Claim Missing Document
Check
Articles

Temu Kembali Citra Makanan Menggunakan Ekstraksi Fitur Gray Level Co-occurrence Matrix dan CIE L*a*b* Color Moments Untuk Pencarian Resep Masakan Ahmad Fauzi Ahsani; 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 (726.903 KB)

Abstract

Recipes retrieval is an important thing in this technological era. Many people use search engine to find preferred food recipes. However, most people still use text query to search. Query text have many disadvantages, one of them is the lack of representation of food object because each person will be different in describing food. This problem can be solved if given query is an image of the food itself. This technique commonly referred as Content Based Image Retrieval. This study proposes image retrieval for cooking recipe searching using Gray Level Co-occurrence Matrix (GLCM) as a texture feature extraction method and CIE L*a*b* Color Moments as a color feature extraction method. The result of this study indicate that the MAP value is 97,604% when using combination of texture and color features, Minkowski distance algorithm and k = 10 with 1303 images of data training and 31 images of data testing. Based on these results, it can be concluded that GLCM and CIE L*a*b* color moments can be used on food image retrieval for searching cooking recipes.
Peringkasan Teks Untuk Deteksi Kejadian Pada Dokumen Twitter Berbahasa Indonesia Dengan Metode Affinity Propagation Rezky Dermawan; Fitra A. Bachtiar; 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 (631.23 KB)

Abstract

Twitter is on of many social medias where the user often tell about events that are happenings around them, ranging from insignificant to important things. Twitter's qualities where the user could make a tweet anywhere in a brief time frame, make it feasible for critical information to appear before the media even report it. However, it is difficult to comprehend what relevant events are occuring in a specific region because of the sheer size of scale and diverse sort of tweets. Accordingly, there is a need of a framework that could do pertinent event detection and give a summary about that event. In light of the reason expressed over, this research center around text summarization for event detection of Indonesian Twitter archive utilizing Affinity Propagation. Through the process of clustering, the resulting clusters become the representation of events occuring in a specific place and time period. Two kinds of data are used for assessment, first is themathic which has spesific kind of event happening in the time frame of the tweet and second is generic where the tweet are taken from an arbitary time frame. In order to get the best resulting cluster, parametesr of Affinity Propagation are evaluated reuslting in preference of quartile 3 dan minimum, damping factor of 0,3 and 0,5, changed limit of 1 and 2, iteration maximum of 250 as the best parameters for the thematic and generic data. The result of tweet summary from the clustering process are then compared with a specialist's summary to be evaluated by ROGUE-N method, scoring 0,459 and 0,4009 respectively on two kinds of data.
Implementasi Algoritme Extreme Learning Machine (ELM) Untuk Prediksi Harga Emas Bagi Investor Laila Restu Setiya Wati; Imam Cholissodin; 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 (1006.244 KB)

Abstract

There are a variety of investing one is gold. Plain gold made into a long-term investment, since the benefits of investing in gold is easily exchanged, no taxes and investing in gold because it has properties that are resistant to inflation. The nature of the resistance it that make interested investors to invest. Tough investors get information mengenahi changes up and down the gold price with the issue so that investors desperately need information for predictions as a consideration of when to buy and sell gold in order to get the profit in accordance with the perancanaan that have been made. This research uses algorithms Extreme Learning Machine (ELM) for predicting the price of gold. Testing in predicting model algorithms so that the gold price to ELM produce gold price predictions with optimal. Test analysis results by using the best of previous testing variables produce the Mean Absolute Percentage Error (MAPE) of 0.29%, best of MAPE generated less than 10% indicates that Extreme Learning Machine (algorithms ELM) good to be implemented in doing the predictions of the gold price.
Analisis Sentimen Pada Ulasan Aplikasi BCA Mobile Menggunakan BM25 Dan Improved K-Nearest Neighbor Indriya Dewi Onantya; Indriati Indriati; 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 (768.962 KB)

