penentuan status mutu air. Kedua teknik tersebut digunakan pada tahapan prapemrosesan. Penelitian ini terdiri dari beberapa tahapan, yaitu penentuan kelas status mutu air menggunakan teknik indeks pencemaran, prapemrosesan, pembagian data, klasifikasi serta evaluasi kinerja. Ada tiga algoritma klasifikasi yang digunakan sebagai perbandingan, yaitu KNN, CART dan random forest. Berdasarkan hasil penelitian menunjukkan peningkatan rerata akurasi dari penggunaan ketiga algoritma klasifikasi tersebut dengan tanpa dilakukan prapemrosesan, penggunaan ROs serta integrasi ROs dan ORC secara berurutan sebagai berikut 83,81%; 94,87% dan 95,51%. Jadi penggunaan teknik Ros dan ORC terbukti meningkatkan performa kinerja pada machine learning.