Jurnal Teknologi Informasi dan Ilmu Komputer最新文献

{"title":"Klasifikasi Tenun Timor Menggunakan Metode SVM Berdasarkan Speeded Up Robust Features","authors":"Y. Kelen, Budiman Baso","doi":"10.25126/jtiik.1067625","DOIUrl":"https://doi.org/10.25126/jtiik.1067625","url":null,"abstract":"Penelitian ini dilakukan sebagai upaya untuk melestarikan kain tenun Timor di bidang teknologi informasi, kususnya bidang pengolahan citra digital, yaitu pengenalan pola yang merupakan solusi untuk mengenali citra tenun secara otomatis. Dalam penelitian ini, klasifikasi citra tenun Timor mengaplikasikan metode SURF (Speeded Up Robust Feature) sebagai ekstraksi fitur dengan representasi BoVW (Bag of Visual Words) sedangkan SVM (Support Vector Machine) digunakan sebagai metode classifier. Agar kinerja BoVW lebih baik, digunakan pendekatan untuk menentukan jumlah cluster yang tepat untuk mengelompokkan pola visual words. Penentuan parameter algoritma klasifikasi SVM dilakukan adalah kernel dan metode multi class SVM yang digunakan. Data citra tenun Timor digunakan sebanyak 420 dengan 7 kelas motif citra akan dibagi menjadi data latih dan data uji menggunakan 5-fold cross validation. Berdasarkan hasil percobaan yang dilakukan, diperoleh hasil yang berbeda pada pengujian nilai cluster dan parameter SVM yang digunakan. Pada visual words dengan nilai cluster 500 dengan algoritma klasifikasi multi class SVM yaitu metode OVO (One Versus All) menggunakan kernel linear memperoleh hasil terbaik pada penelitian ini dengan tigkat Accuracy mencapai 98,10%. Dari hasil penelitian ini didapatkan metode untuk klasifikasi citra motif tenun Timor yang lebih akurat.   Abstract This research was conducted as an effort to preserve Timor woven fabrics in the field of information technology, especially in the field of digital image processing, namely pattern recognition which is a solution to recognize weaving images automatically. In this study, the classification of Timorese woven images applies the SURF (Speeded Up Robust Feature) method as feature extraction with BoVW (Bag of Visual Words) representation while SVM (Support Vector Machine) is used as a classifier method. For better BoVW performance, an approach is used to determine the right number of clusters to group visual words patterns. Parameters for the SVM classification algorithm are determined using the kernel and the SVM multi-class method used. 420 Timorese weaving image data are used with 7 classes of image motifs which will be divided into training data and test data using 5-fold cross validation. Based on the results of the experiments conducted, different results were obtained in testing the cluster values and SVM parameters used. In visual words with a cluster value of 500 with the SVM multi-class classification algorithm, namely the OVO (One Versus All) method using a linear kernel, the best results were obtained in this study with an accuracy level of 98.10%. From the results of this study, a more accurate method for classifying images of Timorese woven motifs was obtained.%.","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":" 17","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139139957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Penerapan Metode Extreme Programming pada Rancang Bangun Sistem Analisis Sentimen Portal Berita","authors":"Gede Bagus, Premana Putra, M. Sudarma, I. Bagus, Gede Manuaba","doi":"10.25126/jtiik.20231056904","DOIUrl":"https://doi.org/10.25126/jtiik.20231056904","url":null,"abstract":"Berita dalam bentuk portal online di era globalisasi menjadi suatu wadah yang dapat digunakan oleh setiap individu untuk menyampaikan informasi tentang seorang individu ataupun organisasi, yang didalamnya terdapat penyampaian nilai emosional pribadi, baik itu bersifat negatif, netral, ataupun positif (atau lebih dikenal dengan sentimen). Keberadaan berita tersebut menciptakan suatu peluang untuk pengembangan sistem analisis sentimen terdapat informasi yang telah disampaikan dalam portal berita. Sistem analisis sentimen tersebut dapat dikembangan