CICES (Cyberpreneurship Innovative and Creative Exact and Social Science)

Efektivitas Digital Learning Platform terhadap Motivasi Mahasiswa menggunakan Studi Literatur

Richard Andre Sunarjo — 2025-02-08

Penelitian ini bertujuan untuk mengeksplorasi dan mengevaluasi penerapan digital learning platform untuk meningkatkan motivasi mahasiswa di era digital. Di tengah perubahan lanskap pendidikan yang dipengaruhi oleh teknologi, motivasi mahasiswa menjadi faktor kunci keberhasilan belajar. Penelitian ini mengintegrasikan konsep-konsep dari teori motivasi, teknologi pendidikan, dan metode digital learning platform untuk merancang strategi pembelajaran yang berfokus pada partisipasi aktif mahasiswa. Pendekatan penelitian memadukan untuk memahami dampak penerapan metode digital learning platform terhadap motivasi mahasiswa. Temuan menunjukkan bahwa penggunaan metode digital learning platform, seperti pembelajaran berbasis realita virtual, pembelajaran berbasis gamifikasi, dan metode pembelajaran simulasi komputer dapat meningkatkan keterlibatan dan motivasi mahasiswa dalam belajar secara signifikan. Implikasi dari penelitian ini menunjukkan bahwa penerapan digital learning platform dapat memberikan manfaat yang signifikan bagi mahasiswa, termasuk peningkatan motivasi, keterlibatan, dan keterampilan belajar. Dengan memanfaatkan teknologi digital secara efektif, mahasiswa dapat mencapai hasil belajar yang lebih baik dan siap menghadapi tantangan di era digital.

Implementasi Arsitektur Mikroservis dan Orkestrasi Kubernetes dengan Paradigma DDD pada Website Freelancing

Hafi Ihza Farhana — 2025-02-08

The rapid development of the digital era triggered by COVID-19 has changed the way people earn income, with more and more people turning to freelance work. M-Knows Consulting responded to this change by creating a website-based freelance platform, designed to be a place for Indonesian freelancers to develop their careers. Given the complexity of the system and the high interaction of various users, a more modular development is needed to increase efficiency, especially in handling diverse project challenges. Therefore, a microservice architecture was chosen as a more appropriate solution than a monolithic architecture. The design of this microservice architecture involves several important steps, including the application of the Domain-Driven Design (DDD) paradigm with the principle of bounded context to clearly separate business domains and implement a multi-database approach that suits the specific needs of each service. The deployment process will be carried out using Kubernetes to manage the workload of each microservice and ensure system scalability and reliability. With this approach, it is hoped that the development of a website-based freelance platform can run more efficiently and quickly, so that it can immediately provide optimal services for freelancers in Indonesia.

Perancangan Aplikasi Mobile Pembelajaran Bahasa Berbasis Podcast dan Penerapan Hybrid Recommender System

Rico Putra Anugerah — 2025-02-08

This research develops a mobile application based on podcasts to enhance language skills, particularly in listening. Listening is considered a priority because vocabulary comprehension is necessary before mastering speaking, reading, and writing. Podcasts are chosen as the learning medium due to their ability to present audio on specific topics, aiding users in more effectively understanding the language. The application is also equipped with a recommendation system that utilizes the Hybrid Recommender System method, tailoring content based on user behavior and content similarity. The research results show that this application can optimize language learning, with a particular focus on language learning through podcasts, and helps users improve their language skills with a precision value of 85,6%, recall 85,9%, F1-Measure 88% and 80,2 for SUS testing.

Implementasi ANFIS Untuk Forecasting Penjualan Sembako Pada CV XYZ

Muhammad Daffa Fitriansyah — 2025-02-08

This study compares the performance of three fuzzy membership functions—Gaussmf, Gbellmf, and Trimf—in forecasting basic goods sales. The evaluation was conducted by measuring the Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) on both training and testing data across various window sizes. The evaluation results indicate that the Trimf membership function achieved the best performance. For a window size of 4, Trimf yielded a testing RMSE of 1.77 and a testing MAPE of 8.23%, outperforming Gaussmf (RMSE 2.82, MAPE 12.57%) and Gbellmf (RMSE 4.64, MAPE 17.54%). Meanwhile, Gaussmf and Gbellmf exhibited weaker performance on testing data, particularly at larger window sizes. These findings suggest that the appropriate selection of fuzzy membership functions can significantly enhance prediction accuracy. Future research could explore combinations of membership functions or other parameters that may further improve forecasting performance.

