Article Per Year (5 Year)
p-Index From 2020 - 2025
1.448
P-Index
This Author published in this journals
All Journal Techno.Com: Jurnal Teknologi Informasi CALYPTRA : Jurnal Ilmiah Mahasiswa Universitas Surabaya Journal of ICT Research and Applications Journal of Information Systems Engineering and Business Intelligence JOIV : International Journal on Informatics Visualization Indonesian Journal of Information System Teknika ABDIMASTEK
Joko Siswantoro
Departement Of Informatics Engineering, Faculty Of Engineering, Universitas Surabaya, Jalan Raya Kali Rungkut, Surabaya, 60293
Civil Engineering, Building, Construction & Architecture Computer Science & IT Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Mechanical Engineering

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Application of Color and Size Measurement in Food Products Inspection Siswantoro, Joko
Indonesian Journal of Information Systems Vol 1, No 2 (2019): Februari 2019
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (957.249 KB) | DOI: 10.24002/ijis.v1i2.1923

Abstract

Color and size are external aspects considered by consumers in purchasing a food product and are used in food product inspection using computer vision. This paper reviews recent applications of color and size measurement in food product inspection using computer vision. RGB, HSI, HSL, HSV, La*b spaces and color index are widely used to measure color in food product inspection. Color features, including value, mean, variance, and standard deviation of each channel in a color space are widely used in food product inspection. The applications of color measurement in food product inspection are for grading, detection of anomaly or damage, detection of specific content and evaluation of color changes. Length, width, thickness, average radius, Feret’s diameter, area, perimeter, volume, and surface area are common size measurements in food product inspection. The applications of size measurement in food product inspection are for estimating size, sorting, grading, detect unwanted objects or defects, and measurement of physical properties.
PEMBUATAN WEBSITE BERBAHASA INDONESIA UNTUK PENCARIAN RESEP MASAKAN DENGAN METODE COSINE SIMILARITY Edwin Indarto; Monica Widiasri; Joko Siswantoro
CALYPTRA Vol. 8 No. 1 (2019): Calyptra : Jurnal Ilmiah Mahasiswa Universitas Surabaya (September)
Publisher : Perpustakaan Universitas Surabaya

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

Abstract

Abstraksi - Website pencarian resep masakan berbahasa Indonesia sudah banyak tetapi banyak yang pencariannya tidak memunculkan resep yang relevan, dapat melakukan plagiasi resep oleh user lain, dan tidak memiliki pengembangan inputan user(query expansion) dimana query expansion dapat membantu user dalam menentukan keyword yang sesuai. Untuk resep yang sama tetapi dipost oleh orang yang berbeda membuat user bingung menentukan resep mana yang bagus. Dibuatnya website pencarian resep masakan menggunakan metode cosine similarity dengan melihat rating resep untuk membuat website pencarian resep masakan yang relevan dengan keyword. Sistem juga memiliki query expansion dengan metode top-k retrieval. User dapat mengubah dan menghapus query expansion bila terdapat query expansion yang salah. Website dapat melakukan post resep dimana user dapat menyimpan resep. Website memiliki beberapa fitur seperti rating resep, report resep, dan komen resep. Admin juga memiliki peran seperti mevalidasi resep bila user melakukan post resep, menghapus resep, memvalidasi query expansion, dan menambah serta menghapus kategori. Uji coba dilakukan dengan menghitung precision, recall, dan f-measure serta waktu pencarian dari hasil pencarian. Uji coba juga dilakukan terhadap nilai precision, recall, dan f-measure sebelum melakukan query expansion serta sesudah melakukan query expansion. Dari uji coba yang dilakukan dapat disimpulkan bahwa pencarian sudah relevan. Kata kunci: website resep masakan, pencarian resep masakan, information retrieval, cosine similarity Abstract – Website for finding food recipe in Indonesian language already many but the search result sometimes not show relevance recipe, can duplicate the recipe, and don’t have query expansion. For the same recipe but different people can make user confused which recipes are good. Making website for finding food recipe using cosine similarity and rating for finding relevant recipes with keyword. System can expand user’s query(query expansion) using top-k retrieval method. User can edit and erase the query expansion if there’s any wrong query expansion. Website have post recipe feature where user can save their recipes. Website has categories too where categories can be add or removed by admin. Website has feature like report recipe, rating recipe, and comment recipe. Admin’s job is to validate user’s recipe, remove recipe from website, validate query expansion, and add and remove categories. Test runs for finding precision, recall, and f-measure and time when searching. Test runs done for finding precision, recall, and f-measure before using query expansion and after using query expansion. From the result of the test, get conclusion that the searching function already relevant. Keywords: food recipe website, finding food recipe, information retrieval, cosine similarity.
Volume Measurement Algorithm for Food Product with Irregular Shape using Computer Vision based on Monte Carlo Method Joko Siswantoro; Anton Satria Prabuwono; Azizi Abdullah
Journal of ICT Research and Applications Vol. 8 No. 1 (2014)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2014.8.1.1

