Jurnal Teknik Informatika dan Sistem Informasi
Not a member yet
499 research outputs found
Sort by
Penerapan Digital Marketing Multichannel untuk Pemasaran Program Studi Sistem Informasi
Full text linkThe digital era has driven the development of marketing at light speed. Conventional marketing has begun to transform into online marketing platforms or commonly referred to as digital marketing. An Information System Study Program at a Private University located in Bandung city, Indonesia implemented an increase the intensity of soft selling to potential new students by creating a landing page Belajarsisfo using components related to digital marketing. Belajarsisfo is a site for sharing knowledge and tips and tricks about the world of Information Technology. Belajarsisfo used soft selling sales techniques that were made with the main aim of getting leads for the Information Systems Study Program. An attempt to optimize the digital marketing efforts was to conduct multichannel digital marketing efforts through several platforms of Social Media, Website, Blog Site, and Email. The results of this research were evaluated using Google Analytics, Instagram Insight, Facebook Insight, Facebook Pixel, and Email Campaign Report to determine future adjustment to the target consumer and can produce measurable and accurate data.
The digital era has driven the development of marketing at light speed. Conventional marketing has begun to transform into online marketing platforms or commonly referred to as digital marketing. An Information System Study Program at a Private University located in Bandung city, Indonesia implemented an increase the intensity of soft selling to potential new students by creating a landing page Belajarsisfo using components related to digital marketing. Belajarsisfo is a site for sharing knowledge and tips and tricks about the world of Information Technology. Belajarsisfo used soft selling sales techniques that were made with the main aim of getting leads for the Information Systems Study Program. An attempt to optimize the digital marketing efforts was to conduct multichannel digital marketing efforts through several platforms of Social Media, Website, Blog Site, and Email. The results of this research were evaluated using Google Analytics, Instagram Insight, Facebook Insight, Facebook Pixel, and Email Campaign Report to determine future adjustment to the target consumer and can produce measurable and accurate data.
Optimasi Penentuan Menu Makanan Pendamping Air Susu Ibu Menggunakan Algoritma Genetika
Full text link Indonesia has a bad situation in stunting. Stunting is a problem because of the consumption of less nutrition. This is caused by giving food that is not in accordance with the nutritional needs of infants. Infants 0 until 24 months old need attention in choosing a weaning food to support the baby’s growth. The purpose of this research is to find an optimized way to improve the menu of weaning food with the genetic algorithm method. It is expected to be able to reduce stunting suffering in Indonesia. The process of the genetic algorithm method uses the fitness function of a baby’s daily nutritional needs. The selection is Roulette wheel selection method, the crossover is whole arithmetic crossover with 0.5 crossover rate, and the last is the mutation process with 0.6 mutation rate. The research used 100 generations and the result is menus for breakfast, lunch, and dinner for 6 days. The genetic algorithm can determine optimal weaning food’s menu.Indonesia has a bad situation in stunting. Stunting is a problem because of the consumption of less nutrition. This is caused by giving food that is not in accordance with the nutritional needs of infants. Infants 0 until 24 months old need attention in choosing a weaning food to support the baby’s growth. The purpose of this research is to find an optimized way to improve the menu of weaning food with the genetic algorithm method. It is expected to be able to reduce stunting suffering in Indonesia. The process of the genetic algorithm method uses the fitness function of a baby’s daily nutritional needs. The selection is Roulette wheel selection method, the crossover is whole arithmetic crossover with 0.5 crossover rate, and the last is the mutation process with 0.6 mutation rate. The research used 100 generations and the result is menus for breakfast, lunch, and dinner for 6 days. The genetic algorithm can determine optimal weaning food’s menu
Analisis Algoritma Gradient Boosting, Adaboost dan Catboost dalam Klasifikasi Kualitas Air