dengan dengan berbagai teknik dan layanan, salah satunya adalah dengan mengintegrasikan antara sistem dan layanan Google NLP, yang telah memiliki service untuk menentukan score sentimen dari setiap kalimat yang diberikan, serta penerapan teknik web scrapping sebagai metode untuk pengambilan data. Sistem dikembangan dengan framework Laravel dengan metode pengembangan Extreme Programming yang mendukung pengembangan sistem dalam waktu singkat. Pemilihan website sebagai base sistem dengan tujuan agar sistem bisa diakses dari berbagai device baik itu mobile maupun desktop. Keberadaan sistem analisis sentimen bisa dijadikan sebagai alternatif solusi bagi individu dan organisasi untuk melakukan analisis sentimen, sehingga mampu membantu dalam proses pengambilan keputusan maupun evaluasi kinerja.   Abstract News of online portals in the era of globalization has become a forum can be used by every individual to convey information about individual or organization, in which there’s the delivery of personal emotional value, negative, neutral or positive (or better known as sentiment). The existence of news creates an opportunity for development of a sentiment analysis system based on information that has been submitted in the news portal. The sentiment analysis system can be developed using various techniques and services, one of which’s by integrating the Google NLP system and service, which already has a service to determine the sentiment score of each given sentence, as well as the application of a web scrapping techniques as a method for data collection. The system was developed using the Laravel framework with the Extreme Programming development method which supports system development in short time. Selection of the website as the base system with aim that can be accessed from various devices, both mobile and desktop. The existence of a sentiment analysis system can be used as an alternative solution for individuals and organizations to carry out sentiment analysis, so that it can assist in the decision-making a process and performance evaluation.","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":" 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139139262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inovasi Rancangan Aplikasi Gizi Nutrief dalam Optimalisasi Asupan Gizi Menggunakan Pendekatan Design Thinking","authors":"Irsa Ainun Nisa Sofia Nur Rohma Faiza, Herman Tolle, Dwi Cahya Astriya Nugraha","doi":"10.25126/jtiik.1078020","DOIUrl":"https://doi.org/10.25126/jtiik.1078020","url":null,"abstract":"Pola makan yang tidak sehat berpotensi menyebabkan gangguan gizi, seperti status gizi lebih atau status gizi kurang. Maka, penting mangatur dan memantau pola makan sehat sehingga memperoleh asupan gizi seimbang. Namun, kesulitan yang dialami oleh masyarakat dalam memahami status gizi dan mengontrol pola makan. Maka, dibutuhkan suatu aplikasi yang dapat membantu dalam memantau asupan kalori, memantau jumlah asupan makanan sesuai kebutuhan, serta aplikasi yang menyediakan layanan untuk konsultasi dengan ahli gizi. Metode yang digunakan dalam perancangan aplikasi yaitu, design thinking. Metode design thinking dipilih dibandingkan metode lain seperti user-centered design ataupun human-centered design karena metode tersebut berfokus pada perspektif pengguna akhir. Sedangkan, metode design thinking fokus pada pendekatan berdasarkan empati terhadap pengguna dan dapat menemukan solusi inovatif. Hasil pengujian usability pada aspek efektivitas oleh pengguna teregistrasi sebesar 97,78%, dan ahli gizi sebesar 95,7%. Pada aspek efisiensi memperoleh hasil 0,049 goals/sec. Kemudian, aspek kepuasan dengan menggunakan kuesioner System Usability Scale (SUS) memperoleh hasil 79,5 oleh pengguna teregistasi, dan 89 oleh ahli gizi. Hasil pengujian user experience menggunakan user experience questionnaire (UEQ) memperoleh hasil 2,65 pada aspek daya tarik, 2,60 pada aspek kejelasan, 2,58 pada aspek efisiensi, 2,50 pada aspek ketepatan, 1,30 pada aspek stimulasi, dan 2,43 pada aspek kebaruan. Semua aspek mendapatkan hasil exellent, kecuali satu aspek, yaitu aspek stimulasi mendapatkan hasil above average.   