Abstract

Volume is one of important issues in the production and processing of food product. Traditionally, volume measurement can be performed using water displacement method based on Archimedes' principle. Water displacement method is inaccurate and considered as destructive method. Computer vision offers an accurate and nondestructive method in measuring volume of food product. This paper proposes algorithm for volume measurement of irregular shape food product using computer vision based on Monte Carlo method. Five images of object were acquired from five different views and then processed to obtain the silhouettes of object. From the silhouettes of object, Monte Carlo method was performed to approximate the volume of object. The simulation result shows that the algorithm produced high accuracy and precision for volume measurement.
Hybrid Neural Network and Linear Model for Natural Produce Recognition Using Computer Vision Joko Siswantoro; Anton Satria Prabuwono; Azizi Abdullah; Bahari Indrus
Journal of ICT Research and Applications Vol. 11 No. 2 (2017)
Publisher : LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2017.11.2.5

Abstract

Natural produce recognition is a classification problem with various applications in the food industry. This paper proposes a natural produce recognition method using computer vision. The proposed method uses simple features consisting of statistical color features and the derivative of radius function. A hybrid neural network and linear model based on a Kalman filter (NN-LMKF) was employed as classifier. One thousand images from ten categories of natural produce were used to validate the proposed method by using 5-fold cross validation. The experimental result showed that the proposed method achieved classification accuracy of 98.40%. This means it performed better than the original neural network and k-nearest neighborhood.
Application of Color and Size Measurement in Food Products Inspection Joko Siswantoro
Indonesian Journal of Information Systems Vol. 1 No. 2 (2019): Februari 2019
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v1i2.1923

Abstract

Color and size are external aspects considered by consumers in purchasing a food product and are used in food product inspection using computer vision. This paper reviews recent applications of color and size measurement in food product inspection using computer vision. RGB, HSI, HSL, HSV, La*b spaces and color index are widely used to measure color in food product inspection. Color features, including value, mean, variance, and standard deviation of each channel in a color space are widely used in food product inspection. The applications of color measurement in food product inspection are for grading, detection of anomaly or damage, detection of specific content and evaluation of color changes. Length, width, thickness, average radius, Feret’s diameter, area, perimeter, volume, and surface area are common size measurements in food product inspection. The applications of size measurement in food product inspection are for estimating size, sorting, grading, detect unwanted objects or defects, and measurement of physical properties.
Analisis Sentimen Multi-Kelas Untuk Film Berbasis Teks Ulasan Menggunakan Model Regresi Logistik Anasthasya Averina; Helen Hadi; Joko Siswantoro
Teknika Vol 11 No 2 (2022): Juli 2022
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v11i2.461

Abstract

Pengutaraan pendapat atau pengutaraan pemikiran secara sukarela terhadap suatu film pada situs pengulas film merupakan hal yang sering dilakukan oleh pengguna. Beberapa pengguna kadang-kadang memberikan ulasan yang ambigu terhadap sebuah film, yaitu dengan memberikan komentar yang buruk tetapi memberikan rating yang baik atau sebaliknya. Hal ini dapat berpengaruh pada citra film tersebut. Maka dari itu, diperlukan sistem yang dapat memprediksi rating agar sesuai dengan komentar yang diberikan atau sistem pembenaran rating. Penelitian ini bertujuan untuk memprediksi rating suatu film berdasarkan ulasan yang diberikan oleh pengguna menggunakan model Regresi Logistik. Dataset yang digunakan pada penelitian ini adalah data ulasan 10 film yang berbeda dari Mendeley Data. Tahap pra-pemrosesan dilakukan dengan penghapusan kata umum, tanda baca, pengurangan dimensi, dan pengekstrakan ciri dari teks ulasan menggunakan library scikit-learn. Dengan 80% data sebagai training dan sisanya digunakan untuk testing, hasil perhitungan akurasi prediksi 10 kelas rating yang didapatkan dari feature extraction CountVectorize adalah 36% dan TfidfVectorizer sebesar 32%. Sedangkan hasil dari perhitungan akurasi prediksi 2 class sentiment, didapatkan hasil tertinggi sebesar 83% oleh feature extraction CountVectorizer dan feature extraction TfidfVectorizer sebesar 76%.
Melanoma Detection using Convolutional Neural Network with Transfer Learning on Dermoscopic and Macroscopic Images Jessica Millenia; Mohammad Farid Naufal; Joko Siswantoro
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.8.2.149-161