Full text linkThis research aims to find the highest accuracy of the three classification algorithms. The highest accuracy algorithm will be used as a reference in this water quality classification. and test the performance of the third model. The method used in this analysis to overcome missing data is the median method. Then to handle unbalanced data, the SMOTE method is used. In this study, we compared the accuracy and performance of Gradient Boosting, Adaboost, and Catboost. The results found that the Catboost algorithm has the highest accuracy and performance of 68%, followed by Gradient Boosting at 60% and Adaboost at 58%. Then the performance of the AUC Catboost value is 0.678, Gradient Boosting is 0.595, and Adaboost is 0.584. But the results of accuracy and performance are still lacking.Penelitian ini bertujuan untuk mencari akurasi tertinggi dari ketiga algoritma klasifikasi tersebut. Algoritma dengan akurasi tertinggi akan digunakan sebagai acuan dalam klasifikasi kualitas air ini. Serta menguji kinerja ketiga model ini. Metode yang digunakan dalam analisis ini untuk mengatasi data yang hilang adalah metode Median. Kemudian untuk menangani data yang tidak seimbang digunakan metode SMOTE. Dalam penelitian ini, peneliti membandingkan akurasi dari kinerja Gradient Boosting, Adaboost, dan Catboost. Hasilnya ditemukan bahwa algoritma Catboost memiliki akurasi dan kinerja tertinggi sebesar 68%, diikuti oleh Gradient Boosting sebesar 60% dan Adaboost sebesar 58%. Kemudian performansi nilai AUC Catboost sebesar 0,678, Gradient Boosting sebesar 0,595, dan Adaboost sebesar 0,584. Namun hasil akurasi dan performanya masih kurang
Pengembangan Dashboard Informasi Gereja Tangguh Bencana dengan Metode User Centered Design
Full text linkIndonesia is a country prone to natural disasters, from earthquakes to annual flood. These can affect, and even at times, endanger people's lives. JAKOMKRIS PBI or the Christian community for disaster management in Indonesia has the duty to aid with Christian churches and institutions to actualize the concept of disaster-resilient church. One of the ways that can help JAKOMKRIS PBI's main goal is to create a website-based dashboard displaying information related to the concept of disaster-resilient church. This research applies the principles of User-Centered Design which in its development focuses on the user. User-Centered Design requires information about the appearance of the interface desired by the user. The results of the research are expected to be able to assist users in preparing churches for disaster events by providing provisions and disaster risk reduction based on managed data. This research uses usability tests using performance metrics and System Usability Scale (SUS) methods. The performance metrics test results for the efficiency value of 90.95% for the user role and 100% for the admin role, while the effectiveness value is 96% for the user role and 100% for the admin role and the results of the System Usability Scale (SUS) test are 81.5 for the user role and 81.25 for admin roles.Pada saat ini bencana merupakan salah satu peristiwa yang mengancam kehidupan masyarakat oleh sebab itu komunitas kristen untuk penanggulangan bencana di Indonesia (JAKOMKRIS PBI) melakukan sebuah langkah untuk menanggulangi bencana dengan upaya meningkatkan peran pendamping bagi gereja atau lembaga untuk dapat mewujudkan konsep gereja tangguh bencana. Berdasarkan permasalahan yang dihadapi maka diperlukannya sebuah sistem informasi berbentuk website yang dapat menampilkan data dalam bentuk visualisasi dashboard. Penelitian ini dibangun dengan menerapkan prinsip-prinsip User Cenetered Design dimana dalam pengembanganya berfokus kepada pengguna. User Centered Design memerlukan informasi mengenai tampilan antarmuka yang diinginkan oleh pengguna. Hasil dari penelitian nantinya diharapkan mampu untuk dapat membantu pengguna dalam menyiapkan gereja dalam menghadapi kejadian bencana dengan memberikan bekal dan pengurangan risiko bencana berdasarkan data yang telah dikelola. Penelitian ini menggunakan uji usabilitas dengan menggunakan metode performance metrics dan System Usability Scale (SUS). Hasil pengujian performance metrics untuk nilai efisiensi sebesar 90.95% untuk role pengguna dan 100% untuk role admin, sedangkan untuk nilai efektivitas sebesar 96% untuk role pengguna dan 100% untuk role admin dan hasil pengujian System Usability Scale (SUS) didapatkan hasil 81.5 untuk role pengguna dan 81.25 untuk role admin
Implementasi Deep Convolutional Generative Adversarial Network untuk Pewarnaan Citra Grayscale