Abstract Unhealthy eating habit can result in nutritional disorders, such us overweight, or malnutrition. So, it is important to manage and monitor a healthy eating habit so get a balanced nutrition intake. However, the difficulties experienced by the community in understanding nutrition status and controlling eating habit. So, an application is needed that can help monitor calorie intake, monitor the amount of food intake as needed, as well as an application that provides services for consulting with a nutritionist. The method used in application design is design thinking. The design thinking method was chosen over other methods such as user-centered design or human-centered design because these methods focus on the end-user perspective.  Meanwhile, the design thinking method focuses on an empathy-based approach to users and being able to find innovative solutions. The results of usability testing on the effectiveness aspect by registered users were 97.78%, and nutritionists were 95.7%. On the efficiency aspect, the result is 0.049 goals/sec. Then, aspects of satisfaction using the System Usability Scale (SUS) questionnaire obtained 79.5 for registered users, and 89 for nutritionists. The results of user experience testing using the user experience questionnaire (UEQ) obtained 2.65 on the attractiveness aspect, 2.60 on the clarity aspect, 2.58 on the efficiency aspe","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":" 19","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139138684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluasi User Experience Aplikasi “J-KOPI (Jember Kota Pintar)” Menggunakan Metode Survei Dengan User Experience Questionnaire Dan User Interview","authors":"Pradiptya Kahvi Sugiharto, S. Wijoyo, M. C. Saputra","doi":"10.25126/jtiik.1067430","DOIUrl":"https://doi.org/10.25126/jtiik.1067430","url":null,"abstract":"Aplikasi J-KOPI (Jember Kota Pintar) merupakan aplikasi yang dikembangkan oleh DISKOMINFO Pemkab Jember. Aplikasi J-KOPI bertujuan untuk menjadi “SuperApps” yang menyediakan beragam informasi dan berbagai layanan masyarakat yang terintegrasi dengan OPD (Organisasi Perangkat Daerah) dari Pemerintah Daerah Kabupaten Jember dalam satu aplikasi. Berdasarkan hasil observasi dan hasil wawancara dengan DISKOMINFO, ditemukan bahwa terdapat beberapa permasalahan yang terdapat pada aplikasi sehingga dapat menurunkan kualitas pengalaman pengguna. Penelitian ini bertujuan untuk melakukan evaluasi pengalaman pengguna pada aplikasi J-KOPI untuk memperbaiki masalah yang berkaitan dengan user experience dan memperbaiki aspek-aspek yang perlu ditingkatkan. Evaluasi ini menggunakan metode UEQ (“User Experience Questionnaire”) untuk mengukur level pengalaman pengguna pada aplikasi dan User Interview untuk menemukan masalah yang lebih detail. Evaluasi awal dengan 30 responden yang terdiri dari mahasiswa, masyarakat umum dan OPD menunjukkan bahwa aplikasi J-KOPI memiliki level user experience yang netral dan kategori UEQ benchmark yang “Dibawah rata-rata”. Selain itu, ditemukan 4 topik permasalahan yang terdiri dari 11 poin permasalahan. Berdasarkan permasalahan tersebut, dilakukan perancangan rekomendasi perbaikan yang dilanjutkan dengan pengujian ulang. Hasil perbaikan menunjukkan bahwa berhasil meningkatkan pengalaman pengguna terhadap seluruh aspek pada kuesioner UEQ dan peningkatan pengalaman pengguna pada benchmark UEQ untuk skala Attractiveness dan Stimulation mencapai kategori “sangat baik”. Sementara skala Perspicuity, Efficiency, Dependability dan Novelty mencapai kategori “baik”.   