Jurnal Teknik Informatika dan Sistem Informasi
Not a member yet
499 research outputs found
Sort by
Implementasi Realtime Cloud Service dalam Pengelolaan Nilai Tugas Akhir Mahasiswa
Full text linkFinal Project is one of the requirements that must be fulfilled by students to complete their studies at the university. In this case study in a non-technical study program at a private university, each student will be accompanied by two supervisors and will be tested by two examiners. Students will face three trials and each lecturer needs to give an assessment, both the process and the product. The grade of the product is also prioritized because this study program expects that each student can produce a product that has added value for society. With so many things involved and manual recording, it is necessary to create a final assignment grade management system. To simplify implementation, the system is created by utilizing a realtime cloud service, namely Firebase. Firebase is a service from Google to make it easier for developers to develop applications on various platforms. Data is stored in JSON and synchronized in real time to each user. This system can be accessed by Admins and Lecturers, this system is also equipped with a Dashboard as a recapitulation of existing data, trial reminders via email, and data import-export. Based on the survey conducted, it easier for Admins and Lecturers to manage final assignments.Tugas Akhir adalah salah satu syarat yang harus dipenuhi mahasiswa untuk menyelesaikan studinya di perguruan tinggi. Pada studi kasus kali ini di salah satu program studi non teknik di universitas swasta, setiap mahasiswa akan didampingi oleh dua orang dosen pembimbing dan akan diuji oleh dua orang dosen penguji. Mahasiswa akan menghadapi tiga kali sidang dan setiap dosen perlu memberi penilaian, baik proses maupun produknya. Nilai produk juga diutamakan karena program studi ini mengharapkan setiap mahasiswanya dapat menghasilkan sebuah produk yang memiliki nilai tambah bagi masyarakat. Dengan banyaknya hal yang terlibat dan pencatatan yang masih manual, perlu dibuatlah sistem pengelolaan nilai tugas akhir. Untuk mempermudah implementasi, sistem dibuat dengan memafaatkan realtime cloud service, yaitu Firebase. Firebase merupakan layanan dari Google untuk memudahkan developer dalam mengembangkan aplikasi di berbagai platforms. Data disimpan dalam bentuk JSON dan disinkronkan secara realtime ke setiap pengguna. Sistem ini dapat diakses oleh Admin dan Dosen, sistem ini dilengkapi juga dengan Dashboard sebagai rekapitulasi data yang ada, reminder sidang melalui email, dan import-eksport data. Berdasarkan survei yang dilakukan, sistem ini dapat memudahkan Admin dan Dosen untuk mengelola tugas akhir
Implementasi dan Analisis Digital Marketing pada Toko Kebutuhan Bayi dan Anak
Full text linkThe use of digital marketing to market products in this modern era has flourished due to the COVID-19 Pandemic emergence. The interactive ability possessed by digital marketing in providing 2-way communication in real time is one of the attractive advantages for business owners. Toko Makmur is a brick-and-clicks store that sells various needs for babies and children. Toko Makmur chose digital marketing as a marketing medium to market its products to the target market. Digital marketing at Toko Makmur was done by optimizing the use of Facebook and Instagram social media, optimizing the use of Google My Business, and creating a blog site called “Gagasan Bunda” for soft marketing using Wordpress. Optimization is carried out both organically by optimizing SEO (Search Engine Optimization) and uploading information content about mothers and children. In addition, Toko Makmur also conducted paid advertisement through social media Facebook. The data sources used to see the results of digital marketing implementation were from Google Analytics, Instagram Insight, Facebook Insight, and Google My Business Insight.
The use of digital marketing to market products in this modern era has flourished due to the COVID-19 Pandemic emergence. The interactive ability possessed by digital marketing in providing 2-way communication in real time is one of the attractive advantages for business owners. Toko Makmur is a brick-and-clicks store that sells various needs for babies and children. Toko Makmur chose digital marketing as a marketing medium to market its products to the target market. Digital marketing at Toko Makmur was done by optimizing the use of Facebook and Instagram social media, optimizing the use of Google My Business, and creating a blog site called “Gagasan Bunda” for soft marketing using Wordpress. Optimization is carried out both organically by optimizing SEO (Search Engine Optimization) and uploading information content about mothers and children. In addition, Toko Makmur also conducted paid advertisement through social media Facebook. The data sources used to see the results of digital marketing implementation were from Google Analytics, Instagram Insight, Facebook Insight, and Google My Business Insight.
