1,720,970 research outputs found
Algoritma J48 Dan Logistic Model Tree Untuk Memprediksi Predikat Kelulusan Mahasiswa: Studi Kasus STT XYZ
Full text linkSalah satu hal yang dinilai dalam proses akreditasi adalah rata-rata Indeks Prestasi Komulatif (IPK) lulusan dalam tiga tahun terakhir. Sekolah Tinggi Teknologi (STT) XYZ telah terakreditasi BAN-PT namun nilai akreditasi yang didapatkan belum maksimal. Salah satu hal yang mempengaruhi adalah rata-rata IPK lulusan yang masih rendah. Oleh karena itu, dilakukan analisis data mining dengan model klasifikasi pada data akademik dan non akademik mahasiswa. Algoritma klasifikasi yang digunakan adalah J48 dan Logistic Model Tree (LMT). Tujuan dari penelitian ini adalah untuk membandingkan algoritma J48 dan LMT dalam memprediksi IPK akhir mahasiswa melalui predikat kelulusan dan mengetahui faktor apa saja yang mempengaruhi IPK akhir mahasiswa. Data yang digunakan adalah data mahasiswa jenjang sarjana yang telah dinyatakan lulus pada yusidium tahun 2015 sampai 2019 sejumlah 1050 data. Hasil penelitian ini adalah algoritma algoritma J48 menghasilkan akurasi sebesar 75,5%, sedangkan algoritma LMT menghasilkan akurasi sebesar 73,5%. Pada kedua algoritma, atribut yang berpengaruh pada predikat kelulusan mahasiswa adalah IPS semester 2, IPS semester 1, dan IPS semester 4. Algoritma J48 mampu mengklasifikasikan predikat kelulusan mahasiswa dengan lebih baik dan melakukan proses klasifikasi dengan lebih sederhana juga membutuhkan waktu yang lebih singkat.
Kata Kunci:predikat kelulusan, klasifikasi, J48, LM
Logistic Model Tree and Decision Tree J48 Algorithms for Predicting the Length of Study Period
Full text linkOne point to be assessed in the accreditation process in an institution is the length of the student's study period. The Informatics department in XYZ college has been accredited by the national accreditation bureau for higher education (BAN-PT), but the accreditation has the potential to be improved. One thing that affects the accreditation value is many students did not graduate on time. Therefore, the current study used available student data, both academic and non-academic, using data mining. Two model classifications were used, i.e. Logistic Model Tree (LMT) and Decision Tree J48. The study was aimed to compare LMT and Decision Tree J48 algorithm in predicting the length of student’s study and to find out the influence factors. The data were Informatics Engineering students who have graduated in February 2018 to February 2019 (135 records). Results showed that the LMT algorithm produced an accuracy rate of 71% better than Decision Tree J48 (62.8% accuracy) in predicting the length of the student’s study. The factors influencing the length of study of students are temporary grade point average (GPA) of the first semester, temporary GPA of the second semester, organizational status, and employment status
Analisis Arsitektur E-government dengan Menggunakan Kerangka Kerja Federal Enterprise Architecture (FEA)
Full text linke-government kini menjadi salah satu hal yang penting dalam penyelenggaraan pemerintahan. Hal tersebut disebabkan penerapan e-government dapat meningkatkan kualitas layanan pemerintahan menjadi lebih efektif dan efisien. Purwakarta merupakan salah satu kabupaten di Indonesia yang telah menerapkan e-government. Namun, penerapan e-government di Kabupaten Purwakarta masih pada tahap catalogue, yaitu sebatas pemberian informasi pemerintahan melalui website pemerintahan. Oleh karena itu, diperlukan suatu analisis mendalam mengenai arsitektur e-government di Pemerintahan Kabupaten Purwakarta yang hasilnya dapat digunakan untuk menggambarkan tingkat maturitas setiap komponen arsitektur dan juga dapat digunakan sebagai acuan untuk merencanakan pengembangan arsitektur e-government sampai ke tahap horizontal integration. Penelitian ini mengimplementasikan Federal Enterprise Architecture (FEA) dengan menggunakan Collaborative Planning Methodology (CPM) sebagai metodenya. Implementasi CPM hanya pada fase Organize and Plan yang terdiri dari tiga tahapan, yaitu Identify and Validate, Research and Leverage, serta Define and Plan pada aktivitas yang berkaitan dengan analisis kondisi arsitektur yang saat ini sedang berjalan. Implementasi kerangka kerja FEA pada penelitian ini tidak dilakukan secara utuh tapi disesuaikan dengan kondisi Pemerintahan Kabupaten Purwakarta. Hasil dari penelitian ini adalah analisis arsitektur strategi, bisnis, data, aplikasi, infrastruktur, dan keamanan sistem e-government di Kabupaten Purwakarta, serta tingkat maturitas dari setiap arsitektur tersebute-government kini menjadi salah satu hal yang penting dalam penyelenggaraan pemerintahan. Hal tersebut disebabkan penerapan e-government dapat meningkatkan kualitas layanan pemerintahan menjadi lebih efektif dan efisien. Purwakarta merupakan salah satu kabupaten di Indonesia yang telah menerapkan e-government. Namun, penerapan e-government di Kabupaten Purwakarta masih pada tahap catalogue, yaitu sebatas pemberian informasi pemerintahan melalui website pemerintahan. Oleh karena itu, diperlukan suatu analisis mendalam mengenai arsitektur e-government di Pemerintahan Kabupaten Purwakarta yang hasilnya dapat digunakan untuk menggambarkan tingkat maturitas setiap komponen arsitektur dan juga dapat digunakan sebagai acuan untuk merencanakan pengembangan arsitektur e-government sampai ke tahap horizontal integration. Penelitian ini mengimplementasikan Federal Enterprise Architecture (FEA) dengan menggunakan Collaborative Planning Methodology (CPM) sebagai metodenya. Implementasi CPM hanya pada fase Organize and Plan yang terdiri dari tiga tahapan, yaitu Identify and Validate, Research and Leverage, serta Define and Plan pada aktivitas yang berkaitan dengan analisis kondisi arsitektur yang saat ini sedang berjalan. Implementasi kerangka kerja FEA pada penelitian ini tidak dilakukan secara utuh tapi disesuaikan dengan kondisi Pemerintahan Kabupaten Purwakarta. Hasil dari penelitian ini adalah analisis arsitektur strategi, bisnis, data, aplikasi, infrastruktur, dan keamanan sistem e-government di Kabupaten Purwakarta, serta tingkat maturitas dari setiap arsitektur tersebu