Full text linkThe process of adding color to a grayscale image is needed so that improvements to the image can be done quickly and without special knowledge. Image coloring using Deep Convolutional Generative Adversarial Network (DCGAN) and Generative Adversarial Network (GAN) methods. The model training uses the Places365 dataset, which contains 98,721 training data and 6,600 test data. The image is converted into the CIELAB color space, using the L channel as grayscale input and the AB channel as the other input. The test is done by comparing the accuracy values using the Mean Absolute Error (MAE) and Structural Similarity Index Matrix (SSIM) methods. The calculation results of the MAE method show that the average MAE value of the DCGAN method is smaller than the GAN method, with a score of 10.18 and 10.81. The results of the calculation of the SSIM method show that the DCGAN method has a higher average with a score of 91.54% and 68.32% for the GAN method. The results of the questionnaire conducted on 30 respondents showed that the DCGAN method was chosen by more respondents than the GAN method, respectively 88.40% and 11.60%.Proses menambahkan warna pada citra grayscale diperlukan agar perbaikan pada citra dapat dilakukan secara cepat dan tanpa pengetahuan khusus. Pewarnaan citra menggunakan metode Deep Convolutional Generative Adversarial Network (DCGAN) dan metode Generative Adversarial Network (GAN). Pelatihan model menggunakan dataset Places365, yang berisikan 98.721 data pelatihan dan 6.600 data pengujian. Citra dikonversi ke dalam ruang warna CIELAB, dengan memanfaatkan channel L sebagai input grayscale dan channel AB sebagai input lainnya. Pengujian dilakukan dengan membandingkan nilai akurasi menggunakan metode Mean Absolute Error (MAE) dan Structural Similarity Index Matrix (SSIM). Hasil perhitungan metode MAE menunjukkan bahwa rata-rata nilai MAE metode DCGAN lebih kecil dibandingkan metode GAN, dengan skor 10,18 dan 10,81. Hasil perhitungan metode SSIM menunjukkan bahwa metode DCGAN memiliki rata - rata yang lebih tinggi dengan skor 91,54% dan 68,32% untuk metode GAN. Hasil kuesioner yang dilakukan terhadap 30 responden menunjukkan bahwa metode DCGAN dipilih oleh lebih banyak responden dibandingkan metode GAN, masing-masing sebesar 88,40% dan 11,60%
Implementasi Augmented Reality Pengenalan Hewan, Buah dan Kendaraan Untuk Pendidikan Usia Dini
Full text linkAs a result of the implementation of social distancing rules, the education sector is forced to implement the Distance Learning system or study from home which sometimes makes students feel bored in its implementation. Therefore, an alternative learning media is needed to overcome this boredom. One method that can be used is learning through applications with the addition of augmented reality technology. The purpose of this study was to design an interactive learning media for early childhood based on augmented reality technology and to determine the impact of its use. This type of research is action research, while the software development method used is the waterfall model. This app is designed using Unity 3D and Vuforia SDK. The results of the calculation of the questionnaire, obtained a value of 98.6% which means the application is included in the very effective criteria according to the Likert Scale. And from the results of the paired t-test of application users before and after using the application, it was concluded that there were differences in the assessment of learning outcomes before and after using augmented reality-based basic learning applications for early childhood.Akibat dari pemberlakuan aturan social distancing, sektor pendidikan dengan terpaksa harus menerapkan sistem Pembelajaran Jarak Jauh (PJJ) atau belajar dari rumah yang terkadang membuat para pelajar merasa bosan dalam pelaksanaannya. Oleh karena itu dibutuhkan sebuah media pembelajaran alternatif untuk mengatasi rasa bosan tersebut. Salah satu metode yang dapat digunakan adalah belajar melalui aplikasi dengan penambahan teknologi augmented reality. Tujuan dari penelitian ini adalah merancang sebuah media pembelajaran interaktif untuk anak usia dini berbasis teknologi augmented reality dan untuk mengetahui dampak penggunaannya. Penelitian ini berjenis penelitian tindakan, sedangkan untuk metode pengembangan software yang digunakan adalah model waterfall. Aplikasi ini dirancang menggunakan Unity 3D dan Vuforia SDK. Hasil dari perhitungan kuesioner, didapatkan nilai sebesar 98,6% yang berarti aplikasi masuk ke dalam kriteria sangat efektif menurut Skala Likert. Dan dari hasil uji-t berpasangan terhadap pengguna aplikasi sebelum dan sesudah menggunakan aplikasi, mendapatkan kesimpulan terdapat perbedaan penilaian hasil belajar sebelum dan sesudah menggunakan aplikasi pembelajaran dasar untuk anak usia dini berbasis augmented reality.  