Perancangan System Crawler dengan MenerapkanArsitektur Distributed Task
Full text linkPDC Media Group is a company engaged in online trading. The need for data insight in the online marketplace is very important. Likewise, how to get quite a lot of data, of course, requires automation such as crawling data on the marketplace website. Due to the large amount of data, crawler systems are often not optimal in crawling data. The application of distributed tasks on the crawler system provides convenience in scaling the server both vertically and horizontally. Therefore, the large and growing data can be handled by the crawler system. The application was developed with the Python language, with the application server using Google Cloud Computing. In a distributed task architecture requires a component in the form of a message broker. The message broker used in designing this system is RabbitMQ. Testing the crawler system uses 3 scenarios, namely with 1 worker, 2worker, and 3 worker. The results for the 1 worker scenario are 19.3 requests per second and 332 ms for response time. The results for the 2 worker scenario are 41.4 requests per second and 328 ms for response time. While the results for the 3 worker scenario are 60 requests per second and 331 ms for response time.PDC Media Group is a company engaged in online trading. The need for data insight in the online marketplace is very important. Likewise, how to get quite a lot of data, of course, requires automation such as crawling data on the marketplace website. Due to the large amount of data, crawler systems are often not optimal in crawling data. The application of distributed tasks on the crawler system provides convenience in scaling the server both vertically and horizontally. Therefore, the large and growing data can be handled by the crawler system. The application was developed with the Python language, with the application server using Google Cloud Computing. In a distributed task architecture requires a component in the form of a message broker. The message broker used in designing this system is RabbitMQ. Testing the crawler system uses 3 scenarios, namely with 1 worker, 2worker, and 3 worker. The results for the 1 worker scenario are 19.3 requests per second and 332 ms for response time. The results for the 2 worker scenario are 41.4 requests per second and 328 ms for response time. While the results for the 3 worker scenario are 60 requests per second and 331 ms for response time
Hustler Sebagai Pengembang Bisnis dan Pengerjaan Konten Digital Marketing
Full text linkThe enactment of the Community Activity Restriction Regulation (PPKM) in Indonesia makes school learning carried out online so that it cannot carry out activities as usual. Many problems are experienced by teenagers and do not find solutions because disturbances in school effectiveness activities are not monitored and cannot be directed by counseling teachers who are already available in schools. To help with existing problems, a web-based application called Arspira was created, where the application is an event marketplace that connects professional counselors with teenagers who are looking for a place to find solutions to the problems they face. The process of designing and making this application certainly would not have happened without the “hustler” as business developers and promotion through social media content to get good feedback from potential customers. This is done to match the work in progress and make the application what the prospective customer wants. This research aims to see the role of hustler as a business development in the startup company Arspra. The results of this study indicate the role of the hustler when forming the Arspira startup.
Pemberlakuan Peraturan Pembatasan Kegiatan Masyarakat (PPKM) di Indonesia membuat pembelajaran sekolah dilakukan dengan cara online sehingga tidak dapat melakukan aktivitas seperti biasanya. Banyak permasalahan yang dialami oleh remaja dan tidak menemukan solusi sehingga mengganggu dalam kegiatan efektivitas sekolah karena tidak terpantau dan tidak bisa diarahkan oleh guru konseling yang sudah sekolah sediakan. Untuk membantu permasalahan yang ada, maka dibuatlah suatu aplikasi berbasis web bernama Arspira, dimana aplikasi tersebut merupakan event marketplace yang menghubungkan konselor profesional dengan remaja yang mencari tempat untuk mendapatkan solusi dari permasalahan yang dihadapinya. Proses perancangan dan pembuatan aplikasi ini tentunya tidak akan terjadi tanpa adanya peran hustler sebagai pengembang bisnis serta promosi melalui konten media sosial untuk mendapatkan feedback yang baik dari calon pelanggan. Hal ini dilakukan untuk mengevaluasi pekerjaan yang berlangsung dan menjadikan aplikasi tersebut sesuai dengan yang diinginkan oleh calon pelanggan. Penelitian ini bertujuan untuk melihat bagaimana peran hustler sebagai pengembangan bisnis di perusahaan rintisan Arspra. Hasil penelitian ini menunjukan peranan hustler pada saat membentuk perusahaan rintisan Arspira.