Penerapan Prediksi Penjualan pada Optimasi Stok dan Manajemen Persediaan Menggunakan Holt-Winters

Ardiana Deka Maharani — 2025-02-08

Penjualan memegang peranan penting sebagai penggerak utama perekonomian dan menjadi salah satu indikator keberhasilan suatu bisnis karena mencerminkan kemampuan perusahaan dalam memenuhi kebutuhan dan keinginan konsumen. Seiring dengan perkembangan teknologi dan perubahan tren bisnis, strategi penjualan pun mengalami evolusi menyesuaikan dengan kebutuhan pasar yang semakin kompleks. Dalam menghadapi dinamika pasar yang berubah, perusahaan perlu mengembangkan strategi penjualan yang efektif dan adaptif. Salah satu cara untuk mengatasi tantangan ini adalah dengan melakukan prediksi penjualan yang akurat. Penelitian ini bertujuan untuk mengembangkan sistem prediksi penjualan menggunakan metode Holt-Winters dalam mengoptimalkan manajemen persediaan. Metode ini diterapkan untuk mengantisipasi permintaan pasar dan mengurangi resiko terkait dengan ketidakpastian penjualan. Metode Holt-Winters mengintegrasikan tiga komponen utama: level (α), tren (β), dan musiman (γ), memungkinkan prediksi yang lebih presisi, baik untuk jangka pendek maupun jangka panjang. Penelitian ini memanfaatkan 768 data yang dibagi menjadi 2 yakni data uji dan data latih. Hasil Penelitian menunjukkan bahwa metode Holt-Winters mampu menghasilkan prediksi penjualan dengan tingkat akurasi yang tinggi, ditunjukkan oleh nilai Root Mean Square Error (RMSE) yang terendah sebesar 0.45. Nilai RMSE yang lebih rendah mengindikasikan performa model yang lebih baik dalam memprediksi penjualan. Dengan demikian, penerapan metode Holt-Winters dalam memprediksi penjualan terbukti efektif dalam mengoptimalkan manajemen persediaan.

Implementasi Logika Fuzzy Untuk Pemeriksaan Gizi Berdasarkan IMT Pada Aplikasi Fitpriority

Arif Mardhavi — 2025-02-08

Public awareness of the importance of leading a healthy lifestyle and exercising has
significantly increased in recent years. However, various issues such as a lack of understanding
of proper exercise techniques and nutrition that do not align with fitness goals remain prevalent.
To address these challenges, this study designs a web-based application called Fitpriority to
connect users with professional trainers. One of the main features of this application is a
nutritional status check based on Body Mass Index (BMI). This algorithm was chosen for its
ability to tolerate small changes in nutritional values, unlike the rigid traditional logic methods.
The study employs the Mamdani method to determine nutritional status through the processes of
fuzzification, implication function application, rule aggregation, and defuzzification using the
centroid method. Additionally, the System Usability Scale (SUS) method is used to assess the
usability and user experience of the developed application. The results of this study are expected
to provide an effective solution for individuals aiming to achieve their fitness goals more
efficiently and comfortably, and to serve as a valuable tool for a wide range of users in
maintaining optimal physical health and fitness.

Recognition of Handwritten Hangeul Characters Using Convolutional Neural Network

Kezia Kezia — 2025-02-08

The rapid increase in Indonesian tourists visiting South Korea has highlighted a growing interest in Korean culture, largely fueled by the Korean Wave. However, the inability to read the Korean alphabet (Hangeul) leaves many tourists vulnerable to scams. This paper proposes a novel solution to address this issue by developing a system for recognizing handwritten Hangeul characters, aimed at assisting Indonesian tourists in navigating South Korea safely. The research introduces a hybrid algorithm that integrates Vision Transformers (ViTs) with Convolutional Neural Network (CNN), aiming to overcome the limitations of CNN in capturing global features. The dataset utilized comprises 2,400 images of handwritten Hangeul characters, categorized into consonants and vowels. The study involved pre-processing, training, validation, and testing with three data split ratios (60:20:20, 70:15:15, 80:10:10) and two learning rates (0.001 and 0.0001) over 10 epochs. This hybrid model approach is designed to enhance recognition accuracy and improve the system's adaptability to diverse inputs.