Abstract

Background: Melanoma is a skin cancer that starts when the melanocytes that produce the skin color pigment start to grow out of control and form a cancer. Detecting melanoma early before it spreads to the lymph nodes and other parts of the body is very important because it makes a big difference to the patient's 5-year life expectancy. Screening is the process of conducting a skin examination to suspect a mole is melanoma using dermoscopic or macroscopic images. However, manual screening takes a long time. Therefore, automatic melanoma detection is needed to speed up the melanoma detection process. The previous studies still have weakness because it has low precision or recall, which means the model cannot predict melanoma accurately. The distribution of melanoma and moles datasets is imbalanced where the number of melanomas is less than moles. In addition, in previous study, comparisons of several CNN transfer learning architectures have not been carried out on dermoscopic and macroscopic images. Objective: This study aims to detect melanoma using the Convolutional Neural Network (CNN) with transfer learning on dermoscopic and macroscopic melanoma images. CNN with Transfer learning is a popular method for classifying digital images with high accuracy. Methods: This study compares four CNN with transfer learning architectures, namely MobileNet, Xception, VGG16, and ResNet50 on dermoscopic and macroscopic image. This research also uses black-hat filtering and inpainting at the preprocessing stage to remove hair from the skin image. Results: MobileNet is the best model for classifying melanomas or moles in this experiment which has 83.86% of F1 score and 11 second of training time per epoch. Conclusion: MobileNet and Xception have high average F1 scores of 84.42% and 80.00%, so they can detect melanoma accurately even though the number of melanoma datasets is less than moles. Therefore, it can be concluded that MobileNet and Xception are suitable models for classifying melanomas and moles. However, MobileNet has the fastest training time per epoch which is 11 seconds. In the future, oversampling method can be implemented to balance the number of datasets to improve the performance of the classification model.
Klasifikasi Tulisan Tangan Pada Resep Obat Menggunakan Convolutional Neural Network Mohammad Farid Naufal; Joko Siswantoro; Muhammad Ghifari Kusuma Wicaksono
Techno.Com Vol 22, No 2 (2023): Mei 2023
Publisher : LPPM Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33633/tc.v22i2.8075

Abstract

Obat merupakan bahan kimia yang dapat merepresentasikan tubuh secara fisiologi dan psikologi ketika dikonsumsi. Obat sebagai alat bantu untuk menyembuhkan dari berbagai macam penyakit. Dengan berkembangnya zaman dan bertambahnya wawasan, menyebabkan bertambah juga jenis obat-obatan yang memiliki banyak manfaat dan kegunaanya. Penelitian ini bertujuan untuk mendeteksi nama obat dalam resep dokter menggunakan Convolutional Neural Network (CNN) dengan transfer learning. Metode transfer learning merupakan metode yang popular dalam mengklasifikasi gambar digital yang berguna untuk mempercepat proses klasifikasi. Penelitian ini membandingkan lima artistektur transfer learning yaitu VGG16, Resnet, Xception, LeNet, dan GoogleNet. Penelitian ini juga menggunakan grayscaling, resizing, dan median filter pada tahap preprocessing. Preprocessing digunakan untuk meningkatkan kualitas citra pada citra resep obat dan menghilangkan noise pada citra. ResNet-50 merupakan arsitektur terbaik untuk mengklasifikasi nama obat. Pada percobaan menggunakan ResNet-50, mendapatkan F1 score tertinggi yaitu sebesar 97,56% dan waktu training rata-rata 0,25 detik setiap epoch. Dapat disimpulkan Resnet merupakan arsitektur terbaik untuk mengklasifikasikan nama obat dalam citra resep dokter serta dapat mendeteksi nama obat secara akurat.
Facial Expression Recognition to Detect Student Engagement in Online Lectures Joko Siswantoro; Januar Rahmadiarto; Mohammad Farid Naufal
Teknika Vol 13 No 2 (2024): Juli 2024
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v13i2.853