Abstract The J-KOPI (Jember SmartCity) application is developed by the DISKOMINFO Jember Regency Government. The J-KOPI application aims to become \"SuperApps\" that provides a variety of information and various community services integrated with the OPD (local government agency) of the Jember Regency Regional Government in one application. Based on observations and interviews with DISKOMINFO, it was found that there were several problems with the application that could reduce the quality of the user experience. This research aims to evaluate the user experience on the J-KOPI application to improve problems related to user experience and improve aspects that need to be improved. This evaluation uses the UEQ (\"User Experience Questionnaire\") method to measure the level of user experience in the application and User Interviews to find more detailed problems. Initial evaluation with 30 respondents consisting of students, the general public and OPD showed that the J-KOPI application had a neutral user experience level and the UEQ benchmark category was \"Below average\". In addition, 4 problem topics were found which consisted of 11 problem points. Based on these problems, recommendations for improvement were designed, followed by retesting. The improvement results show that it has suc","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":" 22","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139139883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deteksi Land Surface Temperature Menggunakan Citra Landsat: Studi Kasus Kota Jababeka dan Sekitarnya","authors":"A. Zaky, Suhendra Suhendra, M. A. Arwin","doi":"10.25126/jtiik.1078013","DOIUrl":"https://doi.org/10.25126/jtiik.1078013","url":null,"abstract":"Land Surface Temperature (LST) merupakan salah satu parameter yang dapat digunakan untuk melihat dampak perubahan iklim dan lingkungan akibat perubahan tutupan dan alih fungsi lahan.  Studi kasus dilakukan di Kota Jababeka dan sekitarnya sebagai Area Of Interest (AOI) untuk mendapatkan informasi pola distribusi LST secara spasial dan temporal. Dalam kajian ini LST didapatkan dengan memanfaatkan dan mengolah thermal band pada citra Landsat multi temporal. Land Surface Emisivity (LSE) diturunkan dari NDVI (Normalized Difference Vegetation Index) dan proporsi vegetasi (PV). Nilai LSE digunakan sebagai salah satu parameter untuk menghitung LST dari citra Landsat.  Hasil kajian didapatkan bahwa kenaikan nilai rata-rata LST sebesar 3.03 ºC antara tahun 1990 dengan tahun 2000, dan terjadi penurunan nilai rata-rata LST berturut-turut pada interval periode selanjutnya yaitu sebesar 2.39 ºC antara tahun 2000 dengan tahun 2010 dan sebesar 0.54 ºC antara tahun 2010 dengan tahun 2020. Kondisi ini dipicu oleh adanya kenaikan luasan atas kerapatan vegetasi sekitar 24% dari luas daerah penelitian sepanjang periode kajian yang diketahui berdasarkan distribusi spasial NDVI dan LSE. Hasil kajian ini diharapkan dapat menjadi pertimbangan dalam pengambilan keputusan dan menentukan arah kebijakan pengelolaan dan pengembangan Kota Jababeka dan sekitarnya di masa yang akan datang.   Abstract Land Surface Temperature (LST) is one of parameters used to assess the impacts of climate and environmental changes resulting from changes in land cover and land use conversion. A case study was conducted in Kota Jababeka and its surrounding region as the Area Of Interest (AOI) to obtain information on the spatial and temporal distribution patterns of LST. In this study, LST was obtained by utilizing and processing the thermal band of Landsat multi-temporal images. Land Surface Emissivity (LSE) was derived from NDVI (Normalized Vegetation Index) and proportion of vegetation (PV). LSE value is used as one of parameter to calculate LST obtained from Landsat imagery. The study's findings revealed that the average LST increased by 3.03 ºC between 1990 and 2000, and subsequently, there were consecutive decreases in the average LST during the following time intervals: 2.39 ºC between 2000 and 2010 and 0.54 ºC between 2010 and 2020. These changes were triggered by an increase in vegetation cover of about 24% in the study area throughout the research period, as observed from the spatial distribution of NDVI and LSE. The results of this study are expected to be considered in decision-making and determining the direction of management and development in Kota Jababeka and its surrounding areas in the