Claim Missing Document
Check
Articles

Ekstraksi Fitur RGB Color Channel dan Simple Morphological Shape Descriptors dari Citra Makanan untuk Pencarian Resep Makanan Barbara Sonya Hutagaol; Yuita Arum Sari; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (431.863 KB)

Abstract

Nowadays food is no longer just a basic necessity, but food has been used as an entertainment. As can be seen on social media, there a lots of photos of foods that attract our attention, thus force us to cook and made the food. To make food, a food recipe is needed. In general, food recipes can be found in magazines, television, newspaper, and websites. The recipe is searched by the name of the dish. The limitation of knowledge obout food's name, makes it difficult to find the recipes. By seeing this problem, we can use Content Based Image Retrieval (CBIR) to make the image as the query. Searching by using an image we need digital image processing to obtain the features of the image. The used features are red, green, and blue (RGB) color channel as the color feature, simple morphological shape descriptors as the shape feature, and k-NN as the classification method. The result of this research give the best n value n=5 where mean average precision (MAP) is 94,1892% on the combination of color and shape feature. The use of color and shape feature commonly obtain the best result on the combination of the both feature at n=10, n=15, n=20, dan n=25. The conclusion is when the higher value of n give the worst result of MAP and the use the combination of color and shape features can provide the best results compared using of one feature.
Pencarian Resep Makanan Berdasarkan Citra Makanan Menggunakan Simple Morphological Shape Descriptors, Cie L*A*B* Color Moment Dan Local Binary Pattern Yosua Dwi Amerta; Yuita Arum Sari; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (402.981 KB)

Abstract

A recipe is a guide that contains the ingredients, steps, and how to serve a food. Recipe searches are generally limited to using the title or name of a food, and to overcome these limitations image search is needed. Image based search requires extraction of image features, and there will be 3 feature extraction methods to be used. Extracting color features is done using the CIE L * a * b * Color Moment method, which will take the features of the mean, standard deviation, and skewness. In the shape feature, Simple Morphological Shape Descriptors (SMSD) is used to get 4 feature, aspect ratio, length, width, and diameter features. The third feature, which is texture extracted using the Local Binary Pattern method. Based on the results of these methods, it can be seen that the search uses CIE L * a * b * Color Moment gets the MAP value of 0.70. The SMSD method gets the smallest MAP with a value of 0.46. LBP gets the same value with the combined method which is 0.52. So it can be concluded that LBP has major effects to the results of the combined method.
Klasifikasi Citra Makanan Menggunakan HSV Color Moment dan Local Binary Pattern dengan Naive Bayes Classifier Karunia Ayuningsih; Yuita Arum Sari; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 4 (2019): April 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (567.322 KB)

Abstract

Food is a basic need that must be fulfilled in human life. Eating habits can lead to good and bad habits. Bad eating habits can cause various diseases. Komunikasi, informasi, dan edukasi (KIE) can provide education on eating habits. Food has a variety of types, it is necessary to recognize the type of food to make it easier to identify good types of food. The purpose of this study is to be able to provide education to recognize the types of food. The process begins with image identification using pre-processing to separate between food objects and background. On top of that, using the Hue Saturation Value (HSV) color extraction feature consists of the feature Mean, the Standard Deviation, and the Skewness. Then is the use of the Local Binary Pattern (LBP) texture feature extraction produce feature extraction uses gray scales in the histogram. The results of feature extraction from each image are then carried out using the Naive Bayes Classifier classification. Based on the test results, the use of only the HSV method produces a 65% accuracy value. Meanwhile, the use the LBP method, get a 60% accuracy value. In addition, the results of tests that have been carried out using the HSV method produce an accuracy of 65% and the LBP method produces an accuracy of 60%.
Analisis Sentimen Impor Beras 2018 Pada Twitter Menggunakan Metode Support Vector Machine dan Pembobotan Jumlah Retweet Renaza Afidianti Nandini; Yuita Arum Sari; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 4 (2019): April 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1431.596 KB)

