Jurnal Teknik Informatika dan Sistem Informasi
Not a member yet
499 research outputs found
Sort by
Prediksi Kinerja Pegawai sebagai Rekomendasi Kenaikan Golongan dengan Metode Decision Tree dan Regresi Logistik
No full textEmployee performance is one element that greatly determines the quality of an organization, both government and private. Employee performance appraisal has become a routine for most companies. Performance appraisal is required for the process of salary increases, promotions, and demotions. Until this research was carried out, the processing of employee performance appraisal and evaluation at Prasama Bhakti Foundation was still done manually, so that sometimes employee promotions were carried out late or even on an inconsistent basis for each employee. Therefore, it is necessary to group data with the help of machine learning that can help predict the eligibility of an employee to get a promotion based on his performance. Classification is one method for classifying or classifying data that are arranged systematically. Decision tree and logistic regression methods are classification or grouping methods that have been widely used for solving classification problems. In this study, it will be explained how the process of processing employee performance appraisal data starts from data preparation to determine the accuracy of the decision tree model and logistic regression that is formed. The two classification models are used to predict employee performance as a recommendation for employee promotion at the Prasama Bhakti Foundation.
Employee performance is one element that greatly determines the quality of an organization, both government and private. Employee performance appraisal has become a routine for most companies. Performance appraisal is required for the process of salary increases, promotions, and demotions. Until this research was carried out, the processing of employee performance appraisal and evaluation at Prasama Bhakti Foundation was still done manually, so that sometimes employee promotions were carried out late or even on an inconsistent basis for each employee. Therefore, it is necessary to group data with the help of machine learning that can help predict the eligibility of an employee to get a promotion based on his performance. Classification is one method for classifying or classifying data that are arranged systematically. Decision tree and logistic regression methods are classification or grouping methods that have been widely used for solving classification problems. In this study, it will be explained how the process of processing employee performance appraisal data starts from data preparation to determine the accuracy of the decision tree model and logistic regression that is formed. The two classification models are used to predict employee performance as a recommendation for employee promotion at the Prasama Bhakti Foundation.
Pendeteksi Sampah Metal untuk Daur Ulang Menggunakan Metode Convolutional Neural Network
Get PDFWaste is part material that has no value within the scope of production. If you no longer need it, metal cans can take about 80 to 200 years to decompose. CNN is part of the supervised learning method that exists in deep learning, where those who have expertise in representing images or images from several categories increase recognition, namely in classifying objects, doing scene recognition, and detecting object detection. In this study, using the CNN method as a development model and applying the ResNet 50 network design, which includes the type Convolutional Neural Network (CNN) that operates by way of working, namely receive an input in the form of an image or images. The input will be carried out by training that is set using the CNN architecture so that later it will produce an output that can recognize objects as expected in knowing the types of cardboard and glass waste. The implementation of this research uses the Python programming language, Anvil, and the TensorFlow and Keras libraries. The system has succeeded in detecting the type of metal waste from general waste and assisting third parties, namely implementing it through the website using Anvil. The input shape for CNN modeling in this study is 512x384 pixels, which has a value of 100 eras, and the data set used contains images of metal waste and general waste found 547 images, resulting in an accuracy of 96%.Waste is part material that has no value within the scope of production. If you no longer need it, metal cans can take about 80 to 200 years to decompose. CNN is part of the supervised learning method that exists in deep learning, where those who have expertise in representing images or images from several categories increase recognition, namely in classifying objects, doing scene recognition, and detecting