future.","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":" 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139144486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Klasifikasi Tingkat Stress dari Data Berbentuk Teks dengan Menggunakan Algoritma Support Vector Machine (SVM) dan Random Forest","authors":"Naufal Fathirachman Mahing, Alifi Lazuardi Gunawan, Ahmad Foresta Azhar Zen, Fitra Abdurrachman Bachtiar, Satrio Agung Wicaksono","doi":"10.25126/jtiik.1078010","DOIUrl":"https://doi.org/10.25126/jtiik.1078010","url":null,"abstract":"Stres merupakan keadaan dimana seseorang merasakan adanya tekanan yang berlebih pada dirinya. Pemantauan tingkat stres menjadi hal yang penting bagi manusia. Tingkat stres yang tinggi dapat menimbulkan dampak negatif terhadap kesehatan manusia. Deteksi dini stres menjadi sesuatu yang sangat penting untuk dilakukan. Salah satu cara mengetahui tingkat stres seseorang adalah melalui analisis teks. Penelitian ini dilakukan untuk melakukan klasifikasi tingkat stres berdasarkan data berupa teks menggunakan algoritma Support Vector Machine (SVM) dan Random Forest. Pada penelitian ini melakukan perbandingan beberapa metode transformasi. Transformasi yang dilakukan pada penelitian ini menggunakan TF-IDF, CountVectorizer, NRCLex, dan Word Affect Intensities. Data yang digunakan dalam penelitian ini berupa sebuat teks berbahasa Inggris yang diambil dari media sosial Twitter. Total data yang digunakan yaitu 8439 data. Pelatihan model baik untuk Support Vector Machine dan Random Forest menggunakan 6751 data. Sedangkan untuk pengujian menggunakan 1688 data. Hasil penelitian menunjukkan bahwa algoritma SVM dengan pembobotan menggunakan TF-IDF memiliki performa yang paling baik dibandingkan dengan algoritma Random Forest dan metode transformasi lainnya yang digunakan dalam penelitian. Model algoritma SVM dengan transformasi TF-IDF yang dibangun berhasil mendapatkan akurasi sebesar 84%. Model ini mendapatkan akurasi yang lebih tinggi dibanding model Random Forest yang memperoleh akurasi tinggi sebesar 80% dengan menggunakan transformasi CountVectorizer.   Abstract Stress is a condition where a person feels excessive pressure on himself. Monitoring stress levels is important for humans. High levels of stress can have a negative impact on human health. Early detection of stress is something that is very important to do. One way to find out someone's stress level is through text analysis.This research was conducted to classify stress levels based on text data using the Support Vector Machine (SVM) and Random Forest algorithms. This research compares several transformation methods. The transformation performed in this study uses TF-IDF, CountVectorizer, NRCLex, and Word Affect Intensities. The data used in this research is an English text taken from Twitter social media. The total data used is 8439 data. Model training for both Support Vector Machine and Random Forest uses 6751 data. While for testing using 1688 data. The results showed that the SVM algorithm with weighting using TF-IDF had the best performance compared to the Random Forest algorithm and other transformation methods used in the study. The SVM algorithm model with TF-IDF transformation that was built managed to get an accuracy of 84%. This model obtained a higher accuracy than the Random Forest model which obtained a high accuracy of 80% using the CountVectorizer transformation.","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":"4 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139147171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Arsitektur Sistem Percakapan Otomatis Berbahasa Indonesia dengan Normalisasi Bahasa Informal Menjadi Baku","authors":"Muhammad Fathur Rahman Khairul, R. Perdana","doi":"10.25126/jtiik.1077984","DOIUrl":"https://doi.org/10.25126/jtiik.1077984","url":null,"abstract":"Komunikasi merupakan hal yang paling penting dalam kehidupan sehari-hari. Setiap orang berkomunikasi dengan cara mereka berdasarkan latar belakang serta kedekatan antar pembicara. Oleh karena