Abstract

Mobile banking application is one of the applications that can provide convenience in human activities. One of these applications is BCA Mobile. This application makes users easily to do financial activities without having to go to the relevant bank. This is an option that is very useful for users who have a busy life in their daily lives. From existing mobile applications, there are no features that can be used to group or filter positive and negative reviews. To find out reviews that are classified as positive or negative reviews, a sentiment analysis review is needed. The analysis process begins with pre-processing data, weighing words using the BM25 algorithm, and the process of classification using Improved K-Nearest Neighbor. The results obtained based on the result of 5-fold cross-validation and get the best k-value at 10, with the result of precision value are 0.946, recall value is 0.934, f-measure value is 0.939, and an accuracy is 0.942. These results get fluctuating measurement results because of the amount of k-value. However, it does not influence by the amount classes of data, because even though there are different amounts or proportions of data classes, the new k-value adjust to the amount of data based on the value of each class.
Pencarian Berita Berbahasa Indonesia Menggunakan Metode BM25 Khalisma Frinta; Indriati Indriati; 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 (881.297 KB)

Abstract

Rapid technological developments have resulted in increased use of the internet as a source of online information providers from around the world. Users use a search engine for searching information. These developments also make digital document storage increase. News is a source of information about an event or opinion that has important and interesting value to be widely publicized through the mass media. The unlimited reach of readers and the efficiency of time makes the various media reports turn to online media. Information retrieval aims to produce documents that are relevant to the needs of users of a collection of information automatically based on keywords in the queries given by users. The application of information retrieval is expected to facilitate information retrieval and obtain accurate results. BM25 is a system in the ranking process that is used to sort the results of a match (similarity) to all training documents based on the query. The BM25 method is categorized as the best method in the best match class. Tests are based on precision @k values ​​and r-precision values ​​for 12 queries. The best test results for precision @k values ​​when k=5, which is 0.83. While the best results for r-precision values ​​are 1.
Analisis Sentimen Tentang Kebijakan Ganjil Genap Kendaraan Bermotor di DKI Jakarta Pada Twitter Menggunakan BM25 dan K-Nearest Neighbor Dwi Suci Ariska Yanti; Indriati Indriati; 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 (927.915 KB)

Abstract

Traffic congestion occurs in many places throughout Indonesia, especially in its capital region of Jakarta. Many strategies have been executed by the government of the capital region as a mean to solve the ongoing traffic congestion problem, one of them is the 'odd-even' policy. On the other note, the problem has inflicted a wide social media complains among Jakarta's residents. In this case, Twitter is considered as a relatively fast and effective social media platform to post opinions used by many Indonesians. Considering its large number of users and easy access to public's opinions, Twitter will have a lot of public's opinions' data which can be used as a material to evaluate the 'odd-even' policy in the capital region of Jakarta. Therefore a method which can separate sentiment from user is needed. It's to answer whether the sentiment is categorized as positive or negative class. In this study, the researcher used BM25 method and K-Nearest Neighbor (KNN) as classifiers. The best test results for f-measure values are 66,1% while the results of accuracy is 66,5%.
Klasifikasi Dokumen Abstrak Skripsi Berdasarkan Fokus Penelitian di Bidang Komputasi Cerdas Menggunakan BM25 dan K-Nearest Neighbor Deri Hendra Binawan; Indriati Indriati; 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 (729.723 KB)

Abstract

One of the process that can be implemented in text mining is categorizing text documents. Problems that related the categorizing text documents are found in universities, especially in the reading room of the Faculty of Computer Science, Universitas Brawijaya (FILKOM UB). There is no process for categorizing thesis documents automatically is one of the problem. The thesis documents categorization in FILKOM UB's reading room is still not organized according to the focus of the existing research. The categorization is completed using the BM25 and K-Nearest Neighbor methods. The process was done is pre-processing text document, calculate the BM25 score of each document, then classify them using the K-Nearest Neighbor algorithm. The testing process in this research uses 10 k-fold. Each test used 31 testing documents and 300 training documents. The average results obtained in each test produced the best results at the value of k=11 with a f-measure value is 0.9092, recall is 0.9087, and precision is 0.9265. The greater the value of k cause the classification process runs less optimally because it produces a smaller f-measure value.
Analisis Sentimen Pembangunan Infrastruktur di Indonesia dengan Automated Lexicon Word2Vec dan Naive-Bayes Ananda Fitri Niasita; Putra Pandu Adikara; Sigit Adinugroho
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 (928.892 KB)