object detection. In this study, using the CNN method as a development model and applying the ResNet 50 network design, which includes the type Convolutional Neural Network (CNN) that operates by way of working, namely receive an input in the form of an image or images. The input will be carried out by training that is set using the CNN architecture so that later it will produce an output that can recognize objects as expected in knowing the types of cardboard and glass waste. The implementation of this research uses the Python programming language, Anvil, and the TensorFlow and Keras libraries. The system has succeeded in detecting the type of metal waste from general waste and assisting third parties, namely implementing it through the website using Anvil. The input shape for CNN modeling in this study is 512x384 pixels, which has a value of 100 eras, and the data set used contains images of metal waste and general waste found 547 images, resulting in an accuracy of 96%
Analisis Pengalaman Pengguna Aplikasi Gojek dan Grab dengan Pendekatan User Experience Questionnaire
Get PDFTechnological developments have an impact on the presence of Super Apps, such as: Gojek and Grab. The presence of these two applications has an effect on the lifestyle in society which is increasingly facilitated by various services that are presented in only one application. The Gojek and Grab applications have many similarities, including in terms of their use. These two applications are very popular and favored by the community because they are practical and help various community activities, for example: food ordering services, delivery of goods, transportation, and non-cash payments. This study was conducted to determine whether there are differences in user experience with the application with case studies in people living in Yogyakarta. User experience measurement is carried out using the User Experience Questionnaire (UEQ) approach on attractive, perspicuity, efficiency, dependability, stimulation, and novelty variables. This study uses a comparative descriptive method with a quantitative approach. The results showed that all Gojek and Grab application user experience variables got positive values ??and there were no significant differences in all variables. However, based on the UEQ measurement, it is known that the Gojek application is superior to the Grab application in perspicuity and novelty variables. Meanwhile, the Grab application is superior to the Gojek application in terms of efficiency, dependability, and stimulation variables. To improve the user experience for the Gojek and Grab applications, it is necessary to improve the quality of the perspicuity and dependability variables.Technological developments have an impact on the presence of Super Apps, such as: Gojek and Grab. The presence of these two applications has an effect on the lifestyle in society which is increasingly facilitated by various services that are presented in only one application. The Gojek and Grab applications have many similarities, including in terms of their use. These two applications are very popular and favored by the community because they are practical and help various community activities, for example: food ordering services, delivery of goods, transportation, and non-cash payments. This study was conducted to determine whether there are differences in user experience with the application with case studies in people living in Yogyakarta. User experience measurement is carried out using the User Experience Questionnaire (UEQ) approach on attractive, perspicuity, efficiency, dependability, stimulation, and novelty variables. This study uses a comparative descriptive method with a quantitative approach. The results showed that all Gojek and Grab application user experience variables got positive values ??and there were no significant differences in all variables. However, based on the UEQ measurement, it is known that the Gojek application is superior to the Grab application in perspicuity and novelty variables. Meanwhile, the Grab application is superior to the Gojek application in terms of efficiency, dependability, and stimulation variables. To improve the user experience for the Gojek and Grab applications, it is necessary to improve the quality of the perspicuity and dependability variables
Klasifikasi Isyarat Bahasa Indonesia Menggunakan Metode Convolutional Neural Network