Perbandingan Algoritma Supervised Learning untuk Klasifikasi Judul Skripsi Berdasarkan Bidang Dosen
Full text linkAt the level of education, especially for S1, the graduation requirement is to complete the thesis. In preparing the thesis, students are accompanied by a guidance lecturer who will direct and as a place to consult. The case is still there are students who are confused to take a thesis. There are several reasons that they do not have a title to be submitted, and are confused to choose a tutor who matches their title or theme. Sometimes on campus, students can get a mentor, but not in accordance with the field, and not in accordance with the theme of the thesis title. Therefore, in this study will make a classification of lecturer fields based on student titles. The data used as many as 1598 was taken from the campus of AMIKOM Yogyakarta University by adding some new data. With the lecturer in accordance with the field, it will be easier to guide students. This study conducted stages of labeling, text preprocessing, and word weighting or called TF-IDF (Term Frequency – Inverse Document Frequency). After that, the data split will be classified with naive bayes classifier (NBC), K-Nearest Neighbor (K-NN), and Support Vector Machine (SVM) algorithms. The performance of the three algorithms is compared to find out the performance of the algorithm is good. The results showed the Support Vector Machine (SVM) algorithm performed better by producing an accuracy of 89.24%, while the Naive Bayes Classifier (NBC) algorithm produced an accuracy of 88.29%, and the K-Nearest Neighbor (KNN) algorithm with a k value of 18 produced an accuracy of 85.14%.Pada jenjang pendidikan khususnya S1, syarat kelulusan adalah menyelesaikan skripsi. Dalam penyusunan skripsi, mahasiswa didampingi oleh dosen pembimbing yang akan mengarahkan dan sebagai tempat berkonsultasi. Kasusnya masih ada mahasiswa yang bingung untuk mengambil skripsi. Ada beberapa alasan mereka tidak memiliki judul untuk diajukan, dan bingung memilih tutor yang sesuai dengan judul atau tema mereka. Terkadang di kampus mahasiswa bisa mendapatkan pembimbing, namun tidak sesuai dengan bidangnya, dan tidak sesuai dengan tema judul skripsi. Oleh karena itu, pada penelitian ini akan membuat klasifikasi bidang dosen berdasarkan gelar mahasiswa. Data yang digunakan sebanyak 1598 diambil dari kampus Universitas AMIKOM Yogyakarta dengan menambahkan beberapa data baru. Dengan adanya dosen yang sesuai dengan bidangnya maka akan lebih mudah dalam membimbing mahasiswa. Penelitian ini melakukan tahapan pelabelan, preprocessing teks, dan pembobotan kata atau disebut TF-IDF (Term Frequency – Inverse Document Frequency). Setelah itu, pemisahan data akan diklasifikasikan dengan algoritma naive bayes classifier (NBC), K-Nearest Neighbor (K-NN), dan Support Vector Machine (SVM). Kinerja dari ketiga algoritma tersebut dibandingkan untuk mengetahui kinerja dari algoritma tersebut baik. Hasil penelitian menunjukkan algoritma Support Vector Machine (SVM) tampil lebih baik dengan menghasilkan akurasi sebesar 89,24%, sedangkan algoritma Naive Bayes Classifier (NBC) menghasilkan akurasi sebesar 88,29%, dan algoritma K-Nearest Neighbor (KNN) dengan nilai k dari 18 menghasilkan akurasi 85,14%
Penerapan Metode Simple Additive Weighting dalam Menentukan Perguruan Tinggi Negeri
Full text linkWorld University Ranking is a system tool that functions to measure and assess all the best universities around the world (World Class University) which aims to advance all Universities through websites owned by each University. There are several problems in choosing a college. The selection of campuses or State Universities (PTN) is still often a problem or obstacle for every prospective student and parent to choose further education for the future of their children, especially as we often know that there are many universities in Indonesia. Indonesia ranges from state universities to private universities. One of the efforts in the selection recommendations made to facilitate this is to conduct an assessment of the best PTN. In this study, the Simple AdditiveWeighting (SAW) method was applied to the best college recommendation system. The criteria used are Tuition Fees, Academic Reputation, Employer Reputation, Teaching, Research, and Citation. After the criteria are determined, the next process is theranking process of the existing alternatives. The results of each method can provide recommendations for students or parents in choosing a college.World University Ranking is a system tool that functions to measure and assess all the best universities around the world (World Class University) which aims to advance all Universities through websites owned by each University. There are several problems in choosing a college. The selection of campuses or State Universities (PTN) is still often a problem or obstacle for every prospective student and parent to choose further education for the future of their children, especially as we often know that there are many universities in Indonesia. Indonesia ranges from state universities to private universities. One of the efforts in the selection recommendations made to facilitate this is to conduct an assessment of the best PTN. In this study, the Simple AdditiveWeighting (SAW) method was applied to the best college recommendation system. The criteria used are Tuition Fees, Academic Reputation, Employer Reputation, Teaching, Research, and Citation. After the criteria are determined, the next process is theranking process of the existing alternatives. The results of each method can provide recommendations for students or parents in choosing a college
Komparasi Metode SMOTE dan ADASYN dalam Meningkatkan Performa Klasifikasi Herregistrasi Mahasiswa Baru
Full text linkUniversities annually accept new students at the beginning of the new school year. In the acceptance of prospective students on the Seleksi Prestasi Akademik Nasional Perguruan Tinggi Keagamaan Islam Negeri (SPAN PTKIN) di State Islamic University Of Sunan Ampel Surabaya, many prospective students who do not register will have an impact on income of the State Islamic University Of Sunan Ampel Surabaya institution. If the institution can find out early on the probability of a prospective student who will resign, then the management can take action to retain the prospective student. To overcome this, data mining classification can be carried out. The methods used in this classification are decision trees and naïve bayes. The number of students who did not re register compared to reregister resulted in the data being imbalanced. Data imbalances can affect the accuracy of the classification results. The imbalance of the data used can result in an unsuitable model. The solution to handle the data imbalance is to use the SMOTE and ADASYN oversampling methods. The purpose of this study was to compare performance of the SMOTE and ADASYN methods. The results show that the SMOTE method can balance the data in a balanced way compared to ADASYN. From the test results, the SMOTE method is more suitable to use than the ADASYN method because the ROCAUC SMOTE value is higher than ADASYN.