Menentukan Aksi Lawan Komputer Pada Game Strategi Menggunakan Algoritma K-Nearest Neighbour
Full text linkAdvances in computer technology allow various devices to complete complex computing, especially in the entertainment industry and the biggest example is games. Strategy game is the type of game that most often gets an Artificial Intelligence or AI system implemented to imitate human behaviour when playing games. Many game AI systems are predictable so players get bored quickly, so adaptive and simple AI is needed to make it easier for game developers. K-Nearest Neighbour is a classification algorithm with supervised learning, this algorithm will be used in this study. The research method tests the level of accuracy in determining the class by providing a sample of data which is divided into training data and test data. The measure of the level of accuracy is calculated using the confusion matrix after the test table is obtained. The results of the study concluded that the K-Nearest Neighbour algorithm can determine computer opponents fairly well. More data samples are needed as data training to increase the level of classification accuracy.Kemajuan teknologi komputer memperbolehkan berbagai perangkat untuk menyelesaikan komputasi rumit terutama pada bidang industri hiburan dan contohnya adalah game. Game strategi merupakan jenis game yang paling sering diimplementasikan sistem Artificial Intelligence atau AI untuk menirukan tingkah laku manusia saat bermain game. Sistem AI game banyak yang mudah ditebak sehingga pemain cepat bosan, maka dibutuhkan AI adaptif dan sederhana untuk memudahkan pengembang game. K-Nearest Neighbour merupakan algoritma klasifikasi dengan supervised learning, algoritma ini akan digunakan dalam penelitian ini. Metode penelitian menguji tingkat akurasi algoritma dalam menentukan kelas aksi dengan memberikan data sampel yang dibagi menjadi data training dan data uji. Pengukuran tingkat akurasi dihitung menggunakan confusion matrix setelah didapat tabel pengujian. Hasil penelitian menyimpulkan bahwa algoritma K-Nearest Neighbour dapat menentukan aksi lawan komputer dengan baik. Dibutuhkan lebih banyak lagi data sampel sebagai data training untuk meningkatkan tingkat akurasi klasifikasi
Model Convolutional Neural Network untuk Mengukur Kepuasan Pelanggan Berdasarkan Ekspresi Wajah
Full text linkCustomer satisfaction shows how well the product or service of an organization meets customer expectations. Customers' facial expressions can show their satisfaction with the services provided. Convolution Neural Network (CNN) is a type of neural network algorithm that can be used to recognize an object in an image. CNN utilizes the convolution process to determine and distinguish an object in the image from other objects such as to recognize various facial expressions. This study aims to measure customer satisfaction by utilizing the CNN model by recognizing any changes in facial expressions. From the results of the CNN model training, an accuracy of 90.57% was obtained. Furthermore, the formed model is implemented into a web-based system that records facial expressions and performs a classification (satisfied or dissatisfied) on any detected facial changes. The most dominant expression is the result of measuring customer satisfaction.Kepuasan pelanggan menunjukan seberapa baik produk atau layanan suatu organisasi secara keseluruhan dalam memenuhi harapan pelanggan. Ekspresi wajah pelanggan dapat menunjukan kepuasan mereka terhadap layanan yang diberikan. Convolution Neural Network (CNN) adalah jenis algoritma neural network yang dapat digunakan untuk mengenali suatu objek di dalam sebuah gambar. CNN memanfaatkan proses konvolusi untuk menentukan dan membedakan suatu objek di dalam gambar dengan objek lainnya seperti untuk mengenali berbagai ekspresi wajah. Penelitian ini bertujuan untuk mengukur kepuasan pelanggan dengan memanfaatkan model CNN dengan mengenali setiap perubahan ekspresi wajah. Dari hasil pelatihan model CNN diperoleh akurasi sebesar 90,57%. Selanjutnya model yang terbentuk diimplementasikan ke dalam sebuah sistem berbasis web yang melakukan perekaman ekspresi wajah dan melakukan klasifikasi (puas atau tidak puas) terhadap setiap perubahan wajah yang terdeteksi. Ekspresi yang paling dominan merupakan hasil dari pengukuran kepuasan pelanggan
Optimasi Prakiraan Cuaca Menggunakan Metode Ensemble pada Naïve Bayes dan C4.5
Full text linkWeather forecasting is important for the survival of the wider community. Therefore, the accuracy of the weather forecast must be high. Based on this, a study was conducted to improve the accuracy of weather forecasting with the naïve Bayes and C4.5 models and then performed an optimization using the ensemble method. The dataset used is weather data observed from BMKG Bandung for 10 years. Accuracy in the pretest process shows that the naïve Bayes algorithm has an accuracy of 49.45% and the C4.5 algorithm produces 41.24% accuracy, while in the posttest process the accuracy obtained is 49.76% for bagging naïve Bayes, 46.47% for boosting naïve Bayes, 45.76 for bagging C4.5 and 38.82% for C4.5.Peramalan cuaca merupakan hal yang penting bagi keberlangsungan hidup masyarakat luas. Oleh karena itu, akurasi dari peramalan cuaca haruslah tinggi. Berdasarkan hal itu maka dilakukan penelitian untuk meningkatkan akurasi peramalan cuaca dengan model naïve Bayes dan C4.5 kemudian dilakukan optimasi dengan metode ensemble. Dataset yang digunakan merupakan data cuaca hasil pengamatan dari BMKG Bandung selama 10 tahun. Akurasi pada proses pretest menunjukkan jika algoritma naïve Bayes memiliki akurasi sebesar yakni 49,45% dan algoritma C4.5 menghasilkan akurasi 41,24%, sementara pada proses posttest akurasi yang didapatkan adalah 49,76% untuk bagging naïve Bayes, 46,47% untuk boosting naïve Bayes, 45,76 untuk bagging C4.5 dan 38,82% untuk C4.5.