Get PDFIndonesian Sign Language is word signs initially taken from the signs conveyed by deaf children. Sign language is common for the deaf and mute, but it is no stranger to ordinary people. For this reason, alternative intermediaries are needed who can become translators between deaf and speech impaired sufferers and ordinary people. This study aims to classify the Indonesian sign system using the Convolutional Neural Network method with VGG-16 and Alexnet architecture. The data divided by each letter from the letter A to the letter Z is 320 test data, 1600 train data, and 320 validation data, and the data will be resized to a size of 224 x 224 pixels, followed by grayscale and augmentation. The results of the VGG-16 test show that the classification using VGG-16 with the Adam optimizer gets the highest level of accuracy, which is 99.32% for each letter, 91.18% for the whole. While the classification results using VGG-16 with the SGD optimizer get the lowest level of accuracy, which is 98.85% for each letter and 84.96% for the whole. Meanwhile, from the AlexNet test results, it can be seen that the results of the classification using AlexNet with the Adam optimizer get the highest level of accuracy, which is 99.16% for each letter and 89.04% for the whole. While the classification results using AlexNet with the SGD optimizer get the lowest level of accuracy, which is 97.33% for each letter and 68.33% for the whole. Bahasa Isyarat Indonesia adalah isyarat kata yang awalnya diambil dari isyarat yang disampaikan oleh anak tunarungu. Bahasa isyarat adalah hal yang biasa bagi orang tuli dan bisu, tetapi tidak asing bagi orang biasa. Untuk itu diperlukan perantara alternatif yang dapat menjadi penerjemah antara penyandang tunarungu dan tuna wicara sertamasyarakat biasa. Penelitian ini bertujuan untuk mengklasifikasikan sistem isyarat bahasa Indonesia menggunakan metode Convolutional Neural Network dengan arsitektur VGG (Visual Geometric Group)-16 dan Alexnet. Data terdiri dari huruf A sampai dengan huruf Z yaitu 320 data uji, 1600 data latih, dan 320 data validasi, dan data akan diubah ukurannya menjadi ukuran 224 x 224 piksel, dilanjutkan dengan grayscale dan augmentasi. Hasil pengujian VGG-16 menunjukkan bahwa klasifikasi menggunakan VGG-16 dengan optimasi Adam mendapatkan tingkat akurasi tertinggi, yaitu 99,32% untuk setiap huruf, 91,18% untuk keseluruhan. Sedangkan hasil klasifikasi menggunakan VGG-16 dengan optimasi SGD mendapatkan tingkat akurasi terendah, yaitu 98,85% untuk setiap huruf dan 84,96% untuk keseluruhan. Sedangkan dari hasil pengujian AlexNet terlihat bahwa hasil klasifikasi menggunakan AlexNet dengan Adam optimizer mendapatkan tingkat akurasi tertinggi, yaitu 99,16% untuk setiap huruf dan 89,04% untuk keseluruhan. Sedangkan hasil klasifikasi menggunakan AlexNet dengan pengoptimal SGD mendapatkan tingkat akurasi terendah, yaitu 97,33% untuk setiap huruf dan 68,33% untuk keseluruhan
Perbandingan Algoritma K-Means dan K-Medoids untuk Pengelompokan Daerah Produksi Kakao
Get PDFCocoa is one of the leading commodities from the plantation sector, even cocoa production is considered capable of increasing the country's foreign exchange. In Indonesia, especially South Sulawesi Province, it has a large cocoa production where almost all districts/cities in South Sulawesi produce cocoa. The purpose of this research is to group cocoa production areas in South Sulawesi Province. The algorithms used are K-Means and K-Medoids, in which K-Means group data by dividing it into several clusters based on the same characteristics. While the K-Medoids algorithm chooses real objects to represent the cluster. In this study, the two algorithms were compared using one dataset. The comparison is made by looking at the Davies-Bouldin Index (DBI) value on RapidMiner. Then the results obtained based on this study are grouping using the K-Means algorithm is more effective than using K-Medoids in grouping cocoa production areas in South Sulawesi Province. With the DBI values obtained, K-Means and K-Medoids have DBI values of 0.292 and 0.365, respectively.Kakao ialah salah satu komoditas unggulan dari sektor perkebunan bahkan produksi kakao dinilai mampu meningkatkan devisa negara. Di Indonesia khususnya Provinsi Sulawesi Selatan memiliki produksi kakao yang besar dimana hampir semua Kabupaten/Kota yang terdapat di Sulawesi Selatan memproduksi kakao. Tujuan dalam melakukan penelitian ini ialah untuk melakukan pengelompokan daerah produksi kakao pada Provinsi Sulawesi Selatan. Adapun algoritma yang digunakan yakni K-Means serta K-Medoids, yang mana K-Means mengelompokan data dengan cara membagi kedalam beberapa cluster berdasarkan ciri yang sama. Sedangakan algoritma K-Medoids memilih objek yang nyata untuk mewakili cluster. Pada penelitian ini kedua algoritma tersebut dibandingkan dengan menggunakan satu dataset. Perbandingan dilakukan dengan melihat nilai Davies-Bouldin Index (DBI) pada RapidMiner. Kemudian hasil yang didapatkan berdasarkan penelitian ini adalah pengelompokan menggunakan algoritma K-Means lebih efektif daripada menggunakan K-Medoids dalam pengelompokan daerah produksi kakao Provinsi Sulawesi Selatan. Dengan nilai DBI yang didapatkan K-Means dan K-Medoids memiliki nilai DBI masing-masing sebesar 0,292 dan 0,365