Abstract

Social media Twitter is one of the largest real time databases and is very useful for knowing people's perceptions in Indonesia. The issue of rice import polemic on Twitter tweets is an important thing to study as text processing. This study discusses sentiment analysis on 2018 rice import Twitter using the Support Vector Machine (SVM) method and Weighting the Number of Retweets. The use of the weighting feature of the number of retweets uses a comparison of certain constants (α and β) 11 times to obtain the results of positive and negative class analysis. The data used in this study were 318 data consisting of two types of data namely training data and test data with a ratio of 70% training data and 30% test data. From the results of accuracy testing using the Support Vector Machine method without weighting the number of retweets by 50.00%, precision by 49.46%, recall by 97.87%, and f-measure by 65.71%. Accuracy testing results using the Support Vector Machine method with a weighting of retweet amount of 50.00%, precision of 49.46%, recall of 01.00% and f-measure of 65.73%. It can be concluded that the use of the weighting feature of the number of retweets can provide optimal results and is able to classify sentiment analysis.
Klasifikasi Citra Jenis Makanan dengan Color Moments, Morphological Shape Descriptors, dan Gray Level Coocurrence Matrix menggunakan Neighbor Weight K-Nearest Neighbor Muhammad Abdan Mulia; Yuita Arum Sari; Sutrisno Sutrisno
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 5 (2019): Mei 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (468.266 KB)

Abstract

The level of development of human growth depends on food consumed daily. The good condition of the human body comes from healthy and hygienic food. Recognizing a food becomes a problem for visitors or tourists who are visiting a food place that has no known nutrient levels and ingredients. To overcome this problem, research needs to be done to classify a food image. Morphological Shape Descriptors (MSD), Color Moments (CM), and Gray Level Co-ocurence Matrix (GLCM) features with Haralick have been shown to produce good features for classification. The Neighbor Weight K-Nearest Neighbor method is also an alternative to the image classification process.Based on the test results from k-fold cross validation with k = 10 and the evaluation method in the form of accuracy, obtained maximum accuracy of 0.86 with parameter values ​​E = 11 and k = 3 in the case of training data amounting to 530 images of single food which has been pre-processing. This shows that the classification of food images based on the extraction of textural features such as form (MSD), color (CM), and texture (GLCM) results in relatively better accuracy. In addition, the combination of the use of these three features affects the results of accuracy. This is indicated by testing which shows that the results of relative accuracy are better achieved in features of a combination of textures, shapes, and colors.
Pengenalan Citra Jenis Makanan menggunakan Ekstraksi Fitur Color Channel dan Gray Level Co-Occurence Matrix Ofi Eka Novyanti; Yuita Arum Sari; Muhammad Tanzil Furqon
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 5 (2019): Mei 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Manually, humans can easily detect and differentiate types of food. But man sees certainly has contrains that meant identification a kind of food inconsistantly different. Rresearches show that human vision influenced by age, disease and physical condition. Through the passing technology, researchers have seen the emergence of food's recognition systems in image processing. The aim of this study is to develop a system that could recognize kinds of food based on it's color and texture by using K-NN. The process was proceded by image segmentation process. The segmented image then used to gain the color feature extraction's value, color channels that use RGB as the channel with 9 sub features and the texture value of feature extraction, GLCM with 20 sub features at angle 0 , 45 , 90 , and 135 . The results is this extracted feature then used in the process of image classification using K-NN. Testing process done through 3 stages that are k value testing, feature extraction testing, distance calculation method testing with 900 data sets of two types of data categories. The result is data which use value k =3 that earn as much as 90,58% of accuration with balanced composition data.
Algoritme Information Gain Feature Selection pada Sistem Temu Kembali Citra Makanan Menggunakan Ekstraksi Fitur Warna dan Tekstur Dyva Agna Fauzan; Yuita Arum Sari; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 5 (2019): Mei 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (889.16 KB)

Abstract

The food name used as a keyword or query in conducting a food recipe search on the search system has limitations, namely the knowledge of the name of the food that the recipe wants to find. So another approach is needed to do recipe searches, namely by the display or the image of food. However, with the many features that are generated from the image it will cause high dimensional data which results in the effectiveness of the search system. For this reason, feature selection is needed to handle high-dimensional data. This research conducted a study of the effect of the number of returns that can provide the highest MAP value and the effect of the Information Gain feature selection on food image retrieval systems using texture feature extraction using Gray Level Co-occurance Matrix and color features using Color Moments and Color Histogram. The number of retrieves (r) of 5 is outperforming other r values with the value of MAP = 1 on the use of only color features and textures and the value of MAP = 0.98 in the combination of both. This indicates a smaller number of returns can give a higher MAP value. The effect of the Information Gain feature selection algorithm on the system is that it can provide the MAP = 1 value on the number of features (n) = 10 on the color feature, n = 5 on the texture feature, and n = 30 on the combination. This shows that the system with feature selection can provide results that are as good (in color and texture) and even better (in combination of features) with fewer features when compared to without feature selection.
Pencarian Teks pada Terjemahan Ayat Al-Qur'an dengan Menggunakan TF-RF dan Bray-Curtis Distance Inas Istiqlaliyyah; Yuita Arum Sari; Moch. Ali Fauzi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 5 (2019): Mei 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (798.229 KB)