BESKlus : BERT Extractive Summarization with K-Means Clustering in Scientific Paper
Full text linkThis study aims to propose methods and models for extractive text summarization with contextual embedding. To build this model, a combination of traditional machine learning algorithms such as K-Means Clustering and the latest BERT-based architectures such as Sentence-BERT (SBERT) is carried out. The contextual embedding process will be carried out at the sentence level by SBERT. Embedded sentences will be clustered and the distance calculated from the centroid. The top sentences from each cluster will be used as summary candidates. The dataset used in this study is a collection of scientific journals from NeurIPS. Performance evaluation carried out with ROUGE-L gave a result of 15.52% and a BERTScore of 85.55%. This result surpasses several previous models such as PyTextRank and BERT Extractive Summarizer. The results of these measurements prove that the use of contextual embedding is very good if applied to extractive text summarization which is generally done at the sentence level.This study aims to propose methods and models for extractive text summarization with contextual embedding. To build this model, a combination of traditional machine learning algorithms such as K-Means Clustering and the latest BERT-based architectures such as Sentence-BERT (SBERT) is carried out. The contextual embedding process will be carried out at the sentence level by SBERT. Embedded sentences will be clustered and the distance calculated from the centroid. The top sentences from each cluster will be used as summary candidates. The dataset used in this study is a collection of scientific journals from NeurIPS. Performance evaluation carried out with ROUGE-L gave a result of 15.52% and a BERTScore of 85.55%. This result surpasses several previous models such as PyTextRank and BERT Extractive Summarizer. The results of these measurements prove that the use of contextual embedding is very good if applied to extractive text summarization which is generally done at the sentence level
Optimasi Hyperparameter pada Penerapan Ensemble Regression Tree untuk Simulasi Pewarnaan Bibir
Full text linkTechnology helps us in many activities and keeps growing, so it makes activities more efficient, time-saving, using fewer resources and also information and entertainment are accessible. Machine Learning technology is the fastest-growing field in computer science that is used in many areas such as marketing, healthcare, manufacturing, information security, and transportation. One of the machine learning methods is the Ensemble of Regression Tree (ERT) which has succeeded in detecting facial features on the eyebrows, eyes, nose, and lips. However, utilization ERT method has not been found to detect specific areas such as lips only for gaining optimization. Then this research will be conducted to extract the facial feature annotation dataset from the iBUG 300W dataset with 68 facial features to 20 lip area points. The results of the extraction are reduced error rate, resources saving, lip features still detected and lip coloring simulation was successfully carried out using the configuration of hyperparameter values, tree = 4, regularization = 0.25, cascade = 8, feature pool = 500, oversampling = 40 and translation jitter = 0. From observations also discovered optimization that hard disk resource savings are 69.36%, RAM 30.8%, and CPU 3.8%; reduce the error rate by 0.058%; and increase inference speed by 39%.Teknologi membantu kita dalam banyak aktifitas dan terus mengalami kemajuan sehingga aktivitas lebih efisien, penggunaan waktu yang lebih hemat, sumberdaya yang lebih sedikit dan juga informasi serta hiburan lebih mudah didapatkan. Teknologi Machine Learning adalah bidang yang paling cepat berkembang dalam ilmu komputer yang penggunaannya mencakup berbagai bidang seperti pemasaran, perawatan kesehatan, manufaktur, keamanan informasi dan transportasi. Salah satu metodemachine learning adalah Ensemble Regression Tree (ERT) yang telah berhasil mendeteksi fitur wajah pada bagian alis, mata, hidung dan bibir. Akan tetapi, belum ditemukan penggunaan metode ERT untuk mendeteksi spesifik area bibir saja. Maka akan dilakukan penelitian untuk ekstraksi dataset anotasi fitur wajah dari dataset iBUG 300W dengan fitur 68 titik wajah menjadi 20 titik area bibir. Hasil dari ekstraksi tersebut yaitu error rate berkurang, penggunaan resource lebih sedikit, fitur bibir dapatterdeteksi dan simulasi pewarnaan bibir berhasil dilakukan dengan menggunakan konfigurasi nilai hyperparameter yaitu tree = 4,regularization = 0,25, cascade = 8, feature pool = 500, oversampling = 40 dan translation jitter = 0. Dari pengamatan juga diketahui bahwa penghematan resource hardisk sebesar 69,36%, RAM 30,8% dan CPU 3,8%; mengurangi error rate sebesar 0,058%; serta meningkatkan inference speed sebesar 39%