Analisis Faktor Pendorong Niat Menggunakan Aplikasi PeduliLindungi Menggunakan Model UTAUT Modifikasi
No full textIn 2020, the world is faced with the sudden presence of the Covid-19 virus which spreads rapidly among people who are in close contact. To control and limit the spread of the virus infection, a mobile health application (mHealth) as a technology-based approach has been used. Contact tracing application is one kind of mHealth system that is capable and suitable for this kind of situation. Many countries have implemented the adoption of contact tracing applications during the pandemic, Indonesia is no exception, it is called Aplikasi PeduliLindungi. The existence of contact tracing application such as Aplikasi PeduliLindungi is considered to be very helpful. Therefore, research related to Aplikasi PeduliLindungi is considered necessary, because contact tracing applications are considered as one of the important steps to cut down the spread of the virus. Investigating factors that can influence the intention to adopt a contact tracing application is highly necessary, since the effectiveness of implementing a Covid-19 contact tracing application relies on the public’s willingness to use the application. To discover the factors that could influence intention of the users to use a new technology, an analysis can be carried out using the UTAUT model. The results is that the factors that significantly influence the intention of the users to use Aplikasi PeduliLindungi are Performance Expectancy, Facilitating Conditions, and Covid-19-related Stress. Meanwhile, Effort Expectancy, Social Influence, Innovativeness, and App-related Privacy Concern were found to have no significant effect on users' intention to use Aplikasi PeduliLindungi. Pada tahun 2020, dunia dihadapkan pada virus Covid-19 yang menyebar dengan cepat di antara orang-orang yang melakukan kontak dekat. Untuk mengendalikan dan membatasi penyebaran infeksi virus, telah digunakan aplikasi mobile health (mHealth) sebagai pendekatan berbasis teknologi. Aplikasi contact tracing merupakan salah satu jenis sistem mHealth yang mampu dan cocok untuk situasi seperti ini. Banyak negara yang telah menerapkan adopsi aplikasi contact tracing di masa pandemi, tak terkecuali Indonesia, yaitu Aplikasi PeduliLindungi. Adanya aplikasi contact tracing seperti Aplikasi PeduliLindungi dinilai sangat membantu. Penelitian terkait Aplikasi PeduliLindungi dirasa perlu, karena aplikasi contact tracing menjadi salah satu langkah penting untuk menekan penyebaran virus. Penelusuran faktor-faktor yang dapat mempengaruhi niat untuk mengadopsi aplikasi contact tracing sangat diperlukan, karena efektivitas penerapan aplikasi contact tracing Covid-19 bergantung pada kemauan masyarakat untuk menggunakan aplikasi tersebut. Untuk mengetahui faktor-faktor yang dapat mempengaruhi niat pengguna dalam menggunakan teknologi baru, dilakukan analisis dengan menggunakan model UTAUT (Unified Theory of Acceptance and Use of Technology). Hasil penelitian menunjukkan bahwa faktor-faktor yang secara signifikan mempengaruhi niat pengguna untuk menggunakan Aplikasi PeduliLindungi adalah Performance Expectancy, Facilitating Condition, dan Covid-19. Sementara itu, Effort Expectancy, Social Influence, Innovativeness, dan App-related Privacy Concern ternyata tidak berpengaruh signifikan terhadap niat pengguna untuk menggunakan Aplikasi PeduliLindungi
CryptMAIL: Keamanan Ganda Email Menggunakan Algoritma Kriptografi
Get PDFThe development of technology and information has changed the way humans communicate. Email is an online correspondence service that makes it easier for users to exchange information and communicate with other parties. The convenience offered attracts many people to switch to using email as a medium for exchanging information, and this creates new opportunities for cybercriminals to take action. Problems with email such as data or information leaks, file misuse or message theft due to negligence or others can occur. One way to anticipate this is to implement Cryptographic Techniques. Cryptography is an encryption technique to hide confidential messages from plaintext messages into ciphertext messages that are difficult to understand. In this study, we will discuss the implementation of cryptography with the AES-128 and RC4 algorithms for encryption and decryption of messages and file attachments sent via email. The result of this research is a web-based application 'CryptMAIL' which can encrypt and decrypt messages using the AES-128 and RC4 cryptographic algorithms. The 'CryptMAIL' application is expected to provide double security to anticipate security problems in email.Perkembangan teknologi dan informasi mengubah