itu, perkembangan bahasa informal terjadi sangat cepat dan tidak jarang menciptakan kata-kata baru sebagai pengganti bahasa formal. Hal ini menjadi masalah jika dilihat dari perspektif pemrosesan bahasa alami (NLP). NLP umumnya hanya dapat dilakukan dengan bahasa yang formal dan tidak mampu menginterpretasikan makna dari kalimat informal. Maka dari itu, penulis mengusulkan pendekatan untuk memungkinkan mesin memahami bahasa informal dengan melakukan normalisasi bahasa infomal menjadi baku dengan memanfaatkan NLP. Pendekatan yang dilakukan akan melatih model pre-trained GPT-2 berbahasa Indonesia dengan data parallel corpus untuk memahami makna dari bahasa informal dan mampu menerjemahkannya ke dalam bentuk baku. Melalui eksperimen yang dilakukan, pendekatan ini mencapai tingkat akurasi 91% dan dapat menerjemahkan bahasa informal dengan baik. Performa ini dapat diraih dengan konfigurasi hiperparameter yaitu Adam optimizer dengan learning rate 1e-4, batch size sebesar 16 dan dropout rate sebesar 0,5.   Abstract   Communication is the most essential thing in daily life. Everyone communicates in their own way based on their background and the closeness between speakers. Thus, the development of informal language occurs quickly and it is often to create new words as a substitute for formal language. This is an issue from a natural language processing (NLP) perspective. NLP generally only works with formal language and is unable to interpret the meaning of informal sentences. Therefore, the authors propose an approach to enable machines to understand informal language by normalizing the informal language to standard by utilizing NLP. The approach will train a pre-trained GPT-2 model in Indonesian with parallel corpus data to understand the meaning of informal language and be able to translate it into standardized form. Through experiments, the method achieved 91% accuracy and can translate informal language well. This performance can be achieved with a hyperparameter configuration, namely Adam optimizer with a learning rate of 1e-4, batch size of 16 and dropout rate of 0.5.","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":" 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139143362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pengembangan Aplikasi Mobile Pengisian Daya Kendaraan Listrik Sesuai Standar OCPP 1.6","authors":"Rachmawan Atmaji Perdana, M. N. Hindratno, Tanzi M. Santoso, Topan Try Harmanda, Friyogi Resvy Mahda, Yahya Andreas Lapian, Monica Dwi W. S., Dionysius Aldion Renata, P. Aji, Meidy Layooari, Kusnanda Supriatna, Rully Kusumajaya, M. Hamdani","doi":"10.25126/jtiik.20231056647","DOIUrl":"https://doi.org/10.25126/jtiik.20231056647","url":null,"abstract":"Makalah ini membahas tentang pengembangan aplikasi mobile untuk pengisian daya kendaraan listrik, yang diberi nama SONIKApp. SONIKApp digunakan untuk melakukan reservasi dan pengendalian pengisian daya secara remote. Fitur reservasi diperlukan mengingat pengisian daya baterai kendaraan listrik membutuhkan waktu tunggu serta masih terbatasnya stasiun pengisian kendaraan listrik umum (SPKLU) di Indonesia. Fitur pengisian daya berbasis remote juga merupakan fitur penting yang memungkinkan pengguna untuk mengendalikan proses pengisian daya kendaraan listrik. SONIKApp juga terhubung dengan sistem manajemen SPKLU berbasis standar OCPP 1.6 secara real-time sehingga data yang ada di aplikasi selalu merupakan data terkini. Aplikasi ini dikembangkan dengan kerangka kerja front-end React Native, sehingga dapat berjalan di atas sistem operasi Android dan iOS. Hasil yang diperoleh adalah terciptanya aplikasi mobile SONIKApp yang memudahkan pengguna dalam pengisian daya kendaraan listrik. Telah dilakukan pengujian SONIKApp untuk fitur reservasi dan pengisian daya secara remote berdasarkan OCPP 1.6, dan hasilnya adalah aplikasi SONIKApp telah berhasil mengimplementasikan fitur-fitur tersebut. Abstract This paper discusses the development of a mobile application for charging electric vehicles, which is named SONIKApp. SONIKApp is used to