Abstract

Qur'an verses search applications have been developed over time due to the significance of Qur'an itself which contains information for the Muslims to be used as a guideline for life. The existence of Qur'an verses search applications can ease Muslims in finding the relevant verse in accordance with the query entered. One of the existing applications is Cari Ayat. Despite having existed for quite some time, however, there still a drawback on its search feature where it cannot display the verses that are relevant to the query when users enter more than two words, making this application system lacks in performance when displaying the relevant verse. In addressing this issue, this research uses the term of weighing and distance metrics. The process begins with carrying out pre-processing of the text after which weighing will be performed into the terms resulting from pre-processing by using the TF-RF and Bray-Curtis distance to measure the distance between the document and the query. As many as 50 query used in the testing process. The test results of k-rank value variety indicate that k-rank 5 produces the best MAP value up to 60.36%, which is higher than those of k-rank 10, 15 and 20. The test results achieved by performing the dataset in which the process of cleaning, weighting term TF-RF, and Bray-Curtis distance has been carried out beforehand, may slightly increase the MAP value on the k-rank 5 by 61.80%. Furthermore, the test results using the Kappa Statistic based on the agreement of the two experts, account the value of kappa by 0.8774 which is considered as almost perfect. Based on these results, it can be inferred that TF-RF and Bray-Curtis distance can be utilized to find the relevant texts in the translation of Qur'an verse.
Klasifikasi Jenis Makanan menggunakan Neighbor Weighted K-Nearest Neighbor dengan Seleksi Fitur Information Gain Vriza Wahyu Saputra; Yuita Arum Sari; Agus Wahyu Widodo
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 5 (2019): Mei 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (540.454 KB)

Abstract

Smartphones with powerful camera sensor capabilities can be used to analyze photos and object recognition. Food is one of the popular photography objects and seeing it makes you want to cook or taste it. Cooking requires recipes as a tool to make dishes because not everyone knows how to make dishes. Food recipe search techniques with food image input are needed because not everyone knows the name of the food made. There are several steps in the method carried out to do the introduction of food types namely preprocessing, feature extraction using the Color Moments and Gray Level Counseling Matrix (GLCM) method, feature selection using the Information Gain method and classification using the Weighted K-Nearest Neighbor (NWKNN) method. Tests were carried out to determine the accuracy of the NWKNN method and also to know the effect of the Information Gain feature selection. The results of testing with the K-Fold Cross Validation method obtained the highest average accuracy of 92.37% by dividing the test data by 30, the number of features by 10, the value of k on the NWKNN by 3 and calculating distances using Cosine Similarity. On other hands, the testing of the Information Gain effect resulted in the highest accuracy of 86.96% with the 15 best features. It can be concluded that the NWKNN method can answer the problem of unbalanced data and Information Gain can find out the best features for classification.
Klasifikasi Hate Speech Berbahasa Indonesia di Twitter Menggunakan Naive Bayes dan Seleksi Fitur Information Gain dengan Normalisasi Kata Ivan Ivan; Yuita Arum Sari; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 5 (2019): Mei 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (910.465 KB)