Abstract

Infrastructure development is a project that being intensively carried out by the current government. With the existence of good infrastructure, the government hopes that in the future the economy and the level of Indonesian welfare will increase. Infrastructure development attracts the community attention. Various comments regarding this project were mentioned through social media, for example Twitter. The number of pros and cons community comparisons known by using sentiment analysis. In this case, sentiment analysis uses a lexicon dictionary to determine whether the data is positive or negative. The lexicon dictionary created automatically using the Word2Vec method. Word2Vec method is used to find closeness between words.. Then, the sentiment class is determine using the Naive-Bayes method. This study uses 100 training data and 50 testing data divided into positive and negative sentiments. The highest accuracy value are 64% with precision of 0.36, re-call of 0.818 and f-measure of 0.5.
Analisis Sentimen Tentang Opini Maskapai Penerbangan pada Dokumen Twitter Menggunakan Algoritme Support Vector Machine (SVM) Arsya Monica Pravina; Imam Cholisoddin; 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 (515.883 KB)

Abstract

With the increasing use of Twitter, social media that works in real-time for the public can convey complaints and appreciation to airlines, it is necessary to create a system that can classify a tweet containing opinions including what is the best class, in this study there are positive and negative classes. This is done so that it can help airline companies in terms of evaluating service improvements and can help people choose the right airline. Thus a sentiment classification with Lexicon Based features which is able to receive information in languages other than Indonesian (in this study used in English) is done to conduct sentiment analysis. Use the support vector machine algorithm to classify. The results of this study show optimal parameters and the effect of using Lexicon Based Features. By using parameter C is 10 and the learning rate is 0.03 also used Lexicon Based Features with an iteration of 50 times giving accuracy 40%, precision 40%, recall 100%, and f-measure 57,14%.
Klasifikasi Citra Makanan Menggunakan K-Nearest Neighbor dengan Fitur Bentuk Simple Morphological Shape Descriptors dan Fitur Warna Grayscale Histogram Muhammad Rizky Setiawan; 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 (977.579 KB)

