JOINCS (Journal of Informatics, Network, and Computer Science)
Not a member yet
80 research outputs found
Sort by
Automated Data Extractor untuk Ekstraksi Data Formulir Evaluasi
Full text linkMakalah ini menyajikan pembahasan tentang program aplikasi sebagai alat ekstraksi data PDF otomatis yang diimplementasikan menggunakan bahasa pemrograman Python, dirancang untuk mengotomatiskan ekstraksi data terstruktur dari dokumen PDF khususnya formulir evaluasi rekan kerja. Aplikasi ini memiliki fitur kemudahan penggunaan, memungkinkan pengguna untuk mengunggah file PDF, memproses ekstraksi data dari formulir PDF standar yang secara tradisional memerlukan entri data manual atau sistem pengenalan karakter optik (OCR) yang kompleks, dan memperoleh tampilan data hasil ekstraksi dalam format tabel. Makalah ini memuat pembahasan tentang metodologi, hasil, dan potensi peningkatan alat di masa depan
On-Time Student Graduation Prediction Modeling: A Comparative Analysis of Naive Bayes Algorithm and Other Data Mining Classifications: Pemodelan Prediksi Kelulusan Mahasiswa Tepat Waktu: Analisis Komparatif Algoritma Naive Bayes Dan Klasifikasi Data Mining Lainnya
Full text linkPredicting the on-time graduation of university students is a crucial task in higher education institutions, enabling proactive support and improving institutional effectiveness. This paper presents a comparative analysis of several machine learning algorithms for predicting on-time graduation, with a specific focus on challenging the performance of the Naive Bayes (NB) algorithm. Although often used as a baseline model, the effectiveness of NB in the complex domain of educational data is frequently debated.
We compare NB with MultinomialNB and Decision Tree (DT), both widely favored in recent literature. Using a public dataset containing students' academic records, we follow the CRISP-DM methodology, incorporating feature selection and SMOTE to address class imbalance. The models are evaluated using accuracy, precision, recall, and F1-score metrics.
Our results show that while Decision Tree achieves the highest accuracy, Naive Bayes offers an appealing balance of performance, computational efficiency, and interpretability, making it a strong candidate for implementation in early warning systems at universities. This study provides empirical evidence on the role of Naive Bayes in the current landscape of educational data mining. The classification results show an accuracy of 0.82 for Naive Bayes, 0.81 for MultinomialNB, and 0.85 for Decision Tree
Pipa vs Landa: Game-Based Learning Based on Gamification in Elementary School Mathematics Learning
Full text linkLearning is an essential component of human existence. One of the learning opportunities in the educational context is available at school, where instruction is typically delivered orally and accompanied by visuals. Using activities to learn is an option that can increase student interest in certain subjects. Game-based learning is a form of education in which students play a game to aid in their education. This study attempts to employ the Pipa vs. Landa learning game's gift and combo system so that elementary school students are more motivated to learn mathematics. The average GEQ Core Module test results are 4,6 for positive affect, 3,9 for competence, 4,59 for sensory and imaginative immersion, 2,46 for flow, 1,25 for tension, 2,36 for challenge, and 1,39 for negative effect. The average scores on the GEQ Post-Game Module test were 4.36 for positive experience, 1.64 for fatigue, 1.2 for negative experience, and 2.20 for the return to reality. This game provides a superior experience for elementary school students
Artificial Intellegence In The Future Of Iraqi Healthcare System: Kecerdasan Buatan Di Masa Depan untuk Sistem Layanan Kesehatan Irak
Full text linkThe expansion of healthcare AI in Iraq highlights the growing necessity for AI education among medical students. The aim of this research is to explore the perspectives of medical students in Iraq regarding artificial intelligence (AI), including their understanding of AI and their career aspirations. Methodologically, a group of Iraqi medical students were invited to participate in an anonymous electronic survey.
The results indicate that a total of 318 responses were collected from 22 medical colleges. The majority of respondents (91.5%, s = 291) hold the belief that AI will have a significant impact on healthcare in the future. Specifically, their responses were categorized as strongly agreeing (33.6%, s = 107) or agreeing (57.9%, s = 184).