Abstract

Hate speech is a form of expression that is done to eliminate hatred and commit acts of violence and oppose someone or a group of people for various reasons. The cases of hate speech are very often encountered on social media, one of which is on Twitter. The goal to be achieved is to create a system that can classify a tweet on Twitter into a class of hate speech (HS) or non hate speech (NONHS). The method used is Naive Bayes and Information Gain feature selection with word normalization. Word normalization is used to solve problems on Twitter such as the number of words abbreviated, the use of slang, misspellings, and the use of languages ​​that are not in accordance with existing standards.Word normalization comes from Indonesian Natural Language Processing REST API. The data used supports 250 data tweets of hate speech in Indonesian with a ratio of 80% for training data and 20% for testing data. The threshold used is 20%, 40%, 60%, 80%, and 90%. Threshold is a limit that is determined to store a collection of terms or a collection of words with the aim of selecting a word that has a high value ​​in the Information Gain feature selection. The best accuracy results obtained by using word normalization in the pre-processing stage and using Information Gain feature selection with an 80% threshold. The best accuracy result is 98%, precision result is 100%, recall result is 96.15%, and f-measure result is 98.03%. Based on the analysis of the results and testing obtained, it can be concluded when doing hate speech classifications in Indonesian on Twitter using Naive Bayes and Information Gain feature selection with word normalization can improve better accuracy of the results.
Co-Authors Achmad Arwan Achmad Dinda Basofi Sudirman Ade Kurniawan Adella Ayu Paramitha Adi Mashabbi Maksun Adinugroho, Sigit Agus Wahyu Widodo Ahmad Efriza Irsad Ahmad Fauzi Ahsani Akbar Imani Yudhaputra Akhmad Muzanni Safi'i Akhmad Rohim Akmilatul Maghfiroh Alip Setiawan Amalia Safitri Hidayati Amelia Kosasih Andina Dyanti Putri Anggita Mahardika Ani Enggarwati Arrizal Amin Barbara Sonya Hutagaol Bayu Rahayudi Berlian Bidari Ratna Sari B Binti Najibah Agus Ratri Budi Darma Setiawan Cahya Chaqiqi Candra Dewi Chindy Putri Beauty Dea Valentina Delischa Novia Sabilla Destin Eva Dila Purnama Sari Devinta Setyaningtyas Atmaja Dhimas Anjar Prabowo Dian Eka Ratnawati Dika Perdana Sinaga Dyva Agna Fauzan Edy Santoso Eka Dewi Lukmana Sari Eka Novita Shandra Fachrul Rozy Saputra Rangkuti Fadhil Yusuf Rahadika Fajar Pradana Fakhruddin Farid Irfani Faraz Dhia Alkadri Farid Rahmat Hartono Fatwa Reza Rizqika Febriana Ranta Lidya Fida Dwi Febriani Fira Sukmanisa Fitra Abdurrachman Bachtiar Fitria Indriani Frisma Yessy Nabella Gabriel Mulyawan Gagas Budi Waluyo Galuh Fadillah Grandis Gregorius Ivan Sebastian Hafid Satrio Priambodo Hamim Fathul Aziz Haris Bahtiar Asidik Ian Lord Perdana Ibnu Rasyid Wijayanto Imam Cholissodin Imam Cholissodin Inas Istiqlaliyyah Indriati Indriati Irma Pujadayanti Ivan Ivan Juniman Arief Karunia Ayuningsih Kenza Dwi Anggita Kresentia Verena Septiana Toy Kukuh Wiliam Mahardika Lita Handayani Tampubolon M. Ali Fauzi M. Ali Fauzi Mala Nurhidayati Marji Marji Moch Alyur Ridho Moch. Ali Fauzi Mohammad Rizky Hidayatullah Muh. Arif Rahman Muhammad Abdan Mulia Muhammad Bima Zehansyah Muhammad Faiz Al-Hadiid Muhammad Rizky Setiawan Muhammad Sanzabi Libianto Muhammad Tanzil Furqon Muhammad Zaini Rahman Nadhif Sanggara Fathullah Noerhayati Djumaah Manis Nova Amynarto Novan Dimas Pratama Novanto Yudistira Nugroho Dwi Saksono Nur Aisyah Asriani Ofi Eka Novyanti Panji Gemilang Panji Prasuci Saputra Pretty Natalia Hutapea Putra Pandu Adika Putra Pandu Adikara Putri Harnis Raditya Rinandyaswara Randy Cahya Wihandika Randy Ramadhan Rasif Nidaan Khofia Ahmadah Ratih Kartika Dewi Ratna Tri Utami Refi Fadholi Renaza Afidianti Nandini Rendi Cahya Wihandika Restu Amara Rezza Pratama Rhevitta Widyaning Palupi Rifki Akbar Siregar Rizky Ardiawan Rizky Maulana Iqbal Rosintan Fatwa Safira Dyah Karina San Sayidul Akdam Augusta Sarah Najla Adha Sarah Yuli Evangelista Simarmata Sigit Adi Nugroho Sigit Adinugroho Sinta Kusuma Wardani Sulaiman Triarjo Supraptoa Supraptoa Sutrisno Sutrisno Tibyani Tibyani Tri Rahayuni Tuahta Ramadhani Utaminingrum, Fitri Vriza Wahyu Saputra Wahyuni Lubis Willy Karunia Sandy Yosua Dwi Amerta