cara manusia dalam berkomunikasi. Email merupakan salah satu layanan surat menyurat secara online yang memudahkan pengguna dalam pertukaran informasi maupun berkomunikasi dengan pihak lain. Kemudahan yang ditawarkan menarik banyak orang untuk beralih menggunakan email sebagai media bertukar informasi, dan ini menjadikan peluang baru bagi cybercriminals untuk melakukan aksinya. Masalah pada email seperti kebocoran data atau informasi, penyalahgunaan file atau pencurian pesan karena kelalaian ataupun lainnya dapat terjadi. Salah satu cara untuk mengantisipasi hal tersebut adalah dengan mengimplementasikan Teknik Kriptografi. Kriptografi adalah sebuah Teknik enkripsi untuk menyembunyikan pesan confidential dari pesan plaintext menjadi pesan chipertext yang sulit dipahami. Dalam penelitian ini akan membahas tentang Implementasi kriptografi dengan algoritma AES-128 dan RC4 untuk enkripsi dan dekripsi pesan serta file attachment yang dikirim melalui email. Hasil penelitian ini adalah aplikasi berbasi web ‘CryptMAIL’ yang dapat menenkripsi dan dekripsi pesan menggunakan algoritma kriptografi AES-128 dan RC4. Aplikasi ‘CryptMAIL’ ini diharapkan dapat memberikan keamanan ganda untuk mengantisipasi masalah keamanan pada email
Perancangan User Interface dan User Experience Sistem Informasi E-learning Menggunakan Design Thinking
Get PDFThe COVID-19 pandemic has caused various activities to be shifted online, one of which is learning activities at school. Because they don't have their own e-learning information system, online learning activities at SMA Tunas Bangsa Palembang utilize various media such as Classrooms to create classes, Google Forms to fill absences, and YouTube to deliver material. Lots of media and there are still perceived shortcomings related to the features of the media used cause the implementation of learning activities become less effective and efficient. Thus, to provide comfort and convenience in these learning activities, an e-learning information system user interface and user experience (UI/UX) design is required. This study uses design thinking as a method that has 5 stages, starting with problem exploration (empathize) to testing the solution design prototype (test). Prototype testing is carried out using the usability testing method, using task scenarios and the System Usability Scale (SUS) and User Experience Questionnaire (UEQ) questionnaires. The results of usability testing using SUS task scenarios and questionnaires include aspects of learnability and efficiency of teacher and student user groups, namely 100% and 0.04 goals/sec, for teacher user satisfaction aspects is 93 with grade scale "A" and for student users is 85 with a grade scale of “B”, the UEQ assessment scores for the two user groups were above 2.0 in all rating categories namely “Attractives”, “Perspicuity”, “Efficiency”, “Dependability”, “Stimulation”, “Novelty”. So, it can be concluded that the e-learning prototype design has had a good user experience.Pandemi COVID-19 menyebabkan berbagai aktivitas dialihkan menjadi secara daring, salah satunya aktivitas belajar di sekolah. Karena belum memiliki sistem informasi e-learning sendiri, kegiatan belajar daring di SMA Tunas Bangsa Palembang memanfaatkan berbagai media seperti Classroom untuk membuat kelas, Google form untuk mengisi absen, hingga Youtube untuk menyampaikan materi. Banyaknya media serta masih terdapat kekurangan yang dirasakan terkait fitur dari media yang digunakan menyebabkan pelaksanaan kegiatan belajar menjadi kurang efektif dan efisien. Sehingga, agar dapat menghadirkan kenyamanan dan kemudahan dalam kegiatan pembelajaran tersebut, diperlukan perancangan user interface dan user experience (UI/UX) sistem informasi e-learning. Penelitian ini menggunakan design thinking sebagai metode yang memiliki 5 tahapan, dimulai dengan empathize sampai pengujian prototype desain solusi (test). Pengujian prototype dilakukan dengan metode usability testing yaitu menggunakan skenario tugas serta kuesioner System Usability Scale (SUS) dan User Experience Questionnaire (UEQ). Hasil pengujian usability testing menggunakan skenario tugas dan kuesioner SUS antara lain untuk aspek learnability dan efficiency kelompok pengguna guru dan siswa yaitu 100% dan 0,04 goals/sec, untuk aspek satisfaction pengguna guru yaitu 93 dengan grade scale “A” dan untuk pengguna siswa yaitu 85 dengan grade scale “B”, skor penilaian UEQ untuk dua kelompok pengguna berada diatas 2,0 di semua kategori penilaian yaitu “Daya Tarik”, “Kejelasan”, “Efisiensi”, “Ketepatan”, “Stimulasi”, “Kebaruan”. Sehingga, dapat disimpulkan bahwa desain prototype e-learning telah memiliki user experience yang baik
Optimasi Konten Pemasaran dan Platform Online dengan Teknik Search Engine Optimization