This research reveals that Iraqi medical students recognize the significance of AI and are enthusiastic about engaging with this technology. Moreover, it suggests that there is a need to expand and enhance medical college training on AI to ensure that future healthcare professionals are well-prepared in this domain
Design and Build The Game "Solid Shapes Explorer" Based on Android: Rancang Bangun Game "Solid Shapes Explorer" Berbasis Android
Full text linkIn mathematics lessons in elementary schools, the learning methods used by teachers are often still conventional, which can reduce students' interest in learning, especially at the elementary level, making them feel that math is not fun. The problem faced by the 5th grade teacher of UPT SD Negeri 192 Gresik is the difficulty of students in understanding the material of geometry, especially the formula for calculating the area and volume of various geometry. The limited learning media used, especially in the material of geometry, causes students to feel bored and have difficulty understanding the material. This research aims to design and produce an educational game. which can be used as a student learning tool related to geometry. In this research, using Game Development Life Cycle (GDLC) as the method used. The pretest and posttest results for the Solid Shapes Explorer game tested showed that the average pretest score of 20 students was 63.5, while for the posttest, the average student score reached 82. From the calculation results, it can be seen that the average posttest score shows an increase compared to the pretest score, with a difference of about 18.5 It can be stated that the use of learning through the Solid Shapes Explorer game has succeeded in improving students' understanding of geometry material
Cascaded Context-Aware Instance Segmentation with Transformer-Encoder for Adverse Weather Condition: Segmentasi Instansi Berbasis Konteks Bertingkat dengan Transformer-Encoder untuk Kondisi Cuaca Buruk
Full text linkLocalizing objects from an image has been a vital part in autonomous driving since object localization performance directly correlate with the safety of the passenger. Robust and accurate object localization that can adapt to any driving environment has always been improved to ensure a safe and reliable system. In this work, we propose CBNet, a two-stage instance segmentation network for an autonomous driving environment. The network leverages a powerful transformer network as the feature extractor to improve performance. In addition, our proposed network utilizes a cascade design for both the object proposal network and the region-of-interests classifier. The cascade design addresses the issue of degrading detections over a high detection threshold. Moreover, we implement shape and edge-aware losses for the segmentation mask and end-to-end knowledge distillation strategy during training to improve the robustness of the network in extreme conditions. Our proposed network achieves 6.5 AP and 5.7 mIoU improvement from the prior methods in Cityscapes driving dataset. Furthermore, we evaluate our network in Foggy Cityscapes dataset to ensure the robustness of our network in extreme conditions. CBNet is able to improve the performance of prior methods by 7.7 AP and 6.7 mIoU in Foggy Cityscapes dataset
Analysis and Design of WLAN-Based Internet Networks Using the TOP-DOWN Method in RT/RW NET: Analisis dan Perancangan Jaringan Internet Berbasis WLAN Menggunakan Metode TOP-DOWN di RT/RW NET
Full text linkPenulis mengelola analisis performa jaringan dan rancangan jaringan internet berbasis WLAN pada RT/RW Net di Dusun Gunungsari, Desa Gunungsari, Kecamatan Dawarblandong, Kota Mojokerto. Konektivitas internet yang berkualitas dan handal menjadi kebutuhan penting bagi masyarakat. Namun, sering kali performa jaringan tidak optimal dan mengakibatkan muncul masalah latensi yang tinggi dan throughput yang rendah. Oleh karena itu, analisis menyeluruh dan perancangan jaringan sangat diperlukan untuk meningkatkan layanan dan kebutuhan pengguna. Metode Top-Down digunakan sebagai landasan, dari perencanaan hingga implementasi. Langkah awal pada tahap analisis performa jaringan adalah dengan mengumpulkan informasi terkait parameter yang nantinya digunakan untuk mengevaluasi dan identifikasi terkait masalah yang dapat terjadi. Setelah analisis performa jaringan, perancangan jaringan dilakukan dengan Cisco Packet Tracer sebagai aplikasi yang digunakan untuk melakukan perancangan terkait solusi masalah jaringan nantinya. Kemudian dilakukan evaluasi lagi dalam perancangan jaringan, dengan mempertimbangkan kebutuhan pengguna dan infrastruktur yang ada. Termasuk pada pemilihan perangkat keras, konfigurasi, frekuensi yang optimal, serta cakupan sinyal yang luas
A Decision Support System For Determining Photography Vendors In The City Of Semarang Using The Hybrid SAW Method In A Multi Attribute Topsis: Sistem Pendukung Keputusan Penentuan Vendor Fotografi Di Kota Semarang Menggunakan Metode Hybrid SAW Dalam Topsis Multi Attribute
No full textAbstractWedding photography vendors are used as one of the most important things in capturing a moment of happiness felt by the newlywed couple, the families of both parties and their closest relatives who were present to enliven the wedding ceremony that was held. The many types of vendors offering their services make it difficult for prospective clients to determine the type of vendor that suits the client's wishes. This is a major problem for prospective clients in finding photography vendors that suit their budget and desires. Apart from that, prospective clients also do not know how many types of photography vendors are available in that city. To overcome this, a system is needed using the SAW and TOPSIS methods. The purpose of this research is. The purpose of this research is to find out the results of implementing the SAW and TOPSIS methods in the support system for determining the type of photography vendor in Semarang City. The system development method used is waterfall. As a result of implementing these two methods, the system created has met expectations to be able to assist in providing recommendations for photography vendors. From the results of black box testing, it can be concluded that the system has succeeded in producing recommendations for photography vendors in Semarang City and meets functional needs
Visual Identity Development Concept on Promotion and Communication Media of Pacitan Vocational Community College: Konsep Pengembangan Identitas Visual Pada Media Promosi Dan Komunikasi Akademi Komunitas Negeri Pacitan (AKN Pacitan)
Full text linkPrevious research on designing a visual guidebook for AKN Pacitan continues in the current research. The visual identity of AKN Pacitan in accordance with the statutes has been packaged in a guidebook, which will later become a visual identity standard for all AKN Pacitan promotional and communication media. The website is one of the media for promotion and communication of AKN Pacitan to the wider community. The visual identity display and website layout are adjusted to those already in the visual guidebook. This research aims to ensure that the visual identity of AKN Pacitan can be implemented into all promotional and communication media of AKN Pacitan, especially for website media
A Decision Making System For Selecting Computer Components Combination To Obtain Benchmark Score Suitable For Requirements Using SAW Method Based On Web Data: Sistem Penentuan Keputusan Dalam Pemilihan Kombinasi Komponen Komputer Untuk Mendapatkan Skor Benchmark Sesuai Kebutuhan Dengan Metode SAW Berbasis Web
No full textABSTRACT
Computer components are devices that are currently indispensable for almost all human needs. In its development, computer components have had a significant increase in data processing capabilities, which sometimes makes the period of use of computer components that comply with minimum specifications shorter. How could it not be, when a new computer component is launched by the company that makes it, then within one to two years the company that makes it has launched a new computer component product with higher specifications and higher efficiency. This can also cause an increase in electronic waste due to computer components that can no longer meet needs. Then, in terms of the software used, there was also a significant increase, forcing component users to replace the computer components used with computer components that have specifications that match the needs of the software used. Thus, I feel the need to help computer component users so that they can determine a good combination of computer components, so that they can achieve the computer component requirements required by the software used.
Keywords: Computer Components, Software, Electronic Waste.