make reservations and control charging remotely. The reservation feature is required considering that charging electric vehicle batteries requires waiting time and there are still inadequate number of public electric vehicle charging stations (SPKLU) available in Indonesia. The remote-based charging feature is also an important that allows users to control the process of charging electric vehicles from the applications. SONIKApp is also connected in real-time to the SPKLU management system based on the OCPP 1.6 standard so that the data presented in the application is always up-to-date. This application is developed with the React Native front-end framework, so it can run on both Android and iOS operating systems. We have successfully created the SONIKApp mobile application which makes it easier for users to charge electric vehicles. SONIKApp has been tested for reservation and remote charging features based on OCPP 1.6, and the result is that the SONIKApp application has successfully implemented these features.","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":"61 s282","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139146527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pengembangan Aplikasi Berlatih Membaca Cepat Berbahasa Inggris Berbasis Progressive Web App dengan Metode Prototyping","authors":"Muhammad Fajar Alfath, Lutfiyanti Fanani, Agi Putra Kharisma","doi":"10.25126/jtiik.1077982","DOIUrl":"https://doi.org/10.25126/jtiik.1077982","url":null,"abstract":"Membaca merupakan proses memahami, menafsirkan, dan mengekstraksi informasi dari serangkaian kata yang memerlukan waktu. Melalui internet, akses membaca semakin luas dengan adanya konten seperti artikel, e-book, jurnal, dan lainnya yang mayoritas disajikan dalam bahasa Inggris. Melalui survei terhadap 30 mahasiswa mengenai kegiatan membaca cepat dan relevansinya terhadap bahasa Inggris, sebanyak 76.7% darinya tidak mengetahui kecepatan membaca mereka dan 56.7% mengaku sering membaca teks berbahasa Inggris. Ada baiknya jika kemampuan membaca cepat dilatih dengan penggunaan bahasa Inggris untuk membangun motivasi terhadap literasi digital yang luas. Melalui pengamatan tersebut, dikembangkan aplikasi berbasis progressive web app (PWA) menggunakan metode SDLC prototyping. Melalui proses prototyping sebanyak 2 kali iterasi, dihasilkan aplikasi PWA ‘Speed Reader’ yang bertujuan untuk membantu berlatih membaca cepat secara senyap dengan materi bacaan berbahasa Inggris. Hasil evaluasi pengujian menunjukkan bahwa aplikasi ini kompatibel pada perangkat mobile dan dapat berjalan secara cross-browser. Setiap fitur berhasil dijalankan dengan tingkat validitas 100% pada pengujian efektivitas. Melalui pengujian efisiensi, didapatkan waktu penyelesaian tugas sebesar 0,156 tugas per detik. Hasil pengujian kepuasan pengguna melalui pengukuran System Usability Scale (SUS) mencapai nilai 84 dengan kategori grade B dan tergolong acceptable. Dengan demikian, dapat disimpulkan bahwa pengguna berhasil mencapai tujuan mereka dan aplikasi ini layak untuk digunakan.   Abstract   Reading is a process of understanding, interpreting, and extracting information from a series of words that takes time. The internet has significantly broadened reading access, providing abundant content like articles, e-books, journals, predominantly in English. A survey conducted among 30 students explored their engagement in speed reading and its relevance to English. Surprisingly, 76.7% of participants were unaware of their reading speed, while 56.7% acknowledged frequent reading of English texts. To foster extensive digital literacy, it is advisable to train speed reading skills specifically using the English language. Based on this observation, a Progressive Web App (PWA) was developed utilizing the SDLC prototyping method. The development of an app called 'Speed Reader' was aimed to facilitate the practice of silent speed reading with English materials. Evaluation tests demonstrated the application's compatibility with mobile devices and its cross-browser