Sistem Rekomendasi Makanan Sesuai Budget Bagi Wisatawan Menggunakan Algoritma Genetika Berbasis Website

Risma Nurhaliza — 2025-02-08

The development of a web-based food recommendation system using Laravel aims to help tourists in Surabaya find places to eat that suit their preferences, overcoming the constraints of limited information and the many choices that are often confusing. This system utilizes a genetic algorithm, which was chosen for its ability to optimize recommendations based on various criteria such as budget and location. Restaurant data in Genteng and Bubutan Districts is collected and analyzed for use in the recommendation process. Functional testing shows that this system functions well, with a genetic algorithm that is able to produce optimal recommendations based on adequate fitness values and fast execution times. To improve this system, it is recommended to improve the user interface design, optimize algorithm parameters, and perform additional testing to ensure system performance and security.

Pemanfaatan Model ResNet50 dan SVM untuk Klasifikasi Penyakit Daun Tebu

Sri Fatmawati Yunizar — 2025-02-08

Indonesia is an agrarian country with an economy that heavily relies on the agricultural sector, including the sugarcane plantation sub-sector for sugar production. Although domestic sugar production continues to increase, the demand for sugar consumption also grows, leading to dependency on imports and fluctuating sugar prices in the domestic market. Therefore, efforts to maintain and enhance the productivity of sugarcane crops are crucial. One of the main challenges in sugarcane cultivation is the attack of pests and diseases such as yellow disease, redrot, mosaic, and rust, which often affect sugarcane plants and reduce their productivity. These diseases must be detected promptly as they significantly impact the quality and quantity of the sugarcane to be harvested. However, manual identification processes are prone to human error and are inefficient for large-scale plantations.

To address this, machine learning technology using Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) was employed. This approach uses CNN for feature extraction and SVM for classification. Through a series of experiments, the study shows that the CNN and SVM models can achieve high accuracy of 90.32% with a computational time of 181.53 seconds.

Pengaruh Manajemen Piutang Terhadap Profitabilitas Studi Industri Di Tangerang

Rizka Mukhlisiah — 2025-02-08

Working capital in management is very important for the survival of an organization. It is also important for the growth of an organization. Management of receivables is an important component of working capital management carried out in a company. The current study empirically tests the effect of the efficiency of receivables management as measured by the debtor turnover ratio in the commercial industry in Indonesia on the profitability of the company. Profitability is measured using the returned capital. The study was conducted in the period 2019 to 2021. The findings show a significant positive relationship between the debtor turnover ratio and the company's profitability. This indicates that receivables management must be the main focus in increasing the profitability of industrial companies.

Klasifikasi Nilai Ujian Menggunakan Algoritma C5.0 di SMA Hangtuah 2 Sidoarjo

Nisa Pratiwi — 2025-02-08

Hangtuah 2 Sidoarjo High School is one of the educational institutions that implements intensive data management practices in all its operational activities. These activities start from processing student personal data, teacher lesson schedules, teaching management, attendance management, library management, financial management as well as evaluating and reporting student grades. In the evaluation process, teachers at Hangtuah 2 Sidoarjo High School often make mistakes in filling in the value data because there is too much data, so that the management of student grades becomes slow and calculation errors occur, resulting in ineffective classification of student grades. For this reason, this research aims to design an academic management system and test score classification using the C5.0 algorithm. With this system, it will be easier for administrators, teachers, librarians and finance departments to store student data and see their grades directly through the system. The results of the average percentage of all the questions that have been distributed have concluded that the UAT test results from the academic management system have very good criteria. The system that has been built can help teachers at Hangtuah 2 Sidoarjo High School to classify exam results based on the parameters of tuition arrears, number of books borrowed. , absenteeism, average UTS and UAS scores, accuracy results obtained from data from 37 students, test data, namely 70%..