Universities annually accept new students at the beginning of the new school year. In the acceptance of prospective students on the Seleksi Prestasi Akademik Nasional Perguruan Tinggi Keagamaan Islam Negeri (SPAN PTKIN) di State Islamic University Of Sunan Ampel Surabaya, many prospective students who do not register will have an impact on income of the State Islamic University Of Sunan Ampel Surabaya institution. If the institution can find out early on the probability of a prospective student who will resign, then the management can take action to retain the prospective student. To overcome this, data mining classification can be carried out. The methods used in this classification are decision trees and naïve bayes. The number of students who did not re register compared to reregister resulted in the data being imbalanced. Data imbalances can affect the accuracy of the classification results. The imbalance of the data used can result in an unsuitable model. The solution to handle the data imbalance is to use the SMOTE and ADASYN oversampling methods. The purpose of this study was to compare performance of the SMOTE and ADASYN methods. The results show that the SMOTE method can balance the data in a balanced way compared to ADASYN. From the test results, the SMOTE method is more suitable to use than the ADASYN method because the ROCAUC SMOTE value is higher than ADASYN.
Peramalan Jumlah Kasus COVID-19 Menggunakan Joint Learning
Full text linkCOVID-19 is a dangerous illness because it spreads quickly and easily. Vaccines are already available but the pandemic isn’t likely to end soon. Forecasting is hoped to help handle the pandemic. Deep learning, specially LSTM, has been used to forecast COVID-19 case count in some regions. However, deep learning models generally need a lot of training data while COVID-19 daily data are scarce. However, COVID-19 pandemic happens in many regions. This research aims to use joint learning with data from other regions to improve model performance with fewer data and to use the model to forecast until 9 months since the date of last data taken. Joint learning was done by making models share some parts and training the models together. To overcome the different data scale and pandemic age in the regions, the data was first transformed into discrete SIRD variables and was evaluated using RMSSE. Joint learning failed to improve the model performance in this research. The proposed model performance was signficantly better than ARIMA-SIRD and SIRD model but wasn’t better than normal encoder-decoder LSTM. The models only reached RMSSE below one occasionally. Additionally, it was found that doing joint learning with all regions without selecting them by clustering can make the model performance worse instead. It was also found that RMSSE is too sensitive to a mostly stagnant time-series due to its division by the error of one-step naïve forecast.the pandemic. Deep learning, specially LSTM, has been used to forecast COVID-19 case count in some regions. However, deep learning models generally need a lot of training data while COVID-19 daily data are scarce. However, COVID-19 pandemic happens in many regions. This research aims to use joint learning with data from other regions to improve model performance with fewer data and to use the model to forecast until 9 months since the date of last data taken. Joint learning was done by making models share some parts and training the models together. To overcome the different data scale and pandemic age in the regions, the data was first transformed into discrete SIRD variables and was evaluated using RMSSE. Joint learning failed to improve the model performance in this research. The proposed model performance was signficantly better than ARIMA-SIRD and SIRD model but wasn’t better than normal encoder-decoder LSTM. The models only reached RMSSE below one occasionally. Additionally, it was found that doing joint learning with all regions without selecting them by clustering can make the model performance worse instead. It was also found that RMSSE is too sensitive to a mostly stagnant time-series due to its division by the error of one-step naïve forecast