Hyperparamaters Fine Tuning for Bidirectional Long Short Term Memory on Food Delivery
Full text linkFood delivery is growing rapidly in Indonesia. Every food delivery order holds big promotions to attract users’ attention, so it has advantages and disadvantages. However, users only focus on evaluating drivers and restaurants, so the company does not get feedback on its services. This research aimed to understand user sentiment and maximize model accuracy with hyperparameters and fine-tuning. Sentiment analysis can be used to determine user sentiment based on reviews, and the results of this analysis can provide suggestions for companies. The bidirectional long short-term memory method was used for sentiment analysis to understand a word’s meaning better. The Bidirectional Short-Term Memory model andWord2Vec extraction features were proven to be better than several other extraction modelsand features. The dataset was balanced, and the hyperparameters in the model and optimization could also improve accuracy. So, the Gofood and Shopeefood research results had an accuracy of 98.1%, and Grabfood’s was 97.4%
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Design And Develop A Mobile-Based Tour Guide Application In Purwakarta City
Full text linkAbstract
Puwrakarta City is one the regencies in West Java that is currently developing. Purwakarta city is located in a geographical area thatis rich in natural attraction, culinary tourism, and cultural tourism so that the city of Purwakarta become a tourist attractio, but not all tourist attractions in the city of purwakarta are know by local tourists and tourists outside the srea who want to visit and the lack of information anda there are many remote areas which are very unfortunate to miss its tourist attraction. Therefore, a mobile-based tourism application was made to make it easier for tourists to find tours. This software development uses the waterfall method to the dev stage, software modeling uses the Unified modeling Language (UML) modeling which consists of 4 stage, namely use case diagrams, activity diagrams, sequence diagrams, and class diagrams, with programming language using Dart, Firebase database, and using Flutter. This research produces a mobile-based application that has information about natural tourism, culinary tourism, and cultural tourism to that it can be used to disseminate between locak tourists and tourists outside the area in Purwakarta City.
 
IMPLEMENTATION OF HAVERSINE FORMULA IN AN ANDROID-BASED GEOGRAPHIC INFORMATION SYSTEM BPJS HEALTH FACILITIES IN PURWAKARTA
Full text linkThis study designs and develops an Application Android-based Geographic Information System (GIS) to assist residents of Purwakarta Regency in locating the nearest BPJS-affiliated healthcare facilities, addressing the limitations of distance information and mapping on the Health Office’s website. To compute distances, the application utilizes the Haversine Formula based on the user’s coordinates. It is developed using Flutter for the Android application and Laravel for the web-based admin system, following the Extreme Programming (XP) methodology. Blackbox Testing is used to ensure system functionality. As a result, the application can display a list and geographic locations of healthcare facilities along with the distance from the user. The application is expected to provide easier access to healthcare information and enhance the quality of health services in Purwakarta Regency
IMPLEMENTATION ANDROID ARCHITECTURE COMPONENT FOR DEVELOPING THE SIMLING APPLICATION (ENVIRONMENT MANAGEMENT SYSTEM)
Full text linkEnvironmental management in Cluster Cahaya Mekar Wangi is still manual, utilizing WhatsApp and Excel for dues recording, financial reports, and security tracking, which often results in data errors and low transparency. This study developed SIMLING, an Android-based application, to digitalize and integrate these processes into a unified system. Built using the Waterfall model with Kotlin (frontend), Golang (backend), and MySQL in Docker (database), SIMLING offers real-time payment recording with receipt uploads, automated validations, transparent reports, QR-based security monitoring, and centralized notifications. The implementation shows SIMLING streamlines administrative tasks, improves transaction validation, and enhances security monitoring, while providing residents with easier payments and clear financial information. This supports smarter, more structured, and sustainable community management
Mobile Based Parking Application Using Extreme Programming (Xp) Method
Full text linkVehicle care is one of the businesses that is quite profitable with quite large capital. However, with this capital it becomes a fairly large and long-term income, and fromthis capital every year the price of this capital will definitely increase because of the area of theland. However, in business, there is a problem that often occurs in each of these safekeeping, namely realtime accounting and data in photos and numbers. Then this research aims to make itcivil in managing the daycare. The model and method used uses Extreme Programming (XP) development and, why did I take mobile programming because in this case study it is better for device users who are indeed flexible.
The feasibility of this system is seen from the point of view of its functionality and according to the user from what is needed according to the case study. The programming language used is Java, and testing is to display the success of system functionality using ablack box, then for modeling using the unified model language (UML) for flow using this system, the database used is firebase.
The purpose of this research is to get a solution to the problems that exist in the place, namely in data collection and reporting to the owner by providing input within certain hours and then conveying it to the owner, with this application providing solutions to problems that occur at this research location
- …