Rancang Bangun Aplikasi Koleksi Resep Makanan Berbasis Sistem Operasi iPhone
Full text linkFood is a necessity that is needed by anyone. One way to obtain food is to cook. Many people choose to cook their own food, even more so during the Covid-19 pandemic which caused cooking preferences to increase. One of the things used when cooking is recipes. Recipes need to be saved for easy reuse. Hence built a food recipe collection app that helps store recipes on mobile devices. The application is built on iOS. To find out the problems and needs in recipe saving, interviews were conducted, and problems were found regarding separated storing location and diverse storing format, limited search capabilities on current saving method, time-consuming input processes, and disturbing automatic-lock on device. Analysis of similar applications were also conducted and found shortcomings related to the flow and application interface. Based on these results, the application is designed with two main features, namely recipe storage and cooking mode. In recipe storage, users can add, change, and delete recipes. Once a recipe is saved, users can view a list of saved recipes, view recipes by category, and search for recipes by title. In cooking mode, users are given a checklist to prepare ingredients and then given a step-by-step. Application development uses the Swift programming language, with Swift User Interface to build the app's interface. Application data is stored locally using Core Data. Testing of application implementation results is carried out using alpha test and beta test. Alpha tests are performed using black-box test, to ensure the accuracy of inputs and outputs of various application functions. The beta test is done by conducting application trials and interviews with cooks to ensure application usability and to obtain feedbacks from users. Based on the test results, all functions in the application run as expected and this application helps users save food recipe collection.Makanan adalah kebutuhan pokok yang diperlukan manusia. Salah satu cara untuk mendapatkan makanan adalah dengan memasak. Banyak orang memilih untuk memasak makanan mereka, terlebih lagi pada masa pandemi covid-19 yang menyebabkan preferensi memasak meningkat. Salah satu hal yang digunakan saat memasak adalah resep. Resep perlu disimpan agar mudah digunakan kembali. Oleh karena itu dibangun aplikasi koleksi resep makanan yang membantu menyimpan resep pada perangkat mobile. Aplikasi dibangun dengan basis sistem operasi iOS. Untuk mengetahui permasalahan dan kebutuhan dalam penyimpanan resep, dilakukan wawancara dan ditemukan permasalahan mengenai lokasi dan format penyimpanan resep yang berbeda-beda, kemampuan pencarian kurang pada metode yang saat ini dilakukan, proses input lama, dan auto-lock perangkat mengganggu. Kemudian dilakukan juga analisis terhadap aplikasi serupa dan ditemukan kekurangan terkait alur dan desain tampilan aplikasi. Berdasarkan hasil tersebut, dirancang aplikasi dengan dua fitur utama yaitu penyimpanan resep dan mode memasak. Pada penyimpanan resep, pengguna dapat melakukan tambah, ubah, dan hapus resep. Setelah resep tersimpan, pengguna dapat melihat daftar resep yang tersimpan, melihat resep berdasarkan kategori, dan mencari resep berdasarkan judul. Pada mode memasak, pengguna diberi checklist untuk mempersiapkan bahan dan diberi panduan langkah demi langkah. Pembangunan aplikasi menggunakan bahasa pemrograman Swift, dengan Swift User Interface untuk membangun tampilan aplikasi. Penyimpanan data pada aplikasi bersifat lokal, menggunakan Core Data. Pengujian hasil implementasi aplikasi dilakukan dengan metode uji alpha dan uji beta. Uji alpha dilakukan menggunakan metode uji black-box, untuk memastikan ketepatan input dan output dari berbagai fungsi aplikasi. Uji beta dilakukan dengan melakukan uji coba aplikasi serta wawancara dengan pemasak untuk memastikan aplikasi dapat digunakan dan juga mendapat masukan dari pengguna langsung. Berdasarkan hasil pengujian, semua fungsi aplikasi berjalan sesuai harapan dan aplikasi ini dapat membantu pengguna melakukan penyimpanan koleksi resep makanan