functionality. Each feature achieved a 100% validity rate in effectiveness testing. Moreover, efficiency testing revealed a task completion time of 0.156 tasks per second. User satisfaction assessments, conducted using the SUS method, yielded a score of 84, categorizing it as grade B and considered acceptable. It can be concluded that the users have successfully achieved their goals, and this application is deemed suitable.","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":" 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139144157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Penerapan SMOTE untuk Mengatasi Imbalance Class dalam Klasifikasi Kepribadian MBTI Menggunakan Naive Bayes Classifier","authors":"Mutiara Persada Pulungan, A. Purnomo, Aliyah Kurniasih","doi":"10.25126/jtiik.1077989","DOIUrl":"https://doi.org/10.25126/jtiik.1077989","url":null,"abstract":"Kepribadian Myers-Briggs Type Indicator ( MBTI ) telah menjadi topik populer dalam memahami karakteristik individu dan dampaknya pada interaksi sosial, karir, dan pengambilan keputusan. Model Machine Learning dengan algoritma Naive Bayes Classifier sering digunakan untuk memprediksi kepribadian MBTI berdasarkan data Twitter. Namun, seringkali terjadi ketidakseimbangan kelas, dengan beberapa jenis kepribadian yang memiliki sampel lebih sedikit. Untuk mengatasi hal ini, penelitian ini menggunakan teknik Synthetic Minority Over-sampling Technique (SMOTE) untuk meningkatkan jumlah sampel pada kelas minoritas. Selain itu, metode Term Frequency-Inverse Document Frequency (TF-IDF) digunakan untuk mengekstraksi fitur penting dari teks. Penelitian ini bertujuan menerapkan teknik SMOTE untuk mengatasi ketidakseimbangan kelas dalam klasifikasi kepribadian MBTI menggunakan beberapa algoritma Naive Bayes Classifier, termasuk Gaussian, Multinomial, Bernoulli, Complement, dan Logistic Regression berdasarkan model Keirsey: Artisan, Guardian, Rational, dan Idealist. Evaluasi menggunakan metode Hold-Out-Validation dengan membagi data menjadi 90% data latih dan 10% data uji. Hasil evaluasi menunjukkan performa rendah algoritma Naive Bayes Classifier untuk kelas Artisan dan Guardian, tetapi baik untuk kelas Rational dan Idealist. Algoritma Logistic Regression memiliki akurasi tertinggi 80% dan performa yang lebih baik secara keseluruhan, meskipun masih rendah untuk kelas Artisan dan Guardian. Dengan demikian, penelitian ini memberikan pemahaman tentang penggunaan algoritma Naive Bayes Classifier dan teknik SMOTE dalam prediksi kepribadian MBTI, dengan potensi peningkatan kinerja melalui penggunaan algoritma Logistic Regression.   Abstract   Myers-Briggs Type Indicator (MBTI) personality is becoming a popular topic in understanding individual characteristics and their impact on social interaction, career, and decision-making. Machine Learning models with Naive Bayes Classifier algorithms are often used to predict MBTI personalities from Twitter data. However, there is often a class imbalance, with some personality types having a smaller sample. To overcome this, this study used the Synthetic Minority Over-sampling Technique (SMOTE) technique to increase the number of samples in minority classes. Additionally, the Term Frequency-Inverse Document Frequency (TF-IDF) method is used to extract important features from text. This study aims to apply SMOTE techniques to address class imbalances in MBTI personality classification using several Naïve Bayes Classifier algorithms, including Gaussian, Multinomial, Bernoulli, Complement, and Logistic Regression based on Keirsey's model: Artisan, Guardian, Rational, and Idealist. Evaluation using the Hold-Out-Validation method by dividing the data into 90% training data and 10% test data. The evaluation results showed low performance of the Naive Bayes Classifier algorithm for the Artisan and Guardian classes, but both for the Rati","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":" 24","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139144458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}