Abstract

Food is one of the energy sources needed by humans. The type of food consumed greatly affect the immune system. But the diversity of existing food causes people to be difficult to recognize the type of food they want to consume. The need for a system that can recognize types of food to make it easier for people to regulate their diet. Before entering the feature extraction process, the first step is to do preprocessing by separating the background from the food image object. Furthermore, color feature extraction is performed using the Grayscale Histogram method. The Grayscale Histogram method produces the mean, standard deviation, skewness features. Then form feature extraction was performed using the Simple Morphological Shape Descriptors (SMSD) method and produced area features, length, width, aspect ratio, rectangular N. After extracting feature results, classification was done using the K-Nearest Neighbor method. Based on the test results if only using the Grayscale Histogram method produces an accuracy value of 60%. If only using the SMSD method produces an accuracy value of 54.8%. If using the Grayscale Histogram method and the SMSD method produces an accuracy value of 77.8%. The Grayscale Histogram method and the SMSD method can be used to process images using the K-Nearest Neighbor classification method.
Co-Authors Adani, Rafi Malik Ade Kurniawan Adinda Chilliya Basuki Adinugroho, Sigit Adiyasa, Bhisma Adriansyah, Rachmat Afrizal Rivaldi Agi Putra Kharisma, Agi Putra Agus Wahyu Widodo Ahmad Fauzi Ahsani Akhmad Sa'rony Al Farisi, Faiz Aulia Al Huda, Fais Albert Bill Alroy Alimah Nur Laili Allysa Apsarini Shafhah Alqis Rausanfita Alvandi Fadhil Sabily Amaliah, Ichlasuning Diah Amar Ikhbat Nurulrachman Ananda Fitri Niasita Anang Hanafi Andina Dyanti Putri Andre Rino Prasetyo Anggraheni, Hanna Shafira Ani Budi Astuti Annisa Alifia Annisa, Zahra Asma Arsya Monica Pravina Aulia Jasmin Safira Aulia Rahma Hidayat Avisena Abdillah Alwi Azhar, Naziha Baliyamalkan, Mohammad Nafi' Barbara Sonya Hutagaol Bayu Andika Paripih Bayu Rahayudi Bryan Pratama Jocom Budi Darma Budi Darma Setiawan Candra Dewi Candra Dewi Dahnial Syauqy Daisy Kurniawaty Danang Aditya Wicaksana Dayinta Warih Wulandari Deri Hendra Binawan Dhanika Jeihan Aguinta Dheby Tata Artha Dian Eka Ratnawati Dika Perdana Sinaga Dimas Fachrurrozi Azam Dwi Suci Ariska Yanti Dwi Wahyu Puji Lestari Dyva Pandhu Adwandha Edy Santosa Eka Dewi Lukmana Sari Elmira Faustina Achmal Evilia Nur Harsanti Faiz Aulia Al Farisi Farid Rahmat Hartono Fattah, Rafi Indra Fayza Sakina Maghfira Darmawan Febriarta, Renaldy Dwisma Ferdi Alvianda Ferly Gunawan Ferly Gunawan Firdaus, Agung Firmansyah, Ilham Fitra Abdurrachman Bachtiar Franklid Gunawan Galih Nuring Bagaskoro George Alexander Suwito Gilang Widianto Aldiansyah Glenn Jonathan Satria Guedho Augnifico Mahardika Haekal, Firhan Imam Hanson Siagian Hendra Pratama Budianto Hernawan, Yurdha Fadhila Hibatullah, Farras Husain Husein Abdulbar Ichsan Achmad Fauzi Ika Oktaviandita Imam Cholisoddin Imam Cholissodin Imam Ghozali Imanuel Juventius Todo Gurning Indah Mutia Ayudita Indriati Indriati Indriati Indriya Dewi Onantya Ivan Fadilla Ivan Ivan Jesika Silviana Situmorang Jojor Jennifer BR Sianipar Jonathan Reynaldo Junda Alfiah Zulqornain Karina Widyawati Karunia Ayuningsih Katherine Ivana Ruslim Khalisma Frinta Krishnanti Dewi Laila Restu Setiya Wati Lailil Muflikhah Laksono Trisnantoro Lubis, Saiful Wardi Lusiyana Adetia Isadi Luthfi Mahendra M. Aasya Aldin Islamy M. Ali Fauzi Maghfiroh, Sofita Hidayatul Makrina Christy Ariestyani Marina Debora Rindengan Maya Novita Putri Riyanto Mayang Arinda Yudantiar Mayang Panca Rini Melati Ayuning Lestari Moch. Khabibul Karim Moh. Dafa Wardana Mohammad Fahmi Ilmi Mohammad Toriq Muh. Arif Rahman Muhammad Faiz Al-Hadiid Muhammad Fajriansyah Muhammad Iqbal Pratama Muhammad Nurhuda Rusardi Muhammad Rizaldi Muhammad Rizky Setiawan Muhammad Tanzil Furqon Muhammad Taufan Muthia Azzahra Nadhif Sanggara Fathullah Nadia Siburian Nanda Agung Putra Nanda Cahyo Wirawan Naufal Akbar Eginda Naziha Azhar Niluh Putu Vania Dyah Saraswati Novan Dimas Pratama Novanto Yudistira Nur Hijriani Ayuning Sari Nurul Hidayat Panjaitan, Mutiharis Dauber Panji Husni Padhila Pengkuh Aditya Prana Prais Sarah Kayaningtias Prakoso, Andriko Fajar Pretty Natalia Hutapea Putri Rahma Iriani Radita Noer Pratiwi Rahma Chairunnisa Raissa Arniantya Randy Cahya Wihandika Randy Cahya Wihandika Randy Ramadhan Ravindra Rahman, Azka Renata Rizki Rafi` Athallah Renaza Afidianti Nandini Restu Amara Rezky Dermawan Rhevitta Widyaning Palupi Ridho Agung Gumelar Riza Cahyani Rizal Maulana, Rizal Rizal Setya Perdana Rizal Setya Perdana Rosy Indah Permatasari Sagala, Revaldo Gemino Kantana Salsabila Insani Salsabila Rahma Yustihan San Sayidul Akdam Augusta Santoso, Nurudin Sigit Adinugroho Sigit Adinugroho Silaban, Gilbert Samuel Nicholas Silvia Ikmalia Fernanda Sindy Erika Br Ginting Sri Indrayani, Sri Sutrisno Sutrisno Tania Malik Iryana Taufan Nugraha Thariq Muhammad Firdausy Tibyani Tibyani Tirana Noor Fatyanosa, Tirana Noor Uke Rahma Hidayah Utaminingrum, Fitri Vergy Ayu Kusumadewi Vinesia Yolanda Vivin Vidia Nurdiansyah Wijanarko, Rizqi Yerry Anggoro Yohana Yunita Putri Yoseansi Mantharora Siahaan Yosua Dwi Amerta Yuita Arum Sari Yuita Arum Sari Yuita Arum Sari Yulia Kurniawati Yurdha Fadhila Hernawan Yure Firdaus Arifin Zahra Asma Annisa