Abstract

In synchronous online lectures, the lecturers often provide the lecture material directly through video conference technology. On the other hand, there are many students who do not pay attention to the lecturers when they are participating in online lectures. As a consequence, in this research, an application was developed to assist lecturers in gathering data regarding the degree to which students who participate in online lectures pay attention to the presented information. The application employed a convolutional neural network (CNN) model to recognize each student's facial expressions and place them into one of two classes: either engaged or disengaged. The captured student facial image was preprocessed to facilitate the classification process. The preprocessing stage consisted of image conversion to gray scale, face detection using the Haar-Cascade Classifier model, and a median filter to reduce noise. In the process of designing a CNN model, three different hyperparameter tuning scenarios were implemented. These tuning scenarios aimed to obtain the best possible CNN model by determining which CNN model hyperparameters were the most optimal. The results of the experiments indicate that the CNN model from the second scenario has the highest level of accuracy in terms of recognizing facial expressions, coming in at 86%. The results of this research have been tested to measure the level of student participation in online lectures. The trial results show that the proposed application can help lecturers evaluate student engagement during online lectures.
PEMBUATAN APLIKASI PENGENALAN WAJAH UNTUK SISTEM PRESENSI KELAS MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK Muhammad Alifian Fajar Pratama; Joko Siswantoro; Vincentius Riandaru Prasetyo
CALYPTRA Vol. 12 No. 1 (2023): Calyptra : Jurnal Ilmiah Mahasiswa Universitas Surabaya (November)
Publisher : Perpustakaan Universitas Surabaya

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

Abstract

Abstract—Attendance is a method used by an agency to record workers who work in an agency or students who are in an educational agency. During the pandemic, the University of Surabaya changed the attendance system it used, the system first used before the pandemic was paper, during the pandemic the University of Surabaya changed the attendance system to use a website. On this website, students only need to select courses that are currently in progress and carry out the attendance process. In 2022 the Indonesian government will allow universities and schools to carry out face-to-face learning processes. The University of Surabaya is also making a transition from online to face-to-face learning, however the attendance system used is still a website, this causes students to have fictitious attendance or make attendance but students do not attend class. Based on these problems, this research created an application that can help the university to prevent students from making fictitious attendance by using face recognition in the attendance process using the Convolutional Neural Network or CNN method. The process of creating a CNN model will use a pre-trained model, namely GoogleNet, which has 1 layer added and the Hyperparameter Tuning process will be used to get the best CNN model by looking for optimal Hyperparameter values based on the predetermined Hyperparameter values and types. One of the results of the CNN model making trial was that the best model was obtained with an accuracy rate of 97%. Keywords: convolutional neural network, face recognition, attendance Abstrak—Presensi merupakan sebuah metode yang digunakan oleh sebuah instansi untuk mencatat para pekerja yang bekerja di sebuah instansi tersebut atau para mahasiswa/i atau siswa/i yang berada di sebuah instansi pendidikan. Pada masa pandemi Universitas Surabaya mengubah sistem presensi yang digunakan, sistem yang pertama kali digunakan sebelum pandemi berupa kertas, saat pandemi Universitas Surabaya mengubah sistem presensi menggunakan website. Pada website ini mahasiswa hanya perlu memilih mata kuliah yang sedang berlangsung dan melakukan proses presensi. Pada tahun 2022 pemerintah Indonesia memperbolehkan Universitas serta Sekolah untuk melakukan proses pembelajaran secara tatap muka. Universitas Surabaya juga melakukan transisi dari pembelajaran online menjadi tatap muka, akan tetapi sistem presensi yang digunakan masih berupa website, hal ini menyebabkan mahasiswa presensi fiktif atau melakukan presensi namun mahasiswa tidak mengikuti kelas. Berdasarkan permasalahan tersebut pada penelitian ini dibuat sebuah aplikasi yang dapat membantu pihak universitas untuk mencegah mahasiswa melakukan presensi fiktif dengan digunakannya pengenalan wajah atau face recognition dalam proses presensi menggunakan metode Convolutional Neural Network atau CNN. Proses pembuatan model CNN akan digunakan model pre-trained yaitu GoogleNet yang ditambahkan 1 layer dan akan digunakan proses Hyperparameter Tuning untuk mendapatkan model CNN terbaik dengan mencari nilai Hyperparameter yang optimal berdasarkan nilai dan jenis Hyperparameter yang telah ditentukan. Salah satu hasil uji coba pembuatan model CNN didapatkan model terbaik dengan tingkat akurasi 97%. Kata kunci: convolutional neural network, face recognition, presensi
Co-Authors Anasthasya Averina Anton Satria Prabuwono Anton Satria Prabuwono Arwoko, Heru Asmawti, Endah Azizi Abdullah Azizi Abdullah Bahari Indrus Edwin Indarto Helen Hadi Januar Rahmadiarto Jessica Millenia Mohammad Farid Naufal Mohammad Farid Naufal Mohammad Farid Naufal, Mohammad Farid Monica Widiasri, Monica Muhammad Alifian Fajar Pratama Muhammad Ghifari Kusuma Wicaksono Soebroto, Juan Timothy Sofia Ariyani Vincentius Riandaru Prasetyo