Get PDFRunning a business just doing production is not enough but must do optimal product marketing. Business actors who market their products through conventional marketing will be unable to compete with other entrepreneurs who market their products through online platforms because online platforms are now widely found via the internet. Conventional product marketing is done because they do not understand the right optimization techniques in product marketing, especially in marketing content optimization strategies and the use of online platforms. Optimization of content marketing and online platforms requires a technique known as SEO or Search Engine Optimization. This technique is used to help optimize marketing precisely in determining content and showing product content in internet searches through online platforms. Product content and optimized online platforms will provide a great help in product marketing. This study aims to explain marketing content optimization strategies and online platform settings so that they can display shrimp cracker product content posts on the search page. The results of this study are able to optimize the marketing content of the right shrimp cracker products and display product keyword search results on internet search pages through the online platforms Tumblr, TribunJualBeli, and Carousell.Menjalankan usaha hanya melakukan produksi saja tidaklah cukup melainkan harus melakukan pemasaran produk yang optimal. Pelaku usaha yang memasarkan produknya melalui pemasaran konvensional akan kalah bersaing dengan pengusaha lain yang melakukan pemasaran produk melalui platform online karena platform online pada saat ini sudah banyak ditemukan melalui internet. Pemasaran produk secara konvensional dilakukan karena tidak memahami teknik optimasi yang tepat dalam pemasaran produk terutama dalam strategi optimasi konten pemasaran dan penggunaan platform online. Optimasi konten pemasaran dan platform online memerlukan teknik yang disebut dengan SEO atau Search Engine Optimization. Teknik ini digunakan untuk membantu mengoptimalkan pemasaran secara tepat dalam menentukan konten dan memunculkan konten produk di pencarian internet melalui platform online. Konten produk dan platform online yang dioptimalkan akan memberikan bantuan yang besar dalam pemasaran produk. Penelitian ini bertujuan untuk menjelaskan strategi optimasi konten pemasaran dan pengaturan platform online agar dapat menampilkan postingan konten produk kerupuk udang pada halaman pencarian. Hasil dari penelitian ini adalah dapat mengoptimalkan konten pemasaran produk kerupuk udang yang tepat dan menampilkan hasil pencarian kata kunci produk pada halaman pencarian internet melalui platform online Tumblr, TribunJualBeli, dan Carousell
Pengembangan Sistem Alumni dengan Informasi Lowongan Pekerjaan
Get PDFThe Faculty of Information Technology, Maranatha Christian University or known as FIT-UK Maranatha has produced many alumni since its establishment in 2002. The recording of alumni data is currently not well managed where the data collected by the faculty is based on the latest information provided by alumni before final presentation or graduate briefing events. It is the hope of the faculty to have a special website-based application that can accommodate alumni data so that the faculty can still communicate with alumni and fellow alumni, while also getting the latest information related to current industry needs. This research will create a web-based application where the application can record alumni data, friendships between alumni, record the data of open job vacancies at the company where alumni work that can be seen by other alumni. The website will be made using the PHP programming language and the Laravel framework, for data storage will use mySQL.
Fakultas Teknologi Informasi Universitas Kristen Maranatha atau dikenal dengan nama FIT-UK Maranatha sampai saat ini sudah menghasilkan banyak alumni sejak berdirinya pada tahun 2002. Pencatatan data alumni saat ini belum dikelola dengan baik dimana data yang dimiliki oleh fakultas berdasarkan informasi terakhir yang diberikan oleh alumni sebelum pelaksanaan sidang atau acara pembekalan lulusan. Harapan dari fakultas memiliki suatu aplikasi khusus berbasis website yang dapat menampung data alumni sehingga fakultas tetap dapat berkomunikasi dengan alumni dan sesama alumni, selain itu juga mendapatkan informasi terkini terkait kebutuhan industri saat ini. Penelitian ini akan membuat sebuah aplikasi berbasis web dimana aplikasi dapat melakukan pencatatan data alumni, pertemanan antar alumni, pencatatan data lowongan pekerjaan yang sedang dibuka di perusahaan tempat alumni bekerja yang nantinya dapat dilihat oleh alumni yang lain. Sistem alumni FIT akan dibuat dengan bahasa pemrograman PHP dan framework Laravel, untuk penyimpanan data akan menggunakan mySQL